Chapter 7: Single-Factor Designs Flashcards
a single factor design has..
one independent variable and can have 2 or more levels
What are the 4 types of single factor designs?
- independent groups
- matched groups
- repeated measures
- ex post facto
What are the questions one must consider when choosing a single-factor design?
- is the IV between- or within-subjects?
- is the IV manipulated or a subject variable?
- if IV is manipulated & BS, will you form equivalent groups by matching or by random assignment?
- if IV is WS, how many times is it tested per condition?
For which single-factor design woud you form equivalent groups using random assignment?
independent groups single-factor design
What do we know about a study if it uses an ex post facto single factor design?
The IV is between-subjects and is a subject variable
What designs can we use if we have a between-subjects manipulated IV?
matched groups or independent groups designs
What design is appropriate for a within-subjects IV?
a repeated measures design
What are the assumptions for a t-test?
- Approximate normal distribution
- Homogeneity of variance: similar variance of each set of scores being compared
when performing a t-test, you can chose between an ____ and a ____ t-test
independent samples, paired (dependent) samples
when is an independent samples t-test appropriate?
When the groups being compared are completely independent of each other (i.e., independent groups design and ex post facto design)
when is a paired samples t-test appropriate?
if the IV is a within-subjects factor (i.e., in a matched groups design or a repeated-measures design)
sWhat is an advantage of single-factor multi-level designs?
they can discover nonlinear effects
what becomes possible with within-subjects multilevel designs?
you can counterbalance single-factor, repeated-measures designs in more than one ways
When is it more effective to use a graph?
if there are large differences, if nonlinear effects occur, or if the result is an interaction between two factors
When is it preferred to use a table?
when data points are so numerous that a graph would be uninterpretable or when the researcher wishes to inform the reader of precise values