You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The current method employed by TaxData to handle CPS top-coding is to augment the topcode by a randomly chosen value, with this process repeated a number of times while keeping the weight of the individual tax entry constant. CPS 2015 uses a different method of swapping values between different but similar households ("rank proximity swapping"), supposedly minimizing the differences in the statistical distribution and to possible calculations from the dataset. This should eliminate the need for TaxData to do the detailed handling of top-coding it does now.
@martinholmer it's in line with the discussion in #174. I asked @lucassz to look into how we should revise our top coding logic and he found that there no longer seems to be a need for any top coding adjustments.
The current method employed by TaxData to handle CPS top-coding is to augment the topcode by a randomly chosen value, with this process repeated a number of times while keeping the weight of the individual tax entry constant. CPS 2015 uses a different method of swapping values between different but similar households ("rank proximity swapping"), supposedly minimizing the differences in the statistical distribution and to possible calculations from the dataset. This should eliminate the need for TaxData to do the detailed handling of top-coding it does now.
@andersonfrailey
The text was updated successfully, but these errors were encountered: