PSY 201 Midterm 1 (PDF)

1 Chapter 1: The Science of Psychology Understanding Science (2) Logical Fallacies: Born due to cognitive and motivational processes Mutually exclusive: totally independent, happening of one ev...

1 Chapter 1: The Science of Psychology Understanding Science (2) Logical Fallacies: Born due to cognitive and motivational processes Mutually exclusive: totally independent, happening of one event proves the not happening of the other event, fully negative correlation What is Science?: general approach to understanding the natural world, which is an another form of acquiring knowledge Organizes knowledge, is systematic, testable and contains predictions Psychology takes the aspect of the natural world: human behavior. uses: intuition, authority, inductive and deductive reasoning, systematic empiricism Features of Science: has three fundamental features Systematic empiricism: ○ Empiricism: learning based on observation ○ Systematic: carefully planned, including making, recording and analyzing observations Empirical questions: questions that can be tested, answered or falsified by systematic observation Public knowledge: publishing the work to the public ○ Science is a social process and includes large-scale collaboration among many researchers distributed across time and space ○ Publishing allows science to be self-correcting: publication allows others in the scientific community to detect and correct errors; over time scientific knowledge increasingly reflects the world. Popper’s Approach: a theory can only be disproven Objections: Inductive reasoning, Theory confirmation, Underdetermination, Contextual factors Science vs. Pseudoscience: Falsifiability: does not necessarily mean the claim is false, rather if it can be empirically tested to be false or not. Pseudoscience: activities and beliefs are claimed to be and may appear scientific but are not due to lacking one of the three fundamental features of science. ○ Hypothesis generated are not testable, non-scientific methodology, anecdotal support, ignoring conflicting evidence, claims tend to be vague and appeal to preconceived ideas, claims are never revised ○ Barnum effect: too general claims so that it can fit anyone ROT test: helps to figure out if a claim is scientific: Repeatable, Observable, Testable  2 Scientific Research in Psychology (8) A Model of Scientific Research in Psychology: 1. Observe and question or check the research literature 2. Making predictions with a good rationale, hypothesis: Formulating a research question 3. Testing the predictions, experimentation: Conduct a study designed to answer the question 4. Reach at an answer, result: Analyze the resulting data 5. Draw conclusions about the answer to the question 6. Publish the result so that they become part o the research literature New research leads to new questions Who conducts scientific research in psychology: Doctoral degrees, PhD, Masters degrees, Assistants w/BA degrees, Government agencies, National associations, Nonprofit organizations, Private sector The Broader Purposes of Scientific Research in Psychology: Basic research: conducted primarily for the sake of achieving a more detailed and accurate understanding of human behavior, without necessarily trying to address any particular practical question. ○ Producing basement information for the applied research ○ Mostly experiment/lab based Applied research: conducted primarily to address some practical problems. ○ For an immediate solution for more practical problems Science and Common Sense (15) Can we rely on common sense? Is scientific approach is necessary, can’t we draw to the same conclusion by using common sense or intuition? Folk psychology: intuitive beliefs about people’s behavior, thoughts and beliefs Many common beliefs about psychology are actually falsified by empirical research: How could we be so wrong? Forming detailed and accurate beliefs requires powers of observation, memory, and analysis to the extent that we do not naturally possess. Mental shortcuts / heuristics: ○ If a belief is widely shared – especially if endorsed by experts – and it makes intuitive sense, we tend to assume its true. ○ Confirmation bias: we tend to focus on cases that confirm our intuitive beliefs and not on cases that disconform them ○ Conjunction fallacy: representative heuristics, probability of an event drops hen conjuncts with “and” ○ We also hold incorrect beliefs in part because it would be nice if they were true  3 Skepticism: does not mean being cynical or distrustful, it means pausing to consider alternatives and to search for evidence – especially systematically collected empirical evidence. Tolerance for uncertainty: accepting there are many things that they simply do not know, because there is often not enough evidence to fully evaluate a belief or claim. Deductive and Inductive Reasoning: Deductive: a logical process of drawing conclusions based on general principles of theories. ○ From general statements to specific predictions or hypotheses ○ In psychology: hypothesis testing, logical coherence, theory confirmation, predictive power, practical applications ○ Provides a structural approach to understanding of human behavior and cognition ○ Strengths: ensuring logical coherence and confirmatory nature of hypothesis, helps researchers make specific predictions or draw conclusions about individual cases ○ Limitations: oversimplification of complex phenomena, dependance on accurate premises Inductive: a logical process of drawing generalizations or theories based on specific observations or evidence ○ It involves moving from specific observations to broader conclusions ○ In psychology: discover new phenomena, the exploration of complex systems, development of practical applications that contribute to our understanding of human behavior and cognition ○ Strengths: generating new hypotheses and theories based on observed patterns and evidence ○ Limitations: the possibility of biased observations, the need for further empirical testing and validation, danger of overgeneralizing. Nonsense deduction Science and Clinical Practice (19) Its application of scientific method and principles to study and understand human behavior, cognition, emotions, and mental processes. goals: ○ Description: observational and survey research Research for describing/depicting situations and events. Systematic observation. Report on the background or context of a situation. Addresses the amount of single given characteristic (not relationship between two or more variables) ○ Prediction: correlational research Research for discovering regularities, relations between/among variables. Contains two or more variables/conditions, series of coordinated observations. Concludes the strength and direction of relations. ○ Explanation: experimental research  4 Research for explaining situations and events. Contains systematic data collection and determines the causes of behavior and answers the question of why. Most frequent objective in the real research world. ○ Application and practical benefits ○ Continuous improvement Diagnosis and treatment of psychological disorders and related problems is the most common and widely known application. Clinical practice: refer to the activities of clinical and counseling psychologists, school psychologists etc. people who work with individuals or small groups to identify and help addressing their psychological problems Psychological disorders and behavioral problems are a part of the natural world, meaning that questions about their nature, causes and consequences are empirically testable. Empirically supported treatments: treatments which are shown to work through testing ○ Cognitive behavioral therapy: for depression, panic disorder, bulimia nervosa, and PTSD ○ Exposure therapy: PTSD ○ Behavioral therapy: depression ○ Behavioral couples therapy: for alcoholism and substance abuse ○ Exposure therapy with response prevention: for OCD ○ Family therapy: for schizophrenia Field studies: Studies conducted outside the laboratory, in a real world setting Typically involve observing or interacting with participants in their typical environments Ecological validity Correlational studies: Investigating the relationship between two things Mostly uses survey methods No causation Can inspire experimental research Causal inferences: experimental psychology Investigating the causal reasons of a phenomenon Experimentation needs at least two groups: control and treatment Explanation of mechanism: mathematical approaches Branch of psychology focusing on the use of mathematical and computational models to explain and predict human behavior  5 Understanding the underneath: neuropsychology A branch of psychology concerned with how a person’s cognition and behavior are related to the brain and rest of the nervous system Professionals in this branch of psychology often focus on how injuries or illnesses of the brain affect cognitive and behavioral funcitons Levels of explanation: Level of explanation Underlying process Examples Lower Biological Depression is in part genetically influenced. Depression is influenced by the action of neurotransmitters in the brain. Middle Interpersonal People who are depressed may interpret the events that occur to them too negatively. Psychotherapy can be used to help people talk about and combat depression. Higher Cultural and social Women experience more depression than do men. The prevalence of depression varies across cultures and historical time periods. Goals of behavioral science: Description: portraying the phenomena Prediction: anticipating the outcome the occurrence of an event Finding causes and explanation, identifying the causes of the phenomena Control/influence/application/manipulation of the conditions that determine a phenomena. Chapter 4: Theory in Psychology Phenomena and Theories (68) Phenomena: is a general result that has been observed reliably in systematic empirical research, its an established answer to a research question More likely to be used for results that are replicated ○ Replication: conducting a study again – either exactly as it was conducted or with modifications – to be sure that it produces the same results ○ Sometimes a replication produces results that differ from the initial study. Meaning that either the initial or the replicated results had occurred by chance and do