EPsych Exam 2 Review PDF

1. The difference between a Theory and Hypothesis is? Theory o An organized set of principles used to explain observed phenomena o Generates Testable Hypotheses o Theories are general, and multiple hypotheses can come from same theoretical framewo...

1. The difference between a Theory and Hypothesis is? Theory o An organized set of principles used to explain observed phenomena o Generates Testable Hypotheses o Theories are general, and multiple hypotheses can come from same theoretical framework Hypothesis o A testable hypothesis is framed as a statement, usually a prediction, that is made prior to data collection 2. The difference between a Sample and a Population is? Participants constitute a sample, which may be considered a subset of some general group, which is called a population 3. The difference between Applied Research and Basic Research is? Basic research – finding out a casual explanation for a given phenomenon (emphasizes describing, predicting, and explaining the fundamental principles of behavior) Applied research – using that information (from basic research) to modify a behavior or phenomena 4. How does a researcher start to develop their research project? 1. Start asking questions o What sounds interesting? o Theory search 2. Search the literature o Is this theory really about my interest o What has and has not been done yet 3. Variables – definition, manipulation and measurement 4. Begin shaping the idea into a hypothesis o A testable prediction about the conditions under which an event will occur 5. In the context of theory criteria – Occam's razor refers to? Simplicity – Parsimony o “Fewer things can go wrong” o The least complex theory is the one you go with 6. In the context of theory criteria – Comprehensiveness refers to? Inclusive – Productivity o Good theories advance knowledge by generating a great deal of research 7. In the context of theory criteria – Falsification refers to? Predictive – testable hypotheses o Meaning your hypothesis can fail o “Theory that appears to explain everything is seriously flawed” 8. When controlling for Experimenter Bias, what is the best possible design feature to have in a study? Protocols Single blind: subjects are unaware, but the experimenters know the condition in which each subject is being tested Double blind: experimenters AND subjects are kept unaware or “in the dark” (blind) 9. Participant Bias may be a problem when... When behavior is affected by the knowledge that one is an experiment and is therefore important to the study’s success This phenomenon is called the Hawthorn effect 10. A Within Participant (subject) design refers to Groups are comprised of Paired, Matched, or the same participant (repeated measures) The same participants are exposed to all conditions of the experiment  Ex: Participants show performance after having full 8 hours of sleep and only one hour of sleep, this is in a randomized order, but every participant does both 11. Between groups Groups have different participants in each cell that are equal across most dimensions except for the experiment level Participants are divided into separate groups where each group experiences only one condition Avoids potential carryover effects 12. Mixed designs Designs that use both within subjects and between groups 13. What is the type of research that has the most control? Laboratory research 14. What is the type of research that has the most mundane realism? Simulating real-life experiences; social psychology Field research 15. Laboratory experiments tend to have poor external validity 16. Research that is typically concerned with measuring and testing hypothesis is Quantitative research 17. Replication is a term that refers to To duplicate the study to see if the effect is consistent or an artifact 18. Having the participant “buy in to the experiment” is the best way to insure Experimental realism – having the participant react in a realistic fashion rather than a contrived behavior 19. A researcher may run a quick study to test all of the “working parts and stats” of the experiment. This is called a Pilot study 20. When a researcher embarks on a long series of experiments that will take a number of years to complete and will result, hopefully, in a number of publications. This is called a Longitudinal study – takes a within subjects' approach in a single group of subjects studied over time 21. The best way to assure that each group is equal in regard to individual differences Random assignment 22. What is the best type of sample to use if I want to compare two groups directly and make sure each group is identical on some given axis Matching/Yoked: participants are grouped together on some subject variable and then distributed randomly to the different groups in the experiment Matching: paired participants based on similar characteristics (ie., IQ, test score, height) Yoked: pair participants across different groups to ensure both groups experience similar conditions 23. How does science double check to make sure your results are not spurious (false)? Replication 24. A problem using longitudinal experimental design is Attrition: people dropping/aging out, group finishing the study is on average made up of different types of people than is the group that started the study, which affects the external validity of the study Cohort effects (ie., age, generational differences, historical events) 25. Internal validity Refers to the methodological soundness of a study; it is free from confounds Did the study measure what it intended to measure? 26. External validity Concerns whether or not the results of the study generalize beyond the specific features of the study Can the findings be applied to other people, settings, times, or situations? 27. Measurement outcome consistency is at the root of Reliability: an instrument is reliable if it performs in consistent, predictable ways 28. Construct appropriate measurement is at the root of Construct validity 29. If we test a survey for internal reliability, we will employ which type of check Manipulation check 30. A researcher is interested in evaluating the effectiveness of a new training strategy to enhance social sensitivity. Using a standardized measure of social sensitivity, the mean score is μ = 60 and the standard deviation is σ = 8. The researcher draws a random sample of size n = 16 from a large group of individuals who have recently received the new training. In this sample, the group mean on the standardized test is M = 56. Does the new treatment significantly increase social sensitivity? What type of test do you use? One-sample because you are comparing a single sample to a population. Z-test because the population standard deviation is known. One-tailed test because the researcher is looking for a specific direction (a decrease in social sensitivity). 31. If the population average income for owners of Mamma Mia Pizza Shops is $30,000, does a special course on pizza store management given to a sample of 121 owners have any effect in increasing revenues. The average for those given the special course is $30,800, with a standard deviation of $4,500 across the sample of 121 owners. Test the hypothesis that the course has a significant effect using an alpha of.05, with a directional one-tail test. What type of test do you use? In this case, you would use a one-sample t-test. Here's why: o The population standard deviation is unknown, and we are using the sample standard deviation (s=4,500s = 4,500s=4,500) instead. In this case, the t-test is more appropriate than the z-test. o The sample size is large (n = 121), so the t-test is still appropriate due to the Central Limit Theorem, which tells us that the sampling distribution of the sample mean is approximately normal.  32. An educator tests a sample of 5 6th graders to determine how much interference the Stroop effect will have on their short-term memory. Theoretically the Stroop effect should have a disastrous effect on short term memory. Therefore, the participants should do much poorer on the posttest. The participants are first tested with a digit span memory task specifically designed to demonstrate the capacity of their short-term memory. Then the participants are given a Stroop exorcise, after which they are immediately asked to recall the digit spans from the first task. Below are the raw data from the study. Use an alpha of.05. What is the appropriate test? In this case, the appropriate test is the paired-samples t-test (dependent t- test) because: o You have two sets of related scores from the same participants (pretest and posttest). o The goal is to see if there is a significant difference in performance after the Stroop exercise. Summary of When to Use Which Tests: One-Sample Z-Test: When comparing a sample mean to a known population mean, and the population standard deviation is known. Two-Sample Z-Test: When comparing the means of two independent groups, both with known population variances and large sample sizes. T-Tests: Independent Samples T-Test: Use when comparing the means of two independent groups (e.g., comparing test scores between a control group and an experimental group). o Data: Continuous, normally distributed, independent samples. Paired Samples T-Test (Dependent T-Test): Use when comparing means from the same group at different times (e.g., measuring stress levels before and after therapy in the same participants). o Data: Continuous, normally distributed, within-subjects/repeated measures designs