Double Bootstrap Research Articles

A double bootstrap data envelopment analysis model for evaluating malaria spending efficiency in Sub-Saharan Africa

Malaria is a major cause of morbidity and mortality in many countries in sub-Saharan Africa. The main objective of this study was to examine malaria spending efficiency and its associated factors in sub-Saharan Africa by employing a two-stage double bootstrap data envelopment analysis (DEA). In the first stage, technical efficiency scores are estimated using the output-oriented variable returns to the scale (VRS) framework. In the second stage, the double bootstrap DEA model is used to identify the environmental variables that affect malaria spending efficiency. We estimate the overall malaria spending efficiency score over the study period. This estimate suggests that malaria treatment and prevention outcomes can improve significantly. We find a significant association between efficiency and education, temperature levels, nurses’ and midwives’ density, and the proportion of children of age five who slept in insecticide-treated bed nets. We conclude that policymakers must not only be concerned with improving educational outcomes but also consider ways to mitigate the effects of climate change and improve access to healthcare services.

Optimal Subsampling Bootstrap for Massive Data

The bootstrap is a widely used procedure for statistical inference because of its simplicity and attractive statistical properties. However, the vanilla version of bootstrap is no longer feasible computationally for many modern massive datasets due to the need to repeatedly resample the entire data. Therefore, several improvements to the bootstrap method have been made in recent years, which assess the quality of estimators by subsampling the full dataset before resampling the subsamples. Naturally, the performance of these modern subsampling methods is influenced by tuning parameters such as the size of subsamples, the number of subsamples, and the number of resamples per subsample. In this article, we develop a novel hyperparameter selection methodology for selecting these tuning parameters. Formulated as an optimization problem to find the optimal value of some measure of accuracy of an estimator subject to computational cost, our framework provides closed-form solutions for the optimal hyperparameter values for subsampled bootstrap, subsampled double bootstrap and bag of little bootstraps, at no or little extra time cost. Using the mean square errors as a proxy of the accuracy measure, we apply our methodology to study, compare and improve the performance of these modern versions of bootstrap developed for massive data through numerical study. The results are promising.

Tourist attraction efficiency and its determinants using a two stage, double bootstrap data envelopment analysis: a case study in Indonesia

ABSTRACT Tourist attractions account for a critical component of tourism competitiveness. However, empirical research regarding tourist attraction efficiency is absent from literature. Respectively, this paper explores efficiency levels of tourist attractions and its determinants. 34 provinces of Indonesia were selected as the study setting. We employed the two-stage double bootstrap data envelopment analysis (DEA), an innovative approach that weathers the statistical shortcomings of the more traditional approaches. A 3-year data from 2017 to 2019 served for the analysis. Tourist attraction efficiency in Indonesia was relatively low. We revealed negative effects from population size, human development index (HDI), climate, and crime rate towards tourist attraction efficiency. Positive relationships were found for formal workforce, micro and small enterprises, and transportation. This study extends literature on tourism efficiency, and presents useful insights concerning tourism management.

Impact of HIV and Covid-19 pandemics on ivorian health system efficiency

Abstract The purpose of this study is to estimate the impact of HIV and Covid19 on the efficiency of the public health system in Côte d'Ivoire. To this end, we use non-parametric data envelopment analysis (DEA) and double bootstrap procedures to analyze the data. The analyze reveals that district hospitals are not technically efficient. These estimates show that in 2019, TB-HIV co-infection and geographic accessibility increases technical efficiency, while respiratory diseases reduce it. In contrast, in 2020, the advent of the Covid-19 pandemic blunted the positive impact of TB-HIV co-infection and geographical accessibility on the technical efficiency of the Ivorian health system observed in 2019. This result, due to the reorientation of resources allocated to the health sector to deal with the Covid-19 pandemic, is similar to the crowding out of the HIV pandemic by that of Covid-19. JEL Classification numbers: C14 - D24 - I12 - I18. Keywords: Double Bootstrap, Tuberculosis/HIV, Covid-19.

