I want to extract data for the year 1970,80,90 and 2000. 1990 and 2000 contain 1% sample measures. However 1980 and 1970 do not have these options. Will choosing a 1%metro or other similar sample data be similar enough? If not, what are the differences that would be created from this?
Combining samples of different percentages should not be a problem if you use the appropriate weights to make each sample representative of that year’s population. It is also important to understand the differences between the samples you are comparing in terms of sample design.
I hope this helps.