I'm trying to calculate the following stats :
25th percentile (95% CI)
Median (Weeks) (95% CI)
75th percentile (95% CI)
by using proc univariate
And I'm getting the results:
But I'm a little bit confused with output CI to the datset, I'm trying like:
ods select Quantiles;
proc univariate data=Sashelp.Cars ciquantnormal(alpha=.1 );
var MPG_City;
output out=a1 q1=q25 q3=q75 median=median min=min max=max lclm=lci uclm=dfd;
run;
But I'm getting an error :
ERROR 22-322: Syntax error, expecting one of the following: CSS, CV, GEOMEAN, GINI, KURTOSIS, MAD, MAX, MEAN, MEDIAN, MIN, MODE,
MSIGN, N, NMISS, NOBS, NORMAL, P1, P10, P5, P90, P95, P99, PCTLNAME, PCTLPRE, PROBM, PROBN, PROBS, PROBT, Q1, Q3, QN,
QRANGE, RANGE, SIGNRANK, SKEWNESS, SN, STD, STDMEAN, STD_GINI, STD_MAD, STD_QN, STD_QRANGE, STD_SN, SUM, SUMWGT, T,
USS, VAR.
I suppose I'm using the wrong way for output CI, can somebody help?
Hello @kaet78ha,
Replace the OUTPUT statement with an ODS OUTPUT statement to get what you want:
ods output Quantiles=want;
Also, if you want 95% CIs, then omit the ALPHA= option (or use ALPHA=.05 explicitly).
Hello @kaet78ha,
Replace the OUTPUT statement with an ODS OUTPUT statement to get what you want:
ods output Quantiles=want;
Also, if you want 95% CIs, then omit the ALPHA= option (or use ALPHA=.05 explicitly).
SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!
Learn the difference between classical and Bayesian statistical approaches and see a few PROC examples to perform Bayesian analysis in this video.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.