Statistical methodology

Abstract

Guided by these expectations about structural and institutional effects on the dynamics of unemployment, the subsequent chapters will pursue a series of thorough empirical analyses of both risks of unemployment incidence and the duration of unemployment in the United States and West Germany. These analyses will rely heavily on a database of harmonized employment history data generated from the U.S. Survey of Income and Program Participation (SIPP) and the German Socio-Economic Panel (GSOEP). The steps taken to ensure the cross-national comparability of these microdata sources, and thus the validity of the subsequent empirical analyses will be described extensively in Section 3.1 below. In addition, the two other sections of this chapter will discuss some fundamentals of the statistical methodology for analyzing event history data, as well as the study’s approach to institutional analysis. With respect to the latter, Section 3.3 will provide a brief discussion about the views on the identification of institutional effects from observational data, and the relationship between institutional and cross-national analysis that underlies much of the following analyses. Readers mainly interested in the substantive analysis may skip this chapter without loss of continuity.