Stochastic Frontier Estimation Research Articles

Productivity and efficiency: Do we need a bridge?

The paper focuses on comparing two popular approaches to estimating firm production technology: the proxy-variable method and the stochastic frontier (SF) analysis approach. We show that although the economic interpretations of productivity and efficiency are not the same, the difference between them is not fundamental and even trivial as far as the estimation techniques are concerned when the same structural framework is assumed. By showing the connection and comparing the difference between these two methods, this paper is aimed at building a bridge to connect these two strands of literature. In addition, we provide the SF audience with a new estimation method, i.e., the modified proxy-variable method, with its advantages in handling the endogeneity issue, along with a new way to estimate technical inefficiency. We examine their finite sample performance using Monte Carlo simulations. In the empirical section, we compare the proposed estimator with the conventional MLE SF estimator using Chinese manufacturing firms in the computer and peripheral sector over the period 1998 to 2007. We find that the estimates from our method are more reasonable in explaining the production behavior of these firms, and firms’ technical inefficiency levels are highly persistent over time.

Market power, human capital efficiency and bank performance in Kenya

PurposeThe study evaluates the influence of human capital efficiency (HCE) and market power on bank performance.Design/methodology/approachThe study employs two measures of bank performance: profitability and stability. Unbalanced panel data of 35 banks operating in Kenya for 2005–2020 collected from published financial statements is utilized. The study employs the feasible generalized least squares (FGLS) method in the analysis and the two-step system generalized method of moments (GMM) for robustness check.FindingsThe study affirms an inverted U-shaped relationship between market power and bank performance. The effect of market power on bank profitability is enhanced when a bank has highly efficient human capital. Further, HCE significantly impacts bank stability for banks with low HCE. Interestingly, a further increase in HCE narrows the net interest margins for banks with high HCE, conferring welfare benefits to customers as interest rate spreads shrink.Practical implicationsThis study provides important insights into the role of human capital in bank performance. First, banks ought to invest in promoting HCE through training and development. As regulators root for bank consolidation, attention to HCE is imperative for fostering profitability and stability.Originality/valueThe study fills an essential gap in the literature by evaluating the effect of firm-level market power on bank performance in an emerging market. We adopt a novel stochastic frontier estimator to generate the Lerner index. Further, this is the first study known to the authors to evaluate the effect of market power on bank performance in the context of human capital efficiency variations.

ESTIMATION OF EFFICIENCY AND THE IMPACT OF COVID-19 ON THE EFFECT OF ACCESS TO FINANCE ON EFFICIENCY OF SMALL AND MEDIUM ENTERPRISES (SMEs) IN THE WESTERN AREA OF SIERRA LEONE

<p>To estimate efficiency and the impact of COVID-19 on the effect of access to finance on the efficiency of small and medium enterprises (SMEs) in the Western Area of Sierra Leone, the study adopted the stochastic frontier estimation method of determining the efficiency of firms. A model of maximum performance (capacity) was estimated using 450 SMEs randomly selected from the population of registered SMEs in the Western Area of Sierra Leone from 2018 to 2020. The model of net business earnings was estimated using the Maximum Likelihood procedure and the firm efficiencies were consequently estimated. The mean inefficiencies are estimated by various categories, including SMEs' access to bank credit to determine firm characteristics that are associated with higher mean efficiencies. The empirical results reveal that the potential of firms is determined positively by capital productivity and labour productivity and negatively by the experience of firms, the latter results suggesting that more experience does not push their production outwards but inwards. However, other factors found significant in efficiency differences among firms include gender of the head of the SME, educational level, professional training of the firm heads, sector of operation and the area of operation of the SMEs. Moreover, firm mean efficiencies are not found to vary across the three periods 2018, 2019 and 2020, suggesting the COVID-19 pandemic did not affect firm efficiencies.</p><p><br /><strong>JEL:</strong> F13, F15</p><p> </p><p><strong> Article visualizations:</strong></p><p><img src="/-counters-/soc/0787/a.php" alt="Hit counter" /></p>

Estimation of Efficiency and the Effect of Access to Finance on Efficiency of Small and Medium Enterprises (SMES) in the Western area of Sierra Leone

