Search

In this paper, a quantile function is suggested as an alternative description of a production technology. Since the quantile function may not share the same functional properties as the frontier function, it is argued that the quantile-based production function serves as a better benchmark for a firm’s production structure analysis. This argument is extended to the metafrontier analysis. The quantile metafrontier is defined as the envelopment of all groups’ quantile frontier at the same quantile level. The quantile technology gap serves as a more relevant indicator of efficiency in the adopted technology than the traditional measure of the metafrontier technology gap. The quantile approach is illustrated using survey data to estimate the earning profiles for men, and the impact of human capital on the industrial wage distributions in the service industry, the manufacturing industry, and all other industries in Taiwan.

The empirical applications of the metafrontier analysis have largely been popularized by the publications of Battese et al. (2004), and O’Donnell et al. (2008). Prior to the estimation of the metafrontier function, it is generally suggested to conduct a likelihood-ratio (LR) test to test if all group frontiers are the same. In this short note, we point out that although the null hypothesis of the suggested LR test restricts all frontiers to be the same for all groups, the heterogeneity in the error distribution may exist and should be considered. We propose a restricted LR test as an alternative procedure.

In this paper, quantile regression models are suggested as an alternative description of a production technology. The quantile of continuous order defines the production profile and the quantile-based individual technical efficiency relative to the quantile order. Quantile-based production frontier and efficiency are easy to derive and estimate and do not envelop all sample observation points. A quantile-based production frontier is more robust to extreme observations than DEA or FDH. Furthermore, quantile regression does not make a distribution assumption. It is more robust to the misspecification of error structure than DFA or SFA. In this paper, the quantile regression methods are extended to semiparametric smooth coefficient models. A local linear fitting scheme to estimate the smooth coefficients is proposed in the quantile framework. An empirical application of the model to the Taiwan manufacturing industry demonstrates the potential for the estimation of production technology and efficiency measures.

This paper proposes a new two-step stochastic frontier approach to estimate technical efficiency (TE) scores for firms in different groups adopting distinct technologies. Analogous to Battese et al. (J Prod Anal 21:91–103, 2004), the metafrontier production function allows for calculating comparable TE measures, which can be decomposed into group specific TE measures and technology gap ratios. The proposed approach differs from Battese et al. (J Prod Anal 21:91–103, 2004) and O’Donnell et al. (Empir Econ 34:231–255, 2008) mainly in the second step, where a stochastic frontier analysis model is formulated and applied to obtain the estimates of the metafrontier, instead of relying on programming techniques. The so-derived estimators have the desirable statistical properties and enable the statistical inferences to be drawn. While the within-group variation in firms’ technical efficiencies is frequently assumed to be associated with firm-specific exogenous variables, the between-group variation in technology gaps can be specified as a function of some exogenous variables to take account of group-specific environmental differences. Two empirical applications are illustrated and the results appear to support the use of our model.

This paper explores the issue of whether investment in information technology (IT) will bring about the Solow productivity paradox. The semiparametric smooth coefficient approach is applied to implement estimations considering how the non-neutral impact of IT might affect labor productivity and thus contribute to productivity. The empirical results are obtained employing firm-level manufacturing data from Taiwan to show that IT investment has as a significantly positive influence on productivity. Specifically, IT exhibits a significant spillover impact on promoting labor productivity in general, particularly for larger and more IT deepened firms.

This study investigates the impact of e-commerce and R&D on productivity, using a unique panel dataset obtained from Taiwanese manufacturing firms for the period from 1999 to 2002. We specifically consider the network externalities of e-commerce and employ the system generalized method of moment (GMM) technique to deal with the endogenous problem of e-commerce adoption. The empirical results show that both e-commerce and R&D capital have a positive influence on productivity, while R&D exhibits a larger productivity-enhancing effect. We also find a complementary relationship between e-commerce and R&D on enhancing productivity. Crucially, the inter-industry network externality of e-commerce significantly contributes to productivity.

