I need to estimate the amount of CF patients in Poland in the next four years. I have:
- estimations of the Polish population for the future years
- a CF patients' register for the last couple of years in the USA
- estimates for the USA population in the next few years.
The catch is: Polish population will be decreasing, but the CF population should be growing, with more awareness, better diagnostics etc.
The question is: can I (assuming that the CF subpopulation's relative growth in the USA is the same as in Poland) use the data about the CF subpopulation in the USA, adjust it for the USA growing population, as well as Polish diminishing population to get a statistically justified estimate of the future CF subpopulation's size in Poland?
All those data seem to have a linear trend for the last couple of years, so I thought I could just make linear regressions for all three data sets and then assume that the polish CF subpopulation will grow according to the slope $\alpha_{\textrm{CF in Poland}} = \alpha_{\textrm{CF in USA}} - \alpha_{\textrm{USA}} + \alpha_{\textrm{Poland}}$, where $\alpha$ are slopes for the respective reggresions.
Is there any statistical merit to this approach?
EDIT: After beginning my calculations I see that my method is wrong (the slopes for Poland's and USA population growth differ greatly in size).