The estimate of a standard error parameter in a mixed logit model could be negative. For a normally distributed random parameter (ε ) in a mixed logit model, the random paramter (ε ) is transformed by a standard normal random variable η variable as follows: ε = b + sη   where b is the mean and s^2 is the variance for ε.  Random variable η is N(0,1).   When estimating mean b, and spread s, since there is no restriction on the sign of s,  the estimate of s could be negative. The absolute value of s should be interpreted as the standard error estimate.   Owen Chen ... View more