In this paper, we propose the copula-based maximum likelihood (ML) approach to estimate the multiple stochastic frontier (SF) models with correlated composite errors. The motivation behind the extension to system of SF regressions is analogous to the classical generalization to system of seemingly unrelated regressions (Zellner in J Am Statist Assoc 57:348–368, 1962). A demonstration of the copula approach is provided via the analysis of a system of two SF regressions. The consequences of ignoring the correlation between the composite errors are examined by a Monte Carlo experiment. Our findings suggest that the stronger the correlation between the two SF regressions, the more estimation efficiency is lost in separate estimations. Estimation without considering the correlated composite errors may cause significantly efficiency loss in terms of mean squared errors in estimation of the SF technical efficiency. Finally, we also conduct an empirical study based on Taiwan hotel industry data, focusing on the SF regressions for the accommodation and restaurant divisions. Our results, which are consistent with the findings in simulation, show that joint estimation is significantly different from separate estimation without considering the correlated composite errors in the two divisions.

This paper derives an analytic closed-form formula for the cumulative distribution function (cdf) of the composite error of the stochastic frontier analysis (SFA) model. Since the presence of a cdf is frequently encountered in the likelihood-based analysis with limited-dependent and qualitative variables as elegantly shown in the classic book of Maddala (Limited-dependent and qualitative variables in econometrics. Cambridge University Press, Cambridge, 1983), the proposed methodology is useful in the framework of the stochastic frontier analysis. We apply the formula to the maximum likelihood estimation of the SFA models with a censored dependent variable. The simulations show that the finite sample performance of the maximum likelihood estimator of the censored SFA model is very promising. A simple empirical example on the modeling of reservation wage in Taiwan is illustrated as a potential application of the censored SFA.

In most empirical studies, once the best model has been selected according to a certain criterion, subsequent analysis is conducted conditionally on the chosen model. In other words, the uncertainty of model selection is ignored once the best model has been chosen. However, the true data-generating process is in general unknown and may not be consistent with the chosen model. In the analysis of productivity and technical efficiencies in the stochastic frontier settings, if the estimated parameters or the predicted efficiencies differ across competing models, then it is risky to base the prediction on the selected model. Buckland et al. (Biometrics 53:603–618, 1997) have shown that if model selection uncertainty is ignored, the precision of the estimate is likely to be overestimated, the estimated confidence intervals of the parameters are often below the nominal level, and consequently, the prediction may be less accurate than expected. In this paper, we suggest using the model-averaged estimator based on the multimodel inference to estimate stochastic frontier models. The potential advantages of the proposed approach are twofold: incorporating the model selection uncertainty into statistical inference; reducing the model selection bias and variance of the frontier and technical efficiency estimators. The approach is demonstrated empirically via the estimation of an Indian farm data set.

