Showing papers on "Tobit model published in 2006"

An Ordered Tobit Model of Market Participation: Evidence from Kenya and Ethiopia

Abstract: Do rural households in developing countries make market participation and volume decisions simultaneously or sequentially? This article develops a two-stage econometric method to test between these two competing hypotheses regarding household-level marketing behavior. The first stage models the household's choice of whether to be a net buyer, autarkic, or a net seller in the market. The second stage models the quantity bought (sold) for net buyers (sellers) based on observable household characteristics. Using household data from Kenyan and Ethiopian livestock markets, we find evidence in favor of sequential decision making, the welfare implications of which we discuss.

Measuring the Cost Efficiency of International Tourist Hotels in Taiwan

Abstract: This study employs data envelopment analysis (DEA) to evaluate the relative cost efficiency of 49 international tourist hotels in Taiwan. The study uses five different measures: overall efficiency (OE), allocative efficiency (AE), technical efficiency (TE), scale efficiency (SE) and pure technical efficiency (PTE). Applying efficiency measures derived from the DEA estimation, hotel efficiency determinants are evaluated using the Tobit regression model. A bootstrapping technique is applied to overcome the interdependency problem of the DEA efficiency scores adopted in the regression analysis. The empirical results demonstrate that the international tourist hotel industry in Taiwan is inefficient, with most efficiency losses attributable to technical inefficiencies, of which scale inefficiencies are the primary cause � the scale of operations of international tourist hotels in Taiwan being too small to enable the cost-savings associated with larger-scale operations. The Tobit regression results indicate that the proportion of foreign individual travellers (FIT), online transaction function (WEB) and franchising (HOTELTYPE) are related to a better performance of international tourist hotels in Taiwan. The number of years a hotel has been operating (AGE) is not significantly related to any of the efficiency measures.

A Sample Selection Approach to Censored Demand Systems

Abstract: The multivariate sample selection model is extended to a nonlinear equation system with partial selection and applied to household meat consumption in China. Elasticity estimates differ from those obtained from conventional maximum likelihood and Tobit estimates. Chinese meat products are gross complements while net substitution also exists in some cases. The use of micro survey data has been popular in estimating consumer demand equations. Important features of microdata include censored dependent variables. Estimation procedures for censored consumer demand systems include the primal (Kuhn-Tucker) approach of Wales and Woodland (1983), dual (virtualprice) approach of Lee and Pitt (1986), and the Tobit system (Amemiya 1974) estimated by generalized maximum entropy (Golan, Perloff, and Shen 2001) and maximum simulated likelihood (Dong, Gould, and Kaiser 2004; Yen, Lin, and Smallwood 2003) procedures. Less efficient alternatives include the quasi-maximum likelihood estimator (Yen, Lin, and Smallwood 2003), the generalized method of moments estimator (Meyerhoefer, Ranney, and Sahn 2005), and a number of two-step estimators (Heien and Wessells 1990; Perali and Chavas 2000; Shonkwiler and Yen 1999). Yen (2005) recently proposed a maximum likelihood (ML) procedure for the multivariate sample selection model (MSSM), an extension of the bivariate sample selection model (Heckman 1979), which had motivated the procedures of Heien and Wessells (1990) and Shonkwiler and Yen (1999). The MSSM was developed in the context of linear equations and, in addition, is not strictly applicable for a partially selective equation system, viz.,

Determinants of fertilizer use on maize in Eastern Ethiopia: A weighted endogenous sampling analysis of the extent and intensity of adoption

Abstract: Factors influencing the extent and intensity of fertilizer adoption on maize production in Ethiopia were analyzed. A Weighted Endogenous Sampling Maximum Likelihood estimator was used in the specification of a Probit and Tobit fertilizer adoption models. The results have important implications for the formulation of policies and programs targeted to promotion of fertilizer use in small-scale maize production. Those include improved road infrastructure, consideration of weather related crop failure insurance programs, development of drought tolerant cultivars and targeting particular farmer groups.

Determinants of the future level of use of electronic marketplaces: The case of Canadian firms

Abstract: Based on the literature dealing with the diffusion of innovation and with information systems, and building on the emerging concepts in electronic commerce (e-commerce), this paper aims at assessing the influence of various factors on firms' future level of use of electronic marketplaces (e-marketplaces). This theoretical model is tested on data collected from 1,200 senior managers in Canadian firms. Findings indicate that a firm's past experience in e-commerce, as well as the factors relating to its business relationships ultimately affect its future use of e-marketplaces. Results of TOBIT regressions also show that the complexity of sophisticated e-commerce implementations is negatively correlated with the future level of use of e-marketplaces, and that consultants and other experts play an essential role in encouraging and facilitating the use of this new type of electronic platform. Finally, our survey data demonstrate that the relative influence of some determinants differs according to the firms' size.

