What is the difference between stratification and blocking in experimental design(or randomized control trial)?

Blocking is to obtain homogeneity in a controlled factor. However, I can block more than 1 variables($X_1,X_2$) to obtain homogeneity within $X_1=x_1,X_2=x_2$.

(pre-)Stratification of prognostic variables $X_1,X_2$ seems to control homogeneity of subjects as well to increase precision. I could not see difference between the two here. Post-stratification changes the story here in general. It seems that stratifying $X_1,X_2$ is blocking $X_1,X_2$ to me.

If I do not use unbalanced design and making replications within each cell, it seems that both will arrive at the same model.

In sampling design, the two makes huge difference. Or is it possible due to invoking population model in experimental design which results difference here?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.