Psyb70 Midterm 1 Revision Notes PDF

💯 midterm 1 - notes topics created @October 4, 2024 7:26 PM week 1 ch I 1. Definition of Psychology Psychology: The scientific study of human behaviour and mental processes. 2. Methods o...

💯 midterm 1 - notes topics created @October 4, 2024 7:26 PM week 1 ch I 1. Definition of Psychology Psychology: The scientific study of human behaviour and mental processes. 2. Methods of Knowing 1. Intuition: Relying on gut feelings or instincts. Weakness: Prone to cognitive biases; may not rely on facts. 2. Authority: Accepting ideas from authoritative figures (parents, doctors, etc.). Weakness: Authorities can be wrong or biased. 3. Rationalism: Acquiring knowledge through logical reasoning. Weakness: If premises or logic are flawed, conclusions will be invalid. 4. Empiricism: Gaining knowledge through observation and experience. Weakness: Limited by what we can observe; senses can be deceptive. 5. Scientific Method: midterm 1 - notes 1  The most reliable method involves systematic collection and evaluation of evidence. Weakness: Time-consuming and resource-intensive, can't answer all questions. 3. Understanding Science Features of Science 1. Systematic Empiricism: Learning based on observation. 2. Empirical Questions: Focus on questions that can be answered through observation. 3. Public Knowledge: Results are shared through professional publication for transparency and collaboration. 4. Science vs. Pseudoscience Pseudoscience: Claims that appear scientific but lack the core features of science (e.g., falsifiability). Examples: Cryptozoology, homeopathy, and past-life regression. Importance: Learning about pseudoscience sharpens understanding of real science and prevents reliance on false beliefs. 5. Goals of Science 1. Describe: Observe and report phenomena (e.g., through surveys). 2. Predict: Use observed patterns to predict future events or behaviours. 3. Explain: Identify causes behind behaviours. 6. Basic vs. Applied Research Basic Research: Conducted to understand behaviour without immediate practical application. Applied Research: Aims to solve practical problems. 7. Science and Common Sense midterm 1 - notes 2  Folk Psychology: Intuitive beliefs about human behaviour. Heuristics: Mental shortcuts that can lead to errors. Confirmation Bias: Focusing on information that confirms existing beliefs. Skepticism: Questioning claims and seeking evidence. Tolerance for Uncertainty: Accepting that some things are unknown. 8. Experimental and Clinical Psychologists Experimental Psychologists: Conduct research to advance knowledge. Clinical Psychologists: Apply research to diagnose and treat psychological disorders. 9. Empirically Supported Treatments ACT (Acceptance and Commitment Therapy): Used for depression, anxiety, and chronic pain. CBT (Cognitive Behavioural Therapy): Effective for anxiety, depression, eating disorders. Exposure Therapy: Used for PTSD, phobias. week 2 research ethics Historical Abuses in Research 1. Tuskegee Syphilis Study (1920s) Who: 399 Black/African-American men diagnosed with syphilis. What: Men were denied treatment and subjected to painful procedures. Ethical Issues: Lack of informed consent, racial discrimination, exploitation. 2. Nazi Medical Experiments and Nuremberg Code (WWII) midterm 1 - notes 3  Who: Nazi doctors experimented on at least 7,000 concentration camp prisoners. What: Horrific procedures without consent. Ethical Response: Nuremberg Code (1947) established, emphasizing informed consent and weighing risks against benefits. 3. Indigenous Health Research (1942-1952) Who: Indigenous children at six residential schools in Canada. What: Nutrition experiments without proper consent. Ethical Issues: Exploitation of marginalized groups, lack of protection for vulnerable populations. 4. HeLa Cells (1951) Who: Henrietta Lacks unknowingly provided cells used for medical research. What: Her cells were commercialized, raising questions about consent and ownership. Ethical Issues: Privacy, informed consent, and the rights over biological materials. 5. Project MKUltra (1950s-60s) Who: McGill psychiatrist Ewan Cameron, CIA. What: Mind control studies using electroshock therapy and LSD. Ethical Issues: Lack of informed consent, mental and physical harm. 6. John/Joan Case (1960s) Who: Psychologist John Money. What: Encouraged sex reassignment and studied gender identity without proper consent. Ethical Issues: Manipulation of vulnerable populations, long-term psychological harm. 7. Tearoom Trade Study (1970s) midterm 1 - notes 4  Who: Sociologist Laud Humphreys. What: Secretly recorded men’s information from same-sex encounters in tearooms. Ethical Issues: Privacy violations, deception, lack of consent. Research Ethics 1. Respect for Persons Ensure free, informed, and ongoing consent. Protect vulnerable populations (e.g., children, cognitively impaired individuals). 