Aggregate Time Series Data Research Articles

Estimating a matching function and regional matching efficiencies: Japanese panel data for 1973–1999

In estimating matching functions by using aggregate time series data, an implicit assumption is imposed that search efficiencies are common to all regions in a country. This paper estimates the matching function using annual panel data covering 47 Japanese prefectures from 1972 to 1999, which allows variation of matching efficiencies over regions. We find that the matching function exhibits mildly but statistically significantly decreasing returns to scale regardless of whether unobservable regional heterogeneity be controlled or not. Further, we find a statistical evidence that estimated matching efficiency is negatively correlated with population density and per capita income. This contradicts previous finding that, ceteris paribus, matching is better for higher population density area. We give a verbal interpretation of this finding.

Social Security Reforms and the Structure of the Labor Market: The Case of Brazil

The purpose of this report is to document the scale of uncovered employment in Brazil and to describe the trends in this phenomenon at least since the transition to democracy in the late 1980s. Micro-data obtained from annual Brazilian household surveys from 1992 onwards are used to model the determinants of the that employees face between covered and uncovered employment, in order to address the question of whether uncovered employment arises as a consequence of segmentation in the labor market or because of what appears to be a genuine choice process on the basis of the costs and benefits of social protection. This modeling exercise allows us to attempt to identify the valuation that employees place on social protection, and to see whether this valuation accords with actual costs borne by employees. It also allows us to compute elasticities of relative labor supply (uncovered relative to covered) with respect to the wage differential that an individual employee might expect to enjoy from moving from one sector to the other. Aggregate time series data available on a monthly basis from 1982 onwards is then used to provide a time series econometric investigation of covered and uncovered employment levels. The outcome of the modeling approach is to provide estimates of labor demand elasticities in the two sectors.

House Price Appreciation, Transactions and Structural Change in the British Housing Market: A Macroeconomic Perspective

This paper constitutes the first of two interrelated studies and is concerned with the relationship between house prices and transactions. Using aggregate time–series data, we find a strong relationship in Britain between the two variables, but the relationship changed during the 1990s. Transactions became much lower. We suggest that structural changes in macroeconomic relationships are increasingly likely to occur in a world of greater inequality and our results are one symptom. We argue that macroeconomic estimation needs to be complemented by careful microeconomic analysis. The second study, also appearing in this issue, therefore examines the microeconomic aspects of the issue.

Capital Structure and Investment Behaviour of Malaysian Firms in the 1990s: a study of corporate governance before the crisis

This is an empirical study analysing the corporate finance and governance structure in Malaysia before and after the financial crisis of 1997, utilising the agency cost approach. The contribution of this paper is to link the corporate governance mechanism with the role of banks and corporate ownership structure peculiar to Malaysia, taking into account the institutional framework and historical background of the Malaysian financial system, such as government protection for the banking sector and the social dispersion of corporate ownership related to the Malay First policy.Based on data for 375 non–financial KLSE (Kuala Lumpur Stock Exchange) listed companies during fiscal years 1995–99, our analysis is organised into three parts. Characteristics of corporate finance in Malaysia in the 1990s using aggregated time–series data are outlined, followed by an examination of the determinants of capital structure via cross–sectional regressions in terms of dependency on banks and ethnic ownership structure, controlling ownership concentration, availability of internal funds, corporate size, industry effects, etc. We then estimate simple investment functions with panel data in order to examine the effects of debt financing on corporate investments before the crisis.Empirical results show the following. Firstly, the commitment of banks to finance corporate debt as well as lending obviously increased debt ratios. Secondly, increasing ownership by native Malays, both the direct and indirect holding of corporate shares, played no significant role in disciplining corporate management. However, ownership concentration mitigated conflict between managers and owners. Foreign ownership also contributed to a reduction in the agency cost of equity financing in financial liberalisation. Finally, high dependency on debt led to excessive corporate investment before the crisis. These results imply that the concentration of risks on the banking sector and social policy advocating the dispersion of corporate ownership weakened the corporate governance mechanism, thereby exacerbating the distress of Malaysia's corporate sector during the financial crisis.

Cigarette smoking in Japan: Examination of myopic and rational models of addictive behavior

Myopic and rational addiction models are employed to investigate cigarette consumption in Japan using aggregate time-series data. The estimations provide support for the rational addiction models. Therefore, we conclude that addiction of Japanese cigarette smokers is not a result of myopic consumer behavior, but future effects are considered in their current decisions.

