FROM THE GROUP TO FROM THE GROUP TO THE INDIVIDUALTHE INDIVIDUAL

CCáátedra Jean Bourgeois-Pichattedra Jean Bourgeois-PichatMexico (2007)Mexico (2007)

Daniel CourgeauDaniel Courgeau

IntroductionIntroduction

We consider here the opposition between We consider here the opposition between society and the individual which raises society and the individual which raises crucial issues in the social sciences.crucial issues in the social sciences.

Should social movements be viewed as Should social movements be viewed as the consequence of social facts the consequence of social facts generated by supra-individuals, or on generated by supra-individuals, or on the contrary as aggregates of the the contrary as aggregates of the actions of the individuals?actions of the individuals?

From theFrom the groupgroup level…level…

• Period analysisPeriod analysisofof social groups social groups

Example: Migration in Norway

Using classical linear-regressionmethods we can estimate theparameters of a relationshipbetween the regional migration rates and the proportion of farmers

An underlying paradigm:An underlying paradigm:

Social facts exist independently of the Social facts exist independently of the persons who experience them. They are persons who experience them. They are explained by various economic, political, explained by various economic, political, social, and other characteristics of society: social, and other characteristics of society: this defines a form of causality originating in this defines a form of causality originating in society itself and not in the individual, a society itself and not in the individual, a causality whose effects are felt on an entire causality whose effects are felt on an entire population.population.

This approach is a form of holism, in that it This approach is a form of holism, in that it explains the evolution of a society in terms explains the evolution of a society in terms of its overalls goals, without bringing the of its overalls goals, without bringing the individual will into play.individual will into play.

Methodological issues:Methodological issues:

Synthetic indices that are hard to interpret: they Synthetic indices that are hard to interpret: they don’t correspond to the probabilities of the event. don’t correspond to the probabilities of the event.

Regressions that are hard to interpret: some Regressions that are hard to interpret: some correlations exist between characteristics. correlations exist between characteristics.

The ecological fallacy: aggregate data cannot be The ecological fallacy: aggregate data cannot be used to study individual behaviors.used to study individual behaviors.

•Introduction of seniority in the Introduction of seniority in the groupgroup

Try to isolate demographic phenomena in their pure Try to isolate demographic phenomena in their pure state, so as to rid them of the effect of disturbing state, so as to rid them of the effect of disturbing phenomena and allow comparisons between phenomena and allow comparisons between countries or periods.countries or periods.

Work on generations or cohorts and track them Work on generations or cohorts and track them through their lives from birth or from an other event through their lives from birth or from an other event linked to the studied event.linked to the studied event.

The probabilities to know an event are identical for The probabilities to know an event are identical for all members of the population, all members of the population, homogeneity,homogeneity, and and there is there is independenceindependence between the studied event between the studied event and the others, called disturbing events.and the others, called disturbing events.

Paradigm of the cohort approachParadigm of the cohort approach

The demographer can study the occurrence of only The demographer can study the occurrence of only a single event, during the life of a generation or a a single event, during the life of a generation or a cohort, in a population that preserves all its cohort, in a population that preserves all its characteristics and the same characteristics for as characteristics and the same characteristics for as long as the phenomenon manifests itself.long as the phenomenon manifests itself.

This approach is also a form of holism, albeit This approach is also a form of holism, albeit different from the holism that informs period different from the holism that informs period analysis: it denies the existence of individual analysis: it denies the existence of individual entities, in order to confine itself to comparisons entities, in order to confine itself to comparisons between homogeneous groups, observed during between homogeneous groups, observed during their entire life.their entire life.

Methodological issuesMethodological issues

Independence must be ensured: this hypothesis is Independence must be ensured: this hypothesis is fairly implausible for many demographic events.fairly implausible for many demographic events.

It precludes the study of exits due to competing It precludes the study of exits due to competing events, interacting events and of events in a events, interacting events and of events in a population with entry and exit flows.population with entry and exit flows.

Homogeneity of the population must be ensured: if Homogeneity of the population must be ensured: if we define more restricted groups this will require we define more restricted groups this will require such detailed breakdowns of the population as to such detailed breakdowns of the population as to invalidate any serious calculation.invalidate any serious calculation.

