Psy 311 - Advanced Research Methods (1S) PDF

`Psy 311 - Advanced Research Methods (1S) INTRODUCTION 4th Oct’23 The term psychology is derived from the root words ‘psyche’ meaning mind and ‘logos’ meaning study. This psychology is defined as the scientific study of behavior and mental process. Behaviors are things that are observable, while me...

`Psy 311 - Advanced Research Methods (1S) INTRODUCTION 4th Oct’23 The term psychology is derived from the root words ‘psyche’ meaning mind and ‘logos’ meaning study. This psychology is defined as the scientific study of behavior and mental process. Behaviors are things that are observable, while mental processes refer to non-observational internal experiences such as dreams, thought, perception, feelings, etc. The aim of science is to produce knowledge to know, understand, and explain some aspects of the world around us. Psychology is science because it takes general approach as biology, astronomy, chemistry, and physics to understanding one aspect of natural world human behavior. SOURCES OR METHODS OF KNOWING 1. Authority: This is the source of knowing where knowledge is gained from the source that is judged to be an expert or influential in some way, it could be a person; children and their parents, doctors and their patients, lecturers and their students or textbooks, congregations and their leaders, or a book which tells us how things are done that no argument or alternatives are allowed. Authority can sometimes be wrong and lead people astray; e.g doctors can misdiagnose their patients, textbooks can be published with inaccurate information, lecturers can be biased to their students. 2. Rationalization: It involves using logic and reasoning; a premise is stated and logical rules are followed to arrive at conclusions. For example, if given the premise that all girls like money, Jane is a girl and it is logical to conclude that Jane likes money. The problem is that if the premise is wrong the conclusion will not be valid. The conclusion depends on the truth of the first statement. 3. Intuition or Common Sense: This is knowledge that is based on feelings on instinct that may or may not turn out to be true. It involves believing what feels true rather than using fact. We all have intuiting beliefs about people’s behavior, thoughts, and feelings that are sometimes reasonably accurate however most of it is not. For example, most people believe that anger can be relieved by letting it out. Perhaps by punching something or screaming loudly. Scientific research however has shown that this approach tends to leave people feeling more angry not less (Bushman 2002). Our intuitions can be wrong because it involves cognitive and motivational biases rather than logical reasoning or scientific evidence. People’s intuition about human behavior often turns out to be wrong. This is one primary reason that psychology relies on science rather than common sense. 4. Empiricism: This is the accepted and reliable way of knowledge in psychology. …scientific empiricism requries a research …… Psychology uses the  scientific method which is the process of systematically collecting and evaluating evidence to test ideas and answer research questions. The researcher 5. Psychology covers a wide range of topics and interests. Psychologists study normal and abnormal behaviors, such as sleep, emotion, intelligence, childhood, memory, personality. 5. Knowledge of research methods will make you a more informed and critical consumer of information. It helps us to intelligently understand and evaluate day to day information we encounter. We become more sensitized to flaws in the information we receive. 6. As a professional practitioner of psychology whether clinical psychologist, counselor, or school psychologist, you will need to do research at the graduate school level so the course in methodology is an obvious first step in learning the necessary skills. FIRST STEP - Your chances of getting into any type of graduate program have improved significantly if: - You did well in undergraduate research methods and statistics courses. - You were involved in doing some research as an undergraduate. 7. Update your knowledge: you will have a better understanding of where scientific knowledge in psychology comes from and appreciation of its strengths and limitations and an awareness of how it can be applied to solve practical problems in psychology and …? As a practitioner psychologist, your research skills will be invaluable even if you don’t do research, you will need to keep up with the latest research in your area of expertise and be able to read research critically. FEATURES OF SCIENTIFIC METHOD 11th, Oct ‘23 All scientific studies shares certain characteristics and features the first is systematic empiricism: 1. EMPIRICISM Empiricism is a way of understanding the world that relies directly or indirectly on what we experience through our senses; sight, hearing, taste, touch, and smell. Empiricism refers to learning based on observation and scientists learn about the natural world systematically by carefully planning, making, recording, and analyzing observations of it. The scientist’s systematic observation include using: a. Precise definitions of the phenomena being measured. b. Reliable and valid measuring tools that yield useful and interpretable data. c. Generally accepted research methodologies. d. A system of logic for drawing conclusions and fitting those conclusions into general theories. 