Ch7: The Experimental Research Strategy Flashcards
What is the goal of experimental research strategy?
to establish the existence of a cause and effect relationship between two variables
Four basic elements of a true experiment:
- Manipulation
- Measurement
- Comparison
- Control
The variable that is measured is called the ___ ___ and that which is manipulated is the ____ ____
The variable that is measured is called the DEPENDENT VARIABLE and that which is manipulated is the INDEPENDENT VARIABLE
What does a true experiment try to show?
that changes in one variable are directly responsible for the changes in a second variable
Third-variable problem
Although a study may establish that two variables are related, it does not necessarily mean that there is a direct (causal) relationship between the two variables.
It is possible that a THIRD (unidentified) VARIABLE is controlling the two variables and responsible for producing the observed relation
alternative methods to hypothesis testing?
- Cohen’s d
- R squared
- Confidence intervals
3 conditions for determining cause and effect:
- covariation of cause and effect
- temporal precedence (directionality problem)
- alternative explanations (third variable problem)
Directionality problem
Although a research study may find a relationship between two variables, this does not explain the direction of the relationship. Problem is to determine which variable is the cause and which is the effect.
e.g., does aggressive cause a kid to play more violent video games, or do violent video games cause aggressive behaviour?
Two elements that are unique only to experimental research strategies
- control of extraneous variables
- manipulation of one variable
Researcher observed that people who suffer from eating disorders tend to have low self-esteem. He’s not sure whether the self-esteem leads to an eating disorder or whether having an eating disorder leads to low self-esteem. This is an example of what problem?
directionality problem
Researcher is interested in how a new drug impacts symptoms of depression. Name 3 ways they could test the effectiveness of the drug.
3 WAYS TO MANIPULATE THE IV:
- Different levels of treatment: 2 groups receive diff. dosage levels.
- Different treatment categories: one group receives new treatment, the other receives existing treatment.
- Treatment vs no treatment: one group receives drug, one group does not.
Researchers interested in the effect of alcohol consumption on socializing carefully control the amount of alcohol they allow participants to consume and observe the number of people each participant speaks to. What kind of manipulation is being employed?
Different levels of treatment/IV
Which necessary condition of causality does manipulation in an experiment help?
- temporal precedence/directionality.
- by manipulating one variable, experimenter is ensuring directional/temporal precedence.
In general, whenever there is a relationship between two variables, a researcher can use manipulation to determine which variable is the ___ and which is the ____
cause and effect
What is a manipulation check?
an additional measure to assess how the participants perceived and interpreted the manipulation and/or to assess the direct effect of the manipulation.
It directly measures whether the IV had the intended effect on the participant.
Which necessary condition of causality does experimental control help?
helps rule out ALTERNATIVE EXPLANATIONS
What kinds of variables need to be controlled for in an experiment?
CONFOUNDING variables
All individuals in an experiment are observed in the same room, at the same time of day, by the same researcher. What method is this an example of?
- a method of CONTROLLING EXTRANEOUS VARIABLES by HOLDING A VARIABLE CONSTANT.
- this eliminates extraneous variables by holding them constant
In an experiment, participants are assigned so that the average age is the same for all the different treatment conditions. This is an example of what method of control?
MATCHING values across treatment conditions.
-in this case, age is balanced across treatments and, therefore, cannot be a confounding variable
2 benefits of random assignment
- as sample size gets larger, the differences between the groups become smaller
2. even if there are differences, they aren’t systematic
the use of a random process to help avoid systematic relationship between two variables is called ___
randomization
A researcher’s schedule requires some observations in the morning and some in the afternoon. How can he control for environmental variables?
he could toss a coin each day to determine whether treatment I or treatment II is to be administered in the morning. In this way, morning hour is equally likely to be assigned to treatment condition I or II.
Thus, time of day is randomly distributed across treatments and does not have a systematic effect on the outcome.
RANDOMIZATION technique
Holding a variable constant has the disadvantage of limiting _____
generalization (external validity)
When a drug with no medical effect is administered and the participant still shows a response, this is called ___ ___
placebo effect
In an experiment, a _____ ____ ____ is a condition in which the participants do not receive the treatment being evaluated
no-treatment control group
A ___ ___ ___ is a condition in which participants receive a placebo instead of an actual treatment
placebo control group
4 methods of experimental control
- random assignment
- holding constant
- matching
- control conditions
In a ____-____ ____, each participant is exposed to all levels of the IV, while in a ___-____ ____, each participant is only exposed to one level of the IV
In a WITHIN-SUBJECTS DESIGN, each participant is exposed to all levels of the IV, while in a BETWEEN-SUBJECTS DESIGN, each participant is only exposed to one level of the IV