I. INTRODUCTION Institutions of higher education comprise knowledge creation (research) and knowledge dissemination (teaching). Thus, the university's mission is to deliver quality undergraduate and graduate education and to expand the frontier of academic research. Numerous studies (Verry and Layard 1975; Cohn, Rhine, and Santos 1989; deGroot McMahon, and Volkin 1991; Nelson and Hevert 1992; Lloyd, Morgan, and Williams 1993; Dundar and Lewis 1995; Koshal and Koshal 1995, 1999) have investigated, as in the case of firms, the multiple-product cost function of producing the vector of outputs on undergraduate and graduate education and research. The cost structure of higher education is studied via the scale economies and the scope economies of the cost function. However, these measures of scale and scope economies may be elusive if the quality dimension of colleges and universities is not considered. Without taking into account the quality variation, in the short-run, a university can reduce the average cost of operation by lowering the quality. Universities with more congested educational facilities are substituting facility utilization for capital; universities with a higher student/faculty ratio and less research engagement are substituting quality of education for quantity of undergraduate and graduate enrollment. The consequence is an upward bias in estimating the economies of scale and scope. This conclusion is consistent with the early studies of Nelson and Hevert (1992) which showed that failure to control for class size in cost function may result in specification bias, and an economy of scale is evident if class size is allowed to expand. Quality of higher education is multidimensional. Quality in instruction, faculty research, and the quality of educational environment are all significant factors determining the long-run university cost structure and the crucial determinants of the scale and scope economies of higher education. How and to what extent quality affects a university's operating cost depends on the goal and orientation of the institutions. Higher quality increases the university's cost of operation. But, in a large research-oriented university, a disproportional share of the budget often benefits the graduate, not the undergraduate program. It is unrealistic to assume that quality affects only the average cost and that the marginal costs of various educational programs are independent of quality. Quality is unlikely to be simply a neutral cost-shifting factor. The purpose of this paper is to propose a university cost function and a semiparametric-estimating technique that treats quality as a nonneutral cost-shifting factor, which directly affects the marginal cost of outputs in undergraduate and graduate education. More precisely, the marginal costs of outputs are specified as a nonparametric smooth function of quality. A semiparametric specification of university cost is applied to 56 comprehensive and science/technology universities in Taiwan over the period 2000-2003. II. SEMIPARAMETRIC COST FUNCTION AND ESTIMATION TECHNIQUE Following the conventional multiproduct cost specification for higher education (Cohn, Rhine, and Santos 1989; deGroot, McMahon, and Volkin 1991; Lloyd, Morgan, and Williams 1993; Dundar and Lewis 1995; Koshal and Koshal 1995, 1999), the total cost (C) is specified as a quadratic function of outputs, undergraduate and graduate enrollments. However, the quadratic cost function is modified by allowing for the coefficients to be functions of quality in the following form: (1) C = [[beta].sub.0](Q) + [k.summation over i=1] [[beta].sub.i](Q)[Y.sub.i] + (1/2) X [k.summation over i=1], [k.summation over j=1], [[beta].sub.ij](Q)[Y.sub.i][Y.sub.j] + [m.summation over i=1], [[alpha].sub.i][Z.sub.i] + [epsilon] where C is the total cost of producing k educational outputs (Y), and [Z.sub.i] is the ith institutional characteristics. …

An important issue when conducting stochastic frontier analysis is how to choose a proper parametric model, which includes choices of the functional form of the frontier function, distributions of the composite errors, and also the exogenous variables. In this paper, we extend the likelihood ratio test of Vuong, Econometrica 57(2):307–333, (1989) and Takeuchi’s, Suri-Kagaku (Math Sci) 153:12–18, (1976) model selection criterion to the stochastic frontier models. The most attractive feature of this test is that it can not only be used for testing a non-nested model, but also still be applicable even when the general model is misspecified. Finally, we also demonstrate how to apply this test to the Indian farm data used by Battese and Coelli, J Prod Anal 3:153–169, (1992), Empir Econ 20(2):325–332, (1995) and Alvarez et al., J Prod Anal 25:201–212, (2006).

In this article, we formulate a behavioural model under uncertainty to estimate Total Factor Productivity (TFP) in the Taiwan banking industry. In particular, the article provides a model based on the safety-first rule under uncertainty to measure the risk premium in banking operations that are subject to loan default and other investment risks. With panel data of 40 banks in 1981–1996, a translog cost function and the associated share equations are used to estimate the dual rate of Total Cost Diminution (TCD), the dual Returns To Scale (RTS) and the derived primal rate of TFP. A constant elasticity of transformation output function is employed to construct an aggregated output index of loan and investment activities. The empirical results indicate zero productivity growth and a highly risk-averse banking industry. Government-owned banks are generally more risk-averse than privately owned banks. As expected, the Taiwan banking industry became more risk-venturesome after the deregulation and liberalization...

