BookmarkSubscribeRSS Feed
SAS-questioner
Obsidian | Level 7

Hi, I have a question about the complex survey data. If the data is simple, we can only use proc reg, proc glm to check the linear regression. Usually, we check the assumptions when we try to conduct the linear regression such as checking if the residual of the outcome variable is normally distributed. But when we want to use proc surveyreg for complex survey data, do we still need to check the assumption? If we need to check the assumption, how could we check the assumption if we have weight, multiple strata and clusters? If the assumption is not met, do we have any other methods to check the complex survey data?

 

And same question goes for mean difference comparison in the complex data, we can use proc surveyfreq. But SAS website didn't demonstrate if we need to check assumption or not? Could anyone help me please? Thank you!

1 REPLY 1

sas-innovate-2024.png

Available on demand!

Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.

 

Register now!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 401 views
  • 1 like
  • 2 in conversation