Factorial Design
Pretests, Tests, and Posttests
Evaluations and confounds
Errors and error
Testing
100
This type of design has more than one independent variable or "factor".
What is a factorial design?
100
A one-group post-test only design lacks this crucial element of a true experiment.
What is a control group?
100
When people first take a test, they may have extremely high or low scores. When their scores tend to move closer to the mean when retested, we call it this.
What is regression to the mean?
100
This type of error is also called a "false positive".
What is a Type I error?
100
We choose the appropriate one of these by looking at the number of groups we're comparing, or the number of independent and dependent variables.
What is a statistical test?
200
There are this many experimental conditions in a 2 x 2 factorial design.
What is four (4)?
200
Studies using a pretest-posttest design can suffer from these three
What are maturation, testing effects, and history effects?
200
Developmental psychologists use all kinds of methods to study children. However, this kind of design is not typically used because of the ethical problems involved when you manipulate children to see if you can affect development.
What is the experimental method?
200
Increasing this is one easy way to reduce your confidence interval and Type II error.
What is sample size (n)?
200
This is a magnitude that we calculate in part because finding a significant treatment effect does not necessarily mean that it is a large one.
What is effect size?
300
This is the number of experimental conditions we would have in a factorial design examining the effects of anxiety (low, moderate, and high) as well as time spent studying (none, little, moderate, and high) on test performance.
What is twelve (12)?
300
In this kind of design, behavior is measured at baseline, then again at treatment, then again after treatment has been withdrawn.
What is ABA design?
300
Efficiency assessment, program theory assessment, and process evaluations are all examples of this.
What are program evaluations?
300
This tells you the probability of avoiding Type II error, and it is affected by the alpha level, the effect size, and the sample size used in the test.
What is statistical power?
300
You use this kind of statistical test to see if there are meaningful differences between two groups.
What is independent samples t-test?
400
This kind of effect is only possible with a factorial design. An example of this effect could be found, for example, if caffeine only increased alertness if it was in drinks without sugar.
What is an interaction effect?
400
This is like ABA design, but it has an additional treatment and measurement.
What is ABAB design?
400
This kind of program evaluation focuses on whether or not there are problems that need to be addressed in the target population.
What is the needs assessment program evaluation?
400
This alpha level means that the probability of Type I error is less than 5%.
What is .05?
400
When we take out the true difference caused by our independent variable, this is what causes the rest of the differences between experimental groups.
What is random error?
500
This kind of factorial design is a combination of independent groups and repeated measures designs, where two or more different groups experience all conditions.
What is a mixed factorial design?
500
This design is used to demonstrate the effects of treatment across many circumstances.
What is multiple baseline design?
500
In a one-group pretest-posttest design, this type of effect is best described as any confounding event that occurs at the same time as the experimental manipulation.
What is a history effect?
500
This type of error is properly defined as rejecting a true null hypothesis.
What is Type 1 error?
500
We do this to the null hypothesis when we find a statistically significant effect.
What is rejection?
M
e
n
u