PSY 9703 Study Guide PDF

Lecture 1: Generating Models Whats a theory? - - The principle of Parsimony - - - Scientific process 1\. Define the problem 2\. Determine variables 3\. Select design methods and sample 4\. Collect data 5\. Analyze and interpret Research Problem - Basic vs Applied Research...

Lecture 1: Generating Models Whats a theory? - - The principle of Parsimony - - - Scientific process 1\. Define the problem 2\. Determine variables 3\. Select design methods and sample 4\. Collect data 5\. Analyze and interpret Research Problem - Basic vs Applied Research - - Applied research - - - Sources of Hypotheses - - - - - - - - Causality - - - - - - - Lecture 2: Measurement Variables - - - Measurement = the assignment of numerical values to variables Conceptual vs Operational variables  - - Objective measures - - Subjective measures - - Explicit Measures - - - Implicit Measures - - - Common Rating Techniques - - - - - NOIR: Nominal, ordinal, interval, ratio Nominal Scale - - Ordinal Scale - - - - - - Interval Scale - - - Ratio - - - - - - - - - RELIABILITY AND VALIDITY - - - - - RELIABILITY - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Reliability of Measures - Validity - - - - - Validity=Accuracy Validity is a relative property describing how well it measure the underlying construct. The accuracy can vary from low to high (and in between). It is NOT true that score are either valid or invalid. Measures can be describes as being "highly" valid or having "strong" validity, or just "valid". In contrast: "low validity", "weak validity", or "not valid" - - - - - **Example, study guide:** Threats to validity - - - - - - - - **Internal validity** is defined as the extent to which the observed results represent the truth in the population we are studying and, thus, are not due to methodological errors. - - - - - - - - - - - - - - - **External validity** refers to how well the outcome of a research study can be expected to apply to other settings. This is important because, if external validity is established, it means that the findings can be generalizable to similar individuals or populations - - - - - - - - - **Statistical Conclusion Validity(SCV)**, or just Conclusion Validity is a measure of how reasonable a research or experimental conclusion is. - - [External Validity](https://www.statisticshowto.com/external-validity/): the test or research can be applied to other areas. [Internal Validity](https://www.statisticshowto.com/internal-validity/): the test or instrument is measuring what it's supposed to. [Construct Validity](https://www.statisticshowto.com/construct-validity/): the research/tests are well-constructed using established standards and methods. **Construct Validity** - - - - - - - - - - - - - - - - -  Content Validity - Face Validity - - - - Criterion-related Validity - - - - - - - - - Lecture 3: Sampling - - - - - - - - - - - - - Sampling Error - - - - - Probability Sampling - - - - - - - Non probability Sampling - - - - - - - - Systematic Sampling - - - Probability Sampling: Stratified Random Sampling - - - - - - Probability Sampling: **Cluster Sampling** - - - - - Non-probability sampling - - - - - - - - - - - - - - - - - - - - Sample Size - - - Errors in Sampling Type I error = alpha (α) - - Type II error = Beta (β) - - Null hypothesis: ρxy = 0 POWER - - - - - - - Lecture 4: Qualitative and observational methods - - - - - - - Observational research: involves the direct observation of a phenomena - - - - - - - - - - - - - - - - - - - - - - - - Indirect observation - - Challenges: Limitations of the Methodology - - - - - - - - - Quantitative Analytical Methods - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - Lecture 5: Experimental Methods - -  Experiments - - - - - Manipulations Control and comparison grounds - - Measurement - Realism - - - - \*\*Experimental Methods\*\* - - - - - Fidelity - - - Manipulation checks - - - - - CONFOUNDS Confounding Variable - - - - -  What are the confounds here? - \- Q: How is the best way to handle confounds? How can we be reasonably sure that we have investigated the confound (s) in question? \- A: If you cannot use an experiment, try quasi experiments. Anticipate confounds ahead of time, and design a study to control for them. Inferences of cause and effect require 3 elements - - - - - - Randomization Randomization - an important concept - - - - - - How is randomization different from random sampling? - - - - - - Quasi Experiments - - - - - - - - - - - - - - Matching - - - Factorial Designs - - - - - - - - Factorial Designs are fully crossed - - Factorial designs result in several types of hypotheses Main effects - - - Interaction effects - Example Female Negotiators When women advocate for themselves - When they advocate for other people, the relationship flips when they are not acting assertive - - - - - - Asking about a main effect of negitation style on DV - - - - - - - - - - - Lecture 6: Survey methods - - - - - - - - - - - - - - - - - - - - - - - - - - - - -  Issues with surveys Casuality - - - - - - - - - - - - CROSS SECTIONAL VS LONGITUDINAL STUDIES At once- cross sectional - - - - - More than once- longitudinal - - - - - - Cons - -  Lecture 7: evaluating research 4 main types of validity - - - - - - - - Threats to construct validity - - - - Common threats to construct validity - - - - - - - - - - - - - Threats to internal validity - - - - - - - - - - - - - - - - - - - - - - - Ethical Principles Guiding Research - - - - - - - - - - - - - - - - Lecture 9: Alternative and emerging methods Work samples - - - - - - Experience Sampling Method (ESM) Daily diary study - Meta Analyses - study of studies