|
⇤ ← Revision 1 as of 2009-12-09 10:17:03
Size: 614
Comment:
|
Size: 649
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 3: | Line 3: |
| This [attachment:james.pdf paper] outlines a weighted linear regression which produces confidence intervals for a pooled estimate of log odds from various studies. The regression uses log odds as outcome, the inverse of the sample size of each study as the only predictor and a weights each study using the inverse of the variance of the log odds. The variance of the log odds is found by simply summing the inverses of each of the four cells in the table of frequencies which are used to compute the odds ratio. | This [attachment:james.pdf paper] outlines a weighted linear regression which produces confidence intervals for a pooled estimate of log odds from various studies. The regression uses log odds as outcome, the inverse of the sample size of each study as the only predictor and a weights each study using the inverse of the variance of the log odds. The variance of the log odds is found by simply summing the inverses of each of the four cells in the table of frequencies which are used to compute the odds ratio (see an example [:FAQ/oddsr here.]) |
How do I use regression to obtain a confidence interval for a log odds using meta-analysis?
This [attachment:james.pdf paper] outlines a weighted linear regression which produces confidence intervals for a pooled estimate of log odds from various studies. The regression uses log odds as outcome, the inverse of the sample size of each study as the only predictor and a weights each study using the inverse of the variance of the log odds. The variance of the log odds is found by simply summing the inverses of each of the four cells in the table of frequencies which are used to compute the odds ratio (see an example [:FAQ/oddsr here.])