Conferences

In recent years, labour markets in industrialised countries have shown quite a high degree of mobility. Extensive literature on the micro-dynamics of the labour market focuses on job-to-job flows, only a few papers explore the kind of job changes that workers experienced. The complexity of job mobility also demands analysing these changes while changing employer. The literature on job matching suggests that a significant number of workers who switch job also change employment characteristics, mainly industry and occupation.

Some studies show that job characteristics, particularly industry and occupation, collected in surveys are affected by measurement error. The effect of these errors is to exaggerate the occurrence of changes in such characteristics, at least when information is obtained at two points in time with independent interviews. Other studies demonstrate that, in general, industry is reported more accurately than occupation and that the agreement rate between employees’ and employers’ reports, classified according to a single-digit coding scheme, is higher than that resulting when reports are categorised according to a more detailed classification.

In this paper we deal with measurement error, and its potentially distorting role, in information on industry and professional status. As a case-study we consider two-wave panels one year apart collected by the Italian Quarterly Labour Force Survey (QLFS) in the period from April 1993 to April 2003.

The QLFS refers to a sample of the resident non-institutional population. Thus, it collects information on job characteristics of (almost) all the employed. The survey is cross-sectional with a 2-2-2 rotating design, which yields two-wave panels one quarter and one year apart. The focus of our analyses is on inconsistent information on employment characteristics – industry and professional status – resulting from yearly transition matrices for workers who reported that they were continuously employed over the year and did not change job.

First, we compute and comment upon some usual indicators of disagreement. We find clear evidence that there is sizable measurement error in both industry and professional status, and that industry is reported more accurately than professional status.

Then, we test whether the consistency of repeated information significantly increases when the number of categories is collapsed. As regards the detail of variable classification for cross-section estimates, Istat – the Italian statistical agency – provides the following indications. For professional status, a reliable classification reduces to a binary one: Employee and Self-employed. For industry, Istat asserts as dependable a classification in 12 categories. By means of the hierarchical Kappa coefficient, we obtain evidence that supports the first indication by Istat, but casts severe doubts on the second.

We further explore the patterns of inconsistencies among categories of variables by testing several specifications of Goodman’s quasi-independence model, which is almost always rejected.

Lastly, we consider and compare alternative 4-category classifications obtained by collapsing professional status and industry into a single variable. The standard classification labels respondents as Self-employed, Employee in agriculture, Employee in industrial sector, and Employee in services. As an alternative, another 4-category classification was recently used in the study of worker turnover, with the four categories given by Self-employed, Employee in agriculture, Employee in industrial sector and private services, and Employee in Public Administration and social services. Interestingly enough, the latter classification turns out to be almost uniformly better than the former, standard one.