On the estimation and testing of mixed geographically weighted regression models

Mixed geographically weighted regression (MGWR) model is a useful technique to explore spatial non-stationarity by allowing that some coefficients of the explanatory variables are constant and others are spatially varying, but its estimation and inference have not been systematically studied. This paper is concerned with estimation and testing of the model when there are certain linear constraints on the elements of constant coefficients. We propose a constrained two-step technique for estimating the constant coefficients and spatial varying coefficients, and develop a test procedure for the validity of the linear constraints. Finally, some simulations are conducted to examine the performance of our proposed procedure and the results are satisfactory.     

The determinants of coupon usage

This paper uses a large sample of survey data to investigate the empirical determinants of coupon usage. The broad set of control variables allows for comparisons of the relative importance of individual determinants and groups of determinants. We find that the set of variables measuring consumer shopping habits and attitudes explains more of the variation in coupon usage across households than the group of socioeconomic and demographic variables. However, the latter variables are jointly significant, and their estimated coefficients have the expected signs.     

STOCHASTIC ANALYSIS OF INPUT–OUTPUT MULTIPLIERS ON THE BASIS OF USE AND MAKE TABLES

Although technical coefficients are estimated on the basis of flow data (use and make matrices), they are rarely treated as random variables. If this is done, an error term is added to the coefficients, rather than derived from the distribution of the data. Even so, the calculation of multipliers, by means of the Leontief inverse, is difficult. Due to the nonlinearity of this operation, the multiplier estimates are biased. By going back to the flow data, this paper provides unbiased and consistent employment and output multipliers estimates for the Andalusian economy. Rectangular use and make matrices are accommodated and problems associated with the construction and estimation of technical coefficients and the Leontief inverse are circumvented.     

生产变量、基础设施和区域产业结构升级——对广东省的实证研究

产业结构升级不仅取决于生产变量提升的速度。还取决于基础设施是否作出了相应改进。本文构建指标体系，并利用熵值法和主成分方法计算准则层和目标层指数，分析广东省生产变量和基础设施与区域产业结构升级的关系及其动态变化。结果表明生产变量、基础设施和产业结构升级互为Granger因果关系；在产业阶段较低时，生产变量和基础设施的弹性均显著，但后者改进释放出的推动力远高于前者；随着产业阶段提高，基础设施的弹性系数依然显著，但对产业升级的支撑逐渐显得乏力。揭示出自然资源、资本和人力资源与科技创新等生产变量的提升固然重要，同时也要重视硬性和软性基础设施的优化。     

Direct effects of money on aggregate demand: another look at the evidence

Now that a number of central banks are faced with short-term nominal interest rates close to or at the zero lower bound, there is a renewed interest in the long-running debate about whether or not changes in the stock of money have direct effects. In particular, do changes in money have additional effects on aggregate demand outside of those induced by changes in short-term nominal interest rates? This article revisits and reinterprets the empirical evidence based on single equation regressions which is quite mixed, with some results supporting and other results denying the existence of direct effects. We use a structural model with no direct effects of money to show that the finding of positive and statistically significant coefficients on real money growth can be misleading. The model generates data that, when used to estimate analogues of the empirical regressions, produce positive and statistically significant coefficients on real money growth, similar to those often found when using actual data. The problem is that single equation regressions leave out a set of variables, which in turn, give rise to an omitted variables bias in the estimated coefficients on real money growth. Hence, they are an unreliable guide to calibrate monetary policies, in general, including at the zero lower bound.     

A new index of financial conditions

We use factor augmented vector autoregressive models with time-varying coefficients and stochastic volatility to construct a financial conditions index that can accurately track expectations about growth in key US macroeconomic variables. Time-variation in the models׳ parameters allows for the weights attached to each financial variable in the index to evolve over time. Furthermore, we develop methods for dynamic model averaging or selection which allow the financial variables entering into the financial conditions index to change over time. We discuss why such extensions of the existing literature are important and show them to be so in an empirical application involving a wide range of financial variables.     

A note on the optimal choice of monetary and fiscal policy

This paper studies the instrument-target problem associated with a simple macroeconomic model with conditions of uncertainty. The purpose of the paper is to demonstrate that if a model is linear with nonstochastic coefficients and with additive disturbances and if the policy objective is to maximize the expected value of the quadratic loss function, then it is the choice of endogenous variables that alters the expected loss value. This contrasts with the findings of Poole, Sargent, Turnovsky, et al., in which the expected losses are compared for different instruments while endogenous variables are changed at the same time. Thus, if basic model specifications are unchanged, an important cause for different expected losses under different policy instruments is seen to lie in the choice of endogenous variables.     

