Fichas
BRM H9
Fichas del conjunto (28)
- 1probabilistically equivalentthe notion that two groups that are random assigned would on average perform identically
- 2confoundingother factors that influence the outcome
- 3t-testjust two groups, see if difference in means is because of chance or not
- 4ANOVAtwo or more groups, see if difference in means is because of chance or not
- 5random selectionhow you draw the sample of people from a population for your study -sampling, external validity
- 6random assignmenthow you assign the sample that you draw to different groups or treatments in your study- experimental design, internal validity
- 7factorial designsif the treatment/program has effect, focus on program, dimensions, major components
- 8covariance designshelps minimize the noise by including more variables (covariates) that account for some of the variability
- 9blocking designshelps minimize the noise by grouping the participants into one or more classifications called blocks that account for some of the variability
- 102x2 factorial designdon't have to use four different studies to come up with an answer for which variation of your program works best
- 11factormajor independent variable (=treatment or program) time in instruction, setting
- 12levelsubdivision of a factor (1h/w and 4h/w, in class and pull-out)
- 13the null outcome/the null case(results 2x2 design)when the treatment has no effect
- 14the main effects (result 2x2 design)outcome that shows consistent differences between all levels of a factor (=independent variable)
- 15interaction effects (result 2x2 design)when differences on one factor depend on which level you are on another factor
- 16determine whether an interaction existswhen you do a statistical analysis the table will report on all main effects and interactions, there is an effect when you can't talk about the effect of one factor without mentioning the other factor, you can spot an interaction in the graphs of groups means - whenever lines aren't parallel there's an interaction
- 17benefits basic factorial designgives flexibility for exploring the signal in the study, its efficient, its the only effective way to examine interaction effects
- 18signalkey variable of interest
- 19noiseall the random factors in the environment that make it harder to see the signal
- 202x3 factorial designstwee keer drie blokjes
- 21threes-factor exampleheeft twee 'blokken' en aan de rechterkant ook nog een factor staan
- 22incomplete factorial designwhen There are too many groups and levels and it becomes a mess and not everything is relevant so you decide to leave some out (leave empty) and let it incomplete
- 23fully crossed factorial designpairing of every combination of factor levels
- 24randomized block designthe sample is grouped into relatively homogeneous subgroups or blocks within which your experiment is replicated, it reduces noise - blocks must be more homogeneous than the entire sample
- 25analysis of covariance (ANCOVA)estimates the difference between groups on the posttest after adjusting for differences on the pretest, reduces noise
- 26covariatea variable you adjust for in your study, can be included in an analysis to make a more exact estimate of the relationship between an independent and dependent variable
- 27switching-replications designtwo-group design in two phases defined by three waves of measurement, in the middel the two groups switch roles, control group becomes treatment group and other way around - one of the strongest experimental designs
- 28limitations experimental designsdropouts, challenging on ethical grounds, limitations of the degree to which you can generalize
Información
- Descripción
- Fichas sobre BRM H9, creado por s stevens el 16/12/2021.
- Creado por
- s stevens · dic 2021
- Actualizado
- 17 dic 2021
- Visitas
- 0
- Valoración