Maximum Simulated Likelihood Estimation Research Articles

Agricultural innovations and food security in Malawi: Gender dynamics, institutions and market implications

The main objective of this paper was to analyze the driving forces that enhance farm households' decision to adopt agricultural innovations and the implications of these decisions on household food security. Maize variety diversity, soil and water conservation and improved storage or combinations of these accounted for 98% of agricultural innovations followed by the farmers in the study area. Using data from 892 randomly sampled households obtained from six districts of Malawi, the research employed a maximum simulated likelihood estimation of a multinomial endogenous treatment effect model to account for unobservable heterogeneity that influences technology adoption decision and maize productivity. Results revealed considerable heterogeneity in the choice of agricultural innovations practiced by smallholder farmers ranging from none to all practices within their fields. For instance 24% adopted improved maize varieties and storage; 14% improved maize, soil and water conservation, 14% improved maize only and 36% practiced all the technologies while 12% practiced none. In addition, the results showed that spouse's education, marital status, religion and informal networks are important factors in shaping women's participation in agricultural technology choice decisions. Exposure to production shocks such as drought, access to input and output markets, land size and gender of the plot manager of the plots explained the variation in farmers' propensities to adopt agricultural innovations. Respondents from drought prone areas, with small land size had higher incentives to adopt all the agricultural technologies as risk minimizing strategies. Conversely, farmers from high potential regions with bigger land sizes and higher asset and crop diversity indexes were less likely to adopt these agricultural innovations. Overall, adoption of improved maize and storage technologies resulted in significant increase in maize output per unit area though it may be important for researchers and policy makers to understand the social and institutional settings in which the technology is targeted, to benefit both men and women farmers equally.

Variety and Experience: Learning and Forgetting in the Use of Surgical Devices

We use a unique, hand-collected dataset to examine learning and forgetting in hip replacement surgery as a function of a surgeon’s experience with specific surgical device versions and the time between their repeat uses. We also develop a generalizable method to correct for the left-censoring of device-version-specific experience variables that is a common problem in highly granular experience data, using Maximum Simulated Likelihood Estimation (MSLE) with simulation over unobservables conditional on observables. Even for experienced surgeons, the first usage of certain device versions can result in at least a 32.4% increase in surgery duration, hurting quality and productivity. Furthermore, with the passage of time, surgeons can forget knowledge gained about the use of particular devices. For certain devices, when the time gap between repeat uses increases from its median to its 75th percentile, surgery duration increases by about 3.4%. The high productivity and quality costs associated with device variety suggest that the gain from a new device design needs to be large enough to compensate for the short term disadvantages of starting up on a new learning curve and of increasing the chances of knowledge depreciation over time.

Persistent and transient productive inefficiency: a maximum simulated likelihood approach

The productive efficiency of a firm can be seen as composed of two parts, one persistent and one transient. The received empirical literature on the measurement of productive efficiency has paid relatively little attention to the difference between these two components. Ahn and Sickles (Econ Rev 19(4):461–492, 2000) suggested some approaches that pointed in this direction. The possibility was also raised in Greene (Health Econ 13(10):959–980, 2004. doi: 10.1002/hec.938 ), who expressed some pessimism over the possibility of distinguishing the two empirically. Recently, Colombi (A skew normal stochastic frontier model for panel data, 2010) and Kumbhakar and Tsionas (J Appl Econ 29(1):110–132, 2012), in a milestone extension of the stochastic frontier methodology have proposed a tractable model based on panel data that promises to provide separate estimates of the two components of efficiency. The approach developed in the original presentation proved very cumbersome actually to implement in practice. Colombi (2010) notes that FIML estimation of the model is ‘complex and time consuming.’ In the sequence of papers, Colombi (2010), Colombi et al. (A stochastic frontier model with short-run and long-run inefficiency random effects, 2011, J Prod Anal, 2014), Kumbhakar et al. (J Prod Anal 41(2):321–337, 2012) and Kumbhakar and Tsionas (2012) have suggested other strategies, including a four step least squares method. The main point of this paper is that full maximum likelihood estimation of the model is neither complex nor time consuming. The extreme complexity of the log likelihood noted in Colombi (2010), Colombi et al. (2011, 2014) is reduced by using simulation and exploiting the Butler and Moffitt (Econometrica 50:761–764, 1982) formulation. In this paper, we develop a practical full information maximum simulated likelihood estimator for the model. The approach is very effective and strikingly simple to apply, and uses all of the sample distributional information to obtain the estimates. We also implement the panel data counterpart of the Jondrow et al. (J Econ 19(2–3):233–238, 1982) estimator for technical or cost inefficiency. The technique is applied in a study of the cost efficiency of Swiss railways.