not reflect something that is generally true. But additional replications may solve this discrepancy  6 Theory: Is a coherent explanation or interpretation of one or more phenomena. Although theories can take a variety of forms, one thing they all have in common is that they go beyond the phenomena they explain by including variables, structures, processes, functions, or organizing principles that have not been observed directly. Perspective: a board approach – more general than theory – to explaining and interpreting phenomena Model: a precise explanation or interpretation of a specific phenomenon – often expressed in terms of equations, computer programs, or biological structures and processes. Hypothesis: an explanation that relies on just a few key concepts – although this term more commonly refers to a prediction about a new phenomenon based on a theory Theoretical framework: can be as broad as a perspective or as specific as a model, but it is the context applied to understanding a phenomenon. What are theories for? Main: providing accurate explanations or interpretations Three additional purposes: ○ Organization of known phenomena: organize phenomena in ways that help people think about them clearly and efficiently Parsimony, Occcam’s razor: holds that a theory should include only as many concepts as necessary to explain or interpret the phenomena of interest. Simpler, more parsimonious theories organize phenomena more efficiently than complex, less parsimonious theories. ○ Prediction of outcomes in new situations: allow researchers and others to make predictions about what will happen in new situations ○ Generation of new research: generate new research by raising new questions. theory suggests new questions A theory does not have to be accurate to generate new questions. If the theory is inaccurate the new direction will lead researchers to reevaluate the theory. ○ Multiple theories: usually multiple theories are considered for any set of phenomena. One reason is that because human behavior is extremely complex, it is always possible to look at it from different perspectives. A second reason is that – even from the same perspective – there are usually different ways to “go beyond” the phenomena of interest. Different theories of the same set of phenomena can be both complementary or competing: Complementary: each one supplying one piece of a larger puzzle Competing: if one is accurate, the other is probably not.  7 The Variety of Theories in Psychology (76) The characteristics of theories: Formality: the extent to which the components of the theory and the relationships among them are specified clearly and in detail. ○ At the informal end of this dimension are theories that consist of simple verbal descriptions of a few important components and relationships ○ Informal theories: tend to be easier to create and to understand, less precise in their predictions, more difficult to test, appropriate in the early stages of the research ○ Formal theories: tend to be more difficult to create and understand – sometimes requiring a certain amount of mathematical or computer programming background – tend to be more precise in their predictions, easier to test, appropriate in later stages of research Scope: the number and diversity of the phenomena they explain or interpret. ○ Many early psychological theories were extremely broad in that they attempted to interpret essentially all human behavior ○ Freudian theory was applied not only to understanding psychological disorders but also to slips of tongue and other everyday errors, dreaming, sexuality, art, politics, and even civilization itself. ○ Broad theories tend to be imprecise and difficult to test, they are not particularly successful at organizing or predicting the range and complexity of human behavior, they often end up being vague and can seldom make specific predictions. ○ At the broad end of this dimension are theories that apply to many diverse phenomena. ○ At the narrow end of this dimension are theories that apply to small number of closely related phenomena ○ Broad theories organize more phenomena but tend to be less formal and less precise in their predictions, narrow theories organize fewer phenomena but tend to be more formal and more precise in their predictions. Theoretical approach: theories in psychology vary widely in the kinds of theoretical ideas they are constructed from Functional theories: explain the phenomena in terms of their function and purpose ○ Answers the question “why” Mechanistic theories: focus on specific variables, structures, processes, and how they interact to produce the phenomena ○ Answers the question “how” ○ Involve identifying a mechanism or explanation for the pe-henomenon and providing context for when or how intense the phenomenon happens. Stage theories: provide organization without necessarily providing a functional or mechanistic explanation. ○ Specify a series of stages that people pass through as they develop or adapt to their environment  8 ○ As people pass through the stages, they integrate their outcomes from previous stages to help them succeed in the next stage. ○ Progressing forward or stopping is the only option, because stage theories do not allow for reverting to the previous stage Typologies: provide organization by categorizing people or behavior into distinct types. ○ Include theories that identify several basic emotions, several distinct types of intelligence, and distinct types of personalities ○ People do not progress though the typologies in any order at all. Multiple approaches are necessary to provide a complete understanding of any set of phenomena. Using Theories in Psychological Research (81) Theory testing and revision: Hypothetico Deductive method: conceptualized as a cycle 1. Identify the problem/question 2. Do some background research 3. Form a hypothesis 4. Test the hypothesis 5. Analyze the results: if the data supports the hypothesis, existing theory works; if not new theory through revision is needed (self-correction) 6. Communicate the results Constructing or choosing a theory: A researcher must know in detail about the phenomena of interest and about any existing theories based on a thorough review of literature. The new theory must provide a coherent explanation or interpretation of the phenomena of interest and have some advantage over existing theories. Deriving hypothesis: a hypothesis is a prediction about a new phenomena that should be observed if a particular theory is accurate. Theories and hypotheses always have this if-then relationship. 1. One way is to generate a research question and then ask whether any theory implies an answer to that question. 2. A second way is to focus on some component of the theory that has not been directly observed. Evaluating and revising theories: If theory → hypothesis If not hypothesis → not theory  9 Chapter 2, Part 3: Reviewing the Research Literature (38) What is the research literature? Its all the published research in that field. Does not include self-help and other pop psychology books, dictionary and encyclopedia entries, websites and similar sources that are mainly intended for the general public. (considered unreliable since they are not peer reviewed) Professional journals: periodicals that publish original research articles. Empirical research articles: describe one or more new empirical studies conducted by the authors. Introduce a new research question, explain why is it interesting, review previous research, describe their method and results and draw their conclusions. Review articles: summarize previously published research on a topic and usually present new ways to organize or explain results. ○ When a review article devotes to mainly promoting a new theory, they are referred to as a theoretical article. ○ Double blind peer-review: researcher submits a manuscript to the editor, who in turn sends it to two or more experts on the topic. Each reviewer reads the manuscript, writes a critical but constructive review, and sends the review back to the editor along with their recommendations. Reviewers dont know who the researcher is and vice versa. Scholarly books: books written by researchers and practitioners mainly for use by other researchers ○ Monograph: written by a single author or a small group and usually gives a coherent presentation of a topic like an extended review article. ○ Edited volume: have an editor or a small group of editors who recruit many authors to write separate chapters on different aspects of the same topic. Literature search: early in the research process its important to conduct a review of the research literature on the topic to refine the research question, identify appropriate research methods, place the question in the context of other research, and prepare to write an effective research report. There are several strategies for finding previous research on the topic: like online databases, PsychINFO, google scholar, etc. Chapter 3: Research Ethics Moral Foundations of Ethical Research (48) Framework for thinking about research ethics: Four general principles: Respecting people’s rights and Weighing the risks against benefits dignity Acting responsibly and with integrity Seeking justice  10 Three groups of people that are affected by Scientific community research: Society Participants Respect for persons: respecting autonomy by ensuring free, and ongoing consent and protecting those incapable of ensuring autonomy ○ Informed consent Concern for welfare: ensuring that participants are not exposed to unnecessary risks, considering participants’ privacy and maintaining their confidentiality as well as providing them with enough information to be able to adequately assess risks ○ Privacy and confidentiality Justice: obligation to treat people fairly and equitably, including by considering the vulnerability of participants and ensuring that marginalized groups are not unjustly excluded from research. Ethical conflict in psychological research is unavoidable. Researchers must think through the ethical issues raised by the research, minimize the risks, weigh the risks against the benefits, be able to explain their ethical decisions, seek feedback about these decisions from others and ultimately take responsibility for them. From Moral Principles to Ethics Codes (54) Informed consent: obtaining and documenting people’s agreement to participate in a study, having informed them of everything that might reasonably be expected to affect their decision. Includes details of the procedure, the risks and benefits, the fact that they have the right to decline to participate or withdraw from the study, consequences of doing so, and any legal limits to confidentiality. Deception: might include misinforming the participants about the purpose of the study, using confederates, using phony equipment, presenting participants with false feedback about their performance. Debriefing: process of informing the participants as soon as possible of the purpose of the study, revealing any deception, and correcting any other misconceptions they might have as a result of participating. Scholar Integrity: APA rule of ethical conduct Fabricating: making up wrong data ○ But if an error is found afterwards, it can be fixed through publishing an erratum. ○ In psychological sciences, if something is too good to be true then it’s possibly wrong. Monitoring: open data archives and keeping the data ○ Replication, more difficult in psychological research since we are working with humans. There are lots of different things that affect the result. Plagiarism: presenting portions of others’ work or data as their own, even if the original work or data is cited occasionally.  