The effects of the Basle accord on bank credit: the case of Japan

This paper has documented the empirical evidence that the Basle Accord had significant effects on bank credit in Japan. The Accord reduced the ratio of the credit increase to the total asset by 0.09-0.24% for banks with the international standard, and by 0.06-0.21% for those with the domestic standard, respectively. According to the Fixed Effects Model estimates, the impacts of the regulation are in between 0.12% and 0.13% for those banks with the international standard. These estimates are smaller than the corresponding estimate with aggregate time series data, 0.40%.

Are the Poor Protected from Budget Cuts? Evidence for Argentina

Macroeconomic adjustment programs often emphasize the need to protect social spending from cuts, and to protect pro-poor spending in particular. But does this happen in practice during fiscal contractions? The paper presents evidence for Argentina. Using aggregate time series data the paper first finds that social spending was not protected historically, although more “pro-poor” social spending was no more vulnerable. Turning next to new data for an externally-financed workfare scheme introduced in response to a macro crisis, the paper finds that this program was far better targeted than other social spending. However, it appears that the program still had to assure that a small but relatively well-protected share of its benefits went to the non-poor. This appears to be a political economy constraint.

An analysis of the application and enrollment processes for in-state and out-of-state students at a large public university

This paper extends prior work by jointly modeling the application and enrollment decision for in-state and out-of-state freshmen at a large public university. Two separate empirical analyses use individual and aggregate time-series data for the University of Oregon to estimate and compare the responsiveness of applicants and enrollees to person-specific and time-specific variation in the net price. The results show that prior studies may understate student price responsiveness by separately focusing on the application or enrollment decision. Moreover, the elasticity estimates are found to differ for in-state and out-of-state students and can be sensitive to whether the price variation occurs across individuals or over time.

Capital Structure Decisions in the Insurance Industry: Stocks Versus Mutuals

Mutual insurers generally face higher costs of raising new capital than stock insurers. Other things being equal, the higher costs of raising capital should cause mutual insurers to have higher ex ante target capital to liability ratios than stock insurers. Mutual insurers' capital ratios also should be more sensitive to income than capital ratios for stock insurers and therefore adjust more slowly toward their long-run targets. We provide evidence concerning these issues using aggregate time series data for stock and mutual insurers during 1984-1999 and a large panel data set during 1991-1998. Our regressions provide strong evidence that annual changes in capital to liability ratios are more sensitive to income for mutual insurers than for stock insurers. We also provide evidence that mutual insurers' capital ratios are on average higher than those for stock insurers after controlling for several factors that could influence capital ratios.

Endogeneity and Heterogeneity in a Probit Demand Model: Estimation Using Aggregate Data

Two issues that have become increasingly important while estimating the parameters of aggregate demand functions to study firm behavior are the endogeneity of marketing activities (typically, price) and heterogeneity across consumers in the market under consideration. Ignoring these issues in the estimation of the demand function parameters can lead to biased and inconsistent estimates for the effects of marketing activities. Endogeneity and heterogeneity have achieved prominence in large measure because of the increasing popularity of logit models to characterize demand functions using aggregate data. The logit model accounts for purchase incidence and brand choice by including a “no-purchase” alternative in the consumer's choice set. This allows for category sales to change as a function of the marketing activities of brands in the category. There are three issues with using the logit model with the no-purchase option to characterize demand when studying competitive interactions among firms. (1) The marketing literature dealing with brand choice behavior at the consumer level has found that the IIA restriction is not appropriate, as each brand in the choice set is more similar to some brands than it is to others. (2) Studies have found that the purchase incidence decision is distinct from the brand choice decision. Hence, it may not be appropriate to model the no-purchase decision as just another alternative in the choice set with the IIA restriction holding across all brands and the no-purchase option. (3) Even if the distinction between the purchase incidence and brand choice decisions is accounted for via, for example, a nested logit specification, accounting for the purchase incidence decision with aggregate data requires assumptions for computing the share of the no-purchase alternative which is otherwise unobserved. In this paper, we propose a probit model as an alternative to the logit model to specify the aggregate demand functions of firms competing in oligopoly markets. The probit model avoids the IIA property that affects the logit model at the individual consumer level. Furthermore, the probit model can naturally account for the distinction between the purchase incidence and brand choice decisions due to the general covariance structure assumed for the utilities of the alternatives. We demonstrate how the parameters of the proposed model can be estimated using aggregate time series data from a product market. In the estimation, we account for the endogeneity of marketing variables as well as for heterogeneity across consumers. Our results indicate that both endogeneity as well as heterogeneity need to be accounted for even after allowing for a non-IIA specification at the individual consumer level. Specific to our data, we also find that ignoring endogeneity has a bigger impact on the estimated price elasticities than ignoring the effects of heterogeneity. A comparison of the elasticities obtained from the probit model with those from the corresponding logit specification indicates that the range of elasticities obtained from the probit model across brands is larger than that obtained from the logit. The results have implications for issues such as firm-level pricing. In addition to specifying a probit model and providing comparisons with the logit model, the paper also addresses the third issue raised above. We propose a simple alternative to the purchase incidence/brand choice specification by decomposing the demand for a brand into a category demand equation and a conditional brand choice share equation. We provide a comparison of results from this specification to those from the specification that includes the no-purchase alternative and find that estimated elasticities are sensitive to the specification used. We also estimate the demand function parameters using a traditional specification such as the double-logarithmic model. Here, we find that the estimated elasticities could be signed in such a manner as to be not useful for firm-level pricing decisions. One of the key limitations of the proposed model is that while it accounts for the purchase incidence and brand choice decisions of households, it does not account for differences across consumers in their purchase quantities. The model and analysis are best suited for product categories in which consumers typically make single-unit purchases. Another limitation is more practical in nature. While recent advances have been made in computing probit probabilities, it could nevertheless be a challenge to do so when the number of alternatives is large.

