topic Re: Majority of data points in SAS Programming

Majority of data points

statiswak — Fri, 20 Apr 2018 14:03:34 GMT

Hello,

I need to find the time period (3 month increments; Jan-Mar, Feb-Apr, etc.) where the majority of my data points (rates) are. The dataset extends 2 years. Would it be best to create a graph/visualization such as a scatterplot? Or use a proc freq statement on the dates? Any help would be greatly appreciated.

Re: Majority of data points

PaigeMiller — Fri, 20 Apr 2018 14:12:54 GMT

"majority of data points" might mean something different to me than it means to you

Nevertheless, I can think of two approaches

Histograms (bar charts) of the data
Run PROC UNIVARIATE and use the MODE that is computed (MODE is the value occurs the most)

Re: Majority of data points

ballardw — Fri, 20 Apr 2018 14:21:02 GMT

If you have a date associated with the measures then 1) make sure it is a SAS date value (NOT character or numeric like 20180120 that only looks date-like) and 2) use a format like YYQ6. for the variable.

Then procs like Freq will group the variables into calendar quarters and display the value like 2017Q1 (first quarter of 2017)

Re: Majority of data points

statiswak — Fri, 20 Apr 2018 20:11:57 GMT

Thank you. The proc freq did the trick. I did a cross-tabulation, so I could see the frequency of the ID's by date and quarter.

Re: Majority of data points

statiswak — Fri, 20 Apr 2018 20:14:07 GMT

Thank you!