Abstract To estimate the efficiency of SMEs and the effect of access to finance on the efficiency of SMEs the study adopted the stochastic frontier estimation method of determining efficiency of firms. A model of maximum performance (capacity) was estimated using 450 SMEs randomly selected from the population of registered SMEs in the Western Area of Sierra Leone from 2018 to 2020. The model of net business earnings was estimated using the Maximum Likelihood procedure and the firm efficiencies were consequently estimated. The mean inefficiencies are estimated by various categories, including SMEs access to bank credit to determine firm characteristics that are associated with higher mean efficiencies. The empirical results reveal that the potential of firms is determined positively by capital productivity and labour productivity and negatively by experience of firms, the latter results suggesting that more experience (in terms of age) does not push their production outwards but inwards. However, other factors are found significant in efficiency differences among firms. These are: gender of the head of the SME, educational level, professional training of the firm heads, sector of operation and the area of operation. JEL classification numbers: F14, F18, G14, G21. Keywords: Efficiency, Finance, Small and Medium Enterprises.

Rural revitalization through improvements of technical efficiency in honey production: Evidence from Horo Guduru Wollega Zone, Oromia, Ethiopia

Making apiaries more effective is only one aspect of reviving the beekeeping industry. Additionally, the beekeeping industry is generating employment both in rural and urban locations. This study’s goal was to identify the technical levels of honey production in Ethiopia’s Horo Guduru Wollega zone and their contributing factors. To accomplish the aforementioned objective, structured questionnaire data collected from 396 households were used. Stochastic production frontier estimator shows that the number of hives, the amount of work put into producing honey, and the area of the land all significantly influenced the amount of honey produced. In the mean technical of both traditional and modern hives, there were 56.68% and 73.93%, respectively. This demonstrates how technically more efficient farmers who use contemporary hives to make honey are. According to mean technical efficiency, both beekeepers were, however, operating below the production frontier. Household sex, credit utilization, extension services, training, beekeeping experience, and family size were significant technical efficiency variables for honey producers. The study suggests policies to address technical inefficiencies by increasing the number of hives, extending the best performers’ experience by increasing the frequency of extension contacts on honey production, facilitating and expanding credit service in the study area, making bee forage access simple, and increasing forest coverage on land area in line with current policy of Ethiopia. Additionally, since farmers in the study area spend their time guarding the honey from damage by ants, labor that utilizes technology must be made available.

Marginal abatement costs for GHG emissions in Canada: a shadow cost approach

This study approximates the marginal abatement costs (MACs) of reducing GHG emissions in Canada using the shadow cost approach. Utilizing industry level data, we are the first to offer Canadian estimates based on a Hyperbolic Output Distance Function (HODF) and the stochastic frontier estimation. Accounting for GHG emissions caused by energy consumption, we obtain an average shadow MAC of $130/t across 30 industries. In the GHG-intensive industries such as the electric utilities and non-conventional oil extraction, MACs are lower than the CO2 levy of $50/t imposed by the federal government. Since these low-MACs sectors account for about 98 per cent of total GHG emissions and 94 per cent of total energy use in industries studied, the envisaged $50/t carbon levy could notionally result in a significant GHG abatement in Canada.Graphical abstractFig. aEstimated Marginal Abatement Costs by Sector

Estimating technical efficiency in the presence of farm heterogeneity: evidence from maize production in Ethiopia

