Significance test in nonstationary logit panel model with serially correlated dependent variable

- Nonstationary panel logit with serially correlated dependent variable is analyzed.
- The limit distribution of LM statistic is shown proportional to Chi-square.
- Significance test ignoring the serial correlation can result in spurious logit link.

We derive the asymptotic distribution of the overall significance/LM test in logit panel models with nonstationary covariates when the binary dependent variable is serially correlated. The asymptotic distribution of LM statistic is shown proportional to Chi-square distribution. Spurious logit link could arise if one fails to take into account the serial correlation.