Chapter 5 - Introduction to Experimental Research Flashcards
(21 cards)
Experimental Research
Defines expected relationship (IVs and DV) and there’s researcher manipulation OR use of unchangeable/subject variables.
True Experiment
Sometimes used to describe an experiment where the experimenter controls all aspects of the study except the DV.
Independent Variables (IVs)
Variables being studied to see if it’d influence the DV.
Manipulated Independent Variables (IVs)
Under the researcher’s control, considered true experimental variables.
Manipulated IVs - Situational IVs
Researchers manipulate environmental features.
Manipulated IVs - Task IVs
Participants are given different tasks or problems to solve.
Manipulated IVs - Instructional IVs
Participants are given different instructions for completing the same task.
Subject Independent Variables (IVs)
IVs that define a group without researcher intervention or assignment. Experiments that use them are sometimes called quasi experiments.
Dependent Variables (DVs)
The factor/variable that is the measured outcome of a study.
Covariates (Extraneous Variables)
Any variable that’s not of interest but might influence the DV in your study.
Confounds
An extraneous variable that correlates with the IV. You can either design a study that eliminates them or you can take them into account to control statistically.
External Validity
Extent to which results can be generalized to a wide range of situations, cultures, environments, etc.
Internal Validity
Extent to which the experiment is free of errors. Differences in the DV are only due to the IV.
Internal Validity (Threats) - History
An event may happen between assessments that produces large changes.
Internal Validity (Threats) - Maturation
An individual’s scores may change over time due to maturing with age.
Internal Validity (Threats) - Regression to the Mean
Tendency for scores to go back (regress) towards the sample mean. If someone provides an extreme score, their next score is more likely to be close to the mean (due to probability).
Big Problem: Subjects are often selected based on an extreme score (ex. patients with anxiety) and they will naturally have a lower score later in the study.
Internal Validity (Threats) - Testing
When taking a pre-test can influence the post-test (ex. participants learning how to perform better with repeated testing).
Internal Validity (Threats) - Instrumentation
When the pretest and the posttest differ (ex. a researcher getting better at administering the test or changes directions).
Internal Validity (Threats) - Subject Selection
When the groups are NOT EQUIVALENT and it’s impossible to tell whether the results are due to the IV or the group differences.
Internal Validity (Threats) - Attrition
When subjects leave the study.
Problem: What if there was a difference between those who stayed vs. left?
Solution: Test for differences (ex. making sure the original sample and final sample didn’t differ on anxiety).
Internal Validity (Threats) - Confounds
Makes it hard to interpret research findings.
Example: you find that depression (IV) and weight gain (DV) are significantly related to one another.
–> People who are depressed are more likely to be taking antidepressants (variable correlated with IV).
–> Antidepressants can cause weight gain (impacts the DV).
–> Antidepressant use is an example of a ________.