1. INTRODUCTION The financial plight and plunging quality of higher education has dominated the current debate about educational reforms in Taiwan. The debate has provided a forum on the issues of the economic behavior of institutions of higher education, including the amalgamation of institutions, in the search for economies of scale, the conglomeration of undergraduate and graduate programs, in the search for economies of scope, and the enormous quality disparity between private the public institutions. The paper aims to illuminate the debate by providing an empirical study on the scale and scope economies by estimating a multi-product university cost structure in Taiwan. The number of colleges and universities in Taiwan has increased rapidly in the last two decades. As of 2003, there were 139 colleges and universities compared with only 26 institutions in 1980. During the same period, the number of college student enrollments increased fivefold, and real educational expenditure per student more than tripled. (1) The variation in unit instructional costs among colleges and universities is substantial. For small institutions, the per-student instruction cost is on average 71% higher than in larger institutions. while public, research-oriented institutions' unit instructional costs are more than twice that of private institutions. (2) The cost differences may be due to the difference in orientation and goals between undergraduate teaching and graduate research. If the larger institutions have lower unit costs. it might be because there are economies of scale and scope. Many empirical studies in the United States and in other developed countries have uncovered factors that account for costs in higher education. However, there are no empirical studies investigating the existence or magnitude of economies of scale and scope or the impact of the dual role of higher education in teaching and in research on the university cost structure in Taiwan. Over the last several decades, the universities in Taiwan have essentially been administered at the discretion of the government. The Ministry of Education oversaw every step of university operations, both in public and in private universities, ranging from student admission and enrollment, faculty hiring and promotion, curriculum design and instruction, to budgeting decisions and administrative appointments. In recent years, the government has gradually lessened its rigid control and allowed universities more administrative and financial independence. This policy change has exerted undue pressure on administrators and policy makers to emphasize productivity, efficiency, and cost-effective management. In this paper, we explore university cost structure by estimating a stochastic frontier cost function. Particular attention is given to the estimation of cost efficiency and to the effect of quality-adjusted outputs on economies of scale and scope. While most empirical studies of higher education production in other countries show some evidence of scale and scope economies, (3) we demonstrate in this paper that they are elusive because the studies have failed to account for quality variation among colleges and universities, in particular, the endogeneity of congestion in facility utilization. In the short run, a university can reduce the average cost of enrollment by tolerating more congested living and learning environments in dormitory rooms and in recreational space, in classrooms and in libraries, etc. Since the congestion factor is endogenous, this leads to a reduced average cost, and it may give a myopic administrator an incentive to engage, at least in the short run, in a policy of overutilizing the university's fixed capital resource. Congestion thus has an implicit long-run cost in higher education production. While many empirical studies have linked the student-faculty ratio and faculty research activity to the quality of university's under-graduate and graduate education, these studies generally ignored how the congestion is linked to the estimation of university cost structure, in particular to scale and scope economies. …

This study adopts a semiparametric smooth coefficient model to evaluate the export–wage premiums, firm size–wage premiums, and the wage gap between skilled and unskilled labor. Particular focus is placed upon widespread evidence indicating that pay levels in ‘large’ and ‘export-oriented’ firms are higher than in their ‘small’ and ‘domestic-oriented’ counterparts. Applying the firm-level data for Taiwanese manufacturing firms, we find a positive export–wage premium for skilled workers and a negative export–wage premium for unskilled workers. The hypothesis of a constant export premium across firm size is rejected. While most of the export–wage premiums for skilled labor can be attributed to the small and medium firms, the large exporting firms have a significant adverse effect on wages for unskilled labor. Moreover, our results suggest that the firm size–wage premiums for skilled workers are larger than those for unskilled workers. The wage gap between the two skill groups is also sensitive to size categories.

This paper develops a general model that addresses the starting point bias in the dichotomous choice evaluation data by incorporating both the anchoring effect and yea-saying bias. The model is applied to a contingent valuation study that evaluated the health benefits of air quality improvement in three major metropolitan areas in Taiwan. The empirical evidence shows a strong anchoring effect but an insignificant yea-saying bias. The results show a serious understated willingness to pay if the biases in anchoring and yea-saying are not controlled.