2. OBJECTIVITY Objectivity means observation that is free from emotion or human bias or preconception. However, objectivity in its true sense is rarely ever possible because our interpretation of events is inevitably distorted to some extent by factors not under our conscious control, such as our past and present experiences, culture, language, beliefs, and  expectations. Thus, objectivity in science means agreement on the results of a given observation by two or more independent observers working under the same conditions. This usually takes the form of defining the terms and research procedures precisely enough so that any other person can systematically repeat the research and presumably achieve the same observable outcome. This is known as replication. In this way, they can decide whether a researcher’s subjectivity has distorted the conclusions. 3. VERIFIABLE After asking their empirical questions, making their systematic observations, and drawing their conclusions, scientists publish their work. This usually means writing an article for publication in their journal in which they put their research question in the context of previous research, describe in detail the methods they used to answer their research question. The explanation and findings of the research must be clearly communicated to others. Publication is an essential feature of science for two reasons; One is that science is a social process, that is it is a large-scale collaboration among many researchers distributed across both time and space. Our current scientific knowledge of most topics is based on many different studies conducted by many different researchers who have shared their work publicly over many years. The second is that publication allows science to be self-correcting. Individual scientists understand that despite their best efforts, their methods can be flawed and their conclusions incorrect. Publications allow others in the scientific community to detect and correct these errors so that over time scientific knowledge increasingly reflects the way the world actually is. As results are replicated, public confidence in  the reality of some psychological phenomenon is increased while questions are raised when results cannot be replicated. THE STEPS IN CONDUCTING PSYCHOLOGICAL RESEARCH Psychology uses the scientific method which is the process of systematically collecting and evaluating evidence to test ideas and answer research questions. The researcher (or group of researchers) will:  a. Ask or formulate a research question. For example; does emotion affect educational performance or why do students experience exam anxiety or how does time management during the academic session affect involvement in exam practice or attitude towards exam malpractice. b. Conduct a study or experiment designed to answer the research question. c. Analyze the data from the study. d. Draw conclusions about the result and report the findings. e. Invite others to replicate the results. ETHICS IN PSYCHOLOGICAL RESEARCH Ethics is the branch of philosophy that is concerned with morality, that is what it means to behave morally and how people can achieve that goal. It can also refer to a set of principles and practices that provide moral guidance in a particular field. There is an ethics of business, medicine, teaching, and of scientific research. Many kinds of ethical issues can arise in scientific research especially when it involves human participants. Ethics consist of standards of right and wrong. It tells us how to act in moral and responsible ways when doing research. Scientists are supposed to conduct their research with care, be truthful in reporting their findings and be open to criticism and new ideas. The APA’s ethical principle for psychologists and code of conduct, also known as the APA ethics code, was first published in 1953 and has been revised several times since then, most recently in 2002. It includes about 150 specific ethical standards that psychologists and their students are expected to follow when conducting research. It includes guidelines for psychological research that uses both human participants and animal subjects. There are three groups of people that are usually affected by scientific research. a. The research participants b. The scientific community c. The society. Consequently, there are three broad areas of ethical concerns a. The ethics of treatment of participants. b. The ethics of data collection and analysis. c. The ethics of responsibility to society. ETHICS OF TREATMENT OF PARTICIPANTS 16th, Oct ‘23 Researchers have ethical obligations regarding the treatment of their participants. Several portions of the ethics code are designed to ensure that participants are treated fairly and with respect during their participation, that they receive complete information about the study and its conclusion, that any stress they encounter is relieved and that they’re participation is kept in confidence. There are four major areas of concern in this regard, a. The Potential Harm: Participants in the research have a right to personal safety. Researchers should not expose participants to substantial risk of physical or psychological harm unless the benefits of participation exceed the risk and the participants knowingly choose to participate. Harm is not only physical (physical harm may include pain, illness, injury, dizziness, nausea, noise, electric shock, heat, or cold. It can also be personal (humiliation or embarrassment, discomfort, loss of respect, damage to their employability, loss of income, etc), psychological  (anxiety, depression, guilt, shock, loss of self esteem, etc), and social (by losing their trust in others or losing their social network. For example, survey researches can harm participants by asking questions about illegal behavior that could put them at risk of criminal prosecution if the information is disclosed. Ethical practices that are designed to protect participants from harm include: Researchers should inform participants of any reasonable or foreseeable risk or discomfort before the study commences so that they can decide whether or not to participate. Researchers should screen out research participants who might be harmed by the research