Unveiling covariate inclusion structures in economic growth regressions using latent class analysis

We propose the use of Latent Class Analysis methods to analyze the covariate inclusion patterns across specifications resulting from Bayesian model averaging exercises. Using Dirichlet Process clustering, we are able to identify and describe dependency structures among variables in terms of inclusion in the specifications that compose the model space. We apply the method to two datasets of potential determinants of economic growth. Clustering the posterior covariate inclusion structure of the model space formed by linear regression models reveals interesting patterns of complementarity and substitutability across economic growth determinants.     

Distinguishing Between the Effects of Primary and Post-primary Education on Economic Growth

The paper follows Benhabib and Spiegel (Journal of Monetary Economics, Vol. 34, 1994:143–73) in examining the effect of human capital accumulation on economic growth. The paper is innovative in two ways. First, it takes the R&D‐based models more seriously. This delivers more structural specifications in which human capital affects growth as an input of final output and as a catalyst of technological innovation and imitation. Second, owing to data availability it is possible to disaggregate human capital and assign different roles to primary and post‐primary education. Regression estimates obtained from these alternative specifications suggest that the relative contribution of human capital to technology adoption and final output production vary by country wealth. More importantly, regression estimates suggest that primary education contributes mainly to production of final output, whereas post‐primary education contributes mainly to innovation and imitation of technology.     

The Evolution of Income-related Health Inequalities in Switzerland Over Time

This article presents new evidence on income-related healthinequality and its development over time in Switzerland. Weemploy the methods lined out in Van Doorslaer and Jones (2003,"Inequalities in self-reported health: validation of a new approachto measurement", Journal of Health Economics 22(1), 61–78)and Van Doorslaer and Koolman (2004, "Explaining the differencesin income-related health inequalities across European Countries",Health Economics 22(7), 609–628) measuring health usingan interval regression approach to compute concentration indicesand decomposing inequality into its determining factors. Nationallyrepresentative survey data for 1982, 1992, 1997, and 2002 areused to carry out the analysis. Looking at each of the fouryears separately the results indicates the usual positive relationshipbetween income and health, but the distribution is among theleast unequal in Europe. No clear trend emerges in the evolutionof the inequality indices over the two decades. A small butsignificant increase over the first 15 years is followed bystabilization if not a slight decrease in total income-relatedhealth inequality. The most important contributors to healthinequality are income, education and activity status, in particular,retirement. Regional differences including the widely varyinghealth care supply, in contrast, do not exert any systematicinfluence. (JEL codes: D32, I10, I12)     

Quality and quantity in primary care mixed‐payment models: evidence from family health organizations in Ontario

Abstract We study the impact of a mixed capitation model (the Family Health Organization, FHO) on quality and quantity outcomes among primary care physicians in Ontario. Using a panel of administrative data covering one year before and two years after the FHO model was introduced, we find that physicians in the FHO model provide about 6% to 7% fewer services and visits per day, but are between 7% and 11% more likely to achieve preventive care quality targets. These results suggest that the mixed capitation model with contractible quality indicators may be welfare improving relative to the FFS model.     

Goodness-of-fit techniques for count data models: an application to the demand for dental care in Spain

This paper compares the practical performance of alternative goodness-of-fit techniques for count data models in the context of a study of the determinants of demand for dental care in Spain. We apply alternative goodness-of-fit techniques to different specifications. In particular, we implement recently proposed specification tests which are consistent in the direction of general nonparametric alternatives. The analysis suggests that a negative binomial model is an appropriate specification for dental care demand. Dental health and income are identified as important predictors of individuals' behavior. First version received: April 2000/Final version received: March 2001     

Does Regional Financial Development Matter for Growth? Evidence from Indian States

The paper investigates finance–growth relationship across 26 Indian states over the period 1981–2012 in a panel setting. We use four indicators of financial development: credit-GSDP ratio, deposit-GSDP ratio, credit-deposit ratio and branch density and apply panel generalized method of moments (GMM) techniques. We observe positive and significant effect of financial development on economic growth and our findings are robust across alternate indicators of financial development and model specifications. Our findings highlight pivotal role played by financial intermediaries in fostering savings mobilization and financing investment activities across states through channels of deposit mobilization, expansion of credit and greater branch expansion in unbanked locations and consequent reduction of transactions costs. These findings are consistent with observations that much of India’s superior growth performance is attributed to high level of domestic savings. The paper also takes care of issues of bias and precision of various GMM estimators arising out of small sample typically prevalent in empirical growth models like ours.     