Modelling crime and punishment

This paper provides an extended supply of labour model which allows for different intensities of legal and illegal (criminal) activities and in which criminal activities may be considered both as work and leisure. Heterogeneity of individuals is also taken into account. The model is estimated from Finnish aggregate time-series data, pooled Finnish municipalities data and pooled international cross-country data. With the Finnish aggregate data, a volume index of crime is constructed and then used in testing the model. All empirical results give strong support to the hypothesis that apprehension and punishment are important deterrents of crime. By contrast, the role of sosioeconomic and demographic variables turns out to be of little importance.

Downward Nominal Wage Rigidity in Japan

This paper analyzes whether or not Japanese nominal wages exhibit downward rigidity. We posit a wage adjustment model in which, below a certain wage inflation rate, wages may or may not move as much as optimal or notional wages do. By using data on wages of 18 industries and aggregate time series data, we find that nominal wages were rigid downward until 1998, but not with the inclusion of years 1999 and 2000. That is, Japanese wages responded flexibly downward to the recession of 1997–1998, but with a lag. The interpretation of such results is not straightforward. But we provide some preliminary discussions of possible factors behind such a pattern of wage movements, focusing on the relationship between wage changes and the seniority-based wage system. J. Japan. Int. Econ., March 2001, 15(1), pp. 50–67. The Bank of Japan, Chuo-ku, Tokyo 103-0021, Japan. Copyright 2001 Academic Press.Journal of Economic Literature Classification Numbers: E24, E31, J30.

On Aggregation of Micro-Relations : a Research Program

The message of this presentation is: by taking into account heterogeneity of the population in modelling macroeconomic behavioral relations one can make use of cross-section data in addition to aggregate time series data. To rely on this richer data set - i.e., time series of cross-section data - will improve the empirical content of macro-modelling.

A comparative study of structural models of corporate bond yields: An exploratory investigation

This paper empirically compares a variety of firm-value-based models of contingent claims. We formulate a general model which nests versions of the models introduced by Merton (1974), Leland (1994), Anderson and Sundaresan (1996), and Mella-Barral and Perraudin (1997). We estimate these using aggregate time series data for the US corporate bond market, monthly, from August 1970 through December 1996. We find that models fit reasonably well, indicating that variations of leverage and asset volatility account for much of the time-series variations of observed corporate yields. The performance of the recently developed models which incorporate endogenous bankruptcy barriers is somewhat superior to the original Merton model. We find that the models produce default probabilties which are in line with the historical experience reported by Moodys.

The Effects of Worker Participation, Employee Ownership and Profit Sharing on Economics Performance: A Partial Review

For alternative sharing arrangements, we review theory on the economic effects on employment, productivity, investment, income and wealth distribution, and life cycle and survival. We find that predictions are often ambiguous and that sometimes the nature and size of the specific effect is determined in part by the particular institutional arrangements. Next recent econometric work is studied. We review studies using aggregate and industry level time series data for Japan as well as studies that use enterprise and establishment level data for firms in North America and Western Europe. Worker participation, employee share ownership and profit sharing schemes are often found to affect that studies obtained conflicting results. However, available evidence is strongly suggestive that for employee ownership schemes to have a strong positive impact they need to be accompanied by provision for worker participation in decision making.