procedures. If stress or potential harm is possible, measures should be taken to assess harm after the study and participants should be informed of procedures for contacting the researcher for follow-up counseling or debriefing. b. Informed Consent Participants should be given enough information about the study’s purpose and procedures in order to decide if they wish to volunteer. Participants should not be coerced into participating in social research but should be made to understand that their participation is voluntary. Just how much information should be shared with the participants depends on the nature of research. Full disclosure about the research purpose and procedure is usually not necessary. However, tell participants the general purpose of the research and who is sponsoring it. Tell participants that their participation is voluntary, and that they’re free to withdraw from the study at any time. A written consent form should be signed by the participants of their legal guardian. c. Use of Deception Deception occurs when researchers deliberately mislead or misinform participants about some aspects of the study. Some scholars believe that without the use of deception it would be difficult to effectively study many forms of behavior such as aggression, conformity, and helping behavior during an emergency. In the absence of deception in certain studies participants would not act naturally. The prevailing sentiment therefore, is that deception is permissible to some extent as long as: It is used as a last resort after careful consideration of alternative procedures. The information to be gained outweighs the negative impact of deceiving the participants. Care is taken to debrief the participants afterwards and ensure that they leave the study in a positive frame of mind. d. Privacy Invasion Research participants should be confident that their identities would not be known by anyone other than the researcher or group of researchers and that only group or disguised data will be reported. The more sensitive the research material, the greater the care that must be exercised in obtaining, handling, and storing the data. To minimize the risk of loss of confidentiality, researchers should only collect personal information that is absolutely essential to the research activity. If personal data is to be collected, it should be coded as early in the activity as possible and securely stored. Researchers should use all means possible to protect the confidentiality of information provided by research participants. For example, by removing names, and other identifying information from the data (anonymity) by not disclosing individual identities in any report of the study and by not divulging  information to a third party without the research participant’s permission. The only exception to this occurs in cases where researchers might be compelled by law to report certain things disclosed by participants. For example, child abuse of a clear intent to harm oneself or another person. ETHICS OF DATA COLLECTION AND ANALYSIS (SCIENTIFIC FRAUD) Research psychologists in particular are expected to be scrupulously honest in all of their scientific activities. It is a researcher’s obligation to others and to their discipline, to make sure that their data are sound and trustworthy. The APA ethics code states that, “Psychologists should seek to promote accuracy, honesty, and truthfulness in the science, teaching, and practice of psychology” (APA, 2002 p.1062). WHAT IS SCIENTIFIC FRAUD? Scientific or research fraud is fabrication, falsification, or deception in conducting or reporting research results in order to secure unfair or unlawful gain. For example; publication, promotion, awards, or graduation. There are two major types of fraud in science TYPES OF FRAUD 1. Data falsification The integrity of data is an issue of pivotal importance and can take several forms:  - Scientific research: This type of fraud can take several forms. Data falsification: This is when a Scientist fails to collect any data at all and Simply manufactures it. Altered data: Some of the collected data are altered or omitted to make the overall results look better. Guessed data: This is when data is collected but missing are guessed at or created in a way that produces a data set that agrees with the researcher’s expectation. When the researcher fails to report results that contradict a favored hypothesis or an entire study is suppressed because its results failed to come out as expected. Applying an appropriate statistical test that will yield significant results. In each of these cases, the deception is deliberate and the researcher presumably secures an unfair or unlawful gain. How to Identify Scientific Fraud. a. Failure to replicate findings of the research b. An unwillingness to share findings with colleagues c. Through the pair review process. How can researchers guard against data falsification? a. Scientists are expected to be ethical in their research by following procedures scrupulously and never succumbing to the temptation to manufacture even a single piece of data. b. Never discard data from a participant unless there are clear procedures for doing so, and these procedures are specified before the research or experiment begins. For example, if the participant doesn’t follow procedures or if the experimenter doesn’t administer the procedure correctly.  c. Keep the raw data set or at the very least, the data summary sheet. Your best protection against an accusation that your result seemed unusual is your ability to produce the data on request. d. A researcher should place the pursuit of knowledge above personal gain or the promotion of a particular philosophy or ideology. 