Impact of liquidity risk on variations in efficiency and productivity: A panel gamma simulated maximum likelihood estimation

The objective of this study is to assess the importance of short- and long-run liquidity or debt risk on technical inefficiency and productivity. An alternative panel estimator of normal-gamma stochastic frontier model is proposed using a simulated maximum likelihood estimation technique. Empirical estimates indicate a difference in the parameter coefficients of gamma stochastic production function, and heterogeneity function variables between the pooled and the Swamy–Arora panel models. The results from this study show short and long run risk or variations in liquidity or debt-servicing ratio play an important role in explaining the variance in efficiency and productivity.

Simulated maximum likelihood estimation for discrete choices using transformed simulated frequencies

Many existing methods of simulated likelihood for discrete choice models require additive errors that have normal or extreme value distributions. This paper focuses on a situation where the model does not admit such additive errors so that the popular method of GHK or logit estimation is not applicable. This paper proposes a new method of simulated likelihood that is free from simulation bias for each finite number of simulations, and yet flexible enough to accommodate various model specifications beyond those of additive normal or logit errors. The method begins with the likelihood function involving simulated frequencies and finds a transform of the likelihood function that identifies the true parameter for each finite simulation number. The transform is explicit, containing no unknowns that demand an additional step of estimation. The estimator achieves the efficiency of MLE when the simulation number increases fast enough. This paper presents and discusses results from Monte Carlo simulation studies of the new method.

Bayesian procedures as a numerical tool for the estimation of an intertemporal discrete choice model

Discrete choice models usually require a general specification of unobserved heterogeneity. In this paper, we apply Bayesian procedures as a numerical tool for the estimation of a female labor supply model based on a sample size that is typical for common household panels. We provide two important results for the practitioner: First, for a specification with a multivariate normal distribution for the unobserved heterogeneity, the Bayesian MCMC estimator yields almost identical results as a classical maximum simulated likelihood (MSL) estimator. Second, we show that when imposing distributional assumptions that are consistent with economic theory, e.g., log-normally distributed consumption preferences, the Bayesian method performs well and provides reasonable estimates, while the MSL estimator does not converge. These results indicate that Bayesian procedures can be a beneficial tool for the estimation of intertemporal discrete choice models.

Efficient estimation of conditionally linear and Gaussian state space models

An efficient estimation procedure for conditionally linear and Gaussian state space models is developed. Efficient importance sampling together with a Rao-Blackwellization step are used to construct a highly efficient estimation method that produces continuous approximations to the likelihood function, greatly enhancing simulated maximum likelihood estimation. An application where the unobserved component stochastic volatility model is used to model inflation is proposed and parameter estimates for all G7 countries are shown to be statistically different from calibrated values used in the literature. The estimated model is used to forecast inflation of these countries.

Governance Strategies and Welfare Effects: Vertical Integration and Contracts in the Catfish Sector in Vietnam

Using an original dataset from the Vietnamese catfish sector, we study the impact of vertical coordination options on household welfare and the implications of different stages of vertical coordination for the success of the whole sector. The welfare gain from contract farming and employment on processor-owned estate farms is estimated using a maximum simulated likelihood estimator. Our results show positive welfare effects from participating in contract farming, but not from employment on processor-owned estate farms. The results imply that contract farming presents opportunities for economic growth, but additional effort is required to make the contracts more accessible to smallholders.

