The effect of item-nonresponse and multiple imputation of missing data on the estimation of productivity based on German Establishment Data

Abstract

"This paper illustrates the effects of item-nonresponse in surveys on the results of multivariate statistical analysis when estimation of productivity is the task. To multiply impute the missing data the 'data augmentation' algorithm is applied. Data of the IAB Establishment Panel 2000 are used to estimate the plant's productivity. Basis of the empirical analysis is a translog production function with labour and capital as input factors. Also the influence of industries and the use of modern technologies are considered. Furthermore, we include interaction variables that indicate deviations in the parameters concerning the two parts of Germany. Next to differences between industries, we find also a higher productivity, if modern technologies are installed. The results for Eastern and Western Germany only differ for some industries and the constant. Using only the available cases these differences seem to be biased. Calculating the regression coefficients using the imputed data sets and combining the results according to the multiple imputation principle reduce these deviations about 10%-pionts. In addition the differences of the industrial branches between east and west decrease." (Author's abstract, IAB-Doku) ((en))

Cite article

Kölling, A. & Rässler, S. (2003): Die Einflüsse von Antwortverweigerung und mehrfacher Ergänzung fehlender Daten auf Produktivitätsschätzungen mit dem IAB-Betriebspanel. In: Jahrbücher für Nationalökonomie und Statistik, Vol. 223, No. 3, p. 279-311.