← SASnRDescriptive statistics for numeric variables

Introduction

Descriptive statistics — n, mean, standard deviation, min, max — are the everyday summary of any numeric variable.
Typical requests: height summary across all subjects, then the same summary broken down by sex or by treatment arm.
SAS offers proc summary (or the closely related proc means) to compute these on the full dataset or within class levels.
Tidyverse uses summarize() with group_by() for the grouped form — a compact, pipe-friendly pattern.
Base R uses aggregate() with a small custom function to return several statistics at once, plus an unpacking step.
This lesson computes n, mean, and sd for Height on CLASS, first overall and then split by Sex.

Descriptive statistics for numeric variables

SAS (Base SAS)+

data CLASS;
 infile datalines dlm='|' dsd missover;
input Name : $8. Sex : $1. Age : best32. Height : best32. Weight : best32.;
label ;
 format ;
 datalines4;
Alfred|M|14|69|112.5
Alice|F|13|56.5|84
Barbara|F|13|65.3|98
Henry|M|14|63.5|102.5
James|M|12|57.3|83
;;;;
 run;

proc summary data=class;
 var height     ;
 output out=stats01 n=n mean=mean std=sd;
 run;

proc summary data=class nway;
class sex    ;
 var height     ;
 output out=stats02 n=n mean=mean std=sd;
 run;

proc summary data=class; runs on CLASS; var height; names the analysis variable.
output out=stats01 n=n mean=mean std=sd; writes one row with columns named n, mean, and sd.
For a grouped run, we add class sex; plus the nway option.
nway restricts the output to the finest-class combinations; without it, SAS would also add overall-total rows we do not want here.
After running, STATS01 should have one overall summary row and STATS02 should have one row per Sex level.
Open both datasets and confirm the n for STATS02 adds up to the n in STATS01.

R (tidyverse)+

class<-tribble( 
~Name,~Sex,~Age,~Height,~Weight, 
"Alfred","M",14,69,112.5, 
"Alice","F",13,56.5,84, 
"Barbara","F",13,65.3,98, 
"Henry","M",14,63.5,102.5, 
"James","M",12,57.3,83, ) 

stats01<-summarize(class,
n=n( ), 
mean=mean(Height),
sd=sd(Height)) 

stats02<-class %>% 
group_by(Sex) %>% 
summarize(
n=n( ), 
mean=mean(Height),
sd=sd(Height)
)

In tidyverse, summarize() reduces a tibble to a single row of statistics; combined with group_by(), it produces one summary row per group.
summarize(class, n = n(), mean = mean(Height), sd = sd(Height)) gives the overall summary — the equivalent of the ungrouped proc summary call.
n() is the dplyr helper that counts rows in the current group; mean() and sd() come from base R and work on the tibble column transparently.
For the grouped form, pipe the data through group_by(Sex) first, then call summarize() — we get one row per Sex level.
The result is a tibble, ready to pipe into a plot, a join, or a report without an explicit out=.
We run and compare the tibble rows against SAS STATS01 and STATS02 — they should match row for row.

Happy learning!

Search lessons

Introduction

Descriptive statistics for numeric variables