Class 10- oct 5 -Special designs: 1. Single case experiments: ABA reversal design, ABAB reversal design, Multiple baseline design 2. Quasi experiments: One group posttest only, One group pretest-posttest, Nonequivalent control group, Nonequivalent control group pretest-posttest 3. Multiple repeated measure quasi experiments: interrupted time series, control series 4. Developmental: cross sectional, longitudinal, sequential -Reversal designs: 1. Single reversal design is difficult to attribute DV to treatment, since something might have happened between (confound) 2. This can be solved by using multiple reversals 3. Single case designs in general though, suffer from lack of generalisability -Quasi experimental designs: 1. No randomisation 2. Uses pre existing groups (or allows participants to assign themselves to groups) 3. Randomization is not possible or realistic -One group posttest only design ex: Smoking cessation program offered -> Students who signed up (participant group) -> Smoking cessation program (treatment) -> Smoking frequency one pack a week (posttest). Program may have had an effect -One group pretest posttest design ex: Smoking cessation program offered -> Students who signed up (participant group) -> Smoking frequency 4 packs per week (pretest) -> Smoking cessation program (treatment) -> Smoking frequency 1 pack per a week (posttest). Program may have had an effect -Nonequivalent control group design: 1. Smoking cessation program offered -> Students who sign up (participant group) -> Smoking cessation program (treatment) -> Smoking frequency one pack a day (posttest) 2. Smoking cessation program offered -> Students who don't sign up (participant group) -> No program (treatment) -> Smoking frequency three packs a day (posttest) -Nonequivalent control group pretest posttest design: 1. Smoking cessation program offered -> Students who sign up (participant group) -> Smoking frequency 5 packs a day (pretest) -> Smoking cessation program (treatment) -> Smoking frequency 1 pack a day (posttest)
2. Smoking cessation program offered -> Students who don't sign up (participant group) -> Smoking frequency 5 packs a day (pretest) -> No program (treatment) -> Smoking frequency 4 packs a day (posttest) -Quasi experimental vs correlational: -Similarities: no randomization, outcome variables are measured, challenges to causal claims, can deal with discrete groups or continuous variables -Quasi can deal with multiple discretes, while correlational can only deal with two discrete groups Class 11 oct 7 -Threat to internal validity: 1. History: any event happening between first and second measure 2. Maturation: people change over time (fatigue effect, get hungrier, more mature), independent of manipulation 3. Testing: taking a pretest is enough to change a participant's posttest (practice effect) 4. Instrument decay: characteristics of a measure, or people's use of a measure changes over time 5. Regression towards the mean: participants who are selected based on their extreme scored tend to subsequently score closer towards the mean, Ex: midterms scores is really hard to get 1% or 99% two times in a row History Maturation Testing Instrument decay Regression towards the mean ABA reversal design One-group posttest only One-group pretest- posttest Non-equivalent control group Non-equivalent control group pretest-posttest -Longitudinal developmental design: measures one person as they age,