Persistence of Innovation in Dutch Manufacturing: Is it Spurious?

Abstract: This paper studies the persistence of innovation and the dynamics of innovation output in Dutch manufacturing using firm data from three waves of the Community Innovation Surveys (CIS), pertaining to the periods 1994-1996, 1996-1998, and 1998-2000. We estimate by maximum likelihood a dynamic panel data type 2 tobit model accounting for individual effects and handling the initial conditions problem. We find that there is no evidence of true persistence in achieving technological product or process innovations, while past shares of innovative sales condition, albeit to a small extent, current shares of innovative sales.

Determinants of the Innovation Process: An Empirical Test for the Portuguese Manufacturing Industry

Abstract: The aim of this paper is to analyze the determinants of the main phases of the innovation process in Portuguese manufacturing firms. The analysis will adopt as its main frame of reference an interactive model of the innovation process, on which empirical tests will be carried out, making use of tobit and probit models and simultaneous equation systems. It is broadly concluded that the relationships shown between the main variables that are typical of the innovation process in the context of Portuguese manufacturing firms are tenuous and unsystematic.

A Classification of Dutch Manufacturing based on a Model of Innovation

Abstract: The paper studies the degree of homogeneity of innovative behavior in order to determine empirically an industry classification of Dutch manufacturing that can be used for policy purposes. Defining homogeneity in terms of an economic model distinguishes our classification from existing taxonomies such as those of the OECD, Pavitt and the various classifications based on a principal components analysis. We use a two-limit tobit model with sample selection, which explains the decisions by business enterprises to innovate and the impact these decisions have on the share of innovative sales. The model is estimated for eleven industries based on the Dutch Standard Industrial Classification (SBI 1993). A likelihood ratio (LR) test is then performed to test for equality of the parameters across industries. We find that Dutch manufacturing consists of three groups of industries in terms of innovative behavior, a high-tech group, a low-tech group and the industry of wood. The same pattern shows up in the three Dutch Community Innovation Surveys.

Transportation Expenditures and Ability to Pay: Evidence from Consumer Expenditure Survey

Abstract: Data at several levels of aggregation and spatial resolution show that mobility (measured by different outcomes such as vehicle miles traveled and automobile ownership) increases with income. It is equally likely that, in turn, investments in mobility (purchase and operation of private automobiles, consumption of public transportation services) allow greater quality of life in general and the ability to increase one's income. This possibly circular relationship is explored by using the Consumer Expenditure Survey (CEX) data set. Single-equation Tobit models of annual household transportation expenditures are posited with, in the first case, annual before-tax income and, in the second case, annual total household-level expenditures as a proxy for permanent income. With a variety of demographic, community and spatial, economic, family, and life-cycle conditions of the household controlled, it is found that permanent incomes explain mobility investments better than annual incomes. However, mobility investmen...

Foreign direct investment in Brazil and home country risk

Abstract: This study looks into the factors that explain foreign direct investment in Brazil by country of origin of investment. Based on a sample of more than 100 countries that invested and have not yet invested in Brazil, multiple estimation techniques, such as the Tobit, Heckit and Probit, are used to isolate the effect of country risk on outward foreign direct investment. In sharp contrast to the findings of previous studies on the effect of home country risk on foreign investment in the United States, the findings in this paper reveal that less risky countries invest more in Brazil. These results are controlled for size of the home country, distance, trade intensity and previous investments abroad. A simple out of sample check shows that the model correctly predicts probability of investing for a large number of countries. The existing literature does not document these results.

Modeling fresh organic produce consumption: a generalized double-hurdle model approach

Abstract: Using actual retail data, this study is intended to profile consumers' social economic characteristics related to the growth of the fresh organic produce market with a generalized double-hurdle model. The nested test shows that the above model performs significantly better than Cragg's independent double-hurdle model and Tobit model.

Weather Risk and the Off-Farm Labor Supply of Agricultural Households in India

Abstract: As one of the measures to smooth income, this paper focuses on the diversification of labor allocation across activities. A key feature of this paper is that it pays particular attention to differences in the covariance between weather risk and agricultural wages and between weather risk and nonagricultural wages. We estimate a multivariate tobit model of labor allocation using household data from rural areas of Bihar and Uttar Pradesh, India. The regression results show that the share of the off­farm labor supply increases with the weather risk, and the increase is much larger in the case of nonagricultural wage work than in the case of agricultural wage work. Simulation results based on the regression estimates show that the sectoral difference is substantial, implying that empirical and theoretical studies on farmers' labor supply response to risk should distinguish between the types of off-­farm work involved.

