Help
Options
Didn't know it?
click below
click below
Knew it?
click below
click below
Don't Know
Remaining cards (0)
Know
retry
shuffle
restart
0:00
Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.
Normal Size Small Size show me how
Normal Size Small Size show me how
Adv Research Design
Exam #4
| Question | Answer |
|---|---|
| factorial design | multiple IVs |
| reasons to use a quasi-experimental design | can't manipulate the IV, can’t randomly assign, when ethical to do so (ex. look at hurricane after it happened, not manipulated) |
| reasons to use an single-case design | rare, tracking an individual’s changes, therapy, ethical (may modify behavior), in-depth analysis |
| Chi-square-goodness of fit | nonparametric, random sample, sample to population, variance is heterogenous |
| Chi-square- independence | 2 or more groups/levels |
| Friedman’s | repeated measures ANOVA (w/in) |
| Kruskal-Wallis | randomized ANOVA (btw) |
| Wilcoxon rank sum | independent/btw, ordinal data |
| matched pairs signed ranks | dependent/within, ordinal data |
| Wilcoxon rank sum assumptions | ordinal data (or converted), not normal distribution, independent |
| matched sets | matched on characteristics (more than 2) |
| natural sets | triplets, quadruplets |
| repeated measures | pre, mid, post assessment; all w/in |
| threats to internal validity in a pretest-posttest | regression to the mean, mortality, history, instrumentation, ceiling/floor effects |
| Wilcoxon obtained value | < or = CV- obtained value has to be greater than p= .05 for significance (p> .05) |
| Chi square independent-sample | must be random |
| Chi square | nominal |
| Wilcoxon | ordinal/converted ordinal |
| Chi square goodness of fit assumptions | 5 cases, random selection, non-parametric |
| 2 group design | btw group |
| multiple group design | btw, add placebo, level, or control group |
| parametric tests | t-tests, ANOVAs |
| non parametric | Wilcoxon rank sum, Friedman, Kruskal Wallis, Mann Whitney, chi squares |
| small n/single case design | are quasi and within |
| multiple baselines | behaviors, situation, & participants |
| ABAB design is... | more ethical- end on treatment phase than baseline, a reversal design |
| types of small n designs | rehearsal, time series, multiple baselines |
| problems with single group designs | increased confounds, no equivalent control group, no comparison group |
| single case design | 1 participant |
| small n design | a few participants |
| cross-sectional | snapshot of multiple cohorts, 1 time |
| longitudinal | 1 cohort |
| regression to the mean | go back to the average (mean) |
| types of quasi-experimental designs | Single-group posttest only, Single-group pretest-posttest, Single-group time-series, Multiple-group time-series, Non-equivalent control group posttest only, Non-equivalent control group pretest-posttest |
| confound | uncontrolled, extraneous variable that messes with control |
| internal validity | IV affects the DV |
| external validity | generalizability |
| single group time series design | repeatedly measured across time |
| nonequivalent control group pretest/posttest | assessed twice (pre-posttest) |
| time series design | multiple measures across time |
| manipulated variable ex. | therapy |
| nonmanipulated variable ex. | gender, disorder, age, classification |
| subject variable | a lot of nonmanipulated variables are subject variables |
| nonmanipulated IV | can't randomly assign |
| factorial notation | # = IVs, the # itself = levels |
| main effects | effect of IV (look at IVs) |
| interactions | interaction btw different variables & levels |
| graph of interaction | slopes will be different |
Created by:
Finch35i