2. Concern for Welfare Ensure participants’ privacy and confidentiality. Provide enough information for participants to assess risks and benefits. 3. Justice Treat participants fairly, ensuring no group faces undue risk. Core Principles in Ethical Research 1. Informed Consent: Participants must be fully informed about the study, risks, and benefits. Consent must be voluntary and ongoing. 2. Concern for Welfare: Research should avoid exposing participants to unnecessary risks. Confidentiality is key—ensure personal data is protected. 3. Seeking Justice: Ensure that vulnerable groups are not exploited, and that benefits and risks are fairly distributed. 4. Unavoidable Ethical Conflict: midterm 1 - notes 5  Ethical dilemmas (e.g., use of deception) may arise. These conflicts should be carefully weighed and minimized. Ethical Codes and Frameworks 1. Nuremberg Code (1947): First international ethics code emphasizing informed consent and weighing risks against benefits. 2. Declaration of Helsinki (1964): Expanded on the Nuremberg Code, requiring research to be based on written protocols and reviewed by independent committees. 3. Belmont Report (1978): Established principles of Respect for Persons, Beneficence, and Justice. 4. Tri-Council Policy Statement (Canada): Code of ethics for research involving humans, focusing on respect for persons, concern for welfare, and justice. Informed Consent and Deception 1. Informed Consent: Participants must be aware of the procedure, risks, and benefits. Exceptions: When research poses minimal risk or is part of normal activities. 2. Deception: Should be used sparingly and only when necessary for the research question. Deception must be explained in the debriefing process. 3. Debriefing: Researchers must inform participants of the study’s true purpose afterward and minimize harm caused by deception. Scholarly Integrity midterm 1 - notes 6  1. No Data Fabrication or Plagiarism. 2. Sharing Data: Researchers must share data with others to allow verification. 3. Peer Review: Maintain confidentiality during the review process and conduct ethical reviews. Planning a Research Study 1. Research Topic: Start with a clear question based on literature and real-world events. 2. Study Rationale: Justify the need for the research. 3. Research Design: Create a thorough and ethical research plan, considering risks and obtaining necessary approvals. 4. Data Collection and Analysis: Follow the pre-registered plan and document any deviations. 5. Publication: Follow APA style and go through the peer review process. From Moral Principles to Ethics Codes 1. Replication: Replication helps verify results. 2. Open Science: Promotes sharing data/materials to encourage collaboration and transparency. week 3 ch II I. A Model of Scientific Research in Psychology Scientific Cycle: The research literature is both a source and destination for new studies. Research questions arise from: 1. Informal observations (everyday behavior, news, books) 2. Practical problems (real-world issues in fields like education, law) midterm 1 - notes 7  3. Previous research (building on existing studies) Researchers check existing literature to see if their questions have been addressed before conducting new studies. II. Finding a Research Topic Sources of Inspiration: 1. Informal observations: Behavior in daily life or media. 2. Practical problems: Real-world challenges prompting applied research. 3. Previous research: Most common, leads to new questions and studies. Reviewing Research Literature: Focus on: 1. Finding if your question is already answered. 2. Getting ideas for methodology. 3. Placing your study in context. Types of Sources: Empirical reports: Original studies with methods, results, conclusions. Review articles: Summarize previous research, often introducing new frameworks (meta-analyses or theoretical articles). III. Literature Search Strategies Databases: PsycINFO: Main database for psychology, covers over 100 years of research. Google Scholar: Useful for finding a wide range of research. What to Search For: 1. Refine your question. 2. Identify appropriate methods. 