Search

This article deals with the role of time in causal models in the social sciences. The aim is to underline the importance of time-sensitive causal models, in contrast to time-free models. The relation between time and causality is important, though a complex one, as the debates in the philosophy of science show. In particular, an outstanding issue is whether one can derive causal ordering from time ordering. The article examines how time is taken into account in demography and in economics as examples of social sciences in which considerations about time may diverge. We then present structural causal modeling as a modeling strategy that, while not essentially based on temporal information, can incorporate it in a more or less explicit way. In particular, we argue that temporal information is useful to the extent that it is placed in a correct causal structure, thus further corroborating the causal mechanism or generative process explaining the phenomenon under consideration. Despite the fact that the causal ordering of variables is more relevant than the temporal order for explanatory purposes, in establishing causal ordering the researcher should nevertheless take into account the time-patterns of causes and effects, as these are often episodes rather than single events. For this reason in particular, it is time to put time at the core of our causal models.

This paper examines different approaches for assessing causality as typically followed in econometrics and proposes a constructive perspective for improving statistical models elaborated in view of causal analysis. Without attempting to be exhaustive, this paper examines some of these approaches. Traditional structural modeling is first discussed. A distinction is then drawn between model-based and design-based approaches. Some more recent developments are examined next, namely history-friendly simulation and information-theory based approaches. Finally, in a constructive perspective, structural causal modeling (SCM) is presented, based on the concepts of mechanism and sub-mechanisms, and of recursive decomposition of the joint distribution of variables. This modeling strategy endeavors at representing the structure of the underlying data generating process. It operationalizes the concept of causation through the ordering and role-function of the variables in each of the intelligible sub-mechanisms.

Goal of this paper is to analyze and forecast realized volatility through nonlinear and highly persistent dynamics. In particular, we propose a model that simultaneously captures long memory and nonlinearities in which level and persistence shift through a Markov switching dynamics. We consider an efficient Markov chain Monte Carlo (MCMC) algorithm to estimate parameters, latent process and predictive densities. The insample results show that both long memory and nonlinearities are significant and improve the description of the data. The out-sample results at several forecast horizons, show that introducing these nonlinearities produces superior forecasts over those obtained from nested models.

It is well known that, in a multinomial probit, only the covariance matrix of the location and scale normalized utilities are identified. In this study, we explore the relation between these identifiable parameters and the original elements of the covariance matrix, to find out what can be learnt about the correlations between the stochastic components of the non-normalized utilities. We show that, in certain circumstances, it is possible to obtain information on these behavioural parameters and define appropriate tools for inference. We illustrate the usefulness of our results in applied settings using an example.

We take a differential game approach to study the dynamic behaviour of labour managed (LM) firms, in the presence of price stickiness. We find that the oligopoly market populated by LM firms reaches the same steady state equilibrium allocation as the oligopoly populated by profit-maximising (PM) firms, provided that the LM membership and the PM labour force are set before the market game starts. The conclusion holds under both the open-loop solution and the closed-loop solution. The result confirms the point made by Sertel (Eur Econ Rev 31:1619–1625, 1987) in a static framework.

This paper focuses on the youth’s decisions on household formation and human capital investment - in further education or work experience - and the factors influencing these choices. While previous studies limited their analyses to decisions concerning the living arrangements and the labour market, the choice set is extended here to take into account other alternatives. The decisions of either remaining in the parental household or going to live with a partner are modelled jointly with those of either entering the labour market (i.e. investing in work experience) or investing in higher (university) education. Using the Bank of Italy 1995 Sample Survey on Italian Households, a multinomial probit model estimates the probabilities of the different pairs of outcomes. The results highlight the crucial role of economic variables in shaping young adults’ decisions. Among these, expected lifetime earnings from attending university have the most important impact on the choice of studying and coresiding. Implications for policy stem from the estimated impact of housing and labour market performance variables on young adults’ decisions. In particular, a sizeable discouraged worker effect, inducing young people to study when the local unemployment rate is high, is detected. The effect of the cost of housing in delaying young workers’ decisions to leave the parental home and form a new household is also remarkable. Two policy experiments are presented. The former measures the impact of housing policies targeted at reducing housing cost on the probability of marriage. The latter measures the extent to which labour policies targeted at reducing youth unemployment would decrease the number of discouraged workers that choose to study.

In questo lavoro si descrive la costruzione di una base di dati dello stock di capitale, sia privato che pubblico, nelle regioni italiane. Il capitale privato e’ calcolato utilizzando come riferimento una ripartizione regionale dello stock aggregato per l’anno 1981. Le stime per gli altri anni, dal 1970 al 1991, si ottengono ripartendo le variazioni dello stock aggregato in base all’andamento degli investimenti regionali. Il capitale pubblico e’ calcolato con la tecnica dell’inventario permanente. L’investimento pubblico aggregato e’ ripartito per regione e per tipologia di bene utilizzando i dati contenuti nella pubblicazione annuale dell’ISTAT "Opere Pubbliche". Si ottengono cosi’ delle stime del capitale pubblico regionale per gli anni dal 1970 al 1991.

In this paper I consider the estimation of multi-factor exponential affine models of the term structure of interest rates. I start with a survey of the empirical work on the term structure in continuous time, showing that in most cases the implementation of the models has not fully exploited the theoretical restrictions. I also show that these works have almost always focused on “generalizations” of the theoretical model based on the inclusion of measurement errors in bills and bonds prices. I then suggest two approaches to statistical inference: the first is based on the Kalman filter, while the second follows the indirect inference approach. I also briefly discuss the relative properties of the two estimators, and I conclude with a small Monte Carlo experiment for a one-factor Cox-Ingersoll-Ross model, whose results are rather encouraging.

In this paper we analyse the wage price relationship of an economy in transition characterized by important structural changes. It is known (see Perron 1989) that structural breaks in stationary time series can induce apparent unit roots. The stationarity analysis of the series employed in the present model is conducted jointly with the assumption that the breakpoint location is unknown. We follow a testing procedure recently proposed by Zivot and Andrews (1992). Cointegration analysis of wages and prices in presence of structural breaks permits to find empirical evidence in favour of two cointegration vectors involving prices and wages. Our analyses faces on the different structural behavior of price-wage dynamic relationship in the short and long run; we also enuncleate the relative importance of import prices as a source of wage-price short run fluctuations.

Le inchieste nazionali sulla situazione del mercato del lavoro forniscono di solito osservazioni in tempo discreto. Gli individui vengono intervistati in corrispondenza di date distinte, per ognuna delle quali si conosce la loro posizione sul mercato (occupati, disoccupati), ma nulla è noto di quanto si è osservato fra le date di osservazione. Con questi dati non è possibile stimare modelli di durata multi-stato ed è necessario ricorrere a strumenti statistici fondati sulla classe dei processi markoviani omogenei in tempo continuo. Questo articolo applica un tale approccio a dati provenienti dalla Rilevazione Trimestrale sulle Forze di Lavoro, relativi alla regione Lombardia ed al periodo gennaio 1985- aprile 1986. Particolare attenzione viene dedicata alle restrizioni implicite imposte da questa classe di modelli, ed alle direzioni di ricerca che promettono di migliorare le proprietà e le performance empiriche.