options   nosource;   * Rolling Beta Regression Program Notes:   *  Rolling sample periods move forward one  month   at a  time    (per loop iteration) *  Default case uses 2 years or 24 months of daily  data   and the sample periods overlap. *  The program parameters can be changed  to   use a different sample  length .   *   In   the RRLOOP  macro   routine below the regression coefficients are estimated  by   starting with *  a sample period of  &YEAR1   to   &YEAR1   +  &NYEAR   and progresses forward  to   end   at  &YEAR2 .  *  YEAR1 and YEAR2 are defined using START_YEAR and END_YEAR  macro   variables, and NYEAR= SAMPLE_YEAR   *   To   use  end   of  year   (December) only estimation, change MM loop  to :    %do   mm = 12  %to   12;   *  Code below also can be changed  to   use other regression models such as the F-F 3 factor model. *  Change  PROC   REG and the  DATA   step before the APPEND accordingly.   *   Output   dataset includes DATE1 and DATE2 that defines each row sample period   * Example        PERMNO      date1      date2 _DEPVAR_       alpha   beta   _RMSE_   _RSQ_  nobs     10104 2002-02-01 2004-01-31  retrf   -.000284893 1.57198 0.025787 0.38637  503         2002-03-01 2004-02-29  retrf   -.000476811 1.56050 0.025747 0.37886  503         2002-04-01 2004-03-31  retrf   0.000030706 1.61115 0.023942 0.42828  506         2002-05-01 2004-04-30  retrf   0.000285565 1.60345 0.023432 0.43471  505     10107 2002-02-01 2004-01-31  retrf   -.000347769 1.35198 0.014412 0.59856  503         2002-03-01 2004-02-29  retrf   -.000356315 1.34827 0.014413 0.59231  503         2002-04-01 2004-03-31  retrf   -.000399233 1.32516 0.014328 0.58590  506         2002-05-01 2004-04-30  retrf   -.000094302 1.30637 0.014258 0.57960  505   *********************************************************************************;   I put the following macro into my code set, but SAS does not run. I even do not know the error. the log show nothing expect these original codes. Did I miss anything?  The dataset I used is MSF2. So I change the in_ds=MSF2, it still does not work.  My libname is C:/DATA. *****************************************************;   %macro   RRLOOP (year1= 2001, year2= 2005,  nyear= 2, in_ds=temp1, out_ds=work.out_ds);     %local   date1 date2 date1f date2f yy mm;     /*Extra step to be sure to start with clean, null datasets for appending*/ proc   datasets nolist lib=work;    delete   all_ds oreg_ds1; run ;     /*Loop for years and months*/   %do   yy =  &year1   %to   &year2 ;     %do   mm = 1  %to   12;       /*Set date2 for mm-yy end point and date1 as 24 months prior*/   %let   xmonths=  %eval (12 *  &nyear ) ; *Sample period length in months;   %let   date2= %sysfunc ( mdy ( &mm ,1, &yy ));   %let   date2=  %sysfunc   ( intnx ( month ,  &date2 , 0, end )) ; *Make the DATE2 last day of the month;   %let   date1 =  %sysfunc   ( intnx ( month ,  &date2 , - &xmonths +1, begin)) ; *set DATE1 as first (begin) day;   /*FYI --- INTNX quirk in SYSFUNC:  do not use quotes with 'month' 'end' and 'begin'*/     /*An extra step to be sure the loop starts with a clean (empty) dataset for combining results*/ proc   datasets nolist lib=work;    delete   oreg_ds1; run ;     /*Regression model estimation -- creates output set with coefficient estimates*/ proc   reg noprint  data = &in_ds   outest=oreg_ds1 edf;    where  date   between  &date1   and  &date2 ;  *Restricted  to   DATE1- DATE2  data   range  in   the loop;    model retrf = vwretdrf;    by   permno; run ;     /*Store DATE1 and DATE2 as dataset variables and rename regression coefficients as ALPHA and BETA;*/ data   oreg_ds1;    set   oreg_ds1;    date1= &date1 ;    date2= &date2 ;    rename intercept=alpha  vwretdrf=beta;    nobs= _p_ + _edf_;    format date1 date2 yymmdd10.; run ;     /*Append loop results to dataset with all date1-date2 observations*/ proc   datasets lib=work;    append base=all_ds  data =oreg_ds1; run ;       %end ;  %  /*MM month loop*/       %end ; %  /*YY year loop*/     /*Save results in final dataset*/ data   &out_ds ;    set   all_ds; run ;     %mend   RRLOOP;   **********************************; The primary output of this program is a data set with these items: CRSP Permanent Number=10107 date1 date2 _RMSE_  Intercept VWRETD    regobs 01JAN2002 31DEC2004 0.057470   -.005836843 0.97255 36 01FEB2002 31JAN2005 0.057446   -.004874504 0.95958 36 01MAR2002 28FEB2005 0.057358   -.004550887 0.92014 36 01APR2002 31MAR2005 0.057448   -.005048308 0.92846 36 01MAY2002 30APR2005 0.056784   -.000042066 0.81758 36 01JUN2002 31MAY2005 0.056721   0.000278585 0.80891 36 01JUL2002 30JUN2005 0.051923   -.006355348 0.99118 36 01AUG2002 31JUL2005 0.051481   -.004585000 0.91877 36 01SEP2002 31AUG2005 0.053227   -.002505193 0.89010 36 01OCT2002 30SEP2005 0.054340   -.003183394 0.84427 36 01NOV2002 31OCT2005 0.045522   -.003110266 0.52825 36 01DEC2002 30NOV2005 0.045962   -.002508023 0.50723 36 01JAN2003 31DEC2005 0.044918   0.000198639 0.35030 36   ... View more