11 ○ Salami slicing: separately publishing parts of an analysis on one research question. Falsifying credentials: putting something in your cv that you donot have. Putting Ethics Into Practice (62) 1. Knowing and accepting ethical responsibilities 2. Identifying and minimizing risks a. prescreening 3. Identify and minimize deception 4. Weigh risks and benefits 5. Create informed consent and debriefing procedures 6. Get approval from the institution Chapter 2: Getting Started in Research Basic Concepts (23) Variables: is a quantity or quality that varies across people or situations Constants vs. variables Variables should be changing Quantitative variables: a quantity like height, that is typically measured by assigning a number to each individual. Categorical variables: is a quality like major, and is typically measured by assigning a category label to each individual. Sampling and Measurement: Sampling: Population: very large group that psychologists are interested in Sample: small subset of the population ○ All members of the sample have representative power. Even though psychologists want to make conclusions about some very large group reaching to everyone in a population is impossible, therefore they reach out to a sample group to represent the population Sample group should represent the entire population in important aspects ○ Random sampling: in which every member of the population has an equal chance of being selected for the sample. But not very feasible due to reaching out problems ○ Convenience sampling: in which the sample consists of individuals who happen to be nearby and willing to participate But might not be totally representative of the whole population Measurement: to be able to measure it, first we need to define it Operational definition: a definition of the variable in terms of precisely how it is to be measured. Makes it possible to do empirical research  12 ○ Not the same as dictionary definition ○ Most variables can be operationally defined in many different ways that can vary across research and concepts Statistical relationships between variables: There is a statistical relationship between two variables when the average score on one differs systematically across the levels of the other. Instead of telling us about behaviors and psychological characteristics in isolation, it tells us about the potential cause, consequences, development, and organization of those behaviors and characteristics. Two basic forms of statistical relationships: ○ Differences between groups: Difference between the mean scores of the two groups on some variable of interest. To investigate the difference between groups, one of the variables should be categorical Bar graphs ○ Correlations between quantitative variables: Correlation between two quantitative variables, where the average score on one variable differs systematically across the levels of the other Scatterplots Pearson’s r: pearson linear correlation coefficient from -1 to +1 -1: perfect negative linear relationship 0: no linear relationship +1: perfect positive linear relationship Correlation does not imply causation ○ Causal relationship: one of the variables indicate to the happening of the other ○ Independent and dependent variables: Independent: manipulated, the variable that is taught to be the cause Dependent: measured , the variable that is taught to be the effect Note: in correlational studies, the variables cannot be defined as (in)dependent max that can be done is calling them covariance variables. ○ The reasons include: Directionality problem: two variables, X and Y, can be statistically related because X causes Y or vice versa. Third-variable problem: two variables, X and Y, can also be statistically related because some third variable Z, causes both X and Y. Generating Good Research Questions (31) Creative process,curiosity, ordinary thinking strategies and persistence Finding an inspiration: From everyday life, common sense, observations about yourself and others Previous research → doing follow-up studies, in the discussion section, authors propose future directions about what can be done further or what can be improved  13 ○ Repeat studies ○ Improve a previously done study ○ Cross-cultural application: ○ Look for practical applications of the ○ Do a study suggested by the initial research author ○ Try to reconcile studies that produce conflicting results. Practical issues that require solutions Theories in science, finding solutions to developing theories Generating empirically testable research question: Questions expressed in terms of a single variable or relationship between variables Evaluating research questions: Interestingness: ○ A research question that is interesting to the extent that its answer is in doubt. Meaning that they are not previously answered ○ Does answering the question fill a gap in the research literature? ○ Does the answer have important practical implications? Feasibility: many factors affect feasibility of the study to successfully answer the question: time, money, equipment and materials, technical knowledge and skill, access to research participants, and ethical issues that may be raised. ○ Time: like longitudinal research, which spans over the years Chapter 5: Psychological Measurement Understanding Psychological Measurement (89) Measurement: is the assignment of scores to individuals so that the scores represent some characteristic of the individual. Psychometrics: psychological measurement ○ Unlike weighing yourself on the bathroom scale they do not require particular instruments, they require some systematic procedure for assigning scores to individuals or objects so that those scores represent the characteristic of interest. Psychological constructs: Some variables are straightforward and easy to measure: sex, age, height, weight Many other variables are not so straightforward and simple to measure: constructs ○ Include personality traits, emotional states, attitudes, and abilities. Psychological constructs cannot be observed directly. ○ One reason is that they often represent tendencies to think, feel or act in certain ways. ○ Another reason is that they often involve internal processes. Each construct is kind of a summary of a complex set of behaviors and internal processes.  14 Conceptual definition: of a construct describes the behavior and internal process that make up that construct, along with how it relates to other variables. ○ Many scientific constructs do not have counterparts in everyday language Operational definition: a definition of a variable in terms of precisely how it is to be measured. Have three categories: Self-report measures: which participants report on their own thought, feelings, and actions Behavioral measures: which some other aspects of participants’ behavior is observed and recorded. An extremely broad category that includes the observation both in highly structured laboratory tasks and in more natural settings. Physiological measures: involve recording any of a wide variety of physiological processes, including heart rate and blood pressure, galvanic skin response, hormone levels and electrical activity and blood flow in the brain. When scientists use multiple operational definitions of the same construct, they are using converging operations – idea that the various operational definitions are converging or coming together on the same concept ○ When scores based on several different operational definitions are closely related to each other and produce similar patterns of results, this constitutes good evidence that the construct is being measured effectively. Levels of measurement: Level of Category labels Rank order Equal intervals True zero measurement Nominal X Ordinal X X Interval X X X Ratio X X X X Reliability and Validity of Measurement (96) Reliability: refers to the consistency/stability of the measurement Little fluctuations always add a little margin error Observed score = true score + error Stability: ○ Test-retest reliability: measurement from the same person at two different times should be consistent across time. Assessing test-retest reliability requires using the measure on a group of people one time, using it again on the same group at a later time and then looking at the test-retest correlation between two sets of scores. +0.80 or greater is considered to indicate f-good reliability.  