Long-term impact of investments in early schooling — Empirical evidence from rural Ethiopia

We examine the cumulative impact of early schooling investments on later schooling outcomes using enrollment status and relative grade attainment as short-run and long-run measures of schooling. Using a child-level longitudinal data set from rural Ethiopia, we estimate a dynamic conditional schooling demand function where the coefficient estimate on the lagged dependent variable captures the impact of all previous period schooling inputs and resources. We find that a child who is enrolled in the prior period is 33 percentage points more likely to be enrolled currently. These lagged effects are stronger for girls and for children from higher income households.     

Dynamic elasticities of tax revenue: evidence from the Czech Republic

Tax revenue elasticities with respect to tax bases are key parameters for the modeling of public finances. Yet the existing studies estimating these elasticities for emerging countries disregard the effects of tax reforms on tax revenue, which renders their estimates inconsistent. We introduce a framework for estimating both short- and long-run tax revenue elasticities using quarterly data adjusted for the effects of reforms. Our results suggest that the long-run elasticities in the Czech Republic are 1.4 for wage tax, 0.9 for value added tax, 1.7 for profit tax and 1 for social security contributions. The adjustment process for value added tax and social security contributions is fast, but for the remaining two categories, it is important to distinguish between the short- and long-run elasticities: the initial response of revenue to changes in the bases is weak. In the case of wage tax it takes half a year for the elasticity to surpass unity.     

Estimating the covariance matrix for regression models with ar(1) errors and lagged dependent variables

We propose a simple procedure, based on an artificial linear regression, for consistently estimating the covariance matrix of the parameter estimates for linear regression models with serially correlated errors and lagged dependent variables.     

Health expenditure models: A comparison using panel data

In this article, we focus on the estimation of outpatient expenditures with panel data. We model the logarithm of expenditures and consider five different models. The first two are two-part and sample selection cross-section models. Two-part panel data models turn out to be inappropriate for dealing with expenditures. We thus estimate sample selection models with panel data: one without a lagged dependent variable and two with a lagged dependent variable. These two latter models differ in their assumptions on the variance of the residuals. Modelling heteroscedasticity may indeed be important to avoid the bias due to the retransformation problem. We show that lagged dependent variables are important factors for heteroscedasticity. For the models with state dependence, we provide a new solution to the initial conditions problem by controlling for generalised residuals. We establish that panel data models highly improve the correlation explained by the model in the time-series dimension without damaging the fit in the cross-section dimension. For all indicators of fit, the model with state dependence and heteroscedasticity seems to dominate the others.     

An augmented autoregressive distributed lag bounds test for cointegration

An augmented autoregressive distributed lag (ARDL) bounds test for cointegration involves an extra F-test on the lagged levels of the independent variable(s) in the ARDL equation. Originally, this testing strategy was introduced using the bootstrap procedure. This paper provides both the small sample and asymptotic critical values for easier implementation of the test, making it applicable for a broader range of researchers. Two advantages of this augmented ARDL bounds test are that the assumption of an I(1) dependent variable is not necessary, and a clear conclusion on the cointegration status is provided by the three tests. The augmented ARDL bounds test is demonstrated using an empirical study on government taxation and expenditures. The tests support the tax-and-spend hypothesis of the budgetary policy for the US, the UK, and France.     

Expert opinion versus actual transaction evidence in the valuation of non-market amenities

Actual property values are overwhelmingly employed as a dependent variable in hedonic pricing models. Yet, assessed property values are generally more readily available than actual sales values and have, in some studies, been used in lieu of market prices. In this study, we compare estimates of different non-market amenity values based on actual transactions and assessed values. We estimate a Seemingly Unrelated Regression (SUR) model with two hedonic price equations, one with actual market values as the dependent variable and the other with assessed property values, and compare the resulting estimates of shadow prices for open space amenities. We also take into account spatial autocorrelation and combine Method of Moment estimates of the spatial parameters in both equations to create our test statistic. The results indicate that we cannot accept the hypothesis that the impacts of open space on property values are the same for actual sales and assessed values. Moreover, we do observe some differences between the distributions of assessed versus sales values, although the difference between the sizes of open space effects measured within the two equations is rather limited. Thus, while this one study is insufficient to enable one to draw definitive conclusions, there remains the possibility that policy makers cannot reliably base decisions on amenity values obtained from a hedonic model using assessed values.     