Tobit Model Estimation and Sliced Inverse Regression

Abstract: It is not unusual for the response variable in a regression model to be subject to censoring or truncation. Tobit regression models are a specific example of such a situation, where for some observations the observed response is not the actual response, but rather the censoring value (oftenzero), and an indicator that censoring (from below) has occurred. It is well-known that the maximum likelihood estimator for such a linear model (assuming Gaussian errors) is not consistent if the error term is not homoscedastic and normally distributed. In this paper we consider estimation in the Tobit regression context when those conditions do not hold, as well as when the true response is an unspecified nonlinear function of linear terms, using sliced inverse regression (SIR). The propertiesof SIR estimation for Tobit models are explored both theoretically and based on Monte Carlo simulations. It is shown that the SIR estimator has good properties when the usual linear model assumptions hold, andcan be much more effective than other estimators when they do not. An example related to household charitable donations demonstrates the usefulness of the estimator.

Hours Supplied of Cambodian Child Labor and School Enrolment: Simple Theoretical and Empirical Evidence for Policy Implications

Abstract: This paper aims to seek the determinants of hours supplied of child labor in Cambodia On the basic of simple theoretical and empirical model building from existing literatures, we have estimated the latent decision of parents on hours supplied of their children Because this hours supplied are censored at zero hours and depend on the enrolment status of each individual child, therefore, we use simultaneous tobit and probit to find the determinants of hours supplied and enrolment of children by the Maximum Likelihood estimate Given a structure of our model, it allows us to estimate marginal effects of latent status of children which is rarely discussed in literature and it enable us to see dynamics of child labor in Cambodia We found that only after completing primary education, thus parents' education has impact on the probability of child's schooling and reduce hours worked of the child Increasing household's income does increase the human capital formation of the child Importantly child labor (except worse form of child labor) does help increasing human capital formation of the child in the context of developing economy like Cambodia

Studies in the book of Tobit : a multidisciplinary approach

Abstract: 1. Tobit as an expression of the Deuteronomist writer, Margaret Barker (former President of the British Old Testament Society, UK) 2. The insertion of Jonah in Vatincanus Tobit 14, Mark Bredin (Westcott House, Cambridge, UK) 3. The Ceriani Latin text, S. Galicole (Aberdeen University, UK) 4. Rembrandt's depiction of the Tobit story, Trevor Hart (St Andrews University, UK) 5. The Structural relationship between Judith and Tobit, Hans Jogen Ludager 6. Eating and Drinking in Tobit, N. MacDonald (St Andrews University, UK). 7. Kierkergard and Tobit, Hugh Pyper (Sheffield University, UK) 8. Neglected Versions of Tobit, Stuart Weeks (University of Durham, UK) 9. Dead Sea Fragments of Tobit, Albert Lukaszewski (an independent scholar).

A tobit analysis of propensity to discontinue adoption of agricultural technology among farmers in southwestern nigeria

Abstract: While much work has been done on the factors determining the adoption of agricultural technologies, little research has been conducted on the factors that predispose farmers to discontinue the adoption of innovation. Following a survey of arable crop farmers in two states of southwestern Nigeria, econometric analysis was conducted in order to identify variables significant in the farmers’ discontinuance behaviour. The variables included in the study are Attitude, Extension visit, Feedback provision, Marketability and Input availability. Tobit model was estimated on the data collected during the 2002 growing season. From the estimation, significant variables leading to discontinuance of improved maize and cowpea varieties were identified. Foremost among them is extension visits.

Modelling student performance in a tertiary preparatory course

Abstract: []: In this dissertation a review of the literature as it applies to the modelling of educational performance data is undertaken. Statistical linear models, including the novel Beta, Tweedie and Tobit regression models, are then applied to the performance data of students who have undertaken a preparatory mathematics course. These models are then critically reviewed and compared with the commonly used standard linear regression model. Issues that arise from the application of statistical linear models to educational performance data are then explored. For example, the effects of non-Normality, which characterizes educational performance data, and the presence of large numbers of students who fail to complete the course (a characteristic of this particular context), are examined and reported. Both of these effects can violate the underlying assumptions of the standard linear regression model. Simulation studies are then used to assess the appropriateness of the linear model when it is applied under the condition of non-Normality and the presence of large numbers of missing observations. Findings from this study indicate that issues relating to model effectiveness are clouded in the educational context by typically large values of the error variance (high noise) and the difficulty in finding suitable performance predictors. Educational models of performance typically lack statistical power, so that in many instances it doesn’t matter what model is applied to the data. Nevertheless, the study highlights many reasons why models alternative to the standard linear regression model should be applied to such data. For example, in situations where the effect is not constant over the entire domain of the explanatory variable, a linear model based upon the beta distribution will be much more appropriate. Similarly, in situations where the performance data contains exact zeros (for example the performance of students who withdraw from the course without providing any measure of achievement) it is more appropriate to use a Tweedie linear model than the standard linear regression model.