15 ○ Equivalent / alternate / parallel forms: measure the correlation between alternative means of measurement Internal consistency: consistency of people’s responses across the items on a multiple-item measure. ○ All the items on such measures are supposed to reflect the same underlying construct, so people’s scores on those items should be correlated with each other. ○ Especially used for assessments with multiple items on the same construct. ○ Split-half correlation: involves splitting the items into two sets, then a score is computed for each set of items, and the relationship between the two sets of scores is examined. ○ Cronbah’s alpha: conceptually, alpha is the mean of all possible split-half correlations for a set of items. Evaluate the agreement of all items, involve taking the average covariance and dividing it by the average total variance. Quantifies the degree to which these items are correlated with each other. Usually uses SPSS. ○ +0.80 and above is accepted reliable Interrater reliability: the extent to which different observers are consistent in their judgements. Requires extensive training judgment, training both of the observers to make sure that they are looking at the same thing in the same way. To improve reliability: ○ Careful measurement procedures ○ Conducting pilot testing ○ Using multiple items, eliminating bad items, and checking wordings/instructions and revisions Validity: the extent to which the scores from a measure represent the variable they are intended to do. Is it true and supported by evidence? Accuracy of inferences, interpretations, or actions made on the basis of the score (any measurement procedure) Face validity: the extent to which a measurement method appears to measure the construct of interest. Based on experts’ judgements. But its a very weak evidence for validity Content validity: to the extent of which a measure represents all aspects of a given construct. ○ Are there any important aspects/dimensions of the construct left out or over/under-emphasized? Criterion validity: the extent to which people’s scores on a measure are correlated with other variables (criteria) that one would expect them to be correlated with. ○ Obtained by relating one measurement score with one or more relevant and known criteria ○ Criteria is the standard that you want to predict on the basis of the measurement like well established scales  16 ○ Concurrent validity: when the criterion is measured at the same time as the construct ○ Predictive validity: when the criterion is measured at some point in the future ○ Convergent validity: when criterion includes other measures of the same construct. How well the scores received from a new method correspond with scores obtained from other measures of the same/similar variables/constructs. Discriminant validity: the extent to which scores on a measure are not correlated with measures of variables that are conceptually distinct. ○ How different the scores are form scores obtained from other similar methods designed to measure theoretically different constructs ○ Should not be highly correlated Validity of the research also exists: both internally and externally. Practical Strategies for Psychological Measurement (103) a. Conceptually defining the construct Clear and complete conceptual definition of construct allows to make decisions about exactly how to measure the construct b. Operationally defining the construct Using an existing measure: ○ Saves time and there is already evidence for validity. Creating a new measure: ○ Simple and brief ○ The measure should be sensitive to detect differences in the construct important for the study, should be appropriate to the characteristics of the sample and to the objectives of the study. Range effect: adequate distributions of responses to be able to detect differences at one direction Ceiling (high) or floor (low) scores c. Implementing the measure If reactivity effect is possible, unobtrusive or nonreactive measures should be used ○ Reactivity of measure: when participants respond in a specific way. Include socially desirable responding and demand characteristics. d. Evaluating the measure: in terms of reliability and validity. Chapter 6: Experimental Research Experiment Basics (110) What is an experiment? experiment: is a type of study designed specifically to answer the question of whether there is a causal relationship between two variables, whether changes in an independent variable cause a change in a dependent variable.  17 ○ type of research to demonstrate causal relationships between the variables of interest. ○ The main difference between experiment and correlational research is the manipulation of variables. two fundamental features: ○ conditions: the different levels of the independent variable that the researchers manipulate, or vary systematically. ○ extraneous variable: variables other than the independent and dependent, where the researcher controls or minimizes the variability of them unwanted influence leading to misleading or inaccurate results Four big validities: Internal validity: an empirical study is said to be high in internal validity if the way it was conducted supports the conclusion that the independent variable caused any observed differences in the dependent variable. ○ thus experiments are high in internal validity because the way they are conducted — within the manipulation of the independent variable and the control of the extraneous variables — provides strong support for causal conclusions. External validity: the way that experiments are constructed sometimes leads to a different kind of criticism, that is the experiments are often conducted under conditions that seem artificial. ○ an empirical study is high in external validity if the way it was conducted supports generalizing of the results to people and situations beyond those actually studied. ○ ecological validity: can we generalize the conclusions to the nonexperimental settings? ○ as a general rule, studies are higher in external validity when the participants and situations studied are seminal to those that the researcher want to generalize to and participants encounter everyday, often described as mundane realism. how the conditions of an experiment matches real life ○ psychological realism if the same mental process is used in both the laboratory and in the real world. the extent to which the psychological processes, behaviors and reactions observed in a study’s accurately reflect those that occur in real life situations or naturally occurring event.s ○ BUT experiments that seem artificial may actually be not and given the way the study was conducted, it might be likely that the results can hold true when generalized. ○ ALSO experiments that are low in external validity are often conducted to learn about psychological processes that are likely to operate in a variety of people and situations Construct validity: quality of the experiment’s manipulations, the extent to which the test or measure assess what’s its supposed to measure. ○ operationalization: conversion from research question to experiment design  18 ○ the construct validity is high in experiments when the manipulations very clearly speak to the research question. ○ BUT adding more conditions does not necessarily mean increasing the construct validity. Statistical validity: speaks to whether the statistics conducted in the study support the conclusions that are made. ○ usually about small sample sizes ○ proper statistical analysis should be conducted on the data to determine whether the difference or relationship that was predicted was found. the number of conditions and the number of total participants will determine the overall size of the effect. with this information, a power analysis can be conducted to ascertain whether you are likely to find a real difference. ○ to design a statistically valid experiment, thinking about the statistical tests at the beginning of the design will help ensure the results can be believed. prioritizing variables: a research cannot have high validity in all four ares, but this discrepancy does not invalidate the study, only shows where they may be room for improvement for future follow-up studies ○ most psychology studies have high internal and construct validity but sometimes sacrifice external validity. Manipulation of the independent variable: to manipulate an independent variable means to change its level systematically so that the different groups of participants are exposed to different levels of that variable, or the same group of participants is exposed to different levels at different times. conditions: different levels of the independent variable manipulation of an independent variable must involve the active intervention of the researcher, which is crucial for eliminating the third-variable problem. ○ comparing groups of people who differ on the IV is not the same as manipulating that variable. in situations where the independent variable cannot be manipulated for practical and ethical reasons, an experiment is not possible and nonexperimental approaches must be utilized. in many experiments, the IV is a construct that can only be manipulated directly, where researchers often include manipulation check, which is a separate measure of the construct the researcher is trying to manipulate ○ null result: statistically nothing important is observed ○ null results can lead to two conclusions, which can be tested with manipulation check: manipulation failure no causal relationship  19 Control of extraneous variables: an extraneous variable is anything that varies in the context of study other than independent and dependent variables, they also include situational or task variables. they pose a problem because many of them are likely to have some effect on the dependent variable. this influencing factor can make it difficult to separate the effect of the IV from the effects of EV, which is why its important to control EV by holding them constant. ○ by holding the situation or task variable constant by testing the participants in the same location, giving them identical instructions, treating them in the same way, ○ by holding the participant variables constant and by limiting the participants to one very specific category of person (proposes a threat for generalizability, lowers external validity) EV make it difficult to detect the effect of the IV in two ways Extraneous variables as “noise”: adding variability to data. ○ although the mean difference between two groups of noised data can be the same as the ideal data, the difference will be much less obvious in the context of greater variability in the data. ○ making the effect of IV more detectable Extraneous variables as confounding variables: ○ confounding variable: an EV that differs on average across levels of IV, and provide an alternative explanation for any observed differences in the DV. Experimental Design (120) 1. Between-subject experiments: each participant is tested in only one condition. we divide the total number of participants