Empirical econometric evaluation of alternative methods of dealing with missing values in Investment Climate surveys

The Investment Climate surveys (ICSs) are valuable instruments which improve our understanding of the economic, social, political and institutional factors determining economic growth, particularly in emerging and transition economies. However, at the same time, they have to overcome some difficult issues related with the quality of the information provided; measurement errors, outlier observations and missing data are frequently found in this datasets. In this paper we discuss the applicability of recent procedures to deal with missing observations in IC surveys. In particular we present a simple replacement mechanism—for application in models with a large number of explanatory variables—, which we call the ICA method, which in turn is a proxy of two methods: multiple imputation and EM algorithm. We evaluate the performance of this ICA method in the context of TFP estimation in extended production functions using ICSs from four countries: India, South Africa, Tanzania and Turkey. We find that the ICA method is very robust and performs reasonably well even under different assumptions on the nature of the mechanism generating missing data.