Bank competition in transition countries: Are those markets really in equilibrium?

This paper investigates the degree of market competition in the banking industries of 17 Central and Eastern European (CEE) countries over the period 1994–2008, using the H statistic proposed by Panzar and Rosse (J Ind Econ 35:443–456, 1987). Differing from previous works, this paper applies the newly developed censored stochastic frontier model (CSFM) to test whether these markets have achieved long-run equilibrium, which is an issue overlooked by previous literature. The CSFM appears to be preferable to the conventional one that requires adding a unity to the dependent variable return on assets for all observations, making the so-derived dependent variable non-negative. One can then take the natural logarithm of this distorted dependent variable for a subsequent equilibrium test. Inconsistent parameter estimates may occur and lead to doubtful testing results. Empirical outcomes show that a majority of the banking markets under study experience rising H statistics during the sample period and are operating under monopolistic competition. Moreover, our results indicate that some CEE banking sectors are characterized as contestable markets that may have contributed to the recent deregulation and liberalization progress. More importantly, the CSFM confirms that most of the banking sectors are in long-run equilibrium, justifying the use of the Panzar–Rosse model, while the conventional, transformed dependent variable approach tends to reject the equilibrium hypothesis in more sample countries.     

Spatial econometric Monte Carlo studies: raising the bar

We discuss Monte Carlo methodology that can be used to explore alternative approaches to estimating spatial regression models. Our focus is on models that include spatial lags of the dependent variable, e.g., the SAR specification. A major point is that practitioners rely on scalar summary measures of direct and indirect effects estimates to interpret the impact of changes in explanatory variables on the dependent variable of interest. We argue that these should be the focus of Monte Carlo experiments. Since effects estimates reflect a nonlinear function of both \(\beta \) and \(\rho \), past studies’ focus exclusively on \(\beta \) and \(\rho \) parameter estimates may not provide useful information regarding statistical properties of effects estimates produced by alternative estimators. Since effects estimates have recently become the focus of inference regarding the significance of (scalar summary) direct and indirect impacts arising from changes in the explanatory variables, empirical measures of dispersion produced by simulating draws from the (estimated) variance–covariance matrix of the parameters \(\beta \) and \(\rho \) should be part of the Monte Carlo study. An implication is that differences in the quality of estimated variance–covariance matrices arising from alternative estimators also plays a role in determining the accuracy of inference. An applied illustration is used to demonstrate how these issues can impact conclusions regarding the performance of alternative estimators.     

Long-run growth empirics and new challenges for unified theory

Annual estimates of productivity are reported for periods over 500 years for eight countries and for five other countries over shorter periods. One- and two-break time series models are used to investigate discontinuities in productivity growth. The results support two-break models of long-run productivity and they favour approaches to unified growth modelling with three epochs. However, the lessening of productivity gaps and the decisive shifts to higher productivity occurred in the twentieth century, chiefly in the years around the World War II. The timing of the breaks and the complexity of the historical record highlights a need for unified models to connect more closely with economic history.     

Teaching Regressions with a Lagged Dependent Variable and Autocorrelated Disturbances

The author attempts to rectify the unsatisfactory textbook treatment of the finite-sample properties of estimators of regression models with a lagged dependent variable and autocorrelated disturbances. He contends that the bias of the OLS estimator of a regression model with a lagged dependent variable and autocorrelated disturbances is determined by two effects, the dynamic effect and the correlation effect, which may be reinforcing or offsetting. The implications of these two effects are explored within a theoretical and a Monte Carlo framework.     