3. Contextualize your research. midterm 1 - notes 8  4. Find effective reporting techniques. Focus on recent research to stay current (past 1–2 years for active fields, 10 years for older topics). IV. Generating Good Research Questions Empirically Testable Questions: Focus on single variables or relationships. Evaluating Questions: Interestingness: Does it fill gaps in literature? Does it have practical importance? Feasibility: Consider resources, time, participants, and skills. V. Developing a Hypothesis Theory vs. Hypothesis: Theory: Broad explanations. Hypothesis: Specific predictions based on a theory. Theory Testing: Hypothetico-deductive method: Derive hypotheses from theories, test them, and revise theories accordingly. Good Hypothesis: 1. Testable and falsifiable. 2. Logical. 3. Positive: Predicts existence of a relationship. VI. Designing a Research Study Variables: 1. Quantitative: Measures amount (e.g., height). 2. Categorical: Describes characteristics (e.g., chosen major). Operational Definitions: Define how variables will be measured. midterm 1 - notes 9  Sampling: Simple random sampling: Equal chance for all population members. Convenience sampling: Easily accessible participants (can limit generalizability). VII. Experimental vs. Non-Experimental Research Experimental Research: Manipulates an independent variable to determine causal relationships. Non-Experimental Research: Describes relationships without manipulating variables (e.g., surveys). Laboratory vs. Field Research: Laboratory: High internal validity (control over variables). Field: Higher external validity (real-world settings). VIII. Analyzing Data Descriptive Statistics: Summarize data. Mean: Average. Median: Midpoint. Mode: Most frequent. Range and standard deviation: Measure variability. Inferential Statistics: Draw conclusions about a population from a sample. Statistically significant: Indicates a real effect, not random chance. Type I error: False positive (believing there's an effect when there isn't). Type II error: False negative (missing a real effect). IX. Drawing Conclusions and Reporting Results Drawing Conclusions: Confirming a hypothesis strengthens theory, but never fully proves it. Reporting: midterm 1 - notes 10  Peer-reviewed journals or book chapters are prestigious methods of sharing findings. week 3 ch V 1. Experimental Research: Focuses on identifying causal relationships between two variables through manipulation and control. 2. Diffusion of Responsibility: Darley & Latané’s hypothesis: the more witnesses, the less likely any will help, due to diffusion of responsibility. Experiment Basics 1. What is an Experiment?: A controlled study designed to test causal relationships between an independent variable (IV) and a dependent variable (DV). 2. Manipulation of the Independent Variable: Researchers change the IV systematically to observe effects on the DV. Single-factor two-level design: Only one variable is manipulated, with two conditions. Single-factor multi-level design: One variable is manipulated, but with three or more conditions. 3. Control of Extraneous Variables: Extraneous variables are unwanted variables that could affect the DV. Control techniques: Hold them constant or use random assignment. 4. Confounding Variables: Variables that systematically differ along with the IV, providing alternative explanations for results. midterm 1 - notes 11  Experimental Design 1. Treatment and Control Conditions: Treatment condition: Participants receive the intervention. Control condition: Participants do not receive the intervention. Use placebo control conditions to control placebo effects. 2. Random Assignment: Participants are randomly assigned to conditions to control for extraneous variables. Block randomization: Ensures equal distribution of participants across conditions. 3. Matched Groups Design: Participants are matched on relevant characteristics before being randomly assigned to conditions. 4. Within-Subjects Design: Participants experience all conditions of the experiment, reducing noise in the data. Carryover effects: The effect of one condition may influence the next condition. Counterbalancing: Testing participants in different orders to control for carryover effects. Experimentation and Validity 1. Four Big Validities: Internal Validity: Confidence that IV manipulation caused changes in DV. External Validity: Generalization of results to other people and situations. Construct Validity: Accurate measurement of the intended concept. Statistical Validity: Proper use of statistical techniques to analyze results. 2. Operationalization: midterm 1 - notes 12  The process of defining how a concept will be measured or manipulated. Practical Considerations 1. Recruiting Participants: Consider using subject pools or field experiments to recruit participants. 2. Standardizing the Procedure: Use written protocols and consistent instructions to ensure standardization. 