Population Growth and Economic and Social Development

The author compares maximum likelihood estimates of multinomial logit coefficients with coefficients of the same variables of student evaluations of teaching estimated in an ordinary least-squares regression. His results suggest that the logit model is preferable.     

Estimation of relative risk aversion across time

This article examines relative risk aversion in the framework of a three-moment asset pricing model that accounts for skewness. Accounting for skewness in calculating risk aversion gives a more accurate series of estimates of risk aversion and helps to reconcile the wide disparity in risk coefficients found in past literature. Risk aversion coefficients are calculated from 1926 to 2014 using stock market returns. This procedure results in a time series of data that can be related to other variables such as real interest rates and changes in demand for various asset classes.     

Potential ECB reaction functions with time-varying parameters: an assessment

This paper analyses the behaviour of the European Central Bank over the period 1999–2014 through the estimation of monetary policy reaction functions with time-varying coefficients and heteroskedastic error terms. This allows to evaluate whether relevant shifts in the conduct of monetary policy occurred and whether the current financial crisis had an influence on that. The paper considers two different specifications, one with contemporaneous regressors and one with regressors from surveys. The Taylor rule is then enriched with a set of macroeconomic and financial variables with the aim of testing their significance. Results show that forward-looking variables have a better explanatory power over interest rate policy. All the coefficients are found to be stable along the sample so that no shift in the reaction function can be identified and the financial crisis is found to only lead to a change in the size of the shock. Finally, we also provide evidence about the fact that the ECB has been actually constrained by the zero lower bound during the recent crisis.     

Thousands of BEERs: Take your pick

This paper explores the robustness of behavioral equilibrium exchange rate (BEER) models. We highlight the importance of model uncertainty, and employ real exchange rates computed from price‐level data to explore robustness to the inclusion of country fixed effects. The estimated coefficients—and therefore also the implied equilibrium values—are sensitive to the combination of variables included in the model, and to the inclusion of fixed effects. We identify several variables that exhibit a robust link with real exchange rates across specifications. Our findings can help policymakers in understanding the uncertainty associated with estimates of equilibrium exchange rates.     

On the Inconsistency of Instrumental Variables Estimators for the Coefficients of Certain Dummy Variables

In this paper we consider the asymptotic properties of the Instrumental Variables (IV) estimator of the parameters in a linear regression model with some random regressors, and other regressors that are dummy variables. The latter have the special property that the number of non-zero values is fixed, and does not increase with the sample size. We prove that the IV estimator of the coefficient vector for the dummy variables is inconsistent, while that for the other regressors is weakly consistent under standard assumptions. However, the usual estimator for the asymptotic covariance matrix of the I.V. estimator for all of the coefficients retains its usual consistency. The t-test statistics for the dummy variable coefficients are still asymptotically standard normal, despite the inconsistency of the associated IV coefficient estimator. These results extend the earlier results of Hendry and Santos (Oxf Bull Econ Stat 67:571–595, 2005), which relate to a fixed-regressor model, in which the dummy variables are non-zero for just a single observation, and OLS estimation is used.

     

A Base Model for Multifactor Specifications of the Term Structure

In this article, we aim to show that most of the recent multifactor specifications of the term structure can be traced back to a common general equilibrium model, based on an economy of the Cox, Ingersoll and Ross type. This base model of the term structure has a very general form and includes both square root and Gaussian dynamics of the underlying state variables. We establish a direct link among the state variables used in the different specifications of many multifactor models and analyse the structure of the resultant implied relationships. This technique has relevant implications from a practical point of view, as it can allow one to recover from the estimated coefficients of one model the implied value of the coefficients of other models. Moreover, it provides a way of recovering from the term structure the values of such unobservable variables as the real short rate and the expected inflation rate.
(J.E.L.: E43, G12).     

Forecasting UK international trade: A general equilibrium approach

Monthly retail unit sales of clothes washers and dryers in eastern Washington state were regressed on average employment during the current and preceding two months, the average advertised price of these appliances relative to the Consumer Price Index, the expected change in consumer stocks of such applicances for each year on the basis of a hypothetical rate of accumulation, and the unit volume of newspaper advertising in order to determine the viablity of alternative models for analysing and forecasting monthly sales in a localized retail market during the periods of growth, maturity, and decline in market demand.

