BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
sportguy3089
Calcite | Level 5

I wanted to see if this will work?

proc univariate data=sashelp.shoes PLOT;

run;

To see the output and see if I see outliers?

Reeza
Super User
What's your definition of an outlier? Explicitly? You first need to determine your logical criteria and then implementation is easy. The code is the easy part of this work, deciding what/how to do things is the hard part.

An explicit definition is something like:
Any values in the top and bottom 1 percentile is considered an outlier.

Now for percentiles, you also need to consider how you want to handle tied values.
Note that you would make a rule for each variable, not a broad rule as above for all variables. That's a very broad approach, kinda like trying to sharpen a pencil with an axe.

Now what are you planning to do once you've identified these outliers? Remove them?

You may actually get better answers if you explain what you're trying to do overall. What's the context of the analysis problem you're facing that makes you think you have outliers in your data? Are outliers good or bad or both? Do you want to identify them for what reason?

Randomly happened to walk through a review of call center analysis earlier this morning with my analysts. We found calls that were less than a minute which are likely disconnects/wrong numbers so we decided to remove those for example. It usually takes a few minutes to authenticate and verify a user so those are not valid for the analysis we're doing (first call resolution, how many customer service calls were resolved on the first call). Longer calls, like 5+ are our complex calls s those are filtered out for separate analysis and further text analytics.


sportguy3089
Calcite | Level 5

Just to see if there are outliers that is it 🙂 

Reeza
Super User
What's your definition of an outlier? Explicitly?
Reeza
Super User
Not trying to be a pain in the ass, but if you can't answer that question you definitely cannot code the solution because the requirements are unclear.
sportguy3089
Calcite | Level 5

No problem I get it  an outlier differs significantly from other observations.

SAS Innovate 2025: Save the Date

 SAS Innovate 2025 is scheduled for May 6-9 in Orlando, FL. Sign up to be first to learn about the agenda and registration!

Save the date!

Mastering the WHERE Clause in PROC SQL

SAS' Charu Shankar shares her PROC SQL expertise by showing you how to master the WHERE clause using real winter weather data.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 20 replies
  • 2176 views
  • 0 likes
  • 5 in conversation