Exam 3 Flashcards
Statistical Validity
The accuracy of p-value on which a statistical decision is based
Construct Validity
The degree to which the theory behind the research study provides the best explanation for the results observed
External Validity
The extent to which the results of a study generalize to other people, places, or conditions
Internal Validity
The extent to which we can be confident that the observed changes in the DV were due to the IV and not confounding variables
Maturation
Confounding Variable - Changes in the DV are due to the natural maturation of the participant
History
Confounding Variable - Changes in the DV that are due to historical events that occur during the study that are unrelated to and can’t be controlled by the study
Testing
Confounding Variable - Any change in a participant’s score on the DV due to being tested previously
Instrumentation
Confounding Variable - Any change in the calibration of the measuring instrument that affects DV scores
Regression to the Mean
Confounding Variable - Tendency for participants who are selected because they have extreme scores on a variable to be less extreme in a follow-up setting
Selection
Confounding Variable - Any factor that creates groups that are not equivalent at the beginning of the study
Attrition
Confounding Variable - Loss of participants during a study; differential loss is problematic because those who drop out are likely to differ from those who continue
Diffusion of Treatment
Confounding Variable - Change in the response of participants to a condition due to info gained about conditions from other participants
Sequence Effects
Confounding Variable - Effects on performance in later conditions that result from the experience one had from a previous study
Subject Effects
any changes in the behavior of participants that are attributable to being in the study rather than variables in the study
Demand characteristics
cues given to participants on how the researcher expects them to behave
placebo effect
when participants expect a specific effect of an experiment and they think it happens
Control
any procedure used to counteract potential threats to the validity of the research; often keeping other variables still or “constant”
Exact replication
repeating the study exactly as it was carried out originally
Systematic replication
testing a theoretical or procedural modification of the original procedure that will produce desired results only if the original findings were accurate
Conceptual Replication
generating and testing different research hypotheses from the same problem statement
Single-blind procedure
when the researcher working with the data doesn’t know which subjects are affected by what conditions; can be subjects kept in dark too
Double-blind procedure
when both the researcher and participants are blind to the assignment of each condition
Placebo
condition identical in appearance to the tested condition but has no effect
Automation
automatic running of procedures like data recording and giving instructions to reduce experimenter contact bias
Objective measure
measure based on empirically observable and clearly observable events people can agree on
Percent agreement
test of inter rater reliability
Deception
withdrawing study info till the end
Balanced placebo design
using deception on both groups about if anyone receives a placebo
General population
group of all organisms, events, and things we are interested in
Target population
subset population the researcher is primarily is interested in; this is the population we want to generalize our findings to
Accessible population
subset of target pop that is available to the researcher
Sample
subset of accessible pop on which measures are taken
Representative sample
sample that adequately reflects population characteristics
Random sampling
drawing sample so that every member of the population has an equal chance to be selected and the selections don’t change each other
Stratified random sampling
drawing separate random samples from several populations
ad hoc sampling
drawing participants randomly from an accessible population