Final FAQ #1: Types of designs

Q1: What types of designs have we studied again?

A: Here are the ones I mentioned in section:

• Preexperimental designs: one-shot case study, one-group pretest-posttest, static group comparison
• Experiment-type designs:
  
• Quasiexperimental designs: nonequivalent control group, single-group interrupted time series, multiple time series
• Longitudinal designs (usually time series): panel, trend, cohort
• Type of panel design for reducing 3rd-variable problem: cross-lagged panel design
• Within-subjects designs (vs. between-subjects designs)
  
• Factorial designs (used for data analysis in survey/correlational method or true experiments)
  
• True/full experimental designs: posttest-only control-group, pretest-posttest control-group, Solomon four-group (also know the difference between lab experiments and field experiments)
  

When you're trying to tell the difference among all of these, think especially about:

1. How they treat time (One observation? Pretest and posttest? Time series?)
2. How they treat comparison groups (Do they involve any comparison groups? What type -- arbitrary comparison group, comparison group chosen based on pretreatment similarity to treatment group, true randomly assigned control group, or people acting as their own control group? How many control groups & treatment groups-- one of each, or two of each, like in Solomon?)

Also, please note that the nonequivalent control group design involves both a pretest and a posttest -- I think that in one of my sections I implied that it was posttest only (when we were looking at that graph).