Individuals save for future uncertain health care expenses. This is less efficient than pooling health risk through insurance. The provision of comprehensive health insurance may raise welfare by providing the missing market to smooth out consumption through the life cycle. We employ a semiparametric smooth coefficient model to examine the effects of the introduction of the National Health Insurance in Taiwan in 1995 on savings and consumption over the life cycle. The idea is to estimate the coefficients of health insurance which vary with age. Our results suggest that younger households are more sensitive to the risk reductions, and that they demonstrate a greater response in the reduction of their precautionary saving. Copyright © 2004 John Wiley & Sons, Ltd.

In this article, we propose a semiparametric smooth coefficient model as a useful yet flexible specification for studying a general regression relationship with varying coefficients. The article proposes a local least squares method with a kernel weight function to estimate the smooth coefficient function. The consistency of the estimator and its asymptotic normality are established. A simple statistic for testing a parametric model versus the semiparametric smooth coefficient model is proposed. An empirical application of the proposed method is presented with an estimation of the production function of the nonmetal mineral industry in China. The empirical findings show that the intermediate production and management expense has played a vital role and is an unbalanced determinant of the labor and capital elasticities of output in production.

In this paper, a switching regression model is developed to analyze farmers' choice behavior and cost efficiency in field plowing arrangement in Taiwan. We find that the decision on the choice of plowing arrangement is determined by a cost comparison between self-plowing and hired-service, and other non-cost considerations, such as the availability of family labor and machinery, education level, non-farm income, age, and regional effects. Across a spectrum of farmer characteristics, empirical results indicate a potentially substantial cost-savings by hiring service for field plowing than by self-plowing. Self-plowing farmers also subject to a significant level of cost inefficiency.

This paper utilizes the average derivative estimation of Stoker (1986) and the pesudo-likelihood estimation of Fan, Li, and Weersink (1996) to estimate a semiparametric stochastic frontier regression, y = g(x) + e, where the function g(.)is unknown and e is a composite error in a standard setting. The proposed semiparametric method of estimation is applied to data on farmers' credit unions in Taiwan. Empirical results show that the banking services of the farmers' credit unions is subject to economies of scale, but high degree of cost inefficiency in operation.

This paper conducts the goodness of fit test of Bartlett (1954) on the stock prices of 12 countries during the period from January 1921 to December 1930 to examine the market efficiency hypothesis. The market efficiency hypothesis is not rejected for most European countries, but it is rejected for non-European countries. This finding is consistent with the documented active speculation that movements of the stock prices in the 1920s were highly volatile, perhaps due to the immaturity of the Canadian and US financial markets.

This paper proposes a methodology to estimate the monetary target and the probability of monetary intervention in Taiwan. The methodology is based on the estimation of a regime switching model. Empirical results show that a target band between 0.95 and 2.17 percent per month has been in effect, and most often the monetary authority has followed a non-interventionist policy. It is probable that the monetary authority engaged in an expansionary policy when intervention was warranted. Adjustments of the rediscount rate by the central bank were found to be consistent with the magnitude of the intervention pressure as predicted by the model.

We examine the effect of a structural break on stationarity tests. It has been shown that stationarity tests suffer from size distortion problems if a structural break exists but is ignored. This problem parallels the power loss problem of unit root tests ignoring an existing break. Nonetheless, the distributions of stationarity tests are asymptotically invariant to the exclusion of the existing break under the alternative hypothesis of a unit root. Our results thus clarify the nature of the effects of a structural break on inference regarding integrated time series.

This paper takes issues with the appropriateness of applying the stochastic frontier analysis (SFA) technique to account for environmental effects and statistical noise in the popular three-stage data envelopment analysis (DEA). A correctly specified SFA model with a censored dependent variable and the associated maximum likelihood estimation (MLE) are proposed. The simulations show that the finite sample performance of the proposed MLE of the censored SFA model is very promising. An empirical example of farmers’ credit unions in Taiwan illustrates the comparison between the censored and standard SFA in accounting for environmental effects and statistical noise.

