DATA Step, Macro, Functions and more

SASHELP Data sets

Accepted Solution Solved
Reply
Super Contributor
Posts: 298
Accepted Solution

SASHELP Data sets

Do anybody know where the description of the data set, SASHELP.PRDSAL and other two related data sets(PRDSAL2, PRDSAL3) is given? There are two variables, ACTUAL and PREDICT. They refer to furniture sales and predicted sales. How  PREDICT is computed and what goes behind?

I appreciate your help.


Accepted Solutions
Solution
‎02-20-2017 06:55 AM
SAS Super FREQ
Posts: 8,864

Re: SASHELP Data sets

In this document, http://support.sas.com/documentation/tools/sashelpug.pdf starting on page 104, you will find what there is. As several people have suggested, the SASHELP datasets are only intended to provide you with sample data to use for testing. How ACTUAL and PREDICT were calculated is not relevant for data like this. The two variables could have been called SALES1 and SALES2 (or FRED and ETHEL or WOMBAT and KOALA), or just about anything else.

I use the PRDSALE, PRDSAL2 and PRDSAL3 data when I need more categorical variables than numeric variables for a crosstabular report example.

cynthia

View solution in original post


All Replies
Super User
Posts: 7,768

Re: SASHELP Data sets

I guess there's no formula behind the PREDICT values. They are just set more or less arbitrarily to have material for analysis.

---------------------------------------------------------------------------------------------
Maxims of Maximally Efficient SAS Programmers
Super Contributor
Posts: 298

Re: SASHELP Data sets

Posted in reply to KurtBremser

KurtBremser:

Thanks for your reply.

 

I am wondering whether these PRDSALE and other two are used in SAS Documents to know in which context they are used. Otherwise I am not seeing any description of the data sets.

Super User
Posts: 11,343

Re: SASHELP Data sets

Treat the data as something collected by the government or other large client that either won't or can't tell you how the raw values were compiled.

 

The SAS supplied data sets were constructed to use for example analysis. So values may well have been picked to allow/demostrate the results of different options for specific analysis procedures. If the labels on the variables are not sufficient I am not sure what you want.

 

As a brief example the SASHELP.Iris dataset is used to demonstrate graphing procedures G3D,SGPANEL, SGPLOT,SGSCATTER,; used in examples for Procs ACECLUS, CANDISC, CLUSTER, CORR, DISCRIM, FASTCLUS, STEPDISC and TREE.

 

If you installed the online help you can likely search for the dataset name to find a similar list for each of the sets.

Solution
‎02-20-2017 06:55 AM
SAS Super FREQ
Posts: 8,864

Re: SASHELP Data sets

In this document, http://support.sas.com/documentation/tools/sashelpug.pdf starting on page 104, you will find what there is. As several people have suggested, the SASHELP datasets are only intended to provide you with sample data to use for testing. How ACTUAL and PREDICT were calculated is not relevant for data like this. The two variables could have been called SALES1 and SALES2 (or FRED and ETHEL or WOMBAT and KOALA), or just about anything else.

I use the PRDSALE, PRDSAL2 and PRDSAL3 data when I need more categorical variables than numeric variables for a crosstabular report example.

cynthia
Super Contributor
Posts: 298

Re: SASHELP Data sets

Posted in reply to Cynthia_sas

Ballard & Cynthia_sas:

 

Thanks for your replies.

☑ This topic is solved.

Need further help from the community? Please ask a new question.

Discussion stats
  • 5 replies
  • 232 views
  • 3 likes
  • 4 in conversation