PurposeThe purpose of this paper is to measure technical efficiency and examine its determinants while disentangling unobserved time-invariant heterogeneity from actual inefficiency using comprehensive household-level panel data.Design/methodology/approachThis paper estimates technical efficiency based on the true random-effects stochastic production frontier estimator with a Mundlak adjustment. By utilising comprehensive panel data with 4,694 observations from 39 districts of four major maize-producing regions in Ethiopia, the author measures technical efficiency and examine its determinants while disentangling unobserved time-invariant heterogeneity from technical inefficiency. By using competing stochastic production frontier estimators, the author provides insights into the influence of farm heterogeneity on measuring farm efficiency and the subsequent impact on the ranking of farmers based on their efficiency scores.FindingsThe study results indicate that ignoring unobservable farmer heterogeneity leads to a downwards bias of technical efficiency estimates with a consequent effect on the ranking of farmers based on their efficiency scores. The mean technical efficiency score implied that about a 34% increase in maize productivity can be achieved with the current input use and technology in Ethiopia. The key determinants of the technical inefficiency of maize farmers are the age, gender and formal education level of the household head, household size, income, livestock ownership, and participation in off-farm activities.Research limitations/implicationsWhile the findings of this study are critical for informing policy on improving agricultural production and productivity, a few important things are worth considering in terms of the generalisability of the findings. First, the study relied on secondary data, so only a snapshot of environmental factors was accounted for in the empirical estimations. Second, there could be other sources of unmeasured potential sources of heterogeneity caused by persistent technical inefficiency and endogeneity of inputs. Third, the study is limited to one country. Therefore, future research should extend the analysis to ensure the generalisability of the empirical findings regarding the extent to which unmeasured potential sources of heterogeneity caused by persistent technical inefficiency, endogeneity of inputs and other unobservable country-specific features – such as geographical differences.Originality/valueThis paper contributes to the literature on agricultural productivity and efficiency by providing new evidence on the influence of unobservable heterogeneity in a farm efficiency analysis. While agricultural production is characterised by heterogeneous production conditions, the influence of unobservable farm heterogeneity has generally been ignored in technical efficiency estimations, particularly in the context of smallholder farming. The value of this paper comes from disentailing producer-specific random heterogeneity from the actual inefficiency.

EFFICIENCY OF ISLAMIC BANKS: EVIDENCE FROM ISLAMIC WINDOWS OF CONVENTIONAL BANKS IN ETHIOPIA

The study examines the cost and technical efficiency of selected Islamic banking windows of conventional banks in Ethiopia during the period of 2016-2020. The parametric method, stochastic frontier approach (SFA) was employed to measure both cost and technical efficiency of the banks. The efficiency scores of the sampled banks can be measured based on their performance in utilizing inputs to successfully generate output during the study period. It gauges the service quality of the banks taking loans and deposits as well as operating income and expenses into consideration. The study uses time series data from four conventional banks which provide Islamic banking widow in Ethiopia. The statistical findings show that the conventional banks have fairly better technical efficiency individually and collectively; however, the cost efficiency scores indicate that the banks are not efficient enough in terms of minimizing costs for a given scale and mix of outputs. Similarly, the results of the stochastic technical frontier estimates uncovers that there is positive significant relationship between the input variables namely total deposits and total operating expenses and output variables namely total financing and total operating income. The outputs remain an essential contributor to the cost efficiency in Islamic windows conventional banks in Ethiopia.

Foreign direct investment, efficiency, and total factor productivity: Does technology intensity classification matter?

Purpose ― We examine whether the foreign direct investment (FDI) in promoting technical efficiency is controlled by the sector classifications based on the technology intensity (High Technology, Medium-High Technology, Medium-Low Technology, and Low Technology). Methods ― We use the Indonesian firm-level dataset of the large and medium manufacturing survey from 2007 to 2015 and employ the time-varying stochastic production frontier. Findings ― We reveal that FDI, technology intensity and absorptive Capacity significantly affect firms' production and efficiency. We also found that the Indonesian manufacturing industry from 2007 to 2015 experienced positive Total Factor Productivity growth, where High-Technology sectors experienced the largest magnitude among others. Meanwhile, technological progress stemming from FDI is enjoyed more by Low Technology sectors. Meaning to say, technology intensity classification does not matter to technological progress. Implication ― The host country's government should focus on industries with high technical capabilities to accelerate FDI gains for the firms. Simultaneously, human capital improvement also needs to be intensified, for instance, through training or human development, so that firms with lower technical capability can catch up and, consequently, receive similar benefits from FDI activities. Originality ― Our study accommodates the research gap by including the FDI effect in both productivity and efficiency in a single equation. Many studies merely categorize technology intensity following the stochastic production frontier estimation to obtain technical efficiency or TFP growth. In this sense, those studies did not control the impact of the technology-specific effect.