A comparison between the log-linear and the parameterized expectations methods

This paper compares the performance of a log-linear method and a parameterized expectations method in solving a dynamic general equilibrium endogenous growth model with human capital. Quantitative evaluation based on second moment statistics shows that the results provided by the two numerical methods are very similar in this framework whenever the propagation mechanism of technology shocks is weak. However, the cross correlations of some relevant variables in the RBC literature obtained from the two methods are significantly different when the model exhibits a strong propagation mechanism. The parameterized expectations method captures the sensitiviness of second moment statistics to the curvature of the utility function while the log-linear method does not.     

Regional inflation dynamics using space–time models

This article provides empirical evidence of the role of spatial factors on the determination of inflation dynamics for a representative set of tradable commodities in Chile. We present a simple model that explains inflation divergence across regions in a monetary union with similar preferences as a consequence of the geographical allocation of producers in the different regions. Our results indicate that spatial allocation together with transport costs are important determinants of regional inflation, while macroeconomic common factors do not play an important role in this process. Existing literature had obtained the opposite result for Europe, and the reasons for this difference warrant further investigation. Moreover, we find that geographical distance seems to be a more appropriate measure of neighbourhood than the adjacency of regions. Our results are robust to different specifications, regression methods and product groupings.     

REASSESSING SEGMENTATION IN THE LABOUR MARKET: AN APPLICATION FOR ITALY 1995–2004

The aim of this paper is to test for the presence of dualism in a standard wage regression. The disparity in wages between primary and secondary workers, according to labour market segmentation theory, is not provided by worker characteristics, but rather by job characteristics. A standard way to assess this situation is by looking at the estimated coefficients in a standard regression for comparable workers across different labour market segments. In an attempt to avoid arbitrary modelling choices, we deploy mixture regression methods which allow for endogenous determination of the number of existing labour market segments. Using Italian data, our modelling strategy outlines stark differences in returns to human capital between homogeneous workers in different markets. Thus, future policies should consider these findings when implementing labour market measures.     

Competing specifications of the gravity equation: a three-way model,bilateral interaction effects,or a dynamic gravity model with time-varying country effects?

We investigate bilateral trade flows across the EU-15 countries from 1962 to 2003 by different specifications of the gravity model. We augment the basic gravity model with population and exchange rate variables, and then include time-varying country fixed effects, to account for Anderson and van Wincoop (Am Econ Rev 93(1):170–192, 2003) multilateral resistance terms. Then, following the previous theoretical derivations of the gravity model in the presence of panel data in a dynamic setting we change the specification of our gravity model. We compare the results of different specifications showing the improvement in each case. We claim the comparative superiority of the dynamic gravity model with time-varying exporter and importer fixed effects due to its higher explanatory power. Finally, we compare out-of-sample forecasting performance of different specifications of the gravity model.     

Mixed Logit Model Performance and Distributional Assumptions: Preferences and GM foods

Using mixed logit models to analyse choice data is common but requires ex ante specification of the functional forms of preference distributions. We make the case for greater use of bounded functional forms and propose the use of the Marginal Likelihood, calculated using Bayesian techniques, as a single measure of model performance across non nested mixed logit specifications. Using this measure leads to very different rankings of model specifications compared to alternative rule of thumb measures. The approach is illustrated using data from a choice experiment regarding GM food types which provides insights regarding the recent WTO dispute between the EU and the US, Canada and Argentina and whether labelling and trade regimes should be based on the production process or product composition. This paper draws work commissioned by UK Department of Environment Food and Rural Affairs (DEFRA). The views presented in this paper are those of the authors alone and should not be regarded as those of DEFRA or of individuals within DEFRA.     

Econometric diagnostics to distinguish between the IS curve and the Ricardian equivalence

In this article two different specifications of a macroeconomic model are analysed. The first model is the Keynesian IS (Investments–savings) curve. The second is derived from the New Classical Ricardian equivalence. Since the two specifications are observationally equivalent, including the same set of variables, the econometric diagnostics of the regression equations are used to differentiate between the two of them. Six statistical criteria are compared: serial correlation, heteroscedasticity, specification tests, fit, randomness, and normality. The results support much better Ricardian equivalence than the Keynesian IS model.     

Specification and Estimation of Equilibrium Search Models

This paper considers estimation of a pure equilibrium search model in which all heterogeneity is endogenous and due to information asymmetries, and of variations that allow better fits to the data: Measurement error and heterogeneity in the productivity levels of firms. The model is fit to a random sample of individuals representing 1% of the Danish population in the age group 16–75 years over the period 1981–1990. All specifications are fit by maximum likelihood and provide readily interpretable parameter estimates. Variation in estimates across demographic groups is discussed. Several parameters are common across specifications, and their estimates are reasonably robust. Journal of Economic Literature Classification Numbers: C33, C34, C41, C51, C61, C72, J24, J31, J41, J42, J64     