2. Plagiarism. According to the APA, Plagiarism is the act of using another person’s words, ideas, phrases, sentences, results or images without giving appropriate credit or acknowledgement to the author. Proper acknowledgement generally means indicating direct quotations with quotation marks and providing a citation to the source of any quotation or idea used. TYPES OF PLAGIARISM There are two types of plagiarism 1. WORD PLAGIARISM (Improper uses of someone else’s word) According to www.plagiarism.org, all the following are considered plagiarism. ➔ Turning in someone else’s work as your own. ➔ Quotation: using someone’s exact words (word for word) or direct quotes without using quotation marks, citations and page numbers. ➔ Using an author’s exact or similar words and including only an in-text citation. An example of plagiarism is; education in any society tends to reflect the political philosophy of that society. (Kirk, 1972). This is plagiarism because there is no quotation mark or page number. The  correct way should be; “education in any society tends to reflect the political philosophy of that society.” (Kirk, 1972, page 3). ➔ Giving incorrect quotation of the source or the idea. For example; Kephart believed that a child’s first encounter with the environment through their motor activity is the prerequisite for later learning (Kephart, 1964). This is plagiarism because I found this source in Kirk’s (1972) book. The right way to cite the source is (Kephart, 1964 as cited in Kirk, 1972). ➔ Paraphrasing: This involves changing words, but copying the sentence structure of the source without giving credit. For example, we can paraphrase by saying the political philosophy of a society influences its educational practices (Kirk, 1972). ➔ Copying so many words or ideas from a source, that it makes up the majority of your work, even when proper credit and citation are done. The work is no longer considered original but rather plagiarized. 2. IDEA PLAGIARISM (Improper uses of someone else’s ideas). This is taking the intellectual property of another person and proceeding with the idea as your own. It is also when a good argument or concept from a source is presented as if it is yours. Plagiarism in any form whether intentional or accidental is a serious offense and violates ethical standards. HOW TO AVOID PLAGIARISM a. Use direct quotes sparingly and only when it is important to reproduce both what was said and how it was said. When you use someone else’s word verbatim, place those words in quotation marks to let your readers know that these are not your original words, then add an in-text citation that includes the author’s name, the year and the page number.  b. Paraphrase or rewrite the ideas of others using your own sentence. Do not use the same words or sentence structure that is similar to the original. As a general rule, paraphrase when taking notes on a source. Write the paraphrase without looking a the original work. c. Summarize: To summarize is to condense the original sentence using your own words. Do not alter the author’s original idea and meaning. After summarizing, cite the author’s name and year. In general, it is better to summarize and paraphrase than to use numerous quotations in your work. d. Originality: Let your research study be your original idea. There will be fewer chances of plagiarism. Also, use multiple sources of information. ETHICS OF RESPONSIBILITY TO SOCIETY 23 | 10 | 23 Researchers are concerned not only about the ethical implications of their work to research participants, but also the moral and ideological implications of their work to the larger society. There are two main ethics of responsibility to society. 1. POSITION OF NEUTRALITY: Science is non-moral, and a researcher’s only duty is to present their relevant findings and theoretical interpretations. Researchers can take a moral position in their capacity as private citizens, but should not let their personal values affect their research. As much as possible, researchers should guard against bias they may have entered the research with, and carefully note the limitations of their conclusions.  2. APPLICATION OF RESEARCH FINDINGS: Researchers have an obligation to consider how their findings will be used. It is the duty of the researcher to ensure that their research is not misused or misinterpreted by others and to take reasonable steps to correct or minimize misuse. This is because the findings of research can have a major impact on social policy. For example, the supreme court of the United States decision of 1954 (Brown vs. Board of Education Topeka) to end the segregation of black and white children in education was largely based on research findings which showed the detrimental psychological impact. STEPS RESEARCHERS CAN TAKE TO MINIMIZE MISUSE OF RESEARCH FINDINGS 1. Researchers can disseminate knowledge to the widest possible audience. 2. Researchers should increase public knowledge and encourage debate so that no one group can exploit the knowledge for its own welfare. 3. When a research has immediate applications, it is the duty of the researchers to actively promote appropriate use and prevent misuse of their findings. 4. Researchers should assume responsibility collectively for the application of their research through organizations that communicate on their behalf and they should provide a forum for the discussion of policy related issues. RESEARCH DESIGN: TYPES OF PSYCHOLOGICAL RESEARCH DESIGN WHAT IS A RESEARCH DESIGN? A research design is the overall plan or framework for the study you want to conduct. The researcher must select an appropriate strategy for making the observations that will answer the research questions or provide an adequate test of the hypothesis. Most researchers use a combination of methods. The research design does several things. 1. It provides the structure on how the major parts of the research study e.g the participants, instruments, procedure, and data analysis, work together to address the research question. 