Comparison of continuous and discrete representations of unobserved heterogeneity in logit models

Representing unobserved heterogeneity or taste variations in Marketing Analytic behavioral-choice analysis is receiving increasing attention in the estimation of consumer-choice modeling. The mixed logit (MXL) model, which incorporates random coefficients into the multinomial logit model, has been widely adopted for this purpose. The most commonly adopted method in this context is to assume that the random coefficient follows a continuous, unimodal distribution, and the parameters of the distribution as well as the other parameters for the model can be obtained using maximum simulated likelihood estimation. In this article, we refer to this method as the continuous mixed logit (CMXL) model. This method requires the a priori assumption that the distribution of the random coefficient is continuous and, usually, unimodal. One way to relax this assumption is to estimate the distribution nonparametrically, by assuming a discrete distribution with finite support. We refer to this approach as the discrete mixed logit (DMXL) model. Based on the DMXL model, we propose the mass-point MXL model as one alternative to the continuous-distribution assumption and compare its performance with the latent class logit model (LCLM), also part of the DMXL family. Either model can be used to represent unobserved heterogeneity with a discrete distribution in the parameter space. In this article, we conduct empirical analyses and compare the continuous and discrete representations of unobserved heterogeneity in logit models using simulated data with known parameters and real data with discrete choices. Analysis with simulated data provides insights on the ability to distinguish between continuous and discrete parameter distributions and a better understanding of the goodness-of-fit measures used in evaluating model performance with real data. From the simulation study, we find that when the data is generated from a normal distribution, the CMXL model with the unimodal-distribution assumption is preferred to the DMXL mode. From the real data analysis, we find that the CMXL model fails to recover heterogeneity that is identified by the DMXL model. In conclusion, we suggest that when estimating a random-coefficient MXL model, one should start with a CMXL model, but should not accept a ‘no heterogeneity’ conclusion without estimating a series of DMXL models using either the mass-point MXL model or the LCLM with different starting values.

Simulation Estimation of Dynamic Panel Discrete Choice Models Using the $$t$$ t Distributions

In this paper a practical robust simulation estimator is proposed for the dynamic panel data discrete choice models using the $$t$$ t distribution. The maximum simulated likelihood estimators are obtained through a recursive algorithm formulated by Geweke---Hajivassiliou---Keane simulators. Monte Carlo experiments indicate that the proposed robust simulation estimators perform well under the errors with longer than normal tails for a small simulation size, even with the initial conditions problem.

Persistent and Transient Productive Inefficiency: A Maximum Simulated Likelihood Approach

The productive efficiency of a firm can be seen as composed of two parts, one persistent and one transient. The received empirical literature on the measurement of productive efficiency has paid relatively little attention to the difference between these two components. Ahn, Good and Sickles (2000) suggested some approaches that pointed in this direction. The possibility was also raised in Greene (2004), who expressed some pessimism over the possibility of distinguishing the two empirically. Recently, Colombi (2010) and Kumbhakar and Tsionas (2012), in a milestone extension of the stochastic frontier methodology have proposed a tractable model based on panel data the promises to provide separate estimates of the two components of efficiency. The approach developed in the original presentation proved very cumbersome actually to implement in practice. Colombi (2010) notes that FIML estimation of the model is ‘complex and time consuming.’ In the sequence of papers, Colombi (2010), Colombi et al. (2011, 2014), Kumbhakar, Lien and Hardaker (2012) and Kumbhakar and Tsionas (2012) have suggested other strategies, including a four step least squares method. The main point of this paper is that full maximum likelihood estimation of the model is neither complex nor time consuming. The extreme complexity of the log likelihood noted in Colombi (2010), Colombi et al. (2011, 2014) is reduced by using simulation and exploiting the Butler and Moffitt (1982) formulation. In this paper, we develop a practical full information maximum simulated likelihood estimator for the model. The approach is very effective and strikingly simple to apply, and uses all of the sample distributional information to obtain the estimates. We also implement the panel data counterpart of the JLMS (1982) estimator for technical or cost inefficiency. The technique is applied in a study of the cost efficiency of Swiss railways.