Employment and advertising, the two most useful variables in the functions tested, were able to account for 70–75 per cent of the monthly sales variance for automatic washers and dryers. Employment elasticity coefficients, though not linearly related to income elasticity coefficients for these products, appear to be a useful measure of purchasing power for localized demand and forecasting functions. The average advertising elasticity for the products studied was 0.095, which was approximately equal to advertising expenditures as a ratio of the gross margin of furniture and house furnishings corporations and kitchen appliance departments of department stores for the period studied, in keeping with the Rasmussen hypothesis. Correction of the models for the presence of autocorrelation altered the explanatory power of some of the variables substantially and resulted in regression coefficients for some variables that were more nearly consistent with theoretical expectations.     

The interdependence between FDI and R&D: an application of an endogenous switching model to Taiwan's electronics industry

Foreign direct investment (FDI) and research & development (R&D) are mutually dependent and should be treated as endogenous variables in empirical studies. An endogenous switching regression model is used to examine the mutual effect of FDI and R&D in Taiwan's electronics industry. The empirical results show that FDI and R&D are positively related and do reinforce each other. Unbiased coefficients are obtained as they are compared to those estimates if FDI and R&D are treated as exogenous variables. The results have a strong public policy implication for Taiwan's foreign direct investment and can be further used to estimate the difference in R&D expenditures between FDI and non-FDI firms.     

Measuring wage discrimination in Italy: a random-coefficient approach

Using data from a representative 1989 household survey for Italy we estimate random-coefficient earnings frontiers by gender, marital status and location. These estimates are used to calculate discrimination indices. Our results show that fixed coefficients can be rejected in all cases. A wide range on the estimated coefficients indicates a high degree of variation in the quality of the observed human-capital variables as well as different degrees of ability as perceived by the employer. We find reverse discrimination for single females in the South and the North. For married females there is evidence of discrimination, particularly in the South. We isolate the effects of tenure and education on discrimination and find that these reduce discrimination for Southern-married females.     

A Monte Carlo study of growth regressions

Using Monte Carlo simulations, this paper evaluates the bias properties of estimators commonly used to estimate growth regressions derived from the Solow model. We explicitly allow for measurement error, country-specific fixed effects and regressor endogeneity. An OLS estimator applied to a single cross-section of variables averaged over time (the between estimator) performs best in terms of the extent of bias on each of the estimated coefficients. Fixed-effects and the Arellano–Bond GMM estimator overstate the speed of convergence under a wide variety of assumptions, while the between estimator understates it. Finally, fixed effects and Arellano–Bond bias towards zero the slope estimates on the human and physical capital accumulation variables, while the between estimator and the Blundell–Bond system GMM estimator bias these coefficients upwards.      

HETEROGENEITY IN WILLINGNESS‐TO‐PAY FOR THEATRE PRODUCTIONS: INDIVIDUAL SPECIFIC WILLINGNESS‐TO‐PAY ESTIMATES FOR THEATRES,SHOWS AND THEIR ATTRIBUTES

This paper investigates people's preferences for live theatre, and heterogeneity in willingness‐to‐pay (WTP). A stated preference discrete choice model estimates utility and WTP for different attributes of theatre productions. Previous studies assumed fixed coefficients across all theatre‐goers. This study allows coefficients of attributes to vary across individuals in the population, providing information on the heterogeneity of tastes. Theatre‐goers' choices are used to estimate individual‐based parameters for a person's tastes in theatre productions. The analysis reveals the heterogeneity of tastes for different types of plays and ticket price; and the significance of ‘reviews’ by critics and ‘word of mouth’ opinions as important variables determining choice.     

Fixed,random, or something in between? A variant of Hausman's specification test for panel data estimators

This paper proposes a variant of the Hausman specification test for panel models that allows us to examine both the equality of the whole sets of coefficients of two alternative models as well as that of individual variables.     

城乡收入差距影响因素的非参数逐点回归解析

文章利用1987-2008年我国的相关统计数据构建了非参数面板数据模型,采用非参数逐点回归估计方法,估计了我国的教育投入、教育产出、城市化水平、经济开放度、产业结构和政府经济行为等变量对城乡收入差距的影响,刻画了各影响因素关于自变量系数的动态演进趋势。研究表明:各影响因素关于自变量系数的逐点估计结果共有四种类型:"倒U型"、"U型"、"上升型"和"下降型";各影响因素对缩小城乡收入差距都有积极的作用,但在不同时期所起的作用不同。