3. Experimenter Expectancy Effects: Avoid influencing participants’ behavior by using a double-blind study, where both participants and experimenters are unaware of the condition. 4. Manipulation Checks: Verify that the IV was successfully manipulated by using a manipulation check at the end of the experiment. 5. Pilot Testing: Conduct a pilot test to ensure the procedure works as intended and identify any issues. Types of Designs 1. Between-Subjects Design: Different participants are assigned to different conditions. Advantages: Simpler design, no carryover effects. Disadvantages: Requires more participants. 2. Within-Subjects Design: The same participants experience all conditions. Advantages: Controls extraneous variables, fewer participants needed. Disadvantages: Risk of carryover effects. 3. Simultaneous Within-Subjects Design: midterm 1 - notes 13  Participants make multiple responses in each condition, commonly used in cognitive psychology. week 3 36 & 52 1. Conducting Survey Research Sampling Methods 1. Probability Sampling Every individual has a known, equal chance of being selected. Common in survey research to get accurate estimates about a population. Requires a clearly defined population and a sampling frame (list of all members). 2. Types of Probability Sampling: Simple Random Sampling: Equal chance for all individuals. Stratified Random Sampling: Population divided into subgroups (strata) and random samples taken from each. Proportionate Stratified Sampling: Subgroup proportions in the sample match the population. Disproportionate Stratified Sampling: Extra sampling from smaller subgroups to ensure enough data. Cluster Sampling: Randomly selecting clusters and then sampling within those clusters. Efficient for face-to-face surveys. 3. Non-Probability Sampling Cannot specify the probability of selection. 4. Types of Non-Probability Sampling: Convenience Sampling: Select participants who are easily accessible. Snowball Sampling: Participants recruit other participants. midterm 1 - notes 14  Quota Sampling: Selects participants to match the proportions of subgroups. Self-Selection Sampling: Participants volunteer on their own. Sampling Bias Sampling Bias: Occurs when the sample does not represent the population, leading to inaccurate results. Non-response Bias: When non-responders differ significantly from responders, affecting survey accuracy. Offering incentives can increase response rates. Survey Methods 1. In-Person Interviews: Highest response rate, personal contact. 2. Telephone Surveys: Lower response rate but some personal contact. 3. Mail Surveys: Lower cost, lower response rates, prone to non-response bias. 4. Online Surveys: Easy to construct and distribute but may have varying response rates. 2. Describing Single Variables Descriptive Statistics Descriptive Statistics: Techniques for summarizing and displaying data. Distribution of a Variable Distribution: How scores are spread across the levels of a variable. Can be presented using: Frequency Tables: List of scores and their frequencies. Grouped Frequency Tables: When scores span a wide range, group them into intervals. Histograms midterm 1 - notes 15  Histogram: Graphical display of data distribution. x-axis: Variable being measured. y-axis: Frequency of each score or category. No gaps between bars if the variable is quantitative; gaps for categorical variables. Distribution Shapes Unimodal: One distinct peak. Bimodal: Two distinct peaks. Symmetry: A symmetrical distribution has equal halves. Skewed Distribution: Negatively skewed: Peak shifted right, longer left tail. Positively skewed: Peak shifted left, longer right tail. Outlier: Extreme score far from other values. Measures of Central Tendency Mean: Sum of all scores divided by the number of scores. Formula: M = ΣX/N Median: Middle score when data is ordered. Mode: Most frequent score in a dataset. Measures of Variability Range: Difference between the highest and lowest scores. Standard Deviation: Average distance of each score from the mean. Measures variability. Variance: Square of the standard deviation (plays a larger role in inferential statistics). Percentile Ranks and Z-Scores midterm 1 - notes 16  Percentile Rank: Percentage of scores lower than a given score. Z-Score: Indicates how many standard deviations a score is from the mean. Formula: z = (X−M) / SD week 4 ch XIII Study Guide: Understanding Null Hypothesis Testing 1. Introduction to Null Hypothesis Testing Purpose: To draw conclusions about population parameters based on sample statistics. Key Terms: Statistics: Descriptive summary data computed from sample measurements (e.g., means, correlation coefficients). Parameters: Corresponding values in the population. Sampling Error: Random variability in statistics from sample to sample. 