I have two datasets that describe reports of caregivers and parents from 8 daycares. The two data sets are matched by daycare's name. We want to merge the data into a single dataset that will contain parents responses (their children go to a specific daycare) and caregivers' responses. At the end of the day, we want to compare the daycares (N = 8). We have 164 parents, and 68 caregivers. We can average responses per daycare and make a N = 8 dataset. It should be noted that caregivers and parents answered different questionnaires. I wonder whether there is a method that weights the number of observations before/during aggregating data and averaging. Any ideas to handle these datasets to be able to compare daycares?


You can use some metrics for internal consistency, a measure based on the correlations between different items on the same test. These measurements methods are commonly used for surveys.

A common metric use is Cronbach's alpha and Cohen kappa

See here for information on different methods.



Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.