Consumer lending efficiency: commercial banks versus a fintech lender

Fintechs are believed to help expand credit access to underserved consumers without taking on additional risk. We compare the performance efficiency of LendingClub’s unsecured personal loans with similar loans originated by banks. Using stochastic frontier estimation, we decompose the observed nonperforming loan (NPL) ratio into three components: the best-practice minimum NPL ratio, the excess NPL ratio, and a statistical noise, the former two of which reflect the lender’s inherent credit risk and lending inefficiency, respectively. As of 2013 and 2016, we find that the higher NPL ratios at the largest banks are driven by inherent credit risk, rather than lending inefficiency. Smaller banks are less efficient. In addition, as of 2013, LendingClub’s observed NPL ratio and lending efficiency were in line with banks with similar lending volume. However, its lending efficiency improved significantly from 2013 to 2016. As of 2016, LendingClub’s performance resembled the largest banks – consistent with an argument that its increased use of alternative data and AI/ML may have improved its credit risk assessment capacity above and beyond its peers using traditional approaches. Furthermore, we also investigate capital market incentives for lenders to take credit risk. Market value regression using the NPL ratio suggests that market discipline provides incentives to make less risky consumer loans. However, the regression using two decomposed components (inherent credit risk and lending inefficiency) tells a deeper underlying story: market value is significantly positively related to inherent credit risk at most banks, whereas it is significantly negatively related to lending inefficiency at most banks. Market discipline appears to reward exposure to inherent credit risk and punish inefficient lending.

How bad is a bad loan? Distinguishing inherent credit risk from inefficient lending (Does the capital market price this difference?)

Small community banks and the largest banks experience higher ratios of nonperforming loans than other sizes of banks. To what extent does their nonperformance result from lending to riskier borrowers, and to what extent does it result from a lack of proficiency at loan making? Does market discipline punish or reward credit risk and lending proficiency? Using stochastic frontier estimation, we develop a technique to decompose banks’ ratio of nonperforming loans to total loans into three components: the best-practice ratio representing the inherent credit risk of the loan portfolio, the excess ratio representing lending inefficiency, and statistical noise. We apply the decomposition technique to data from 2010, 2013, and 2016 on top-tier U.S. bank holding companies. The largest banks with consolidated assets exceeding $250 billion experience the highest ratio of nonperformance among the five size groups. Our decomposition shows that the high ratio of nonperformance of the largest banks appears to result from lending to riskier borrowers, not inefficiency at lending. Restricting the sample to publicly traded bank holding companies, we find that the nonperformance ratio is negatively related to market value except at the largest banks. When the two components of the nonperformance ratio are used instead, we uncover a more informative underlying story: taking more inherent credit risk enhances market value at many more large banks and the value-enhancing effect increases sharply from 2010 to 2016, whereas lending inefficiency is negatively related to market value at all banks and more so from 2010 to 2016. Market discipline appears to reward riskier lending at large banks and discourage lending inefficiency at all banks − incentives that are both increasing over time.

Recent Advances in the Panel Stochastic Frontier Models: Heterogeneity, Endogeneity and Dependence

This paper primarily reviews the panel stochastic frontier (SF) model in which the composite error term [Formula: see text] has four components, i.e. [Formula: see text] where [Formula: see text] and [Formula: see text] are the persistent and transient inefficiency components, [Formula: see text] is the random firm effect and [Formula: see text] is the random noise. We discuss a variety of model specifications of the four-component SF panel model and estimation approaches developed mostly during the period 2014 to 2021. While discussing these models, we focus on the following issues: heterogeneity, endogeneity of inputs/output(s), inclusion of determinants of inefficiencies via their variances and dependence among the error components. Additionally, we examined models that introduce allocative inefficiency. Models that use both multi-step and system approaches to model allocative inefficiency are also examined.

Technical Efficiency of Ginger Production in Ilam District of Nepal: A Stochastic Production Frontier Approach

This study measured the level of technical efficiency among smallholder ginger growers and examined the determinants of inefficiency by employing the stochastic frontier production function. The paper used a simple random sampling technique to interview 100 ginger farmers in Ilam, a leading ginger-producing district in Nepal, with the help of a pretested interview schedule. The STATA.13 software was used to obtain both stochastic frontier estimates and the determinants of technical inefficiency. The results revealed that the average farm-level technical efficiency is 67.8% which shows the scope of increasing the technical efficiency by 32.2%. The coefficients of seed and farmyard manure were positive and showed significant relation to ginger output at a 1% and 5% level of significance, respectively. Education level, training, and membership in cooperatives had a negative and significant impact on technical inefficiency, whereas areas under ginger production had a positive impact on technical inefficiency. Hence, improving the technical knowledge of farmers through training on optimum input use complemented with motivation to join agriculture cooperatives and farmer’s associations may increase the technical efficiency of ginger growers in the study area.