Unemployment and Mental Disorders - An Empirical Analysis

The purpose of this paper is also to analyze the importance of unemployment and other social factors as risk factors for impaired mental health. It departs from previous studies in that we make use of information about first admissions to a psychiatric hospital or ward as our measure of mental illness. The database for our analyses has been constructed by merging two large Danish longitudinal data sets. The first is a panel of approximately 240.000 individuals which corresponds to 5 per cent of the Danish population aged 16-74, and contains detailed year-by-year information about the individuals' labour market behaviour, incomes, individual characteristics and so on from a fifteen-year period, 1976-91. The other panel is the Central Psychiatric Case register which contains all cases of psychic illness and their diagnoses (a little over 300.000 individuals and a little over one million cases) as registered in all Danish psychiatric hospitals and wards since 1969. The number of people found in both panels is a little over 15.000. We carry out analyses at two levels of the data. Firstly, we examine the determinants of first admission rates using aggregate time series data constructed from the Psychiatric case register. Secondly, we estimate conditional logistic regression models for case-control data on first admissions to a psychiatric hospital. The explanatory variables in the empirical analysis include age, gender, education, marital status, income, wealth, and unemployment (and length thereof) and other labour market statuses during the years preceding the first admission. This allows us to study whether unemployment as a risk factor differs between age groups, men and women, and single and married persons, and whether education and earnings have a moderating effect on the unemployment-mental illness relationship.

Labor market effects of import competition: Theory and evidence from the textile and apparel industries

Since the early 1980s, much attention has been given to the possibility of trade-related job losses and wage effects in the textile and apparel industries. This paper uses aggregate time series data from the Annual Survey of Manufacturers [Bartlesman and Gray, 1996] with import price data from the Bureau of Labor Statistics [Alterman, 1991] for 1977–91 to test the effect of imports on employment and wages in textiles and apparel. Theoretical models suggest that import competition should be a factor in the determination of employment, and possibly wages, regardless of whether the U.S. is represented as a price-setter or price-taker. The empirical analysis provides some support.

Are Crop Yields Normally Distributed?

AbstractThe evidence for nonnormality of crop yields is reassessed. Three methodological problems are identified in typical yield distribution analyses: (i) misspecification of the nonrandom components of yield distributions, (ii) missreporting of statistical significance, and (iii) use of aggregate timeseries (ATS) data to represent farm‐level yield distributions. One or more of these problems infect virtually all evidence against normality to date. The positive contribution of the article is a set of principles that must be followed in any valid investigation of yield normality.

Housing Supply: The Other Half of the Market A Note from the Editor

When I first read Edgar Olsen’s (1987) excellent review of the literature on the demand and supply for housing several years ago I was reminded of a pamphlet I saw during graduate school. The pamphlet purported to be a guide to climbing and fishing at one of Wisconsin’s more obscure parks and included a description of various climbing opportunities. On its last page, the pamphlet reported that there was no fishing at the area. By contrast, Olsen’s review examines the lessons learned from a large amount of literature on housing demand but then concludes that there is a comparative dearth of research on housing supply. While the literature on housing supply (and demand) has certainly grown in the last ten years, housing supply remains enormously understudied relative to demand, a situation that at first glance is puzzling since housing supply comprises half of the housing market. Why then has housing supply received such limited attention? It is unlikely that lack of interest is the reason. Rather, I suspect there is a widespread belief that adequate data do not exist to properly examine empirical issues pertinent to housing supply or possibly that the conceptual foundations of housing supply are difficult to model. With these considerations as a backdrop, this issue seeks to accomplish three principle goals. First, to demonstrate that we can indeed study housing supply, both at the empirical and conceptual levels. Second, to summarize what we know about housing supply and provide an important increment to our knowledge of housing supply. Third, to highlight areas and questions that are both important and feasible to address in future research. To accomplish these goals this issue is organized as follows. The first article by DiPasquale conducts a selected review of the literature on housing supply. The review does not simply list what other studies have done but organizes the literature on housing supply into different categories and identifies areas in which our knowledge to date is lacking. An important point emphasized by DiPasquale is that most of the empirical work on housing supply has utilized aggregate time-series data and that there is a need to develop high-quality micro databases suitable for examining the micro foundations of housing supply. Both for readers familiar with the housing literature, and for readers new to the area, this article is a good starting point before examining the other articles in the issue. Blackley follows with an article that addresses the most frequently researched issue in the literature on housing supply: measuring the elasticity of new housing supply. Using a common database, Blackley estimates the long-run elasticity of new housing supply for four different specifications that have appeared in the literature since 1979 and

Supply Response of Cocoa in Ghana: a Farm-level Profit Function Analysis

Available estimates of cocoa supply response in Ghana are derived from aggregate time series data. The present study presents results of a cross-section profit function analysis, based on farm-level data. The results are compared with those of previous time series studies, and the methodologies of both types of study are compared and evaluated. Copyright 1998 by Oxford University Press.