SAS Support Communities

Say you have a dataset named “have” below; Obs date quantity price totalprice 1 200001 10 5 50 2 200002 10 5 50 3 200003 10 5 50 4 200004 10 5 50 5 200005 10 5 50 6 200006 10 5 50 7 200007 10 5 50 8 200008 10 5 50 9 200009 10 5 50 10 200010 10 5 50 11 200011 10 5 50 12 200012 10 5 50 13 200101 10 5 50 14 200102 10 5 50 15 200103 10 5 50 16 200104 10 5 50 17 200105 10 5 50 18 200106 10 5 50 19 200107 10 5 50 20 200108 10 5 50 21 200109 10 5 50 22 200110 10 5 50 23 200111 10 5 50 24 200112 10 5 50 data have1;       set have;       date1 = put(date,6.);       date2 = input(date1, yymmn6.);       format date2 monyy7.;       quarter = qtr(date2);       year = year(date2); run; proc sort data = have1;       by year quarter; run; ods trace on; proc means data = have1 sum;       var quantity price totalprice;       class year quarter;       ods output summary=out1; run; ods trace off; data havefinal (drop = Nobs VName_quantity VName_price VName_totalprice);       set out1; run; ods html; proc print data = havefinal noobs; run; ods html close; year quarter quantity_Sum price_Sum totalprice_Sum 2000 1 30 15 150 2000 2 30 15 150 2000 3 30 15 150 2000 4 30 15 150 2001 1 30 15 150 2001 2 30 15 150 2001 3 30 15 150 2001 4 30 15 150 If you have country variable then just add country before year in PROC SORT and PROC MEANS. ... View more

Thank you. Please correct me if I'm wrong regarding AIC. ... View more

This is what I was looking for. sad predefined distributions are so limited. Guess I could use PROC FCMP to define distributions that are not predefined. OR... do you know any site that lists other distrtibution functions using PROC FCMP? ... View more

     Thank you for your help. I could try PRCO GENMOD... in DIST option do you know how many distributions are available?      I disagree with you regarding the use of AIC. AIC is a holistic approach to comparing different models, it can do more than comparing various models that have different covariates (it is used to compare any parametric models as it uses likelihood function). AIC is used to test models that are not nested (but of course it can be used for nested models), for example if we have totally different models not only in covariates but also in methods used to fit the model we can compare which model is a better fit by comparing AICs. As distribution functions can differ in number of parameters to estimate and as AIC also takes this in to account (-2LL + 2p), AIC and other ICs, I believe, are the best way to compare parametric models.      Please correct me if I'm wrong. ... View more