Does the adoption of emerging technologies improve technical efficiency? Evidence from Korean manufacturing SMEs.

Despite the proliferation of innovative technologies during the Fourth Industrial Revolution (4IR), there is a severe lack of quantitative and empirical studies that deal with the effectiveness of recently emerging technologies. This study examines the impact of employing core technologies of the 4IR on small and medium enterprises (SMEs). We used the firm-level cross-sectional data on Korean manufacturing SMEs, including the information on technology utilization. The stochastic production frontier estimation with selectivity correction is employed, besides matching technique to obtain unbiased estimates on technology efficiency. The empirical analysis finds that adopting emerging technologies enhances the productivity of SMEs. After observed and unobserved factors are controlled, the technical efficiency of adopters is higher by more than 26% on average, compared to non-adopters. Moreover, if the gap among production frontiers is considered, the difference in productivity would rise further. Additionally, a strategic alliance is a crucial route for SMEs to accept new technologies.

The Stochastic Frontier Model for Technical Efficiency Estimation of Interconnected Container Terminals

Nowadays, container terminals are subject to extensive technological changes and specific transformations. Changes applied to terminals tend to increase their ability to offer high- end personalized services to the customers and finally affect the competitiveness. The estimation of efficiency corresponds to terminals’ ability to increase the production with a specific level of inputs and has been the topic of many studies, especially those conducted on a wider regional or global level. The main objectives of our research are to evaluate the model, conduct sensitivity analysis, and estimate technical efficiencies on a sample of North Adriatic Ports Association (NAPA) interconnected medium-sized terminals, located in the narrow geographic area, on the same transport corridor thus representing each other’s competition. For that purpose, we have implemented a stochastic frontier approach on a balanced panel dataset of first-order and additionally introduced control input variables with Cobb-Douglas and trans-logarithmic functional forms. The stochastic production frontier estimation shows the range of NAPA terminals’ technical efficiencies from 65.24% to 93.92%, with a global average of 78.49% and a positive trend of 1.28% over the observed period of time. Our findings also indicate that NAPA terminals with the highest estimated technical efficiencies do not necessarily need to be the most productive ones, and vice versa.

A Comparison of Economic Efficiency of Monoculture and Multiple Cropping Patterns: The Case of Cassava Farming in Ende, Indonesia

<span lang="EN-US">Nuabosi cassava is an alternative carbohydrate source for the community, which is expected to be a substitute for rice. This commodity has the potential to be developed, but is limited in resources, so it requires technological breakthroughs. This study aims at analyzing the level of technical, allocative and economic efficiency between the cassava cropping pattern and the factors that affect the efficiency. The research was conducted in Randotonda Village, from November 2019 to January 2020 and the samples consisted of 61 monoculture farmers and 46 multiple cropping farmers. Data analysis was performed using the Cobb-Douglass stochastic frontier production function. The allocative and economic efficiency was examined with the stochastic frontier cost function approach. The results of stochastic frontier estimation show that all variables have a positive effect on the production variable. The variables having a positive effect on the total cost include the price of cassava cuttings, the price of fertilizer, production and the dummy cropping pattern. The average level of economic efficiency of monoculture farmers is lower than that of multiple cropping farmers. Factors that affect economic efficiency are age, length of time to cultivate, frequency of obtaining information, dummy of farmer group membership and dummy of cropping patterns. In short, the level of technical, allocative and economic efficiency of monoculture farmers is lower than that of multiple cropping farmers. Farmers are expected to pay attention to the types of plants that are suitable in implementing the multiple cropping pattern</span><span lang="IN">.</span>

Stochastic frontiers or regression quantiles for estimating the self-thinning surface in higher dimensions?

