Programming the statistical procedures from SAS

Confidence Interval

Accepted Solution Solved
Reply
Contributor
Posts: 67
Accepted Solution

Confidence Interval

Hello

 

How confidence intervals are used to decide significant and insignificant variables in regression analysis?

 

Can I get an example?.

 

Thanks


Accepted Solutions
Solution
‎11-26-2016 06:21 AM
SAS Super FREQ
Posts: 3,311

Re: Confidence Interval

It depends on the parameter that you are estimating. If you are estimating an odds ratio, then the OR is not significant if the CI contains 1. See the article on "Odds ratio plots" for an example.

View solution in original post


All Replies
Grand Advisor
Posts: 16,908

Re: Confidence Interval

Confidence intervals are a function of a confidence level, usually denoted alpha. Ie 95% is (100-alpha) 

This is then equivalent to comparing the pvalue to the alpha level. 

 

Confidence intervals are easy to denote significance in some cases, not all. 

If the expected value is 0 or 1 then you can see if the interval contains that value. But in a linear regression there isn't necessarily some easily known value to compare to. 

SAS Super FREQ
Posts: 3,311

Re: Confidence Interval

I assume you are asking about confidence intervals for the regression coefficients in OLS regression.  If a parameter estimate is small, you might as k whether it is significantly different from  zero. If the  CI for the parameter contains zero, then the parameter estimate is not significantly different from zero.

 

For example, the PROC REG documentation uses the Fitness data set. If you analyze it like this

 

ods select parameterestimates;
proc reg data=fitness plots=none;
model Oxygen=Age Weight RunTime RunPulse RestPulse MaxPulse / clb;
quit;

 

you see that the parameters that have large p-values also have CIs that contain zero.

Contributor
Posts: 67

Re: Confidence Interval

Yes, what if CI contains 1.

 

Thanks 

Solution
‎11-26-2016 06:21 AM
SAS Super FREQ
Posts: 3,311

Re: Confidence Interval

It depends on the parameter that you are estimating. If you are estimating an odds ratio, then the OR is not significant if the CI contains 1. See the article on "Odds ratio plots" for an example.

☑ This topic is SOLVED.

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

Discussion stats
  • 4 replies
  • 192 views
  • 3 likes
  • 3 in conversation