Mathematics Stack Exchange is a question and answer site for people studying math at any level and professionals in related fields. It's 100% free, no registration required.

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

For example the variance in the log-odds is $0.07$ $(0.01)$, and the mean log-odds is $-0.65$ $(0.03)$. Just transforming this variance to probability given me $0.51$. So if the probabilities have a variation of $0.51$, the standard deviation is then $0.7$, which would make the $95\%$ coverage bound wider than $1$, which is impossible for probabilities.

Another idea was to calculate the $95\%$ coverage bounds of my log-odds:

$$−0.65 \pm [1.96\cdot\sqrt{0.07}] = [−1.19,−0.15]$$ If I transform these to probabilities:

$$\large \frac{\exp(x)}{1+\exp(x)}=[0.23,0.46]$$

So the $95\%$ range is actually only $0.23$ or $23\%$.

Could someone explain me why this first calculation was wrong, and whether the second is correct?

share|cite|improve this question
You can not transform your variance like that, because $\mathrm{Var}(f(X))\neq f(\mathrm{Var}(X))$ in general. However, $P(a\leq X\leq b)=P(f(a)\leq f(X)\leq f(b))$ if $f$ is increasing for example. – Stefan Hansen Jan 24 '13 at 14:36
up vote 2 down vote accepted

Your first calculation was wrong because the variance is not log-odds, so you can't transform it to a probability. It's the variance of the log-odds, but it's not log-odds itself. It's on a different scale. You can't transform variances the same way you transform measurements.

Note in particular that since variances can't be negative, your transformed "probability variance" would always be greater than $0.5$.

Your second way of doing it gives a correct interval.

share|cite|improve this answer

Your Answer


By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.