2. It guides how the research question or the hypothesis should be written. Several factors affect what type of design a researcher selects including the nature of the research problem, the research goals, the available resources, and the disciplinary and personal preference. Note that thinking through some of these issues in advance will help to prevent serious mistakes and omissions in a study. However, not all problems can be foreseen and some of the decisions at the design stage may change as the work progresses. TYPES OF RESEARCH IN PSYCHOLOGY 1. Basic vs Applied Research Basic research is research that is curiosity-driven and motivated by a desire to expand knowledge. It aims at expanding knowledge by creating new theories. Confirming theories, or modifying existing theories. It is intended to answer the what, why, and how questions of psychology in order to achieve better or more detailed understanding of the fundamental principles of behavior and mental processes. Basic research is aimed to increase knowledge on a topic and not to come up with practical solutions. For example, how does caffeine consumption affect the brain and body, how do panic attacks happen, what are the symptoms of anxiety disorder, are men or women more likely to be diagnosed with depression. Applied research is research that has direct and immediate relevance to real world problems. It is research that is concerned with more relevant problems and is designed to solve them, that is to meet the last goal of psychology which is to change or control them. In many cases, the principles and procedures derived from basic research can potentially be used in a variety of applied situations. Hence, applied research is often a follow-up research design for basic research because it follows up the outcomes to validate the findings in solving real world problems. For example, research to determine what interventions work best for depression in women or what treatment options there are for anxiety disorder or which methods work best to increase employee productivity. Applied research outcomes frequently have relevance for basic research by providing evidence that either support or refute theories. 2. Laboratory vs Field Research Another way of classifying research studies is by location.This distinction hinges on whether the study occurs inside or outside the controlled environment of a laboratory. Laboratory research is research that takes place in a laboratory environment under controlled conditions. This type of research allows the researcher greater control of the study conditions such as the place, time, and participants. Conditions of the study can be specified more precisely and participants can be selected and systematically placed in the different experimental groups and conditions in the study. Because the laboratory environment offers more control, the data collected are typically more precise and less likely to be influenced by extraneous variables. Field experiments involve conducting research in an environment that closely matches the situation we encounter in our daily lives. For example, when psychologists conduct surveys for different groups of people on the streets to find out their thoughts about a certain topic. Field research has several advantages or stress; a. For example, certain conditions in the field cannot be duplicated in a laboratory such as how animals search for food in the wild. b. You can confirm the findings of laboratory studies and correct misconceptions or over simplications that might derive from the safe confines of the laboratory. c. Field research provides the opportunity to make discoveries that could result in an immediate difference in the lives of the people being studied.  The disadvantage of field research is that researchers have less control over extraneous variables. 3. Quantitative vs Qualitative Research Most research in psychology is quantitative in nature. WIth quantitative research the data are collected and presented in the form of numbers and statistics. For example, the average scores of different groups on some task, percentages of people who do one thing or another, graphs and tables of data and so on. This type of research is used to test and or confirm hypotheses and theories. Thus, the results are analyzed using statistical tests, for example, experiments, and some types of observations and surveys with close-ended questions. Qualitative research is research that is expressed in words and seeks to understand and describe concepts, people’s feelings or experiences about a particular phenomenon. It enables the researcher to collect in depth information about a topic that is not well understood. It includes studies that collect interview information with open-ended questions either from individuals or groups. Unlike descriptions of results in quantitative studies, which focus on numerical data and statistical analysis, results in qualitative studies often take longer to describe and include quotes that are said to represent typical responses. CRITICISM OF QUALITATIVE RESEARCH 25|10|23 a. Because of the time and cost involved in qualitative research design, they do not generally use samples from large scale data sets i.e they use very small sample b. It lacks objectivity and it is difficult to evaluate its reliability and validity.  