The short- and long-run impacts of financial crises on youth unemployment in OECD countries

The impact of financial crises on the youth unemployment rate (YUR), compared to the total unemployment rate (UR), is estimated for a panel of OECD countries over the period 1981–2009, using bias-corrected dynamic panel data estimators of short- and long-run coefficients. Both YUR and UR are found highly persistent. Also, short- and long-run effects of financial crises on YUR are significantly large, respectively, some 1.9 and 1.5–1.7 times higher than the short- and long-run effects on UR. Similar results are found for the unemployment impacts of GDP growth lagged 1 year and institutional variables. These results are robust to various dynamic specifications.     

On Efficient Estimation and Correct Inference in Models with Generated Regressors: a General Approach

Two approaches have been developed for deriving the properties of efficiency and consistency of standard errors of two step estimators of linear models containing current or lagged unobserved expectations of a single variable. One method is based on the derivatives of the likelihood function and information matrix, while the other uses the true covariance matrix of the disturbance vector when unknown parameters or variables are replaced by corresponding estimates. In this paper, the second approach is extended to cases where the structural equation is nonlinear and the model contains expectations of more than one variable or expectations of future variables. The properties of a frequently used estimator to deal with missing observations problems, a model involving a variance as an explanatory variable, and a recently developed estimator for autoregressive moving average models can be easily derived using the results of the paper. Methods for improving the efficiency of two step estimators are outlined.
JEL Classification Number: C13     

σ: The long and short of it

Research on the elasticity of substitution between capital and labor – σ – has been proceeding for 75 years. While there is clearly a strong case for the importance of σ in the analysis of growth and other economic issues, much less agreement exists on the value of σ. This paper offers some perspectives on prior estimates of σ, emphasizing the fundamental tension between the short-run data that are available and the long-run parameter that is required. Estimates of σ based on various short-run and long-run models are discussed and, while the estimates range widely, the weight of the evidence suggests a value of σ in the range of 0.40–0.60. There is little evidence to sustain the assumption of a Cobb–Douglas production function.     

A warning on the use of the Cochrane-Orcutt procedure based on a money demand equation

Betancourt/Kelejian [1981] have recently warned against using the Cochrane-Orcutt procedure in models which include a lagged endogenous variable because this procedure can have more than onefixed point even asymptotically. FollowingSargan [1964], we argue instead that fixed points are not necessarily minima and that the question of practical importance is whether the residual sum of squares can have multipleminima. Within this formulation of the problem, we provide the firstreal example of multiple minima obtainable by the Cochrane-Orcutt procedure — with or without a lagged endogenous variable — and use it to caution against routine use of this procedure.     

Long-run estimates of interfuel and interfactor elasticities

Meta-analyses of interfuel and capital-energy elasticities of substitution show that elasticity estimates are dependent on the type of data − time series, panel, or cross-section − and the estimators used. Econometric theory suggests that the between estimator might generate the best estimates of long-run elasticities but no existing estimates of elasticities of substitution have used it. Alternatively, Chirinko et al. argued in favor of estimating long-run elasticities of substitution using a long-run difference estimator. We provide estimates of China’s interfuel and interfactor elasticities of substitution using the between and long-run difference estimators. To address potential omitted variables bias, we add province level inefficiency and national technological change terms to our regression model. The results show that demand for coal and electricity in China is very inelastic, while demand for diesel and gasoline is elastic. With the exception of gasoline and diesel, there are limited substitution possibilities among the fuels. Substitution possibilities are greater between energy and labor than between energy and capital. The results are quite different to some previous studies for China but coincide well with the patterns found in meta-analyses for long-run estimates of elasticities of substitution.     

