I have two datasets. One dataset has families of 2 members and the other dataset has families of uneven sizes. In all the names, there are often minor spelling mistakes so often, we will not get exact matches.
How can I match the 2-member family in the first dataset with the n-member family in the second dataset? The names in the 2-member family must exist in the n-member family although it will not exist exactly due to spelling mistakes.
In some sense, I am trying to find a way to tell STATA to :
“Match if 4 words in the 2-member and n-member families are 80% similar”. I say 4 words accounting for 2 first names and 2 last names in the first dataset for each 2-member family and 80% to account for spelling mistakes.
Is there a way to do this?
Related Posts with Is it possible to match families/groups and not individual observations?
Panel Data Regression on Gravity ModelHi everyone, I am doing an gravity model analysis on panel data of 10 countries for 30 years. This …
Generating dummy variable based on lagged quartile dataHi everyone, I am trying to generate a dummy variable that is conditional on whether the variable o…
Estimates of Marginal Effects after GMMHello Experts and Researchers ! Could anyone suggest me the code and command on how to estimate marg…
Problem with "asdoc" and the order of the categoriesHi, I have a problem with asdoc, I hope you can guide me. The correct tab (with sum) is as follows: …
IR and PR (Prevalence ratio) same for Modified Poisson Regression with Robust Error VarianceHello glm y i.x1 i.x2 i.x3 i., link(log) family(poisson) eform Using the above command, I have fo…
Subscribe to:
Post Comments (Atom)
0 Response to Is it possible to match families/groups and not individual observations?
Post a Comment