Bivariate Correlations
Define Bivariate Correlation.
An association that involves exactly two variables.
What is the difference between Independent-Groups Designs and Within-Groups Designs?
In an independent-groups design there are different people in each study condition. In a within-groups design the same participants are in all study conditions.
Define Regression Threat.
A statistical concept in which extremely low or extremely high performance at Time 1 is less likely to be extreme at Time 2.
How do quasi-experiments differ from true experiments?
Quasi-experiments do not involve random assignment into treatment or control groups.
Define Reversal Design.
Researchers usually observe a baseline of behavior before treatment, next observe the behavior during treatment, and then remove the treatment to see whether the behavior reverts back.
Describe the strength and direction of a relationship with an r value of -0.36.
Based on the r value, this is a moderate negative relationship.
Define Matching. When is it typically better to using matching instead of random assignment?
Matching is measuring a variable and spreading it out evenly amongst the groups in a study. It is typically better to use matching for smaller samples.
A researcher does a study investigating if lack of exercise leads to weight gain, however, they did not control for food consumption. This is an example of which type of threat to internal validity?
Design Confound
There are different participants (groups) at each level of the independent variable. There is at least one treatment group and one comparison group, but unlike in true experiments, participants are not randomly assigned. What type of design is this?
Nonequivalent control group design
Which of the four validities may be problematic in Small-N Designs?
External Validity
When is a bar graph used for graphing associations?
A bar graph is used when graphing an association between one quantitative variable and one categorical variable.
How are order effects prevented in an experiment?
Counterbalancing
A student is participating in a study investigating the effects music on mood. The student realizes what the researcher is investigating and as a result reports a happier mood after a happy song is played and a sad mood after a sad song is played. Which threat to internal validity is this an example of?
Demand Characteristics
List three similarities between quasi-experiments and correlations.
Both may use independent-groups design, neither use random assignment, and neither use manipulated variables.
A researcher observes a behavior for an extended “baseline” period before the intervention or treatment is introduced. If this baseline is stable, and then the target behavior only changes after the treatment, then we can be more certain of its effectiveness. What type of study design is this?
Stable-Baseline Designs
A researcher is doing two different studies both investigating correlations between two variables. In Study 1 the researcher has 13 participants. In Study 2 the researcher has 60 participants. In which study should the researcher be more concerned about outliers affecting statistical validity and why?
Study 1 because there are only 13 participants and outliers have more impact when the sample is small.
Define Manipulation Check. Which type of validity is assessed using manipulation checks?
A manipulation check is an extra dependent variable that researchers can insert into an experiment to convince them that their experimental manipulation worked. This is used when assessing Construct Validity.
How can Attrition Threats be prevented?
One way to prevent attrition is that when participants drop out of a study, the researcher removes their scores from the pretest average. Another approach is to look at the pretest scores of dropouts. If they have extreme scores, then they are more likely to threaten internal validity than if they have more moderate scores.
How can selection effects be controlled for in quasi-experiments?
Matched Groups
What are the differences between Small-N Designs and Large-N Designs?
In Small-N Designs each participant is treated separately and data for each individual are presented. In Large-N Designs participants are grouped and data are represented as group averages.
What is the difference between an association claim and a causal claim in terms of the three rules of causation?
An association claim meets the rule of covariance but does not meet the rule of temporal precedence or internal validity. A causal claim meets all three rules of causation.
Explain the steps of a Repeated Measures Design.
(1) Random Assignment to order of conditions, (2) Group A is exposed to level 1 of the independent variable and Group B is exposed to level 2, (3) The dependent variable is measured, (4) Group A is exposed to level 2 of the independent variable and Group B is exposed to level 1, (5) The dependent variable is measured.
List and define two examples of Combined Threats.
Selection-History Threat: An outside event or factor systematically affects participants at one level of the independent variable.
Selection-Attrition Threat: Participants in one experimental group experience attrition.
A research team investigated the effect of food breaks on parole decisions. All judges received these breaks, so they used a repeated-measures design. The prisoners came from four major Israeli prisons and parole was rejected 65% of the time on average, but whether or not the prisoners came before the judge before had a break or after made a big difference in whether they were given parole. What type of study design was used?
Interrupted Time Series Design
Four individuals who were addicted to nicotine each engaged in several sessions of covert sensitization. After multiple sessions of therapy, all four addicts showed dramatic reductions in their urges to smoke. What type of study design is this?
Multiple Baseline Design