topic Re: tabulate using proc freq! in SAS Programming

tabulate using proc freq!

SAS_taozi — Thu, 08 Feb 2024 00:28:09 GMT

I have this data:

Age Pets Country height (cm)

35 3 US 165

65 2 UK 171

21 2 US 181

28 2 China 159

35 1 China 176

65 1 US 175

40 2 UK 178

And I want to summarize the variables using proc freq (so general summary statistics including n, mean, median, std, q1, q3, min, max) by 3 groups, US, UK and China. A sample table is:

variable		Group			P-value
		US	UK	China
age
	n
	mean
	median
	std
	Q1, q3
	Min,max
Height
	n
	…

The aesthetics can be different by methods and preferences but wanted to know how should I organize the data and merge them into this desired way (summary statistics for each variable in rows, by country in columns). Ideally I want to use proc report to generate the table but if it's too much, I want to know how to most efficiently merge the table at least. Thank you so much!! Discussion is welcomed

Re: tabulate using proc freq!

Astounding — Thu, 08 Feb 2024 02:09:10 GMT

A few points to begin.

PROC FREQ will probably not be part of the solution. It doesn't compute the statistics you are hoping to display.

PROC TABULATE will do the job (and likely PROC REPORT as well, but I'm not as familiar with it). And you won't need to manipulate the data ahead of time.

What procedure are you hoping to use to get p-values? What do the p-values represent? There's no way to include p-values in a program until you can address those questions.

Here's a shell of a program to get you going:

proc tabulate data=want;
class country;
var age height;
tables (age height) * (n mean median std q1 q3 min max),
  country;
run;

Re: tabulate using proc freq!

A_Kh — Thu, 08 Feb 2024 18:42:26 GMT

Additionally, Proc Tabulate or Proc Report give descriptive stats in a different tabular format, not exactly the one you wanted (Min, Max or Q1, Q2 - in the same cell). This requires a pre-processing of data. See the similar post here.

Re: tabulate using proc freq!

Reeza — Thu, 08 Feb 2024 18:51:09 GMT

I highly recommend looking into the TABLEN macro from Jeff Meyers.

https://communities.sas.com/t5/SAS-Communities-Library/Demographic-Table-and-Subgroup-Summary-Macro-TABLEN/ta-p/634030