in two or more groups depending on the condition number, meaning that every single participant is going under one single condition. it is essential that the researcher assign participants to conditions so that the different groups are, on average, similar to each other. ○ a matter of controlling extraneous participant variables across conditions so that they do not become confounding variables Random assignment: using a random process to decide which participants are tested in which conditions, a method for assigning participants in a sample to the different conditions we assume that EV are distributed also randomly across conditions, thus equal variance across conditions and its assumed that random assignment infer causality ○ a genuine or real experiment: random assignment + manipulation two criteria: ○ each participant has an equal chance of being assigned to each condition EV have an equal probability to be in either conditions ○ each participant is assigned to a condition independently of other participants one problem with strict procedures for random assignment is that they are likely to result in unequal sample sizes in the different conditions  20 block randomization: all the conditions occur once in the sequence before any of them is repeated. modified random assignment that keeps the number of participants in each group as similar as possible random assignment is not guaranteed to control all EV across conditions, but is usually not a major concern because: ○ it works better for larger samples ○ inferential statistics takes the fallibility of random assignment into account ○ confounding variable is likely to be detected when the experiment is replicated Treatment and control conditions: between-subjects experiments are usually used to determine whether a treatment works. treatment: any intervention meant to change people’s behavior for the better, which includes psychotherapies and medical treatments for psychological disorders but also interventions designed to improve learning, promote conversation and reduce prejudice etc. randomized clinical trial: in research on effectiveness of psychotherapies and medical treatments. treatment condition: receive treatment control condition: do not receive the treatment ○ no-treatment control condition: receive no treatment whatsoever ○ placebo condition: participants receive a placebo placebo: simulated treatment that lacks any active ingredient or element that should make it effective, where the positive effect of such a treatment is called the placebo effect. due to having the expectations to be healthier etc. 2. Within-subjects experiments: each participant is tested under all conditions, pretest and posttest needs fewer participants, time saving if N number of participants needed, that would be N x k for between subjects designs, where k is the number of conditions; but N number of participants is enough for within-subject design. practice trials to eliminate warm-up effects over trials it provides maximum control of extraneous participant variables. participants in all conditions have the same mean IQ, same socioeconomic status, same number of siblings and so on — because they are the very same people make it possible to use statistical procedures that remove the effect of these extraneous participant variables on the DV and therefore make the data less noisy and the effect of IV is easier to detect. Carryover effects and counterbalancing: carryover effect: an effect of being tested in one condition of participants’ behavior in later conditions.  21 ○ practice effect: where participants perform tasks better in later conditions because they had a chance to practice it ○ fatigue effect: where participants perform a task worse in later conditions because they become tired or bored context effect: being tested in one condition can also change how participants perceive stimuli or interpret their tasks in later conditions. order effect: where the order of the conditions might be influential of the result the order of conditions is a confounding variable, thus any difference between the conditions in terms of the dependent variable could be caused by the order of conditions and not the IV itself. counterbalancing: testing different participants in different order ○ used to solve the order effect ○ participants are assigned orders randomly (random assignment) but instead of randomly assigning conditions, they are randomly assigned to different orders of condition. ○ it controls the order of conditions so that its no longer a confounding variable ○ if there are carryover effects, it makes it possible to detect them by analyzing the data separately. Simultaneous within-subjects designs: there are many ways to determine the order in which the stimuli are presented, but one common way is to generate a different random order for each participant. Between-subjects or within-subjects: between: have the advantage of being conceptually simpler and requiring less testing time per participant, avoid carryover effect without the need for counterbalancing. within: have the advantage of controlling extraneous participant variables, which generally reduces noise in the data and makes it easier to detect a relationship between the independent and dependent variables. 3. Mixed design: contain both between-subjects and within-subjects designs Conducting Experiments (129) Recruiting participants: to use participants from a formal subject pool — an established group of people who have agreed to be contacted about participating in research studies. SONA system even if the participants in a study receive compensation in the form of course credit, a small number money, or a chance at being treated for a psychological problem, they are still essentially volunteers. it's worth considering because people who volunteer have been shown to differ in predictable ways from those who do not volunteer. the task is not recruiting participants but selecting them the point of having a well-defined selection rule is to avoid bias in the selection of participants.  22 Standardizing the procedure: experimenter expectancy effect: experimenter’s expectations about how participants should behave in the experiment affecting the outcome. since they might unintentionally give the treatment group participants clearer instructions or more encouragement or allow them more time to complete a task. the way to minimize unintended variation in the procedure is to standardize it as much as possible so that it is carried out in the same way for all participants regardless of the condition they are in. ○ protocol written in an extremely detailed manner ○ standard instructions read out word for word ○ automating the procedure as much as possible with computers ○ anticipate and answer possible participant questions ○ train multiple experimenters ○ make sure each experimenter tests participants completely double-blind study: experimenters to be blind to the research question or to the condition that each participant is tested in, minimizes experimenter expectancy. ,n double-blind participant is blind to the condition as well. ○ single-blind: participants don’t know the condition but the experimenter knows Record keeping: adding to the list about basic demographic information, the date, time and place of testing, name of the experimenter, comments about unusual occurrences, participant questions, and assigning identification number to each participant Pilot testing: small-scale study conducted to make sure that a new procedure works as planned, where you can recruit participants formally or informally. the number of participants can be small, but should be enough to give you a proper feedback and information about whether the procedure works. Chapter 7: Nonexperimental Research Overview of Nonexperimental Research (137) What is nonexperimental research: research that lacks the manipulation of an independent variable, random assignment of participants to conditions or orders of conditions, or both. When to use nonexperimental research: experimental research is appropriate when the researcher has a specific research question or hypothesis about a causal relationship between two variables — and it is possible, feasible, and ethical to manipulate the independent variable and randomly assign participants to conditions or to orders of conditions. nonexperimental research is appropriate — even necessary — when these conditions are not met. like when:  23 ○ the research question or hypothesis can be about a single variable rather than a statistical relationship between two variables ○ the research question can be about a noncausal statistical relationship between variables ○ the research question can be about a causal relationship, but the independent variable cannot be manipulated or participants cannot be randomly assigned to conditions or orders of conditions. ○ the research question can be broad and explanatory, or it can be about what it is likely to have a particular experience two approach can also be used to address the same research question in complementary ways. Types of nonexperimental research: single-variable research: it focuses on a single variable rather than a statistical relationship between two variables. ○ can answer interesting and important questions but cannot give statistical relationship correlational research: the researcher measures the two variables of interest with little or no attempt to control extraneous variables and then asses the relationship between them. quasi-experimental research: the researcher manipulates an IV but does not randomly assign participants to donations or orders on conditions qualitative research: has a separate set of analysis tools depending on the research question. like thematic analysis Internal validity revisited: experimental research tends to be higher in internal validity because it addresses directionality and third-variable problems through manipulation and the control of EV through random assignment. if the average score on the DV in an experiment differs across conditions its quite likely that the IV is responsible for that difference correlational research is lowest in internal validity because it fails to address either problem. if the average score on the DV differs across levels of the IV, it could be that the IV is responsible but they’re are other interpretations where