The financial sector of the Taiwan economy has experienced major structural changes in the past decade. The banking system has been liberalized, a regulated money market has developed, and the foreign exchange market has been deregulated. Nevertheless, Taiwan's financial sector is still characterized by dualism, with the coexistence of both regulated and unregulated (curb) markets. The ratio of financial loans from the unregulated market to those from the regulated market for the total private enterprise has been consistently large, averaging 27.5% for the period 197188.' Interest rates in the unregulated markets of Taiwan are generally much higher than those in the regulated markets. Figure 1 shows the disparity in interest rates between these two markets. The difference in interest rates grew during the 1970s, reaching an annual rate of 23 percent in the second quarter of 1979. Since then, the differential has declined steadily to about 17 percent in 1988.

A model of expected utility maximization is used to study the optimal allocation of a professor's time between research and teaching in a situation where both production activities are subject to uncertainty. It was shown that, in general, a professor's optimal allocation of time under uncertain production departs from the certainty strategy. An explicit model was developed to evaluate the effects of time effort in research and teaching with respect to changes in the degree of uncertainty, the Pratt-Arrow index of risk aversion, and the unit output rewards of research and teaching (for example, “merit pay”).

Sports, like politics and religion, is a subject to be avoided if peace and quiet are to be maximized. Asking a fan "whose team is best" is akin to speculation about whose god is best. Yet an important difference exists: Even if gods have won-lost records, the statistics are not readily available. Sport, however, results in violent disagreements despite well-documented records. Many disputes center on teams with "great potential" somehow wasted or, conversely, those teams with seemingly inferior talent that consistently "play over their heads" and compile excellent records. Does the best team always win? By estimating a production frontier, this paper considers the possibility that a team with the greatest potential may not prevail as league champion due to inefficient use of its available resources. Estimating the production function also allows us to examine the determinants of a team's performance.

OLS and BLUS residuals in the classical linear regression model are compared with respect to testing the normality of regression disturbances. It is shown that in theory both types of residuals suffer from the common problem of lack of independence under the alternative hypothesis of nonnormal disturbances. Further, Monte Carlo experiments appear to show the superiority of OLS over BLUS residuals, as well as the superiority of the Shapiro-Wilk test over other tests studied, when one is testing for normality.

The three prior criteria for linear recursive causal (path) model evaluation are shown to be equivalent to a more general technique. Hotelling's T2 is introduced as a means of evaluating general hypotheses for the entire model, and some consequences of treating the model as a whole are discussed. The “twice standard error” rule is shown to be misleading for a number of reasons. An example of the application of the procedure and the computational technique is given, and some additional applications are suggested.

An expectation-maximum (EM) likelihood algorithm is used to estimate two seemingly unrelated Tobit regressions in which the dependent variables are truncated normal. An illustrative example on the determination of the life-health insurance and pension benefits is also given.

This paper develops the classical view of the extent of markets by introducing explicitly in the analysis the concept of arbitrage costs. Arbitrage or transaction costs imply that market boundaries are essentially stochastic. While a set of products (or regions) may have binding arbitrage conditions (i.e. may be in the same "market") at a given point in time, they may not at another. Thus, in defining a "market", the probability that a set of agents (or regions) would h3ve binding arbitrage conditions has to be assessed. This paper develops an econometric methodology to estimate the. transaction costs required to arbitrage among a given set of products, as well as the probability that that set of products would be bound by binding arbitrage condi tions. Finally, the methodology is applied to wholesale gasoline in the Northeastern part of the United states. Address for Communications: Pablo T. Spiller Herbert Hoover Memorl~l Bldg. 9348 Stanford, CA 94305

The acceleration in the number of US bank failures during recent years provides valuable data for developing bank failure prediction models. A probit models which incorporates various bank structure variables as well as traditional financial ratios is used to explain bank failures during the 1982—3 period. The empirical findings suggest that important information regarding a bank's likelihood of failure is contained in its balance sheet and income accounting data. It is also found that banks which affiliate with holding companies or are larger in size have a significantly lower probability of failure. This suggests that states which impose unit-banking rules or block holding company formation may be adding to failure risks.