… … to individual levelto individual level

•Analyzing individual dataAnalyzing individual data

Introducing individual Introducing individual

behaviour:behaviour:

We can estimate theWe can estimate the

probability that an probability that an

individual with the individual with the

characteristics will characteristics will

experience the eventexperience the event

Introducing time regressionsIntroducing time regressions

We have to define a random variable T corresponding We have to define a random variable T corresponding to the time elapsed between the initial observation to the time elapsed between the initial observation instant and the occurrence of the event.instant and the occurrence of the event.

The survivor function is defined as the probability of T The survivor function is defined as the probability of T being at least as great as a given value of the time.being at least as great as a given value of the time.

The hazard function specifies the instantaneous rate The hazard function specifies the instantaneous rate of failure at T=t conditional upon survival to time t.of failure at T=t conditional upon survival to time t.

We can analyse with a proportional hazard model the We can analyse with a proportional hazard model the effects of different characteristics on this hazard effects of different characteristics on this hazard function.function.We can also analyse the interaction between We can also analyse the interaction between phenomena.phenomena.

Paradigm of event history Paradigm of event history approachapproach

• Individuals follow complex life-long trajectories that Individuals follow complex life-long trajectories that depend, at a given instant, on earlier trajectories and depend, at a given instant, on earlier trajectories and on the information that they have acquired in the past.on the information that they have acquired in the past.

This resolutely individual approach reflects a This resolutely individual approach reflects a methodological individualism and shows that people’s methodological individualism and shows that people’s behavior is connected to their prior life histories, behavior is connected to their prior life histories, without seeking the motives for their acts in society.without seeking the motives for their acts in society.

It describes an individual life as a stochastic process, It describes an individual life as a stochastic process, unfolding in a given generation or cohort.unfolding in a given generation or cohort.

Methodological issuesMethodological issues

Unobserved heterogeneity: while there is only one Unobserved heterogeneity: while there is only one model without unobserved heterogeneity, there model without unobserved heterogeneity, there exists an infinity of models with unobserved exists an infinity of models with unobserved heterogeneity and estimated hazard functions heterogeneity and estimated hazard functions that differ but adjust identically to the observed that differ but adjust identically to the observed data.data.

Risk of atomistic fallacy, for overlooking the context Risk of atomistic fallacy, for overlooking the context in which human behavior occursin which human behavior occurs

Towards a contextual Towards a contextual and multilevel analysisand multilevel analysisFrom contextual analysis …From contextual analysis …

We need to bring data We need to bring data

measured at the individualmeasured at the individual

and aggregate level intoand aggregate level into

play simultaneously toplay simultaneously to

explain a behaviour thatexplain a behaviour that

remains individualremains individual

Advantages of contextual analysisAdvantages of contextual analysis

This analysis permits to use data measured at This analysis permits to use data measured at different aggregation levels to explain an individual different aggregation levels to explain an individual behaviour.behaviour.

We can now grasp the difference between this We can now grasp the difference between this approach, which uses aggregate characteristics to approach, which uses aggregate characteristics to explain an individual behavior, and the aggregate explain an individual behavior, and the aggregate approach which explained an aggregate behavior approach which explained an aggregate behavior by equally aggregate characteristics.by equally aggregate characteristics.

We can then eliminate the risk of ecological fallacy, We can then eliminate the risk of ecological fallacy, as the aggregate characteristic will measure a as the aggregate characteristic will measure a differentdifferent construct from its equivalent at the construct from its equivalent at the individual level, and the risk of atomistic fallacy, as individual level, and the risk of atomistic fallacy, as we take into consideration the context in which the we take into consideration the context in which the individual lives.individual lives.

Inconvenients of contextual Inconvenients of contextual analysisanalysis

The model assumes that the behaviors of The model assumes that the behaviors of individuals within a group are independent of one individuals within a group are independent of one another.another.

In practice, the risk incured by a member of a given In practice, the risk incured by a member of a given group more likely depends on the risks encountered group more likely depends on the risks encountered by the group’s other members.by the group’s other members.

