In the High 5s study, kindergarten students who had been in Making Pre-K Count program classrooms in pre-K were then individually randomly assigned within schools to High 5s small-group supplemental math clubs or to a business-as-usual kindergarten experience.A notable feature of this two-stage design, illustrated in the figure below, is that the level of random assignment differs across stages: In the first year, a cluster-level design was used to randomly assign from the first-stage treatment group.
But randomizing enough clusters (schools) to create three arms for testing the pre-K and kindergarten programs would have been challenging in its operational demands and use of resources.
Randomly assigning children to kindergarten math clubs within the program arm allowed for reasonable statistical power while balancing the reality of implementing the clubs in so many schools.
The studies all seemed to indicate that a moderate use of alcohol could give a person a healthier heart, yet Fillmore found that many of the studies (47 of them) hadn’t randomly divided the participants into groups of drinkers and non-drinkers.
Instead, it was a comparison between people who drank regularly and people who couldn’t drink because they were either a) old or b) dying. Not because of drinking, but because they were not ill or too old.
By using a two-stage design, we could preserve the original test of the pre-K math curriculum while adding a test of the kindergarten component and a test of their combined effect.
Study design In the Making Pre-K Count study, pre-K programs (schools) were randomly assigned either to implement Building Blocks, with associated professional development to support teacher implementation of the curriculum, or to a pre-K-as-usual control condition.
Random assignment ensures that participants in a cause and effect study are unbiased as it prevents people’s history from causing an extraneous variable within the experiment.
Only for ethical reasons should it be changed; many of the studies could not have used this as it means they would have had to convince non-drinkers to drink.
If by the end of an experiment you have discovered which is the dependent variable and which is the independent variable, you will have created a much more valid study than one which simply finds a connection, as you can then start investigating to what extent the IV affects the DV.
Yet what if you have indeed found a connection, yet the methods you used to imply that connection ended being the reason it occured? conducted a meta-analysis of 54 studies looking at moderate alcohol use and if it had an effect on a person’s health.