Hi everyone! I’ve been working with expenditure data, and I was collapsing data by duplicate and my variable interest, looking at expenses, comes out as a negative number. Am I doing something wrong? Or is there a way to deal with this by using health econometrics? This is my first time working with this data and I’m very wary that I did something wrong.
It’d be great to get some input on this!
Could you please share more about the expenditure variable(s) that have negative values? Sharing the sample(s), variable name(s), and an example of one or two person records that have negative expenditures will help us determine what’s going on. IPUMS MEPS expenditure variables can be equal to zero, but my IPUMS MEPS colleagues have confirmed that none of them have negative values in any of our samples (1996-2023).
It is possible that while manipulating or cleaning your data, or performing data analysis, you modified the values of one or more expenditure variables, resulting in negative values.