Hi,   I have a results dataset with study participant IDs and string result values. The data were recorded over different time period, hence there are multiple rows for each ID, and some IDs have the same result value at different time periods (e.g. for ID #1 resultB is red-apples at both time periods),     data have; input ID resultA :$200. resultB :$200. ; datalines; 1 green-apples red-apples 1 red-apples red-apples 2 green-apples yellow-pears 2 red-apples yellow-pears 3 green-apples red-apples 3 green-apples green-apples 4 red-apples green-apples 4 red-apples red-apples ; run;   I want to generate a unique list of all string result values, and then determine how many IDs had this result (so collapsing the result string values by ID/reporting the result string by total number of IDs with this result...). From my searching on the forum so far, I think I need to first append the resultA and result B columns..   data Appended; set have; array NAMES resultA--resultB; do i = 1 to dim(NAMES); if not missing (NAMES{i}) then do; All_Names = NAMES{i}; output; end; end; drop resultA--resultB i; run; And then perhaps use proc report to generate a summary, similar to a pivot table in Excel   proc report data=Appended; column All_Names id ; define All_Names/group "Names"; define ID/group "id"; run; But I'm not sure if this is the most efficient way to achieve what I want (dataset below) data want; input Names :$200. ID_count ; datalines; green-apples 4 red-apples 4 yellow-pears 1 ; run; Any help much appreciated. Happy to clarify if above unclear.   Thank you,   ... View more

Hi,   I have a results output with study participant IDs and numeric values   data results; input ID resultA resultB; datalines; 1 2392 887 2 1587 902 3 2392 234 4 4035 2392 ; run;   These numeric values correspond to string values (names) found in a reference file   data reference; input num first$ last$; datalines; 2392 joe bloggs 4035 mary smith 1587 bloggs joe 234 sherlock holmes 902 john watson 887 benjamin button ; run; I want to match the string values in the reference file with the numeric values in the results output. This is the output I want to achieve; the string values under resultA and resultB are based on the numbers and corresponding string values in the reference file   data want; input ID resultA :$200. resultB :$200. ; datalines; 1 joe-bloggs benjamin-button 2 bloggs-joe john-watson 3 joe-bloggs sherlock-holmes 4 mary-smith joe-bloggs ; run; I have tried to search for code on the forum to solve this, with no success.   Any help would be greatly appreciated.   Please let me know if my problem is not clear from the above.   ... View more

Hi,   My question relates to general guidance when conducting regression analysis, and I have therefore not provided example data.   I have a patient population with N=1,000.   In this population, a small number of patients (n<50) received a particular drug, which is the exposure focus of interest in my analysis.   I want to run a logistic regression to examine the effect of a patient exposed to this drug and their risk of hospital admission.   To obtain an adjusted effect estimate, I need to include 6 co-variates in my model. When I do this, I get an odds-ratio of ~2 (SE 0.8), and the CIs for the effect estimate are quite wide, no doubt partly due to the small sample.   I am aware of the "rule of 10 events per variable" when running logistic regression, but I am wondering if I am interpreting this correctly - in my above example, does this mean 10 hospital admissions per co-variate included in my model, or 10 patients exposed to the drug of interest per co-variate included in my model?   Thank you in advance for your help,   ... View more