Chapter_9_True Experiments Flashcards
(26 cards)
Determine Causality
- Manipulation of the IV
- Holding all other variables in the research situation constant
- Controlling for individual differences among participants
- random assignment
Nonspecific Treatment Effects
The cause of any differences between the experiment and control conditions
Two situations that call for multiple control or comparison conditions
- Hypothesis Testing
- Ruling Out Specific Alternative Explanations
Characteristics of a Good Manipulation
- Construct Validity
- Reliability
- Strength
- Salience
Construct Validity
The manipulation accurately represents the construct
- Manipulation check
Manipulation check
1.Interview research participants after data have been collected
2. Include dependent variables that assess the construct being manipulated
Reliability
- automating the experiment
- preparing detailed scripts for experimenters to follow and by rehearsing experimenters
Strength
strong manipulation
- The conditions of the independent variable are different enough to differentially affect behavior
- realism
- ethical
Salience
Noticeability or salient manipulation
Holding Extraneous Variables Constant
Assign participants to conditions of the independent variable
- e.g. gender, race, personality
2 Types of Between-Subjects Designs
- Simple Random Assignment
- quasi-random assignment - Matched Random Assignment
Matched Random Assignment
- first measuring the characteristic
- then balancing group membership on the characteristic
Advantages of Within-Subjects Designs
- equivalence of participants in both conditions
- fewer participants are required
The Problem of Order Effects
- Practice effects
- Fatigue effects
- Carryover effects
- Caffeine - Sensitization effects
- Priming
Controlling Order Effects
- Counterbalancing the order
- participants experience the experimental and control conditions - Latin square design
- the number of orders is equal to the number of conditions, with each condition appearing in each place in the order
Washout period
A period of time over which the effects of a condition dissipate.
Differential order effect
the order creates a different amount of effect
Multiple-Group Designs
- Quantitative independent variables
- Qualitative independent variables
Quantitative independent variables
vary by amount
- levels = the conditions of the independent variable
1. linear relationship
1.1 positive
1.2 negative
2. curvilinear relationship
Detecting Curvilinear Relationships
more than two levels of the independent variable
Qualitative independent variables
vary by quality
- the conditions of the independent variable represent different types or aspects of the independent variable
- more than one control group
1) no context
2) context after the information
post hoc analysis
after-the-fact
- directly compares the group means
priori contrasts
prior to conducting the experiment or preplanned
- When you have specific hypotheses about differences in means
Information Provided By Factorial Designs
- main effect
- interaction effect