MSE-improvement of the least squares estimator by dropping variables

It is well known that dropping variables in regression analysis decreases the variance of the least squares (LS) estimator of the remaining parameters. However, after elimination estimates of these parameters are biased, if the full model is correct. In his recent paper, Boscher (1991) showed that the LS-estimator in the special case of a mean shift model (cf. Cook and Weisberg, 1982) which assumes no “outliers” can be considered in the framework of a linear regression model where some variables are deleted. He derived conditions under which this estimator outperforms the LS-estimator of the full model in terms of the mean squared error (MSE)-matrix criterion. We demonstrate that this approach can be extended to the general set-up of dropping variables. Necessary and sufficient conditions for the MSE-matrix superiority of the LS-estimator in the reduced model over that in the full model are derived. We also provide a uniformly most powerful F-statistic for testing the MSE-improvement.     

AN ATTEMPT TO EXPLAIN DIFFERENCES IN ECONOMIC GROWTH: A STOCHASTIC FRONTIER APPROACH

Total factor productivity (TFP), factor accumulation, and growth are analysed for a panel of 40 countries in 2001–11. TFP growth and technical inefficiency are estimated using a stochastic frontier model. Environmental variables are found to have an important role in explaining differences in inefficiency across countries. Over 2001–11, the general improvement in technical efficiency of countries is almost outweighed by technological regress. Results indicate that differences in factor accumulation between OECD and emerging economies are more important than differences in TFP change to explain differences in economic growth. Results also indicate negative and significant random shocks for the OECD countries.     

Fertility and the puzzle of female employment in the Middle East and North Africa

Female labour force participation rates across the Middle East and North Africa (MENA) region have remained low for over four decades even though, in the same period, women's education rapidly increased and fertility rates substantially decreased. This study provides a better understanding of this surprising phenomenon by testing whether the number of children affects the mother's labour supply (using twins at first birth as an instrumental variable.) Despite a strong first stage, it does not find statistically significant effects in the second stage, even in the combined sample of over 100,000 observations. This non‐result, however, does not rule out that fertility affects women's employment in these countries. But it rejects impacts larger than 0.09. Similar twin‐studies in the United States found effects between 0.12 and 0.31. The paper discusses the implications of this result in understanding the puzzle of female participation in MENA and in designing policies to increase women's employment.     

会计实验研究对额外变量的控制

实验研究是对相关会计行为进行研究的主要方法之一.通过对变量之间因果关系的揭示,能够充分说明会计行为、会计判断的内在规律.但在研究中,不仅存在着可由实验者控制的能够对被试反应产生影响的变量,还有一些不用于研究目的却也会对被试反应产生影响的变量,即为额外变量,需要对其进行消除或控制.可以认为,会计实验研究的成败与研究者对额外变量的控制效果密切相关.本文通过对会计实验研究中额外变量的不同控制方法进行分析和说明,使实验研究者可以明确如何在会计相关研究中对额外变量进行有效控制,进而有效提高实验的效度.     

Re-examination of wage, employment, and hours adjustments: what is crucial for differences in the adjustments?

Manufacturing wage, employment, and hours adjustments are significantly different among developed countries, typically between Japan and the US. The problem of explaining the differences is closely related to that of what effect the extent of wage flexibility has on labor market adjustments. However, prevailing theories are invalid or incomplete for explaining the differences. The differences in the adjustments cannot be unrelated with institutional features of the labor market. Indeed, the extent of wage flexibility depends on the differences in the institutional features. Using a new model with such an idea, this paper theoretically re-examines the cause of the differences in the adjustments. The crucial causes are the characteristics of wage flexibility as well as the differences of the institutional features. The characteristics are that wage adjustment is discontinuous, infrequent, and has a lower limit in comparison with changes in demand.     

Class Size,Teacher Hours and Educational Attainment*

We employ a regression‐discontinuity design to identify effects on educational attainment after compulsory school of class size and the number of pupils per weekly teacher hour using administrative rules as instruments. We use Danish administrative panel data. Average class size is 20, about the same as in the US and most European countries. Restricting the sample to observations close to the enrolment discontinuity points where the administrative rules have greatest predictive power, instrumental variables estimates are consistently negative. Estimates from the preferred specification are marginally significant and indicate modest effects in line with earlier studies. Estimates for subgroups are less precise, but they indicate larger effects for pupils from less advantaged backgrounds.     

试论阐述平衡常数存在的问题

本文指出了普通化学中阐述平衡常数存在的两个问题,论证其把经验平衡常数与标准平衡常数混为一谈而导致的概念混乱;以及因处理不妥而产生的错误。并且还提出了相应的修正方法。     

Do family farms really converge to a uniform size? The role of unobserved farm efficiency*

We analyse the growth of family farms in Israeli cooperative villages during a period of economic turmoil. We use instrumental variables to account for the endogeneity of initial farm size, and correct for selectivity as a result of farm survival. We also include a technical efficiency index, derived from the estimation of a stochastic frontier production model, as an explanatory variable. Our aim is to check whether ignoring efficiency could have been the reason for convergence results obtained elsewhere in the literature. We found that technical efficiency is an important determinant of farm growth, and that not controlling for technical efficiency could seriously bias the results. In particular, larger farms are found to grow faster over time, while without controlling for technical efficiency the farm growth process seemed to be independent of initial farm size. The increasing polarisation of farm sizes in Israel has ramifications for the inefficiencies induced by the historical quota system, for the political power of the farm sector and for the social stability of farm communities.     

On estimating Armington elasticities for Japan's meat imports

By fully accounting for the distinct tariff regimes levied on imported meat, we estimate substitution elasticities of Japan's two-stage import aggregation functions for beef, chicken and pork. Although the regression analysis crucially depends on the price that consumers face, the post-tariff price of imported meat depends not only on ad valorem duties but also on tariff rate quotas and gate price system regimes. The effective tariff rate is consequently evaluated by utilising monthly transaction data. To address potential endogeneity problems, we apply exchange rates that we believe to be independent of the demand shocks for imported meat. The panel nature of the data allows us to retrieve the first-stage aggregates via time dummy variables, free of demand shocks, to be used as part of the explanatory variable and as an instrument in the second-stage regression.