Should HCOVPUB == 2 and HCOVPRIV == 2 add up to HCOVANY == 2? This does not work out when I use frequency weights. Additionally, those insured by the component parts of HCOVPRIV (HINSEMP, HINSTRI, and HINSPUR) do not add us to HCOVPRIV. Should these add up?
The population with public and private insurance will not necessarily be equal to the population with any insurance because individuals can be covered by more than one type of insurance, and they can be covered by both private and public insurers. For example, an individual who has both public and private insurance would be coded as HCOVPUB == 2 and HCOVPRIV == 2. This person would be counted twice according to HCOVANY. To further illustrate this phenomenon, I created the following table showing population totals for these three variables in the 2019 ACS.
These same principles apply to your question regarding HCOVPRIV and its components. For more information, see this page on Health Insurance Variables in the ACS.
Thank you for the clarification!