even the direction of causality could be reversed. ○ quasi-experimental research is in the middle because the manipulation of the IV addresses some problems, but the lack of random assignment and experimental control fails to address others. Correlational Research (142) researcher measures two variables and assesses the statistical relationship between them w/little to no effort to control EV. reasons: ○ statistical relationship might not be a causal one ○ manipulation of IV is impossible, impractical, unethical variables can be quantitative or categorical  24 data collection in correlational research: ○ naturalistic observation: observing people’s behavior in the environment which it typically occurs (field research) ○ archival data: data that have already been collected for some other purpose ○ survey research: self-report data Quasi-Experimental Research (148) IV is manipulated but participants are not randomly assigned to conditions or orders of conditions eliminates directionality problem but not the third variable problem (confounding variable problem) nonequivalent groups design: btw-subjects design in which participants are not randomly assigned to conditions pretest-posttest design: within subjects design w/o counterbalancing ○ DV is measured once before the treatment and once after its implemented ○ alternative explanations: history: other things might have happened btw pre-post tests maturation: change in a way that they were going to anyway because they are growing and learning regression to the mean: statistical fact that an individual who scores extremely on a vfairbale on one occasion will tend to score less extremely on the next occasion. spontaneous remission: tendency for many medical and psychological problems to improve over time w/o any form of treatment interrupted time series design: like a pre-posttest design in that it includes measurements of the DV both before and after the treatment but it includes multiple pre-post test measurements taken at intervals over a period of time. combination designs: combining nonequivalent group design and pretest-posttest design to observe, not simply whether participants who receive the treatment improve but whether they improve more than the participants who do not receive the treatment. Qualitative Research (155) originated from anthropology, sociology generally begins with less focused research question, collect large amounts of relatively unfiltered data from a relatively small number of participants, and describe their data using non statistical techniques. less concerned with drawing general conclusions about human behavior than with understanding in detail the experience of their participants purpose: ○ can help researchers to generate new and interesting research questions and hypotheses ○ can provide rich and detailed description of human behavior in the real world context in which it occurs (thick description)  25 data collection: ○ interviews ○ focus groups ○ participant observation the quantitative - qualitative debate: ○ qualitative research lack objectivity and difficult to evaluate in terms of reliability and validity, do not allow for generalizability ○ quantitative research overlooks the richness of human behavior and experience, and answer simple questions, oversimplification and overgeneralization Chapter 9: Survey Research Overview of Survey Research (181) What is Survey Research? quantitative and qualitative method with two important characteristics: ○ the variables of interest are measured using self-report from respondents ○ considerable attention is paid to the issue of sampling (large and random samples) Most survey is non-experimental, used to describe a single-variable Constructing Survey Questionnaires (184) Answers can be influenced by question wording, order of the questions, options given, and etc. Survey Responding as a Psychological Process A Cognitive Model: Respondents must interpret the question, retrieve relevant information from memory, form a tentative judgment, convert the tentative judgment into one of the response options provided, and finally edit their response as necessary. What does the question include? What information should they retrieve? What mental calculations? How to interpret the options? Context Effects on Questionnaire Response: Unintended influences not related to the content of the items but to the context in which the item appears Item order effect: the order of appearing affecting people’s responses, where one item may change how future items are interpreted Response options provided when they are ranging, because people assume middle is the normal/typical.  26 Writing Survey Questionnaire Items: Types of Items: Open-ended items: simply asking a question and allowing participants to answer in whatever way they choose ○ Useful when don’t know how participants might respond, or to avoid influencing ○ More used in vague research question, in early stages ○ BUT need more effort and time for participants to formulate an answer and more difficult to analyze because they need to be transcribed, coded ad submitted to a qualitative analysis Close-ended items: asks a question and provides a set of response options for participants to choose from ○ When interested in a well defined variable/construct ○ More difficult to write but easier to analyze ○ Rating scale: ordered set of responses that participants must choose from Writing Effective Items: BRUSO model: brief, relevant, unambiguous, specific, objective Chapter 10: Single-Subject Research Overview of Single-Subject Research (200) What is Single-Subject Research? type of quantitative research that involves studying in detail the behavior of each of a small number of participants. Btw 2 and 10 participants Group research: studying large numbers of participants and examining their behavior primarily in terms of group means, standard deviations, and so on. Different from qualitative research because it focuses on objective behavior rather than subjective experiences and through experimental manipulation and control, collecting highly structured data, and analyzing those data quantitatively, instead of using narrative techniques. Case study: detailed description of an individual, which can include both qualitative and quantitative analyses ○ Suggest new research questions, illustrate general principles, understanding rare phenomena ○ Cannot determine whether specific events are causally related or even related at all ○ An individual case may be unrepresentative for population Assumptions of SSR: it is important to focus intensively on the behaviour of individual participants ○ group research can hide individual differences and generate results that do not represent the behaviour of any individual.  27 ○ sometimes it is the behaviour of a particular individual that is primarily of interest it is important to discover causal relationships through the manipulation of an independent variable, the careful measurement of a dependent variable, and the control of extraneous variables. ○ SSR has usually good internal validity it is important to study strong and consistent effects that have biological or social importance ○ Applied researchers are interested in treatments that have substantial effects on important behaviours and that can be implemented reliably in the real-world contexts in which they occur. (social validity) Single-Subject Research Designs (205) General Features: DV is measured repeatedly over time at regular intervals. Study is divided into distinct phases and the participants are tested under one condition per phase Reversal Designs (ABA): First phase: a baseline is established for the DV (before treatment) cont. until steady phase is achieved Second phase: researcher introduces the treatment again waited until steady phase is achieved Basic reversal design can be extended with the reintroduction of the treatment: ABABA… Multiple treatment reversal design: ○ ABCACB… ○ Changing of treatment orders for counterbalancing the carryover effects Alternating treatments design: ○ Two or more treatments are alternated relatively quick on a regular schedule ○ Used only when treatments are fast-acting Multiple-Baseline Designs: Problem with reversal design: ○ if the treatment is working then it might be unethical to remove it ○ DV may not return to baseline when treatment is removed A baseline is established for each several participants and the treatments are introduced for each one. Everyone is tested in AB design BUT treatment is introduced at different times for each participant if the dependent variable changes when the treatment is introduced for multiple participants—especially when the treatment is introduced at different times for the different participants—then it is extremely unlikely to be a coincidence Data Analysis: Visual inspection, plotting individual’s data then making judgements.  28 Inferential statistics are typically not used Factors: ○ Level: of he DV from condition to condition ○ Trend: gradual increases/decreases in the DV across observations ○ Latency: the time it takes for the DV to begin changing after a change in condition The Single-Subject vs. Group Debate (215) Data Analysis: visual inspection is inadequate for deciding whether and to what extent a treatment has affected a dependent variable ○ Not sensitive enough ○ Unreliable ○ Results cannot be efficiently summarized or compared across studies External Validity: the difficulty in knowing whether results for just a few participants are likely to generalize to others in the population (for SSR) Studying large groups of participants does not entirely solve the problem of generalizing to other individuals. (for group) As Complementary Methods: conceptualize single-subject research and group research as complementary methods that have different strengths and weaknesses and that are appropriate for answering different kinds of research questions SSR: ○ good for testing the effectiveness of treatments on individuals when the focus is on strong, consistent, and biologically or socially important effects ○ useful when the behaviour of particular individuals is of interest Group: ○ ideal for testing the effectiveness of treatments at the group level. ○ allows researchers to detect weak effects ○ good for studying interactions between treatments and participant characteristics ○ necessary to answer questions that cannot be addressed using the singlesubject approach, including questions about independent variables that cannot be manipulated Chapter 11: Presenting Your Research American Psychological Association (APA) Style (220) What is APA Style? set of guidelines for writing in psychology and related fields set down in the Publication Manual of the American Psychological Association Its purpose is to facilitate scientific communication by promoting clarity of expression and by standardizing the organization and content of research articles and book chapters.  