The frontier profit functions and the optimum demand for hired labor are estimated separately for small and large farms to test the hypothesis of differential efficiency attributable to size and technology. The optimum demand for hired labor is compared against actual demand to measure efficiency in labor utilization, estimated for individual farms, under both certainty and uncertainty cases. The empirical results are based on 1969–70 farm-level data from Punjab and Haryana States in India. Small farm group is less efficient than large farms in achieving the frontier (maximal) profit. Under the profit maximizing behavior with certainty in production, both small and large farms acquired less than optimal amount of hired labor, but small farms acquired much less than large farms. Uncertainty in production, prices, and risk aversion on the part of farmers seems to discourage the demand for hired labor on the basis of estimates using the “safety-first” risk model. Small farms appeared to experience a higher degree of uncertainty measured by comparative variability in production. Even after adjustment for greater uncertainty and risk aversion, small farms remained less efficient in demand for labor, treating other inputs as fixed. Les fonctions frontalieres de profit et la demande optimale pour la main-d'oeuvre ensasee sont estimees separement pour des petites et grandes exploitations agricoles pour verifier l'hypothese d'efficacite differentielle attribuable e l'importance de l'exploitation et a la technologie. La demande optimale pour la main-d'oeuvre engagee est com-paree contre la demande actuelle pour mesurer l'efficacite dans l'utilisation de la main-d'oeuvre. Cette demande est estimee pour des exploitations agricoles individuelles, dans les deux cas de certitude et d'incertitude. Les resultats empiriques sont bases sur les donnees au niveau d'exploitation agricole pendant les annees 1969 e 1970 des Etats Punjab et Haryana de l'lnde. Un petit groupe d'exploitations agricolesest moins efficace que des grandes exploitations agricoles pour realiser un profit (maximal) frontalier. Sous les manieres qui portent au profit maximum avec certitude de production, les petites et grandes exploitations agricoles toutes les deux obtiennent un montant d'engages moins que optimal, mais les petites exploitations agricoles en obtiennent beaucoup moins que les grandes exploitations agricoles. L'incertitude de production, de prix, et l'aversion de risque de la part des fermiers semblent decourager la demande pour la main-d'oeuvre engagee en se ba-sant sur les evaluations qui viennent du modele de risque “securite d'a-bord.” Les petites exploitations agricoles semblent experimenter un plus haut degre d'incertitude mesurepar la variabilite comparative de production. Meme apres l'ajustage pour une plus grande incertitude et l'aversion de risque, les petites exploitations agricoles demeurent moins efficaces pour la demande de main-d'oeuvre, traitant les autres entries comme fixes.

Draper, N. R., and H. Smith, Applied Regression Analysis (New York: John Wiley and Sons, 1966). Geary, R. C., "Relative Efficiency of Count of Sign Changes for Assessing Residual Autoregression in Least Squares Regression," Biometrika 57 (April 1970), 123-127. , "Two Exercises in Simple Regression," The Economic and Social Review 3 (July 1972), 551-559. Granger, C. W. J., and P. Newbold, "Spurious Regressions in Econometrics," Journal of Econometrics 2 (July 1974), 111-120. Johnson, James A., and Ernest H. Oksanen, "SocioEconomic Determinants of the Consumption of Alcoholic Beverages," Applied Economics 6 (Dec. 1974), 293-301. Kendall, Maurice G., and Alan Stuart, The Advanced Theory of Statistics, vol. 2, second edition (London: Charles Griffin & Company Limited, 1967). Koopmans, Tjalling C., "The Bias in Single-Equation Methods of Estimating Behavior Equations Relating to a Small Sector of the Economy," Cowles Commission Discussion Paper, Statistics, no. 336 (dittoed) (Chicago, 1949). Maddala, G. S., "The Use of Variance Components Models in Pooling Cross Section and Time Series Data," Econometrica 39 (Mar. 1971), 341-358. Nerlove, Marc, "Further Evidence on the Estimation of Dynamic Economic Relations from a Time Series of Cross Sections," Econometrica 39 (Mar. 1971a), 359-382. " "A Note on Error Components Models," Econometrica 39 (Mar. 1971 b), 383-396.

