With the data from the Russian Longitudinal Monitoring Survey (RLMS) for 2000–2004 the authors estimate the probabilities of employment in the public sector for various demographic, occupational, and territorial population subgroups. The paper also provides wage gap estimates for all these groups applying switching regression and fixed effects model that correct for endogeneity of the sector selection. As it is shown, the chances to be employed in the public sector are higher for rural residents and those who live in less developed regions. There is significant cross-group variation in the wage gap. Decomposition of the wage gap proves that centralized bureaucratic wage-setting pulls down wages in the public sector while market forces work to compensate for the underpay.