Three Essays on Applied Semiparametric Methods

Analysis of the behavior of technical inefficiency with respect to parameters and variables of a stochastic frontier model is a neglected area of research in frontier literature. An attempt in this direction, however, has recently been made. It has been shown that in a “standard” stochastic frontier model that both the firm level technical inefficiency and the production uncertainty are monotonically decreasing with observational error. In this paper we show, considering a stochastic frontier model whose error components are jointly distributed as truncated bivariate normal, that this property holds if and only if the distribution of observational error is negatively skewed. We also derive a necessary and sufficient condition under which both firm level technical inefficiency and production uncertainty are monotonically increasing with noise-inefficiency correlation. We next propose a new measure of the industry level production uncertainty and establish the necessary and sufficient condition for firm level technical inefficiency and production uncertainty to be monotonically increasing with industry level production uncertainty. We also study the limiting probabilistic behavior of these conditions under different parametric configuration of our model. Finally we carry out Monte Carlo simulations to study the sample behavior of the population monotonic property of the firm level technical inefficiency and production uncertainty in our model.

The present study is attempted to estimate the Technical Efficiency level of paddy farmers in Thiruvarur District of Tamil Nadu, India using Stochastic Production Frontier Model to know the variations in efficiency among the farmers and to analyse the policy making decisions for improving the efficiency. A Cobb-Douglas Production function was considered in which the technical inefficiency effects are defined by a model with Rayleigh distribution. Primary data from 300 households in Thiruvarur district during the year 2015-16, Tamil Nadu were used. The results show that the Technical Efficiency of paddy farmers in the study area ranged from 11 to 85 percent with an average of 55 percent. The average Technical Efficiency level implied 55 percent of the farmers in the study area realised their technical abilities. Based on the technical efficiency score, the average potential to increase the paddy production was 35 percent and if the minimum efficiency farmer can reach the maximum level then the cost can save up to 87 percent. The MLE result shows that Farm Yard Manure and Chemical fertilizers are positively related to the Technical Efficiency. The socio economic factors influencing Technical Efficiency was identified using linear regression model and the result shows that sex of the farmer, education and credit are the important factors to increase the Technical Efficiency.

Maize production is the most important field crop in South Africa produced from ancient years, Mpumalanga and North West Provinces being principal producers. Maize is extensively produced and ascendancy ground crop because maize is greater resilient, less labor exhaustive, rich in food strength and starches, grows actual fast, and easy to produce as other ground crops. Most of the produced maize in South African is consumed domestically. Despite massive extents of arable land and all-inclusive land reform implemented for 25 years, farmers in the former homeland areas of South Africa cultivate only small food plots where they grow mostly maize and a small variety of vegetables. The aim of this paper was to examine the technical efficiency of maize-based farmers who farm within smallholder irrigation schemes. A multi-stage sampling procedure was used to select 120 maize-based irrigation farmers. Descriptive statistics and stochastic production frontier models were used in the study. Maize production in the study area was dominated by males (78%) with an average age of 60 years and an average family size of 4 people in the household. Smallholder irrigators have primary education meaning farmers were literate and able to access farming information and interpret it. Farmers have a minimum average of 10 years of farming experience. Smallholder maize-based farmers were efficient in using their resources given their high farm productivity. The level of technical efficiency for maize farming was 84% which indicates that 16% of maize yield was not realized by smallholder maize farmers in the study area. The study recommends that the government and private sector must improve the farm techniques such as manure and enhanced seeds prepared early and accessible at small and affordable expenses to upsurge maize productivity.

The electricity supply chain system consists of power plants, transmission and distribution. Differences in power plant characteristics cause differences in fuel costs and emissions. Inaccuracies in scheduling the plant have an impact on the surge in fuel use. This becomes the basis for the optimization of power plant scheduling. Optimization on the generator side is usually using the economic dispatch model. However, the Economic Dispatch Model does not consider optimization on the transmission network. Optimization on the transmission network is needed because there are losses in the transmission network. Losses will be even greater when the distance between the power plant and the customer is getting further away. So if distance can be minimized, fuel costs can be reduced. Minimizing the distance for shipping goods can use the transportation model, but the transportation model cannot be used for electricity distribution. This is because there are differences between goods and electricity. Therefore, this study proposes the Single Echelon Economic Dispatch (SEED) model. This model is a combination of the economic dispatch model and the transportation model. This model is able to do simultaneous optimization between the generator side and the transmission side. The model is applied to the Mahakam system in East Kalimantan, using all PLN’s power plants. Load consists of two types, namely low load and peak load. As a result, in peak load and low load conditions, the P11 power plant produces the biggest losses and emissions. This is because electricity production in P11 has to go through a longer path compared to other plants. The P11 is also a power plant that requires the highest fuel costs

Long-run pollution exposure and mortality: Evidence from the Acid Rain Program

In causal inference, interference takes place when the intervention on one unit affects the outcome of other units. Most of the previous methods for estimating network causal effects assume that the covariate information is complete, which may lead to biased estimates when missingness exists. In this study, we consider the partial and direct interference setting. Specifically, the whole population can be divided into different clusters. Within each cluster, the outcome of each unit is dependent on the intervention received by other units, but not dependent on the confounders or outcomes of other units within the same cluster or of those in different clusters. We also assume that the confounders are subject to non-ignorable missingness, and a confounder is considered as missing if any component of it is missing. We propose three consistent estimators for the direct, indirect, total, and overall effect of the intervention on the outcome, and derive the asymptotic results accordingly. A comprehensive study is carried out as well to investigate the finite sample properties of the proposed estimators. We illustrate the proposed methods by analyzing the dataset collected from an acid rain program, which was launched to reduce air pollution in the United States by encouraging the scrubber’s installation on power plants, where the records of some operating characteristics of the power generating facilities are subject to missingness.

