I need to calculate the p-trend of age-adjusted incidences. The age-adjusted incidences were calculated using the direct method, so the numerators and denominators were large. I tried the poison model and found the p-trend was <0.0001, but the incidence rates seem to be non-linear, rather than an increased or decreased trend. Also, I found the value/df are very high (>3500), which should be close to 1 for better accuracy. Is it right to use poison model? Which model is good for calculating the p-trend of age-adjusted incidences? data a; input periods cases pyears; loga=log(pyears); datalines; 1 10000 50000000 2 25000 50000000 3 20000 50000000 4 15000 50000000 ; run; proc genmod data=a; model cases=periods / dist=poisson link=log offset=loga; run;
... View more