2. The Logic of Null Hypothesis Testing Definitions: Null Hypothesis (H0): Assumes no relationship exists in the population; any observed relationship in the sample is due to sampling error. Alternative Hypothesis (H1): Assumes a relationship exists in the population, reflected in the sample. Steps in NHST: 1. Assume H0 is true (no relationship). 2. Determine the likelihood of observing the sample relationship if H0 is true. 3. Decision Rule: Reject H0 if the sample relationship is extremely unlikely. midterm 1 - notes 17  Retain H0 if it is not extremely unlikely. 3. Understanding the p-value Definition: The probability of observing the sample result or a more extreme result if H0 is true. Interpreting p-values: Low p-value (p < α): Reject H0; results are statistically significant. High p-value (p ≥ α): Fail to reject H0; insufficient evidence to conclude a relationship. 4. Significance Levels Alpha (α): The threshold for determining statistical significance, typically set at.05. Type I Error: Rejecting H0 when it is true (5% risk). 5. Sample Size and Relationship Strength Key Concepts: Large sample sizes can lead to statistical significance even with weak relationships. Small sample sizes may fail to detect significant relationships despite their existence. 6. Statistical vs. Practical Significance Statistical Significance: Results unlikely to have occurred by random chance, not necessarily indicative of strong relationships. Practical Significance: Refers to the real-world importance or usefulness of results (also known as clinical significance). 7. Common Null Hypothesis Tests The t-Test Purpose: Most common method for testing statistical relationships. midterm 1 - notes 18  One-Sample t-Test Used for: Comparing a sample mean (M) with a hypothetical population mean (μ0). Hypotheses: H0: μ = μ0 (population mean equals hypothetical mean). H1: μ ≠ μ0 (population mean differs from hypothetical mean). Test Statistic: Calculate the t statistic to find the p-value. 8. Degrees of Freedom Definition: Number of independent values in a dataset that can vary (for one- sample ttest: df = N - 1). 9. Critical Values and Decision Making Critical Value: Threshold for determining if the test statistic is extreme enough to reject H0. Test Types: One-Tailed Test: Tests for an effect in one direction (greater than or less than). Two-Tailed Test: Tests for an effect in either direction (greater than or less than). 10. Making Decisions Compare the computed t score with critical values: Beyond Critical Values: Reject H0. Within Critical Values: Retain H0. study guide pt 2 Statistics vs. Parameters: Statistics: Descriptive summary data from a sample. midterm 1 - notes 19  Parameters: Corresponding values in the population. Sampling Error: Random variability in a statistic from sample to sample. Statistical Relationships: A relationship in a sample may not indicate a relationship in the population. Two interpretations: 1. Relationship exists in the population. 2. Relationship is due to sampling error. Purpose of Null Hypothesis Testing (NHST) NHST helps determine whether there is enough evidence to support a specific claim by deciding whether to retain or reject the null hypothesis (H₀). Null Hypothesis (H₀): Assumes no relationship exists in the population. Alternative Hypothesis (H₁): Assumes a relationship exists. Logic of NHST 1. Assume the null hypothesis is true. 2. Determine the likelihood of the sample relationship if H₀ is true. If unlikely, reject H₀ in favor of H₁. If likely, retain H₀. p-value: Probability of obtaining the sample result (or more extreme) if H₀ is true. Low p-value (< α = 0.05): Reject H₀. High p-value (≥ α): Fail to reject H₀. Type I Error Type I Error: Rejecting H₀ when it is actually true (5% chance if α = 0.05). Sample Size and Relationship Strength Strong relationships can be statistically significant in small samples. midterm 1 - notes 20  Weak relationships require larger samples to achieve statistical significance. Statistical vs. Practical Significance Statistical Significance: Results unlikely due to random chance. Practical Significance: Importance or usefulness in real-world contexts. Common Null Hypothesis Tests The t-Test 1. One-Sample t-Test: Compares a sample mean (M) to a known population mean (μ₀). Null hypothesis: μ = μ₀; Alternative hypothesis: μ ≠ μ₀. 1. Dependent-Samples t-Test: Compares two means from the same sample at different times/conditions. Calculate difference scores: After score - Before score. Null hypothesis: Means are the same; Alternative hypothesis: Means are different. 