A refinement of the relationship between economic growth and income inequality

There is mixed evidence in the literature of a clear relationship between income inequality and economic growth. Most of that work has focused almost exclusively on developed economies. In what we believe to be a first effort, our emphasis is solely on developing economics, which we classify as high-income and low-income developing countries (HIDC and LIDC). We make such distinction on theoretical and empirical grounds. Empirically, the World Bank has classified developing economies in this manner since 1978. The data in our sample are also supportive of such classifications. We provide theoretical scaffolding that uses asymmetric credit constraints as a premise for separating developing economies in such a way. We find strong evidence of a negative relationship between income inequality and economic growth in LIDC to be in stark contrast with a positive inequality–growth relationship for HIDC. Both correlations are statistically significant across multiple econometric specifications. Using international data from 1960 to 2010, this article explores the effect of income inequality on economic growth using dynamic panel technique, such as system generalized method of moments (GMM) that is believed to mitigate endogenous problem. These results are strikingly contrasting to the previous estimation results of Forbes (2000) displaying significant positive correlation between two variables in the short to medium term.     

Catholic schooling and further education

Using new estimation methods and data, I find that Catholic schooling substantially increases years of schooling by 0.42 to 0.47. The estimates are robust to various specifications that account for potential selection bias.     

Estimation and specification analysis of models of dividend behavior based on censored panel data

Dividends move in discrete jumps. Moreover, some companies pay dividends, others do not. Both these aspects necessitate the use of limited dependent variable models in the analysis of dividend behavior. Models of dividend behavior usually ignore these problems and treat dividends as a continuous variable. The present paper analyzes dividend behavior using panel data on 649 firms for 12 years (1976–1987). The model used is a censored regression model which allows for firm-specific and time effects. It is estimated using the maximum likelihood method under three different error covariance specifications. Based on specification tests, it is argued that it is important to allow for the zero observations, industry effects, and firm-specific and time effects in the estimation of models of dividend behavior.     

Local House Price Effects of Internal Migration in Queensland: Australia's Interstate Migration Capital

We examine the causal impact of internal migration on housing prices across 82 Statistical Areas Level 3 regions in Queensland, Australia from 2014–2019. The primary findings are: (i) an annual increase in the inflow of migrants equal to 1 per cent of a region's initial population leads to a 0.6 to 0.7 per cent annual increase in Queensland's house prices across different empirical specifications; (ii) this effect differs between the Greater Brisbane metropolitan area and Rest of State areas; (iii) migration from New South Wales fails to produce a significant influence on house price growth in Queensland.     

Productivity measurement in Swedish departments of gynecology and obstetrics

The rapid growth of public spending and the need to assess its impact on the welfare system has made the studies of productivity in the public sector an important subject. This paper is concerned with the specification and estimation of total factor productivity growth using the primal panel data approach. The total factor productivity growth is decomposed into technical change and scale components. Several competing models are used to explore whether there are any similarities in the estimates of total factor productivity growth and technical change among these models. The models are estimated using different estimation methods. Some of the models, although assuming a Cobb–Douglas technology, exhibit firm-specific technical change. These models are used to measure productivity growth in departments of gynecology and obstetrics in Sweden. Empirical results show evidence of large and negative rate of productivity growth. In comparison among different specifications proposed, the level and the time pattern of productivity measures vary substantially across models and estimation methods.     

Contemporary Monetary Policy in China: An Empirical Assessment

This paper focuses on monetary policy in China. A set of different specifications for the monetary policy reaction function are empirically evaluated using monthly data for 1998–2014. Overall, the performance of the estimated policy rules is surprisingly good. Chinese monetary policy displays countercyclical reactions to inflation and leaning‐against‐the‐wind behaviour. The paper shows a notable increase in the overall responsiveness of Chinese monetary policy over the course of the estimation period. The central bank interest rate is unresponsive to economic conditions during the earlier years of the sample, but response becomes significant in later years. This finding comports with the view that the monetary policy of the People's Bank of China has come to place greater weight on price‐based instruments. A time‐varying estimation procedure suggests that the two monetary policy objectives are generally assigned to different instruments. The money supply instrument continues to be utilized to control the price level. Since 2008, the interest rate instrument has been mainly used to achieve the targeted output growth.     

Within‐Subject Intra‐ and Inter‐Method Consistency of Two Experimental Risk Attitude Elicitation Methods

We compare the consistency of choices in two methods used to elicit risk preferences on an aggregate as well as on an individual level. We ask subjects to choose twice from a list of nine decisions between two lotteries, as introduced by Holt and Laury 2002, 2005 ) alternating with nine decisions using the budget approach introduced by Andreoni and Harbaugh ( 2009 ). We find that, while on an aggregate (subject pool) level the results are consistent, on an individual (within‐subject) level, behaviour is far from consistent. Within each method as well as across methods we observe low (simple and rank) correlations.