As we know, we can estimate the reliability of one variable with split-half method. However, how can we estimate the reliability of a correlation between two variables?

One alternative way is to split the samples into halves. But in this case, the sample size is just half of the whole sample size.

I wonder whether a bootstrapping method can be used as a way to estimate the reliability of a correlation?

More Xiang-Zhen Kong's questions See All
Similar questions and discussions