Confidence Intervals from multiple regression
1 view (last 30 days)
Show older comments
I am using the regress function in the statistics toolbox to estimate how the ozone concentration (near Christmas Island) varies in time and space. The function returns the coefficients (which seem reasonable) along with confidence intervals for the coefficients (which seem really small). For example, the coefficient for time is returned as -0.31 ppb/hour (totally reasonable) but the 95% confidence interval for it is (-.318, -.307) which seems really tight given the R2 value for the entire fit is only 0.55. Is it conceivable that the R2 could be that low with a confidence interval that tight?
0 Comments
Answers (1)
Tom Lane
on 5 May 2011
This is conceivable. If you have lots of data, you might be able to estimate the coefficients very accurately even though there is lots of residual variation so your R^2 value is not close to 1.
0 Comments
See Also
Categories
Find more on Descriptive Statistics in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!