Overlooking this intra-group dependence generally Overlooking this intra-group dependence generally biases the estimates of contextual effects, biases the estimates of contextual effects, generating excessively narrow confidence intervals.generating excessively narrow confidence intervals.

… … to a multilevel analysisto a multilevel analysis

The differences betweenThe differences between

contextual and regionalcontextual and regional

models are given here.models are given here.

However the regionalHowever the regional

models give results toomodels give results too

unstable and could nounstable and could no

longer reveal significantlonger reveal significant

relationships. Therelationships. The

analysis was drownedanalysis was drowned

in random fluctuationsin random fluctuations

A multilevel compromiseA multilevel compromiseIt seems useful to seek aIt seems useful to seek acompromise between acompromise between amodel that places no model that places no constraints on its estimatorsconstraints on its estimatorsbut virtually precludes a but virtually precludes a significant estimation andsignificant estimation anda model with excessively a model with excessively strong constraints whosestrong constraints whosevalidity we can hardly test.validity we can hardly test.

Introducing random termsIntroducing random termswe can restrict our analysiswe can restrict our analysisto variances and covariancesto variances and covariancesbetween these randombetween these randomvariables. This leads to a variables. This leads to a multilevel model.multilevel model.

Advantages of multilevel analysisAdvantages of multilevel analysis

These methods permit hierarchical classifications, These methods permit hierarchical classifications, cross-classifications, and more complex multiple cross-classifications, and more complex multiple membership models.membership models.

They permit to introduce random terms at each They permit to introduce random terms at each level of aggregation and to estimate their variances level of aggregation and to estimate their variances and covariances.and covariances.

They lead to linear analysis of continuous They lead to linear analysis of continuous characteristics, to analysis of discrete characteristics, to analysis of discrete characteristics and finally to multilevel event history characteristics and finally to multilevel event history analysis.analysis.

This last kind of models may be semiparametric Cox This last kind of models may be semiparametric Cox models, accelerated failure time, discrete time models, accelerated failure time, discrete time models …models …

Towards a more complete paradigmTowards a more complete paradigm

AAn individual behavior is dependent on his or her past n individual behavior is dependent on his or her past history, viewed in its full complexity, but it will be history, viewed in its full complexity, but it will be necessary to add that this behavior can also depend necessary to add that this behavior can also depend on external constraints on the individual, whether he on external constraints on the individual, whether he or she is aware of them or not.or she is aware of them or not.

The contact circle, people’s environment and the The contact circle, people’s environment and the information on the world they receive from the press information on the world they receive from the press and television can play a role in their behavior.and television can play a role in their behavior.

Pressure from surrounding society can influence Pressure from surrounding society can influence people’s behaviour without their being fully conscious people’s behaviour without their being fully conscious of it. Conversely we have to see the perverse effect of of it. Conversely we have to see the perverse effect of individual actions whose initial aim was totally individual actions whose initial aim was totally different from the result obtained.different from the result obtained.

General conclusionGeneral conclusion

The aggregate-level objects are not the sum or the The aggregate-level objects are not the sum or the mean of the lower-level objects, for the aggregate mean of the lower-level objects, for the aggregate level’s organization into a whole endows it with new level’s organization into a whole endows it with new properties. At the same time, we need to study the properties. At the same time, we need to study the effect in the opposite direction of the aggregate effect in the opposite direction of the aggregate level on the lower level units that compose it.level on the lower level units that compose it.

By makingBy making it possible to examine simultaneously it possible to examine simultaneously the multiple significance of a human fact, in a the multiple significance of a human fact, in a model that incorporates an active temporality, the model that incorporates an active temporality, the multilevel approach should bring us closer of the multilevel approach should bring us closer of the objectivation of human experience and, more objectivation of human experience and, more generally, towards a new form and a fuller theory in generally, towards a new form and a fuller theory in social science.social science.

For more detailed information on this topic For more detailed information on this topic you can visit my personal website:you can visit my personal website:

•www.courgeau.comwww.courgeau.com

or read the following volumes I published:or read the following volumes I published:

Methodology and epistemology of Methodology and epistemology of multilevel analysis, Kluwer, 2003multilevel analysis, Kluwer, 2003

Multilevel synthesis, Springer, Multilevel synthesis, Springer, 20072007