c. It does not allow for generalization to people or situations other than those actually studied. d. The time required for data collection, analysis, and interpretation is lengthy. e. Data analysis is difficult and expert knowledge of an area is necessary to try to interpret qualitative data. SOLUTIONS OF QUALITATIVE RESEARCH a. The quantitative and qualitative approaches can be combined, this is known as mixed method research. In mixed method research qualitative research can be used for hypothesis generation and quantitative research for testing this hypothesis, or the other way round, qualitative research can be used to explore more of a subject in which the hypothesis has been tested. TYPES OF RESEARCH DESIGN The types of research design are; a. Experimental research b. Non-experimental research i. Quasi-experimental research ii. Correlational research iii. Survey research iv. Qualitative research 1. Experimental Research An experiment is a type of study designed specifically to answer the question of whether there is a causal relationship between two variables. In other words, whether changes in one variable referred to as the independent variable causes changes in another variable referred to as the dependent variable. Any experiment can be described as a study investigating the effect of x on y because it is only through an experiment that a researcher can isolate a single factor and determine the effect of that factor alone on a particular behavior. For example, the effect of violence on TV on aggressive behavior. SEVERAL FUNDAMENTAL FEATURES OR CHARACTERISTICS OF AN EXPERIMENT a. Manipulation of an independent variable: To manipulate an independent variable means to change its levels systematically so that different groups of the participants are exposed to different levels of that variable OR the same group of participants are exposed to different levels of the variables at different times. The researcher manipulates or systematically varies the levels of the independent variable. The different levels of the independent variable are called conditions. Independent variables must have a minimum of two conditions i.e at the very least, an experiment involves a comparison between two groups or situations. For example, to see whether expressive writing affects people’s health, a researcher might instruct some participants to write about traumatic experiences and others to write about neutral experiences. The different levels of the independent variable in this study are traumatic experiences and neutral experiences and researchers often give the conditions short descriptive names to make it easy  to talk and write about them. In this case, the conditions can be called the traumatic condition and the neutral condition. The manipulation of an independent variable must involve the active intervention of the researcher. Comparing groups of people who already differ from the independent variable before the study begins is not the same as manipulating that variable. For example, if a researcher compares the health of people who already keep a journal with that of people who do not keep a journal, the researcher has not manipulated the variable and therefore has not conducted an experiment. The active manipulation of the independent variable is crucial for eliminating alternative explanations for the results. However, there are many situations in which the independent variable cannot be manipulated either for practical or ethical reasons and therefore an experiment is not possible in such situations. b. Experimental design The independent variables in an experimental study are referred to as factors. The design that researchers use to explore the joint effect of two or more variables in a study is known as a Factorial Design. Experiments involving a single independent variable with two conditions are often referred to as a Single Factor Two-Level Design. When an experiment has one independent variable that is manipulated to produce more than two conditions it is referred to as a Single Factor Multi-Level Design. RESEARCH HYPOTHESIS FOR SINGLE FACTOR EXPERIMENTAL DESIGN: There will be a significant effect of the independent variable on the dependent variable. For example, there’ll be a significant effect of expressive writing on health status or a significant effect of watching violence on TV on children’s aggressive behavior. ANALYZING SINGLE FACTOR TWO LEVEL DESIGN To determine whether the differences found between the two conditions of a single independent variable are significant or simply due to chance, some form of inferential statistical analysis is required. When interval or ratio scales of measurement are used in the experiment, the most common approach to analysis is to use one of two varieties of the t-test. The first is the t-test for independent samples, which is used when the two groups of participants are completely different from each other. The second is a t-test for related samples that is the repeated measures design which is used when the two groups have the same participants. Even though t-tests are normally used when the independent variables have just two levels, a One-Factor/ One-Way ANOVA could also be used in this situation. ANALYZING A SINGLE FACTOR MULTI-LEVEL DESIGN Completing multiple t-tests for a single factor multi-level design increases the risk of making a type one error. That is, the more t-test you calculate all conditions, the greater the chances of accidentally yielding significant differences. Studies using more than two-levels of an independent variable, are normally evaluated statistically with a one way analysis of variance. A one way analysis of variance tests for the presence of some overall significance that could exist somewhere among the various levels of the independent variable. A significant f-ratio results in subsequent post hoc testing. For example, (Tukey’s HSD test) , to identify precisely which means and conditions differ from each other. For example, in a study with three conditions, subsequent testing will analyze each of the three conditions in pairs but only after the overall ANOVA has indicated that some significant difference exists. A typical procedure is the test called Tukey’s HSD test, with HSD standing for Honestly Significant Difference. If the ANOVA does not find any significance, subsequent testing