1. Independent-Samples t-Test: Compares means of two separate samples (M₁ and M₂). Null hypothesis: μ₁ = μ₂; Alternative hypothesis: μ₁ ≠ μ₂. Degrees of freedom: N - 2. Analysis of Variance (ANOVA) Used for comparing means of three or more groups. One-Way ANOVA Null hypothesis: μ₁ = μ₂ =... = μᵍ. Alternative hypothesis: Not all means are equal. Test statistic: F (ratio of mean squares between and within groups). midterm 1 - notes 21  Post Hoc Comparisons Conducted after significant ANOVA results to identify specific group differences. Methods include: Bonferroni correction: Adjusts significance level to control Type I error. Fisher’s LSD test: Identifies specific differences using standard error. Tukey’s HSD test: Controls Type I error and identifies specific group differences. Repeated-Measures ANOVA Used for within-subjects designs, comparing means from the same participants across different conditions. Factorial ANOVA Involves two or more independent variables, analyzing main effects and interactions. Testing Correlation Coefficients Pearson’s r: Describes strength of relationships. Null hypothesis: ρ = 0 (no relationship). Alternative hypothesis: ρ ≠ 0 (a relationship exists). 1. Null Hypothesis Testing (NHT) Basics Objective: Draw conclusions about a population based on a sample. Null Hypothesis (H₀): Assumes no effect or no difference (e.g., the means are equal). Alternative Hypothesis (H₁): Assumes there is an effect or difference (e.g., the means are not equal). 2. Types of Errors in NHT midterm 1 - notes 22  Type I Error (α) Definition: Rejecting the null hypothesis when it is true. Significance Level: Commonly set at α = 0.05; indicates a 5% chance of committing a Type I error. Type II Error (β) Definition: Retaining the null hypothesis when it is false. Causes: Often due to insufficient statistical power in the research design. File Drawer Problem Definition: The tendency for non-significant results to remain unpublished, skewing the literature toward significant results. Implication: Increases the likelihood of Type I errors being overrepresented in published research. 3. Statistical Power Definition: The probability of correctly rejecting the null hypothesis (avoiding Type II error). Power Calculation: Power=1−β\text{Power} = 1 - \betaPower=1−β Common Benchmark: A power of 0.80 is generally considered adequate, implying an 80% chance of detecting an effect if it exists. Ways to Increase Power: 1. Increase the effect size (strength of the relationship). 2. Increase the sample size. 4. Criticisms of Null Hypothesis Testing Misinterpretations: Confusing p-values as the probability that the null hypothesis is true. midterm 1 - notes 23  Misunderstanding that 1−p1 - p1−p is the probability of replicating a significant result. Logic Issues: Rigid adherence to p < 0.05 for significance is arbitrary and can distort research findings. Informational Limitations: Rejecting the null only indicates that there is a non-zero relationship, which lacks specificity about the nature of that relationship. 5. Alternative Approaches Effect Size Measures: Accompany null hypothesis tests with effect sizes (e.g., Cohen’s d, Pearson’s r) to indicate the strength of relationships. Confidence Intervals: Provide a range of values for the population parameter with a given confidence level (usually 95%). Bayesian Statistics: Incorporates prior probabilities about hypotheses, updating these based on observed data. 6. Replicability Crisis Definition: Difficulty in replicating previously published research findings. Key Example: The Reproducibility Project found that only 36 of 100 studies could be replicated successfully. Questionable Research Practices (QRPs) Common QRPs: 1. Selective deletion of outliers. 2. Selective reporting (cherry-picking results). 3. HARKing (hypothesizing after results are known). 4. p-hacking (manipulating data to find significant results). 5. Data fabrication. midterm 1 - notes 24  7. Solutions and Best Practices Enhancing Rigor: 1. Conduct studies with adequate statistical power. 2. Publish both null and significant results to reduce bias. 3. Provide detailed research designs to enable replication. 