The lower bound and the causes of monetary policy inertia: evidence from Sweden

In 2009, in the midst of a global recession, Sweden’s Riksbank approached a lower bound on nominal interest rates. This encounter with the lower bound provides a natural experiment for investigating the causes of monetary policy inertia. To exploit this experiment, we estimate Taylor rules with Tobit specifications that permit both interest rate smoothing and persistent shocks (serial correlation) as explanations for inertia. The interest rate smoothing hypothesis leads to a specification in which lagged actual values of the dependent variable appear on the right-hand side of the Taylor rule, while the persistent shocks hypothesis leads to a specification in which lagged values of an unobserved latent dependent variable appear on the right-hand side of the Taylor rule. The divergence of actual and latent dependent variables that occurs at the lower bound provides leverage in distinguishing the two hypotheses. For a conventional Taylor rule, we find evidence of both sources of inertia. For a modified Taylor rule that includes a measure of financial stress, our evidence suggests that interest rate smoothing is the principal source of monetary policy inertia.     

Short and long run democracy diffusion

Does democracy diffuse across borders? If so, how long does it take? Can diffusion cause path dependence, such that if a region is initially democratic (or autocratic), it becomes increasingly so? In this paper I estimate short and long run regional democratic diffusion and account for feedback to and from other countries within the region. Although it is difficult to establish causality, I estimate that when regional democracy in year (t-1) increases, domestic democracy receives or “catches” 40–42% of the increase in the next 5 years, 55–61% in 10 years, and 68–85% in the long run prior to accounting for feedback. When I account for feedback, the average region converges to a unique long-run democracy level regardless of how democratic it is initially. I also provide region-specific and contiguous neighbor estimates, use the model to explain democratization waves, and estimate the alternative V-DEM dataset. In the V-DEM data, democracy diffuses much faster, although the long-run diffusion effects are comparable.     

Adult equivalence scales and food expenditures: an application to Mexican beef and pork purchases

In the analysis of food expenditures, the use of a simple count of household members as an estimate of household size implicitly assumes each household member has the same marginal impact. In this analysis of Mexican food expenditures, endogenously determined adult equivalence scales are estimated in such a way that these marginal impacts are allowed to vary by household member age and gender. The results of a series of hypothesis tests indicate a rejection of the implied null hypothesis of equal marginal expenditure impacts associated with the use of the traditional count based household size variable. This study also rejects the null hypothesis of the equality of adult equivalent scales across the commodities included in this analysis.     

Few and Not So Far Between: A Meta-analysis of Climate Damage Estimates

Given the vast uncertainty surrounding climate impacts, meta-analyses of global climate damage estimates are a key tool for determining the relationship between temperature and climate damages. Due to limited data availability, previous meta-analyses of global climate damages potentially suffered from multiple sources of coefficient and standard error bias: duplicate estimates, omitted variables, measurement error, overreliance on published estimates, dependent errors, and heteroskedasticity. To address and test for these biases, we expand on previous datasets to obtain sufficient degrees of freedom to make the necessary model adjustments, including dropping duplicate estimates and including methodological variables. Estimating the relationship between temperature and climate damages using weighted least squares with cluster-robust standard errors, we find strong evidence that duplicate and omitted variable biases flatten the relationship. However, the magnitude of the bias greatly depends on the treatment of speculative high-temperature (>4 \(^{\circ }\)C) damage estimates. Replacing the DICE-2013R damage function with our preferred estimate of the temperature–damage relationship, we find a three- to four-fold increase in the 2015 SCC relative to DICE, depending on the treatment of productivity. When catastrophic impacts are also factored in, the SCC increases by four- to five-fold.     

Weight-based pricing in the collection of household waste: the Oostzaan case

This paper provides an empirical analysis of the effects of weight-based pricing in the collection of household waste. Using a comprehensive panel data set on all households in a Dutch municipality we estimate short-run as well as long-run price effects for the amounts of both compostable and non-recyclable household waste. We find significant and sizeable price effects, with the elasticity for compostable waste being four times as large as the elasticity for non-recyclable waste. Long-run elasticities are about 30% larger than short-run elasticities.