Stochastic frontier analysis and quantile regression are the two econometric approaches that have been commonly adopted in the determination of the self-thinning boundary line or surface in two and higher dimensions since their introduction to the field some 20 years ago. However, the rational for using one method over the other has, in most cases, not been clearly explained perhaps due to a lack of adequate appreciation of differences between the two approaches for delineating the self-thinning surface. Without an adequate understanding of such differences, the most informative analysis may become a missed opportunity, leading to an inefficient use of data, weak statistical inferences and a failure to gain greater insight into the dynamics of plant populations and forest stands that would otherwise be obtained. Using data from 170 plot measurements in even-aged Larix olgensis (A. Henry) plantations across a wide range of site qualities and with different abundances of woody weeds, i.e. naturally regenerated non-crop species, in northeast China, this study compared the two methods in determining the self-thinning surface across eight sample sizes from 30 to 170 with an even interval of 20 observations and also over a range of quantiles through repeated random sampling and estimation. Across all sample sizes and over the quantile range of 0.90 ≤ τ ≤ 0.99, the normal-half normal stochastic frontier estimation proved to be superior to quantile regression in statistical efficiency. Its parameter estimates had lower degrees of variability and correspondingly narrower confidence intervals. This greater efficiency would naturally be conducive to making statistical inferences. The estimated self-thinning surface using all 170 observations enveloped about 96.5% of the data points, a degree of envelopment equivalent to a regression quantile estimation with a τ of 0.965. The stochastic frontier estimation was also more objective because it did not involve the subjective selection of a particular value of τ for the favoured self-thinning surface from several mutually intersecting surfaces as in quantile regression. However, quantile regression could still provide a valuable complement to stochastic frontier analysis in the estimation of the self-thinning surface as it allows the examination of the impact of variables other than stand density on different quantiles of stand biomass.

Assessing the market power of millers and wholesalers in the Bangladesh rice sector

PurposeBecause of the increasing differential between farm and retail prices, the study proposes to investigate the extent of market power in the rice value chain of Bangladesh using advanced econometric techniques.Design/methodology/approachUsing a Stochastic Frontier Estimation approach on cross-sectional data, the study examines the price spread along the rice value chain to determine whether millers and wholesalers exercise market power.FindingsEmpirical results reveal that, on average, rice millers and wholesalers charge 33 and 29% above the marginal cost, respectively. This study confirms the non-competitive behavior of the rice market with wholesalers and millers wielding substantial market powerResearch limitations/implicationsA limitation of the study is that it does not include the retailers who also play a major role in the Bangladesh rice value chain. This is left for future study.Originality/valueThis study combines primary and secondary data collected on the Bangladesh rice sector to examine the market power of two major players along the value chain, millers and wholesalers, using an advanced econometrics approach.

Enhancing the Financial Returns of R&D Investments through Operations Management

Although much research has been carried out to examine various contextual issues and moderating factors for successful R&D investments, very little research has been conducted to explore the role of a firm's operational and process characteristics. In this study, we explore how firms could possibly enhance the financial returns of R&D investments through quality management, using Six Sigma implementation as an example, and efficiency improvement, using the stochastic frontier estimation of relative efficiency as a proxy. Based on data from 468 manufacturing firms in the United States over the period 2007–2014, we construct a dynamic panel data model to capture the effects of R&D investments on firms’ financial returns in terms of Tobin's q. Using the system generalized method of moments estimator, our results indicate that the financial returns of R&D investments are significantly enhanced when firms adopt Six Sigma and improve efficiency in operations. Our additional analyses further suggest that such an enhancement effect through quality and efficiency improvements is more pronounced under high operational complexity as approximated by labor intensity and geographical diversity. Instead of considering innovation activities and process management as contradictory functions, we show that quality and efficiency improvements indeed support firms’ R&D investments, leading to higher financial returns.

Nonparametric estimation in a regression model with additive and multiplicative noise

In this paper, we consider an unknown functional estimation problem in a general nonparametric regression model with the feature of having both multiplicative and additive noise. We propose two new wavelet estimators in this general context. We prove that they achieve fast convergence rates under the mean integrated square error over Besov spaces. The obtained rates have the particularity of being established under weak conditions on the model. A numerical study in a context comparable to stochastic frontier estimation (with the difference that the boundary is not necessarily a production function) supports the theory.