How does the introduction of persistence affect the interpretation of changes over time?
There are two types of persistence which tend to have opposite effects upon the significance of any observed change in data: persistence in governance and persistence in the measurement error. Persistence in governance is quite common. Quality of institutions tend to change very slowly. Therefore the governance frameowrk in any given country tends to be highly correlated with previous levels. The introduction of persistence in governance, however produces large effects upon the interpretation of significance of changes. Given any observed change in governance levels, the higher the persistence in governance, the more likely that any such change is the result of pure noise and therefore less likely to signal a significant change in unobserved governance. In the limit where governance is perfectly correlated in the two periods, we would know for sure that any change observed in the data must reflect only fluctuations in the error term, and so we would completely discount the observed cha