is normally not done. FACTORIAL DESIGN 30 | 10 | 23 When a study has more than one independent variable, it is called a factorial design. First, a factorial design is described with a numbering system that simultaneously identifies the number of independent variables and the number of levels (conditions) of each variable. Therefore, a 2 x 3 (Read this as two by three) factorial design has two independent variables and 6 conditions. The first independent variable has two levels and the second independent variable has three levels. Or a 2 x 2 (two by two) factorial design which has two independent variables with two conditions each and the total number of conditions/levels is 4. Or a 3 x 2 (three by two) factorial design which has two independent variables. The first one has three conditions and the second one has two conditions being a total of 6 conditions. Or a 2 x 3 x 4 factorial design (two by three by four). This design has 3 independent variables with 2, 3, and 4 conditions respectively being a total number of 24 conditions. N/B: The number of conditions is gained by multiplication. Second, the total number of conditions to be tested in a factorial study or design can be identified by looking at all possible combinations of the different levels of each independent variable. RESEARCH HYPOTHESIS FOR FACTORIAL DESIGN. In factorial design studies, two kinds of results are possible or derived: main effects and interaction effects. 1. MAIN EFFECT The term main effect is used to describe the overall effect of a single independent variable. For example in a study with two independent variables (two by two factorial design) there can be at most two significant main effects. For example, Effect of exercise and time on blood pressure: Hypothesis: - There will be a significant main effect of exercise on blood pressure. - There will be a significant main effect of time on blood pressure. 2. INTERACTION EFFECT An interaction is said to occur when the effect of one independent variable depends on the level of another independent variable. Interactions examine whether the variables combine to form a more complex result. For example, Effect of exercise and time on blood pressure: Hypothesis:  - There will be a significant interaction effect of exercise on blood pressure. - There will be a significant interaction effect of time on blood pressure. Interactions often provide the most interesting results in a factorial study, in fact interactions sometimes render main effects irrelevant. Even if no significant main effect is found, an interaction effect can be found which can produce an interesting outcome. There are many possible patterns of results that can occur in a factorial design. In a simple two by two factorial design for example, there are eight different possible results: - You can find a significant main effect for the first factor only. - You can find a main effect for the second factor only. - You can find a main effect for both first and second factor but no interaction effect. - There’s a significant main effect for the first factor and an interaction effect. - There’s a significant main effect for the second factor and an interaction effect. - There’s a significant main effect for both factors and an interaction effect. - There’s a significant interaction effect only with no main effect. - There’s a significant main effect and no significant interaction effect.  ANALYZING FACTORIAL DESIGN. Factorial designs using interval or ratio data are analyzed with N-Factor ANOVA with N referring to the number of independent variables (factors involved in the study). Hence, a 2 x 3 factorial design will be analyzed using a two-way ANOVA and a 2 x 2 x 4 factorial design with a three-way ANOVA. In principle, factorial designs can include any number of independent variables but in practice, it is unusual to have more than 3 independent variables with more than 2 or 3 conditions each. This is because the number of conditions can become unmanageable and it may not be feasible to get the number of participants required to populate each of these conditions. For a factorial design, more than one F-ratio will be calculated. Specifically, there will be an F-ratio for each main effect and for each possible interaction effect. For example, in an A x B x C factorial design. There will be seven f-ratios calculated; three for the main effect of ABC, three more for the two-way interaction effect (AB on C, AC on B, and BC on A), then one for a three way interaction. Subsequent post-hoc testing may occur with factorial ANOVAs if the interaction is significant. c. Control of extraneous variables. Another fundamental feature of experiments is that a researcher exacts control over or minimizes the variability in variables other than the independent and the dependent variables. These other variables are called extraneous variables. An extraneous variable is any variable that isn't of interest to the researcher but which might influence the behavior being studied if they are not controlled properly. As long as these variables are held constant, they present no danger to the study. Researchers manipulate the independent variable by systematically changing its levels  (conditions) and they control other variables by holding them constant. If a researcher fails to control extraneous variables, they can influence the behavior being measured in some way. This results in what is called ‘confounding’. A confound is any uncontrolled extraneous variable that changes with the independent variable and could provide an alternative explanation for the result. When a study has a confound. The results could be due to the effect of either the confounding variable, or the independent variable, or a combination of both and there’s no way to decide among these alternatives. Studies which have confounds are uninterpretable. d. e.