Hi,
I am performing the Proc Means using dates Aug 1 - Oct 20 and getting results below.
Now I am concern because during that date range we have 3 holidays all falling on a Monday, is it possible to apply weighting for holidays?
proc MEANS NOPRINT data=Temp2;
class day ;
var count ;
output out=Results_Mean mean= MEAN min=MIN max=MAX median = median std= STD var = Variance uclm=UCL LCLM=LCL;
run;
day | mean | Min | Max | median | UCL | LCL |
Friday | 15363.09 | 14520.75 | 16941.08 | 15125.04 | 15835.18 | 14891.01 |
Monday | 15599.47 | 9884.35 | 18428.43 | 16710.27 | 17539.17 | 13659.77 |
Sunday | 5177.31 | 4678.88 | 5627.83 | 5180.03 | 5378.74 | 4975.88 |
Tuesday | 15741.51 | 15093 | 17173.3 | 15478.78 | 16231.36 | 15251.66 |
Saturday | 7365.93 | 6257.15 | 8060.95 | 7559.72 | 7688.33 | 7043.53 |
Thursday | 15488.72 | 14891.9 | 16958.3 | 15222.39 | 15934.34 | 15043.09 |
Wednesday | 15825.44 | 14951.63 | 17371.22 | 15489.8 | 16405.85 | 15245.03 |
Are they holidays that are identified by the holiday() function and, by weighting, would just excluding them using a where data set option suffice?
Depends on how you want to deal with them. Another option would be to classify holidays as a day of the week on its own, but it depends on what type of questions you're looking at.
I'd start off with holidays as its own day of week as below:
day | mean | Min | Max | median | UCL | LCL |
Friday | 15363.09 | 14520.75 | 16941.08 | 15125.04 | 15835.18 | 14891.01 |
Monday | 15599.47 | 9884.35 | 18428.43 | 16710.27 | 17539.17 | 13659.77 |
Sunday | 5177.31 | 4678.88 | 5627.83 | 5180.03 | 5378.74 | 4975.88 |
Tuesday | 15741.51 | 15093 | 17173.3 | 15478.78 | 16231.36 | 15251.66 |
Saturday | 7365.93 | 6257.15 | 8060.95 | 7559.72 | 7688.33 | 7043.53 |
Thursday | 15488.72 | 14891.9 | 16958.3 | 15222.39 | 15934.34 | 15043.09 |
Wednesday | 15825.44 | 14951.63 | 17371.22 | 15489.8 | 16405.85 | 15245.03 |
HOLIDAY xxxxxxxxx .... xxxxxxxxxx
Thank you Reeza & Arthur,
Reeza I found that your suggestion did exactly what I was looking for, thanks.
Fred
Don't miss out on SAS Innovate - Register now for the FREE Livestream!
Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.
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.