Stats- concepts Flashcards
advantages and problems for between-subjects design
problems: more participants required, different conditions might be due to differences between group characteristics, advantages: when IV is a subject variable, using deception
advantages and problems for within-subjects designs
advantages: fewer people, same people means more observations so more statistical power, problems: order effects, progressive effects, carryover effect
basic v. applied research
basic: designed to understand fundamental psychological phenomena, applied: designed to shed light on the solution to real-world problems
descriptive v. inferential statistics
descriptive: info to describe or summarize data, Inferantial: to take info from your sample and infer conclusions about the general population
Direct v. Conceptual replication
conceptual: when parts of the study are purposely changed to test the predictions of the original study, direct: reproduce previously observed results
informed consent
given enough info about the study purpose, and procedure, and allowed to decide if they want to participate, can quit any time
moderator v. mediator
mediator: explains the process through which two variables are related moderator: affects the strength and direction of that relationship
probability vs convenience sampling
probability: each member of the population has a specific probability of being selected, convenience: non-random samples, usually recruited from a pool of easily accessible individuals
random sampling vs. random assignment
random sampling: each member of the population has an equal probability of being selected, random assignment: randomly placed by chance in experimental conditions
case studies
detailed description and analyses of a single individual and criticism are external validity, researcher bias, and based largely on memory
Quasi-experimental and experimental
experimental: manipulated IV, and equivalent groups formed by random assignment or matching. Quasi is when either of these isn’t met
IRB
evaluate research proposals, ensure human subjects are treated ethically, and evaluate risks (institutional review board)
IACUC
IRB but for animals, institutional animal care and use committee
Type 1 error vs Type 2 error
type 1 error: rejecting the null when its actually true, Type 2 error: failing to reject the null when its actually false
Types of control groups
waitlist, yoked, and placebo