A comprehensive understanding of regional income inequality dynamics is an important endeavor since it could have profound policy implications. While income inequality measures provide a “static” view, income mobility measures shed light on the “dynamic” nature of regional income distributions, either being structural or exchange mobility. However, statistical inference about income mobility measures relies on the independently and identically distributed (i.i.d.) assumption which is very likely to be invalid in a regional context due to spatial interactions including trade, migration, technological spillover, etc. My research focuses on investigating the impact of potential spatial dependence on the statistical properties of these measures by employing the Monte Carlo experiments. I find that the size of a two-sample test tends to become increasingly upward biased with stronger spatial dependence in either regional income system, indicating that conclusions about differences in income mobility between two different regional systems need to be drawn with caution as the presence of spatial dependence can lead to false positives. I then propose adjustments and show the consequences of ignoring spatial dependence using an empirical example of comparing the mobility of Chinese provincial per capita incomes pre- and post- 1990. I will also briefly introduce two other methodological advancements of spatial analytics I have been involved in, which are, (1) multiscale geographically weighted regression (MGWR) focusing on investigating process spatial heterogeneity and differentiating scales of spatially varying processes, and (2) time series mining for neighborhood change research.