%macro m(start=,end=); proc expand data=A1 (keep=ID date AAA) out=A3 method=none; %do i=&start %to &end; by permno; id date; convert AAA = AAA_&i / transformout=(reverse MOVPROD &i reverse trimright &j); %end; run; %mend m; %m(start=2,end=50); -------------------------------------------------- Here how to code j ? j=i-1 It is incorrect if I just use "&i-1" in the transformout. Thanks! ... View more

 I am trying to create a reference price measure that is an average of past 250 days stock prices, weighted by the probabilities of a stock not being traded since the date of the corresponding price: reference_price t =(price t-250 *turnover_ratio t-250 *(1-turnover_ratio t-249 )*(1-turnover_ratio t-248 )*...*(1-turnover_ratio t-1 )+price t-249 *turnover_ratio t-249 *(1-turnover_ratio t-248 )*(1-turnover_ratio t-247 )*...*(1-turnover_ratio t-1 )+...+price t-1 *turnover_ratio t-1 )/k, where k is a constant that ensure price weights add up to 1 (see the formula below).   The following link is for STATA: https://www.statalist.org/forums/forum/general-stata-discussion/general/1329146-generating-a-reference-price-measure-as-a-probability-weighted-sum-of-past-stock-prices   For each stock, how to code the reference price in SAS? Price, Turnover ratio each day are given.   Thanks very much!  ... View more

The format of the data set: ID  Date Year Month Day  Variable1  Variable2 The dataset has the daily observations for each ID.  For each ID each month, I want to run a regression of Variable 1 on variable 2 based on recent 6-month daily observations. How to use the macro to run this regression? It is more complicated than the monthly rolling regression.  ------------------------------------------------------------------------- If I do some manipulation and get the following format:   IDNAME   Count   Variable1   Variable2 Here 'Count' measures the date from 1 to a number based on date of each ID (for example, 120). Each ID has different number of count. Now I run a regression of Variable1 on Variable2 using only 6 counts, i.e., 1-6 for the first regression, 2-7 for the second, 3-8,.... How to write this macro for the regression. I am new to the macro. Thanks.   proc reg data=one noprint outest=results; model variable1=variable2; by IDNAME count; run;     ... View more