Child labor response to household participation in credit schemes and household income-generating activities in peru

Abstract: This study contributes to the understanding of the impacts of household borrowing and household income-generating activities on child labor in Peru. Peru lends itself as an interesting case to study given the rise of self-employment, the rapid growth of microfinance and the increase of child labor over the last decade. Using a probit and a tobit model, this study shows that the relationship between borrowing and child labor is not unequivocally negative. Across models and samples, the results suggest that children in households that borrowed for the household enterprise were more likely to work than children in households that did not borrow. The study found the opposite effect for borrowing for the farm. The effects of borrowing for consumption on child labor were mixed across models and samples. This study also found a robust positive relationship between ownership of agricultural and non agricultural enterprise and child labor. Income-generating activities found to increase child labor were agriculture, hotels and restaurants, retail, manufacturing, and domestic work. Although issues of endogeneity of borrowing and child labor limit the internal validity of these estimates, mixed results from the regression analysis should encourage future research. One policy implication gleaned from the study is that expanding access to credit to the poor in order to encourage micro-enterprise activity may potentially increase child labor. This implies the need to think more carefully about the design of micro-credit programs, which could incorporate built-in conditionalities to make access to micro-credit conditional on child school attendance.

A semi-parametric modeling of firms' R&D expenditures with zero values

Abstract: Modeling firms' R&D expenditures often become complicated due to the zero values reported by a significant number of firms. The maximum likelihood (ML) estimation of the Tobit model, which is usually adopted in this case, however, is not robust to heteroscedastic and/or non-normal error structure. Thus, this paper attempts to apply symmetrically trimmed least squares estimation as a semi-parametric estimation of the Tobit model in order to model firms' R&D expenditures with zero values. The result of specification test indicates the semi-parametric estimation outperforms the parametric ML estimation significantly.

Choice of Crops and Employment Uncertainty in the Off-farm Labor Market

Abstract: Cultivator households in some developing areas use off-farm labor supply as an insurance against crop income shocks, whilst employment is uncertain in this off-farm labor market. This paper hypothesizes that, given limited opportunities for ex post consumption smoothing, employment uncertainty influences risk-averse households’ crop choice decisions-- they would opt for more conservative crop choices in case they expect unfavorable supply opportunities in the labor market. A two-period stochastic dynamic programming model is developed. A panel data set from the ICRISAT survey of the semi-arid tropics of India is examined. Estimation is based on random effects and fixed effects Tobit specifications. Estimation results indicate statistically significant impact of household expectation of harvesting period male unemployment rates on ex ante crop choices. Results also indicate strong influence of household irrigated land share on crop choices.

The effect of national policies and labor markets on land use decisions in developing countries: An application of maximum simulated likelihood to a system of censored acreages with panel data

Abstract: This paper estimates land use responses of households to relative output prices and wages, using panel data from the Philippines. We present multi-output profit maximizing model to elicit the role of relative prices on land allocation between crops and fallowing. We estimate systems of random effects Tobit acreage equations using maximum simulated likelihood technique. The results show that rising return to labor and management intensive crop reduces land expansion. In addition rising wages also reduce agricultural expansion. The results reveal a potential role for market based policies in shaping environmental outcomes in developing countries.

Persistence of Innovation in Dutch Manufacturing: Is it Spurious?

Abstract: This paper studies the persistence of innovation and the dynamics of innovation output in Dutch manufacturing using firm data from three waves of the Community Innovation Surveys (CIS), pertaining to the periods 1994-1996, 1996-1998, and 1998-2000. We estimate by maximum likelihood a dynamic panel data type 2 tobit model accounting for individual effects and handling the initial conditions problem. We find that there is no evidence of true persistence in achieving technological product or process innovations, while past shares of innovative sales condition, albeit to a small extent, current shares of innovative sales.

Maximum Likelihood Estimation of Input Demand Models with Fixed Costs of Adjustment

Abstract: Traditional models of input demand rely upon convex and symmetric adjustment costs. However, the fortune of this highly restrictive approach is due more to analytical convenience than to empirical relevance. In this note we examine the model under more realistic hypothesis of fixed costs, show that it can be cast in the form of a Double Censored Random Effect Tobit Model, derive its likelihood function, and finally evaluate the performance of the ML estimators through a Monte Carlo experiment. The performances, although strongly dependent on the degree of censoring, appear to be promising.