Academic journal article Population

Comparing Qualitative Harmonic Analysis and Optimal Matching: An Exploratory Study of Occupational Trajectories

Academic journal article Population

Comparing Qualitative Harmonic Analysis and Optimal Matching: An Exploratory Study of Occupational Trajectories

Article excerpt

Following the example of the Triple biographie survey conducted by INED in 1981, event history surveys are designed to collect retrospective data on complete individual trajectories, often on a yearly basis. These data provide a basis for describing the life course in statistical terms. The Biographies et entourage (event histories and contact circle) survey was carried out by INED in 2001 on a sample of 2,830 individuals born between 1930 and 1950, representative of the corresponding Paris region population at the time of the survey (Lelièvre and Vivier, 2001). Its main aim was to improve knowledge of respondents' residential and family mobility in relation to that of their contact circle. It also produced interesting data on respondents' occupations that warranted more in-depth analysis. The various occupations held by respondents over their life course were recorded on a retrospective annual timesheet. Each stage was then coded using the INSEE socio-occupational categories (SOC).(1) Although occupational trajectories can, in theory, cover the entire range of possibles, they nonetheless exhibit strong trends that reflect concomitant changes in society (Marchand and Thélot, 1997).

The aim of this article is to determine the best way to process these trajectories, qualified as complex in the sense that (i) all the states which characterize them may recur over time and (ii) there are numerous possible transitions"5 between these states. One option, which fits the paradigm of event history analysis (Courgeau and Lelièvre, 1996), is to use exploratory statistical methods to identify life-course typologies that capture individual trajectories in their entirety, and not simply in terms of the events they comprise (Biliari, 2001). Various typological methods exist (Grelet, 2002): chi-square distance, Euclidian distance (Espinasse, 1993), composite indicators, etc. Two of them emerge in the literature as particularly suited to this type of data. Both are capable of systematically describing the sequence of events and their duration. The first is qualitative harmonic analysis (QHA), a factor analysis method developed by French statisticians in the 1980s and which takes account of time. The second is optimal matching (OM), a set of algorithmic techniques imported from the life sciences by American sociologists in the late 1980s. In this article, we will discuss the comparative advantages of the two techniques for analysing the occupational trajectories of male respondents in the Biographies et entourage survey (INED, 2001).

I. Exploratory analysis of occupational trajectories. To what purpose?

1. Processing complex trajectories

A range of standard statistical tools can be used to analyse time spent (survival) in a given state: non-parametric estimations are used to measure survival (Kaplan and Meier, 1958; Nelson, 1972; Aalen, 1978), and semiparametric (Cox, 1972) or parametric(3) models are used to measure the impact of individual characteristics (which are also social properties) on survival in a particular state. These models are meaningful for durations clearly defined by unambiguous start and end dates. However, they are not designed to describe individual trajectories characterized by a complex sequence of changes of state, i.e. when the analysis concerns a succession of repeatable events with numerous possible transitions between states (GRAB, 2006), as is the case for occupational trajectories, for example. How, then, can we explore this type of data?

2. The problem of repeatable events

Modern longitudinal methods, which can be applied at the individual level, have already proved useful for studying labour market trajectories. Using historical data from the French employment agency (Agence nationale pour l'emploi, ANPE), we can, for example, study the labour market reintegration of unemployed persons on the basis of individual characteristics (Degenne and Lebeaux, 1999), and in relation to the benefits and support received by each individual (Crépon et al. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.