29 Levels of APA Style: Organization: ○ Title page. Presents the article title and author names and affiliations. ○ Abstract. Summarizes the research. ○ Introduction. Describes previous research and the rationale for the current study. ○ Method. Describes how the study was conducted. ○ Results. Describes the results of the study. ○ Discussion. Summarizes the study and discusses its implications. ○ References. Lists the references cited throughout the article. Tone is formal, writing is straightforward, avoids biased language References and Citations: Author, A. A., Author, B. B., & Author, C. C. (year). Title of article. Title of Journal, xx(yy), pp–pp. doi:xx.xxxxxxxxxx Intext: (last name, year) Writing a Research Report in APA Style (229) Sections of a Research Report: Introduction: includes the opening, which introduces the research question and explains why it is interesting, the literature review, which discusses relevant previous research, and the closing, which restates the research question and comments on the method used to answer it. Method: that it should be clear and detailed enough that other researchers could replicate the study by following your “recipe.” it must describe all the important elements of the study—basic demographic characteristics of the participants, how they were recruited, whether they were randomly assigned, how the variables were manipulated or measured, how counterbalancing was accomplished, and so on. participants: subsection indicates how many participants there were, the number of women and men, some indication of their age, other demographics that may be relevant to the study, and how they were recruited, including any incentives given for participation. materials: multiple questionnaires, written vignettes that participants read and respond to, perceptual stimuli, and so on. design: overall structure. What were the independent and dependent variables? Was the independent variable manipulated, and if so, was it manipulated between or within subjects? How were the variables operationally defined? procedure: how the study was carried out. It often works well to describe the procedure in terms of what the participants did rather than what the researchers did.  30 Results: where you present the main results of the study, including the results of the statistical analyses. does not include the raw data—individual participants’ responses or scores—researchers should save their raw data and make them available to other researchers who request them. Remind the reader of the research question. Give the answer to the research question in words. Present the relevant statistics. Qualify the answer if necessary. Summarize the result. Discussion: Summary of the research Theoretical implications Practical implications Limitations Suggestions for future research Chapter 12: Descriptive Research Descriptive statistics refers to a set of techniques for summarizing and displaying data. Describing Single Variables (251) The Distribution of a Variable: the way the scores are distributed across the levels of that variable. Frequency Table: one can quickly see several important aspects of a distribution, including the range of scores, the most and least common scores, and any extreme scores that stand out from the rest. Histograms: graphical display of a distribution. It presents the same information as a frequency table but in a way that is even quicker and easier to grasp. variable on the x-axis, frequency on the y-axis. Distribution Shapes: unimodal, meaning it has one distinct peak followed by two tails, bimodal, meaning they have two distinct peaks. symmetrical: left and right halves are mirror images of each other skewed: its peak shifted toward the upper end of its range and a relatively long negative tail  31 ○ positively skewed: its peak toward the lower end of its range and a relatively long positive tail. ○ negatively skewed: peak towards the higher end of the range and a relatively long negative tail outlier: extreme score that is much higher or lower than the rest of the scores in the distribution. Measures of Central Tendency and Variability: Central Tendency (average): The central tendency of a distribution is its middle—the point around which the scores in the distribution tend to cluster. The mean of a distribution (symbolized M) is the sum of the scores divided by the number of scores. median is the middle score in the sense that half the scores in the distribution are less than it and half are greater than it. mode is the most frequent score in a distribution. Measures of Variability: variability of a distribution is the extent to which the scores vary around their central tendency. range, which is simply the difference between the highest and lowest scores in the distribution. standard deviation of a distribution is, roughly speaking, the average distance between the scores and the mean. variance is the mean of the squared differences (SD^2) Percentile Ranks and z Scores: percentile rank of a score is the percentage of scores in the distribution that are lower than that score. The z score for a particular individual is the difference between that individual’s score and the mean of the distribution, divided by the standard deviation of the distribution: ○ z = (X-M) / SD ○ z score indicates how far above or below the mean a raw score is, but it expresses this in terms of the standard deviation. ○ provide one way of defining outliers: z scores +-3.00 (scores that are more than three standard deviations from the mean) Describing Statistical Relationships (264) Differences Between Groups and Conditions:  32 usually described in terms of the mean and standard deviation of each group or condition. effect size: describes the strength of a statistical relationship ○ cohen’s d: most widely used measure of effect size for differences between group or condition means d = (M1 - M2) / SD SD is pooled SD: To compute the pooled within-groups standard deviation, add the sum of the squared differences for Group 1 to the sum of squared differences for Group 2, divide this by the sum of the two sample sizes. it has the same meaning regardless of the variable being compared or the scale it was measured on. Correlations Between Quantitative Variables: linear relationship: the points are reasonably well fit by a single straight line. non-linear relationships: points are better fit by a curved line pearson’s r: its possible values range from −1.00, through zero, to +1.00. A value of 0 means there is no relationship between the two variables. ○ mean cross-product of z scores ○ one starts by transforming all the scores to z scores. For the X variable, subtract the mean of X from each score and divide each difference by the standard deviation of X. For the Y variable, subtract the mean of Y from each score and divide each difference by the standard deviation of Y. Then, for each individual, multiply the two z scores together to form a cross- product. Finally, take the mean of the cross-products. Expressing Your Results (276) Presenting Descriptive Statistics in Writing: statistical results are always presented in the form of numerals rather than words and are usually rounded to two decimal places important to use parallel construction to express similar or comparable results in similar ways. Presenting Descriptive Statistics in Graphs: should always add important information rather than repeat information that already appears in the text or in a table.  33 as simple as possible interpretable on their own layout: ○ The graph should be slightly wider than it is tall. ○ IV should be plotted on the x-axis and the DV on the y-axis. ○ Values should increase from left to right on the x-axis and from bottom to top on the y-axis. axis labels and legends: ○ Axis labels should be clear and concise and include the units of measurement if they do not appear in the caption. ○ Axis labels should be parallel to the axis. ○ Legends should appear within the boundaries of the graph. ○ Text should be in the same simple font throughout and differ by no more than four points. captions: ○ should briefly describe the figure, explain any abbreviations, and include the units of measurement if they do not appear in the axis labels. ○ in an APA manuscript should be typed on a separate page that appears at the end of the manuscript. Bar Graphs: generally used to present and compare the mean scores for two or more groups or conditions. error bars: smaller vertical bars that extend both upward and downward from the top of each main bar, represent the variability in each group or condition. standard error: standard deviation of the group divided by the square root of the sample size of the group, used because a difference between group means that is greater than two standard errors is statistically significant used when variable on the x-axis is categorical Line Graphs: present correlations between quantitative variables when the independent variable has, or is organized into, a relatively small number of distinct levels. Each point represents the mean score on the DV for participants at one level of the IV. used when the variable on the x-axis is quantitative Scatterplots: used to present relationships between quantitative variables when the variable on the x-axis (typically the IV) has a large number of levels. Each point in a scatterplot represents an individual rather than the mean for a group of individuals Expressing Descriptive Statistics in Tables: same general principles as graphs  34 commonly used to present several means and standard deviations (usually for complex research designs with multiple IV and DV). table heading at the top of the table no vertical lines in the APA format correlation matrix Conducting Your Analyses (287) Preparing Your Data for Analysis: be sure they