4. Conduct and report high-quality replications. Open Science Practices: Increase transparency in research methods and results, including pre-registration of studies and sharing of data. 8. Key Terms and Formulas Null Hypothesis (H₀): Assumes no effect or no difference. Alternative Hypothesis (H₁): Assumes there is an effect or difference. Type I Error Rate (α): Probability of incorrectly rejecting H₀. Type II Error Rate (β): Probability of incorrectly retaining H₀. Statistical Power: Power=1−β\text{Power} = 1 - \betaPower=1−β week 4 chVI 1. Overview of Non-Experimental Research Definition: Non-experimental research involves studies where the researcher does not manipulate an independent variable. Instead, they measure variables as they occur naturally. When to Use: Single variable questions (e.g., accuracy of first impressions). Non-causal relationships (e.g., correlation between verbal and mathematical intelligence). Causal questions where manipulation is impractical or unethical (e.g., effects of hippocampus damage on memory). midterm 1 - notes 25  Exploratory research or to understand experiences (e.g., experiences of working mothers with depression). 2. Types of Non-Experimental Research 1. Correlational Research: Focuses on the statistical relationship between two variables without manipulation. Measures two variables, assessing their relationship with little control over extraneous factors. 1. Observational Research: Involves observing behavior in natural or controlled settings without manipulation. Includes: Cross-sectional Studies: Comparing different pre-existing groups without manipulation. Longitudinal Studies: Following a single group over time. Cross-sequential Studies: Combining cross-sectional and longitudinal elements. 3. Internal Validity Definition: The extent to which study design supports conclusions about the relationship between variables. Experimental research has the highest internal validity due to manipulation and control of variables. Non-experimental (correlational) research has the lowest internal validity. Quasi-experimental research lies in between. 4. Correlational Research Definition: Research focused on the statistical relationship between variables. Reasons for Use: midterm 1 - notes 26  To describe the strength/direction of relationships. When manipulation is impossible, impractical, or unethical. To establish reliability/validity of measurements. Characteristics: High external validity, low internal validity. Relationships can be linear or nonlinear. Can indicate correlation strength with Pearson’s correlation coefficient (r). Cautions: Correlation does not imply causation due to: Directionality Problem: Unclear causal direction between variables. Third-variable Problem: Another variable influences both variables. 5. Complex Correlation Involves assessing relationships among multiple variables using a correlation matrix. Factor Analysis: Clusters variables to identify underlying constructs. Statistical Control: Measuring potential third variables (e.g., partial correlation) but cannot fully address causality. 6. Regression Analysis Definition: A statistical technique for predicting one variable based on another. Types: Simple Regression: Predicting one variable from another. Multiple Regression: Using multiple variables to predict an outcome. Equation: Simple: Y = b1X1 Multiple: Y = b1X1 + b2X2 +... + biXi Advantages: Can identify unique contributions of predictor variables. midterm 1 - notes 27  7. Qualitative Research Definition: A research method focusing on understanding experiences rather than statistical analysis. Purpose: Generates new questions/hypotheses. Provides detailed descriptions of behaviors (“thick description”). Data Collection Techniques: Naturalistic observation, interviews (unstructured, structured, semi- structured), focus groups. Data Analysis: Often involves grounded theory, where theory emerges from data through thematic analysis. 8. Observational Research Definition: Studies where behavior is systematically observed and recorded. Types: Naturalistic Observation: Observing behavior in natural settings (can be disguised or undisguised). Participant Observation: Researchers actively participate in the group being studied. Structured Observation: Observing specific behaviors in controlled settings. Case Studies: In-depth analysis of individuals, useful for rare conditions but limited in validity. Archival Research: Analyzing pre-existing data for new insights. Key Terms to Remember Correlation: A measure of the relationship between two variables. Internal Validity: The degree to which a study accurately reflects the causal relationship between variables. midterm 1 - notes 28  External Validity: The extent to which results can be generalized beyond the study context. Pearson’s Correlation Coefficient: A statistical measure of the strength and direction of a linear relationship between two variables. midterm 1 - notes 29