Polycyclic aromatic hydrocarbon (PAH) emissions from coal combustion in power plants are considered an important atmospheric source of such compounds. This paper proposes an evaluation of PAH emission levels from five different thermal power plants fired by pulverised coal. In the first place the sampling and measurement method is described. Then, the results obtained are discussed, in order to determine the characteristic profile of coal combustion in pulverised coal fired power plants, emission factors as well as the influence of operation parameters and type of coal on levels and types of emission. A lack on the PAHs with five or more aromatic rings was observed and also the predominant presence of compounds such as fluorene, phenanthrene and fluoranthene; on the other hand, PAHs present in emission are mainly found in gas phase. The more important factors found in PAHs emission were operating parameters reflected in oxigen excess and unburnt matter in ashes. The coal type exerts a low influence, but just when operating conditions were not optimal. An efficient combustion in the thermal plants in most cases results in very low PAH emissions.

Anthropogenic mercury emissions in South Africa: Coal combustion in power plants

Elemental composition of PM2.5 in Shiprock, New Mexico, a rural community located near coal–burning power plants and abandoned uranium mine tailings sites

Fired steam generators are the dominating technology of coal combustion in power plants. This paper presents a model for pulverized coal fired steam generators in Modelica. The model components are designed as an extension of SiemensPower, a Modelica library for transient simulation of power plants. The focus is on coal combustion, gas-particle-flow and radiation heat transfer in the furnace. The dispersed flow of flue gas has to be modeled because radiation heat transfer gets considerably intensified by the contained coal and ash particles. Customized connectors for the dispersed flow of flue gas had to be developed on the base of Modelica.Fluid. The component oriented approach supports the adaption of the model to different simulation tasks, such as stability analysis of the evaporator or influence of the coal mill on plant dynamics. Component structure, parametrization and spatial discretization were important aspects for the development of maintainable and re-usable components of the model library.

Group-specific stochastic production frontier models with parametric specifications

New technologies and digital infrastructures are enabling smart farming with high productivity levels across countries. Yet, there is dearth of evidence on how they are enabling smallholder farmers in Africa to increase their farm produce. By focussing on smallholder maize crop producers in South Africa and relying on a panel data for the period 2011–2021, this study applied a stochastic production frontier framework and Cobb–Douglas production function to estimate the relationship between variance of yield increase in relation to aggregate modern technologies adopted. The stochastic production frontier model was estimated using simple ordinary least square, maximum likelihood estimation and probit regressions. The analysis adopted a three-stage procedure which began with the specification of regression model, the calculation of least residuals squares of the explanatory variables and finally the estimation of the variances in the functional forms of output levels. The results revealed a positive relation between the application of digital agriculture technologies and increased crop performance for rural maize cultivators in South Africa. The policy inference from this study is that accelerating investment in digital agriculture infrastructure offers the promise of a quadruple return for South Africa’s agriculture sector.

China's Grassland Ecological Compensation Policy (GECP) is the world's most extensive grassland conservation program, based on a payment‐ for‐ ecosystem‐ services framework. Despite comprehensive studies on its impact, the underlying mechanisms remain unclear. Using survey data collected from 1039 forage farmers in Gansu and Qinghai provinces in China, this study employs a propensity score matching approach to address selection bias from observable factors. A selectivity‐corrected stochastic production frontier model was subsequently applied to correct for the bias due to unobservable characteristics. We find that GECP increased technical efficiency by more than 5.7%. Moreover, the unconditional quantile regression results demonstrate that farmers with higher TE quantiles benefit more from GECP than farmers with lower TE quantiles.

The study of the performance of primary and secondary educational institutions has gained popularity in recent years, but cross‐country evaluations of higher education (HE) systems remain rare. This study aims to fill this gap by assessing the technical efficiency (TE) of 87 national HE systems using stochastic production frontier models. The empirical model considers, for each country, the number of universities in the 2023 SCImago Institutions Ranking (SIR) by knowledge areas as the dependent variable, and GDP, R&D expenditures, and national English proficiency as explanatory variables. To offer a comprehensive analysis, the model is applied across all SIR ranking levels. Results show that Western countries generally lead in TE, but three performance profiles emerge: countries that concentrate their resources on a few HE institutions (efficient at the top SIR levels), others with homogeneous HE institutions (high TE across all levels), and low‐performance HE systems. Policy implications are discussed.

The paper examined the efficiency of upland and lowland rice production systems in a prominent rice producing State (Niger State) in Nigeria using descriptive statistics, stochastic production frontier model as well as inefficiency model. The data used were generated from a farm survey involving 240 rice farmers' randomly selected using multistage sampling technique. Results of analysis indicate that upland rice farmers were significantly more technically efficient (81.2%) than lowland rice farmers (76.4%) at P ≤ 0.01. Also, farmers stand the chance of improving their efficiency by 18.8% and 23.6% in upland and lowland production systems respectively and the inefficiency model indicated that this can be achieved when rice farmers plant improved varieties regardless of the production systems. In addition, sex was a significant determinant of efficiency under upland production while experience plays a significant role under lowland production (P ≤ 0.05). Keywords: Stochastic production frontier; efficiency; rice production; NigeriaMoor Journal of Agricultural Research Vol. 7 (1&2) 2006 pp.93-99