During the pre-green revolution years in India, agricultural production, especially of foodgrains, was substantially below the growth in demand arising from income and population growth. Consequently, India required continual and substantial import of food grains under the Public Law (P.L.) 480 program [2, 29]. During the post-green revolution years, the country has built modest food reserves. But India is continuously faced with a challenge of feeding a fast growing population. Even during the post-green revolution period, due to occasional unfavorable weather, foodgrain production has fallen short of its demand, and India had to buy foodgrains from the world market with hard currency. The government is naturally concerned with maintaining the growth in agricultural production above the growth in potential demand. It has been encouraging research to evolve improved agricultural technologies, but it is a slow process. An equally important aim should be to promote production efficiency, at farm-level, under the existing technology. Consequently, economic policy in India has largely been concerned with the efficiency of agricultural production, alternative forms of land tenure, and agrarian organizations. A country like India, which has shortage of all factors of production except labor, obviously cannot afford to make an inefficient use of resources. It is, therefore, important to estimate the level of technical efficiency at the farm-level, and to identify the sources of such inefficiency. Such information is important for formulating appropriate policies for reducing the level of technical inefficiency. Since the release of data from the Farm Management Studies of the Indian Ministry of Food and Agriculture in the mid 1950s, numerous studies have been devoted to the

with the definition that e, = V, U, being the composite error. Various alogrithms such as the Davidon-Fletcher-Powell method are then used for finding the optimal values of the parameter vector 0' = (B', ao, oa). Once the estimates of 0 are obtained, Jondrow, Lovell, Materov and Schmidt (JLMS) [4] recently propose a method of decomposing the estimated error , Y, B'X, into separate components V, and U,. The proposed decomposition method is based on the derivation of the conditional distribution of Ut given the composite

The existing analyses of the general problem of estimating economic relations between a dependent variable Y and a set of independent variables X, e.g., Y = Y(G(X), u), where u is a stochastic error, usually focus on the formulation of the "deterministic part," G(X), of the relationship while little attention is paid to the specification and interpretation of the stochastic distrubance term, u, Two commonly employed specifications, Y = G(X) + u and Y = G(X)eu, appear when G(X) is linear in the parameters. Since nothing a priori is known in practice about the form of the disturbance, a more general specification of the error term based on a family of power transformations, including both additive and multiplicative forms as special cases, has been proposed [2; 4; 6; 9; 10; 11]. However, economic theory is often concerned with the mathematical properties of the deterministic part G (X) and it is natural to ask whether the conditional mean function, E(Y X), preserves these properties. It is well known that if u is normallly distributed the conditional mean function does not equal G (X) when the disturbance is multiplicative. Suppose, for example, that the deterministic part G(X) represents the market demand schedule derived from consumer utility maximization in a non-stochastic world. The actual individual demand schedule Y(G(X), u), however, is a sto

Box, George E. P., and David R. Cox, "An Analysis of Transformations," Journal of the Royal Statistical Society, series B, 26 (Apr. 1964), 211-243. Boyes, W. J., "An Application of Specification Error Tests-The Liquidity Trap," Manchester School of Economics and Social Studies (1978), 139-151. Chang, Hui-shyong, "Functional Forms and the Demand for Meat in the United States," this REVIEW 59 (Aug. 1977), 355-359. Greenfield, J. N., "Effects of Price Changes on the Demand for Meat," Monthly Bulletin of Agricultural Economics and Statistics 23(12) (1974), 1-8. Ramsey, James B., "Limiting Functional Forms for Demand Functions: Tests of Some Specific Hypotheses," this REVIEW 56 (1974), 468-477.

where Y is an N X 1 observation vector of the dependent variable, X is an N X K observation matrix with rank K of regressors, and e is the N X 1 vector of random disturbances. The disturbances are assumed to be temporally independent with constant covariance matrix a2IN. It has been shown that the distribution of the least-square residual vector e is singular normal with zero mean vector and covariance matrix