BookmarkSubscribeRSS Feed
momi
Obsidian | Level 7

Hi,

 

I hope this is a right locaiton to post this quesiton.  I am using PROC SURVEYREG to run a model, but I am not sure how a starata option works.  Would that be a big difference between using the option and not using the option? 

 

Thanks,

 

Momi

3 REPLIES 3
ballardw
Super User

Strata in the survey procedures relates to a sample design issue. The probabilities of selection and likely the weights may vary between different strata. If the data were not collected with a stratified sample design then you do not need a strata statement.If the sample was deisgned with strata then you need to refer to the sample design and provide the strata a probably other information related to the sample design such as a Rate or Total value or dataset the appropriate weight statement.

momi
Obsidian | Level 7

Thank you for your comment.  If I use the strata option, do I need to add the value for Total? 

 

Thanks,

 

Momi

ballardw
Super User

Do you need to calculate a finite population correction? If not then no.

Are you intending to use BRR or Jackknife variance estimation? Then no because those methods do not use TOTAL;

 

If the population in each strata is the same you could use a single value for Total equal to that population size. If not then a data set with teh strata and population total  (or sampling rate)should be used. Note that the variable names in a TOTAL or RATE data set have to match the names and values of the strata variables and any BY variables used and the value variable must be named _Total_ or _Rate_.

sas-innovate-2024.png

Join us for SAS Innovate April 16-19 at the Aria in Las Vegas. Bring the team and save big with our group pricing for a limited time only.

Pre-conference courses and tutorials are filling up fast and are always a sellout. Register today to reserve your seat.

 

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
  • 3 replies
  • 1342 views
  • 1 like
  • 2 in conversation