We extend Harris and Zhao (2007) by proposing a (Panel) Inflated Ordered Probit model, and demonstrate its usefulness by applying it to Bank of England Monetary Policy Committee voting data.

We propose a Tempered Ordered Probit (TOP) model. Our contribution lies not only in explicitly accounting for an excessive number of observations in a given choice category - as is the case in the standard literature on in?ated models; rather, we introduce a new econometric model which nests the...

We consider the estimation of the standard errors of individual-specific parameters calculated ex post from a non-linear random parameters model. Our key contribution lies in introducing a simple method of appropriately calculating these standard errors, which explicitly takes into account the...