Gradient-based simulated maximum likelihood estimation for Lévy-driven Ornstein–Uhlenbeck stochastic volatility models

This paper studies the parameter estimation problem for Ornstein–Uhlenbeck stochastic volatility models driven by Lévy processes. Estimation is regarded as the principal challenge in applying these models since they were proposed by Barndorff-Nielsen and Shephard [J. R. Stat. Soc. Ser. B, 2001, 63(2), 167–241]. Most previous work has used a Bayesian paradigm, whereas we treat the problem in the framework of maximum likelihood estimation, applying gradient-based simulation optimization. A hidden Markov model is introduced to formulate the likelihood of observations; sequential Monte Carlo is applied to sample the hidden states from the posterior distribution; smooth perturbation analysis is used to deal with the discontinuities introduced by jumps in estimating the gradient. Numerical experiments indicate that the proposed gradient-based simulated maximum likelihood estimation approach provides an efficient alternative to current estimation methods.

Modeling visual working memory with the MemToolbox

The MemToolbox is a collection of MATLAB functions for modeling visual working memory. In support of its goal to provide a full suite of data analysis tools, the toolbox includes implementations of popular models of visual working memory, real and simulated data sets, Bayesian and maximum likelihood estimation procedures for fitting models to data, visualizations of data and fit, validation routines, model comparison metrics, and experiment scripts. The MemToolbox is released under the permissive BSD license and is available at http://memtoolbox.org.

Evaluating the performance of simple estimators for probit models with two dummy endogenous regressors

This study considers the small sample performance of approximate but simple two-stage estimators for probit models with two endogenous binary covariates. Monte Carlo simulations show that all the considered estimators, including the simulated maximum-likelihood (SML) estimation, of the trivariate probit model are biased in very small samples (N=100). With moderately small samples (N=500), some of the approximations perform as well as the SML estimator when the degree of endogeneity is not very large. Some of the approximations seem robust with higher correlations and are also promising for testing the exogeneity of binary covariates. The methods are used to estimate the impact of employment-based health insurance and health care (HC) on HC use, where the approximations seem to work at least as well as the SML and in some cases better.

A Hybrid Data Cloning Maximum Likelihood Estimator for Stochastic Volatility Models

Abstract: In this article, we analyze a maximum likelihood estimator using Data Cloning for Stochastic Volatility models. This estimator is constructed using a hybrid methodology based on Integrated Nested Laplace Approximations to calculate analytically the auxiliary Bayesian estimators with great accuracy and computational efficiency, without requiring the use of simulation methods such as Markov Chain Monte Carlo. We analyze the performance of this estimator compared to methods based on Monte Carlo simulations (Simulated Maximum Likelihood, MCMC Maximum Likelihood) and approximate maximum likelihood estimators using Laplace Approximations. The results indicate that this data cloning methodology achieves superior results over methods based on MCMC, comparable to results obtained by the Simulated Maximum Likelihood estimator. The methodology is extended to models with leverage effects, continuous time formulations, multifactor and multivariate stochastic volatility.

A simultaneous equations model of crash frequency by severity level for freeway sections

This paper presents a simultaneous equations model of crash frequencies by severity level for freeway sections using five-year crash severity frequency data for 275 multilane freeway segments in the State of Washington. Crash severity is a subject of much interest in the context of freeway safety due to higher speeds of travel on freeways and the desire of transportation professionals to implement measures that could potentially reduce crash severity on such facilities. This paper applies a joint Poisson regression model with multivariate normal heterogeneities using the method of Maximum Simulated Likelihood Estimation (MSLE). MSLE serves as a computationally viable alternative to the Bayesian approach that has been adopted in the literature for estimating multivariate simultaneous equations models of crash frequencies. The empirical results presented in this paper suggest the presence of statistically significant error correlations across crash frequencies by severity level. The significant error correlations point to the presence of common unobserved factors related to driver behavior and roadway, traffic and environmental characteristics that influence crash frequencies of different severity levels. It is found that the joint Poisson regression model can improve the efficiency of most model coefficient estimators by reducing their standard deviations. In addition, the empirical results show that observed factors generally do not have the same impact on crash frequencies at different levels of severity.