do not include any information that might identify individual participants be sure that you have a secure location where you can store the data and a separate secure location where you can store any consent forms. checking raw data to make sure that they are complete and appear to have been accurately recorded preparing data file Preliminary Analyses: assess the internal consistency of the measure analyze each important variable separately ○ Make histograms for each one, note their shapes, and compute the common measures of central tendency and variability. ○ understand what these statistics mean in terms of the variables you are interested in. identify outliers ○ is it incorrectly entered in the data file ○ doe sit represent some other kind of error, misunderstanding or lack of effort by the participant ○ keep notes on which responses or participants you have excluded and why, Answer Your Research Question: compute necessary calculations for what you are interested in explore your data for other interesting results that might provide the basis for future research (and material for the discussion section of your paper). ○ be careful for fishing, since complex sets of data are likely to include patterns that occurred entirely by chance Chapter 13: Inferential Research Understanding Null Hypothesis Testing (292) The Purpose of Null Hypothesis Testing:  35 the researcher’s goal is not to draw conclusions about that sample but to draw conclusions about the population that the sample was selected from. Thus researchers must use sample statistics to draw conclusions about the corresponding values in the population parameters: corresponding values in the population sampling error: random variability in a statistic from sample to sample any statistical relationship in a sample can be interpreted in two ways: ○ There is a relationship in the population, and the relationship in the sample reflects this. ○ There is no relationship in the population, and the relationship in the sample reflects only sampling error. The Logic of Null Hypothesis Testing: formal approach to deciding between two interpretations of a statistical relationship in a sample null hypothesis (H0): the idea that there is no relationship in the population and that the relationship in the sample reflects only sampling error. sample relationship “occurred by chance. alternative hypothesis (H1): the idea that there is a relationship in the population and that the relationship in the sample reflects this relationship in the population. steps of testing: ○ Assume for the moment that the null hypothesis is true. There is no relationship between the variables in the population. ○ Determine how likely the sample relationship would be if the null hypothesis were true. ○ If the sample relationship would be extremely unlikely, then reject the null hypothesis in favour of the alternative hypothesis. If it would not be extremely unlikely, then retain the null hypothesis. p-value: likelihood of the sample result if the null hypothesis were true ○ low p-value: the sample result would be unlikely if the null hypothesis were true (rejection of the null hypothesis). ○ high p-value: the sample result would be likely if the null hypothesis were true (retention of the null hypothesis) α: criterion for the how low must the p value be before the sample result is considered unlikely enough to reject the null hypothesis ○ usually 0.05 = less than a 5% chance of a result as extreme as the sample result if the null hypothesis were true ○ does not necessarily mean that the researcher accepts the null hypothesis as true—only that there is not currently enough evidence to conclude that it is true. most common misinterpretation is that the p value is the probability that the null hypothesis is true—that the sample result occurred by chance. The p value is really the probability of a result at least as extreme as the sample result if the null hypothesis were true. we do not draw conclusions about whether the null hypothesis is actually true or not  36 Role of Sample Size and Relationship Strength: the stronger the sample relationship and the larger the sample, the less likely the result would be if the null hypothesis were true —> lower the p-value sometimes the result can be weak and the sample large, or the result can be strong and the sample small. In these cases, the two considerations trade off against each other so that: ○ a weak result can be statistically significant if the sample is large enough ○ a strong relationship can be statistically significant even if the sample is small. Statistical Significance vs. Practical Significance: Practical significance refers to the importance or usefulness of the result in some real-world context. statistical significance does not necessarily mean the result is practically significant Some Basic Null Hypothesis Tests (300) The t Test: One Sample t Test: used to compare a sample mean (M) with a hypothetical population mean (μ0) that provides some interesting standard of comparison. (null) μ = μ0 (alt) μ ≠ μ0 test statistic is a statistic that is computed only to help find the p value. degree of freedom for one sample t test: N-1 ○ changes the precise shape of the distribution of t scores t table provides critical t values of t for different df for different α. two tailed test: where we reject the null hypothesis if the t score for the sample is extreme in either direction ○ used when we do not expect the difference of sample and population to go in a particular direction  37 one tailed t test: where we reject the null hypothesis only if the t score for the sample is extreme in one direction that we specify before collecting the data. Dependent Samples t Test (paired-samples): used to compare two means for the same sample tested at two different times or under two different conditions. ○ pretest-posttest design or within-subject experiments (null) means at the two times or under the two conditions are the same in the population. (alt) they are different special case of one sample t test first step: to reduce the two scores for each participant to a single difference score by taking the difference between them. ○ positive and negative signs are important for reducing them to a difference score ○ hypothetical population mean (μ0) of interest is 0 because this is what the mean difference score would be if there were no difference on average between the two times or two conditions. (null) μ0 = 0 (alt) μ0 ≠ 0 Independent Samples t Test: used to compare the means of two separate samples (M1 and M2) between subjects experiments or preexisting groups in a correlational design (null) μ1 = μ2 (alt) μ1 ≠ μ2 N refers to the total sample size, n refers to the group sample size df = N-2 Analysis of Variance (ANOVA): when there are more than two groups or condition means to be compared One-Way ANOVA: used to compare the means of more than two samples (M1, M2...MG) in a between-subjects design. (null) μ1= μ2 =...= μG (alt) at least ONE is different test statistics: F ratio, ratio of two estimates of the population variance based on the sample data  38 ○ MSB: mean squares between groups, based on the differences among the sample means ○ MSW: mean squares within groups, based on the differences among the scores within each group ○ F = MSB / MSW distribution shape depends both on the number of groups and the sample size ○ dfB = G - 1 ○ dfW = N - G ANOVA elaborations: post hoc comparisons: ○ rejecting null in ANOVA can mean different things: With three groups, it can indicate that all three means are significantly different from each other. Or it can indicate that one of the means is significantly different from the other two, but the other two are not significantly different from each other. ○ SO ANOVA results are followed up with series of post hoc comparisons of selected pairs of groups to determine which are different from each other ○ one approach includes conducting series of independent-samples t test comparing each group mean to every other If we conduct several t tests when the null hypothesis is true, the chance of mistakenly rejecting at least one null hypothesis increases with each test we conduct. ○ several modified t test procedures, which keep the risk of mistakenly rejecting a true null hypothesis to an acceptable level Bonferonni procedure, Fisher’s least significant difference (LSD) test, and Tukey’s honestly significant difference (HSD) test. repeated-measures ANOVA: ○ appropriate for within-subjects experiments ○ basics are the same as one-way ○ main difference: measuring the dependent variable multiple times for each participant allows for a more refined measure of MSW. lower value of MSW means a higher value of F and a more sensitive test factorial ANOVA: ○ when more than one IV is included in the factorial design ○ basics are the same ○ main difference: produces an F ratio and p value for each main effect and for each interaction. Testing Pearson’s r: For relationships between quantitative variables, where Pearson’s r is used to describe the strength of those relationships, the appropriate null hypothesis test is a test of Pearson’s r. (null) rho = 0  39 (alt) ρ ≠ 0 also possible to use pearson’s r for the sample to compute a t score with N-2 df. Additional Considerations (315) Errors in Null Hypothesis Testing: conclusions are not guaranteed to be correct type 1 error: rejecting true null hypothesis ○ sampling error ○ α as the type 1 error rate type 2 error: retaining false null hypothesis ○ lacking adequate statistical power (small sample size) reducing α to reduce the type 1 error risk increases type 2 error risk. thus its important to find a balance between two file drawer problem: the tendency to submit significant results when non-significant ones are not accepted/published. Statistical Power: statistical power of a research design is the probability of rejecting the null hypothesis given the sample size and expected relationship strength. Statistical power is the complement of the probability of committing a Type II error. (1 - p) Problems With Null Hypothesis Testing and Some Solutions: Criticism of Null Hypothesis Testing: the p value is widely misinterpreted as the probability that the null hypothesis is true. misinterpretation is that 1 − p is the probability of replicating a statistically significant resul the strict convention of rejecting t