Individual characteristics and stated preferences for alternative energy sources and propulsion technologies in vehicles: A discrete choice analysis for Germany

With respect to the German goal of a transition to a lead market for electromobility within a short time period, this paper empirically examines the preferences for alternative energy sources or propulsion technologies in vehicles and particularly for electric vehicles. The data stem from a stated preference discrete choice experiment with 598 potential German car buyers. In order to simulate a realistic future purchase situation, seven vehicle types were incorporated in each of the six choice sets, i.e. hybrid, gas, biofuel, hydrogen, and electric vehicles besides common gasoline and diesel vehicles. The econometric analysis with flexible multinomial probit models reveals that potential car buyers in Germany currently have a low stated preference for electric, hydrogen, and hybrid vehicles. While our paper also discusses the impact of common vehicle attributes such as purchase price or service station availability, it particularly considers the effect of socio-demographic and environmental awareness variables. The estimation results reveal that younger potential car buyers have a higher stated preference for hydrogen and electric vehicles, males have a higher stated choice of hydrogen vehicles, and environmentally aware potential car buyers have a higher stated preference for hydrogen and electric vehicles. These results suggest that common policy instruments such as the promotion of research and development, taxation, or subsidization in the field of electromobility could be supplemented by strategies to increase the social acceptance of alternative vehicle types that are directly oriented to these population groups. Methodologically, our study highlights the importance of the inclusion of taste persistence across the choice sets and a high number of random draws in the Geweke–Hajivassiliou–Keane simulator in the simulated maximum likelihood estimation of the multinomial probit models.

Bayesian Procedures as a Numerical Tool for the Estimation of Dynamic Discrete Choice Models

Dynamic discrete choice models usually require a general specification of unobserved heterogeneity. In this paper, we apply Bayesian procedures as a numerical tool for the estimation of a female labor supply model based on a sample size which is typical for common household panels. We provide two important results for the practitioner: First, for a specification with a multivariate normal distribution for the unobserved heterogeneity, the Bayesian MCMC estimator yields almost identical results as a classical Maximum Simulated Likelihood (MSL) estimator. Second, we show that when imposing distributional assumptions which are consistent with economic theory, e.g. log-normally distributed consumption preferences, the Bayesian method performs well and provides reasonable estimates, while the MSL estimator does not converge. These results indicate that Bayesian procedures can be a beneficial tool for the estimation of dynamic discrete choice models.

Bayesian Procedures as a Numerical Tool for the Estimation of Dynamic Discrete Choice Models

Dynamic discrete choice models usually require a general specification of unobserved heterogeneity. In this paper, we apply Bayesian procedures as a numerical tool for the estimation of a female labor supply model based on a sample size which is typical for common household panels. We provide two important results for the practitioner: First, for a specification with a multivariate normal distribution for the unobserved heterogeneity, the Bayesian MCMC estimator yields almost identical results as a classical Maximum Simulated Likelihood (MSL) estimator. Second, we show that when imposing distributional assumptions which are consistent with economic theory, e.g. log-normally distributed consumption preferences, the Bayesian method performs well and provides reasonable estimates, while the MSL estimator does not converge. These results indicate that Bayesian procedures can be a beneficial tool for the estimation of dynamic discrete choice models.

Analyzing Probit Bayes Estimator for Flexible Covariance Structures in Discrete Choice Modeling

Research in discrete choice modeling in recent decades has devoted an enormous effort to generalizing the distribution of the error term and to developing estimation methods that account for more flexible structures of error heterogeneity. Whereas the multinomial probit model offers a fully flexible covariance matrix, the maximum simulated likelihood estimator is extremely involved. However, Bayesian techniques have the potential to break down the complexity of the estimator. By using a Monte Carlo study, this paper tests the ability of a probit Bayes estimator based on Gibbs sampling to recover different substitution patterns. The results show that it is possible to use the Bayes estimator of a full covariance matrix to recover different covariance structures, even when small samples are used. Thus, the model can identify the true substitution patterns, by avoiding misspecification, even if these patterns are the result of multiple restrictions over the covariance matrix. In fact, the recovery of simpler covariance structures, such as that of the independent and identically distributed and heteroskedastic covariance without correlation, is more accurate than the recovery of more complicated structures, including fully unrestricted substitution patterns.