Managing nitrogen environmental impacts to improve green technical efficiency in Philippines rice cultivation

The efficient use of nitrogen fertilisers is a global priority to optimise the economic and environmental outcomes of farming. This paper is the first to consider pollution in the form of nitrous oxide emissions and excess nitrogen to analyse technical efficiency (TE) in farming. This is done by extending the two-stage double bootstrap Data Envelopment Analysis to explicitly model nitrogen pollutants as undesirable outputs. We compared green TE (when undesirable pollutants are considered) and conventional TE (without pollutants) using a case study of 33 rice-producing provinces in the Philippines. Provinces in Mindanao, Luzon, and Visayas islands experienced improvements in green TE but stagnant conventional TE from 2006 to 2017. Although transplanting rice seedlings (rather than direct sowing of seeds) improved both green and conventional TE, seed quality was also identified as an important factor for green TE but not for conventional TE. Our analysis has implications for sustainable rice production and such analysis can be extended to other crops. To advance the effective green transformation of rice production, future research should analyse farm-level data to understand farmers’ decisions regarding seed quality, crop establishment method and nitrogen fertiliser application to devise comprehensive farm integrated management plans.

Testing the Appositeness of Off-Balance Sheet Activities in the Indian Banking Industry: A Panel Double Bootstrap Approach

The impact of shifting business towards off-balance sheet (OBS) activities on the technical efficiency of Indian commercial banks is investigated using data envelopment analysis (DEA) based panel double bootstrap approach. Our results show that inclusion of OBS items in the banks’ output has positive causation with estimated efficiency. Thus, policies promoting OBS activities will help Indian banks not only in finding ways to exploit new profit opportunities but also in improving their efficiency.

How mitigation efforts moderate the impact of climate change on agricultural efficiency: a preliminary analysis from China

ABSTRACTIn this paper, we empirically evaluate the effect of climate change on agricultural technical efficiency, considering the moderating effect of mitigation efforts based on emission reduction in China. In particular, we directly measure the intensity of mitigation efforts using the climate change mitigation index. We then apply the two-stage double bootstrap DEA method to build up the empirical model, effectively avoiding biased estimation using the traditional two-stage DEA method. Our results show that the intensity of mitigation measures moderates the impacts of global warming on efficiency and mild mitigation measures are better than drastic ones.

Least Squares and Robust Rank-Based Double Bootstrap Analyses for Time-Series Intervention Designs.

Time-series intervention designs that include two or more phases have been widely discussed in the healthcare literature for many years. A convenient model for the analysis of these designs has a linear model part (to measure changes in level and trend) plus a second part that measures the random error structure; the error structure is assumed to follow an autoregressive time-series process. Traditional generalized linear model approaches widely used to estimate this model are less than satisfactory because they tend to provide substantially biased intervention tests and confidence intervals. We describe an updated version of the original double bootstrap approach that was developed by McKnight et al. (2000) to correct for this problem. This updated analysis and a new robust version were recently implemented in an R package (McKean & Zhang, 2018). The robust method is insensitive to outliers and problems associated with common departures from normality in the error distribution. Monte Carlo studies as well as published data are used to demonstrate the properties of both versions. The R code required to perform the analyses is provided and illustrated.

Healthcare public funding efficiency as exemplified by hospitals in Polish regions

The aim of this study is to evaluate and compare the financial and managerial efficiency of healthcare inpatient systems in one country. The research question is: What factors give rise to efficiency variations within the regional healthcare system (hospitals)?A two-step approach proposed by Simar and Wilson has been applied. The first step applies the Data Envelopment Analysis to estimate the unit (i.e., a Polish region in our research) efficiency scores, which is followed by truncated regression with double bootstrapping to examine the impact of uncontrolled variables on efficiency scores.The efficiency scores obtained in 16 regions from the output-oriented model with non-increasing returns to scale indicate a full effectiveness of five regions. The DEA scores of the other regions exceed the value of 0.8 and do not differ significantly.The bootstrap-corrected DEA scores do not considerably change the efficiency assessment. The direction of the impact of the ‘percentage of people above 65 years of age’ variable and the ‘growth rate of total liabilities on efficiency’ variable is opposite to that observed for the ‘average salary’ variable.The results obtained suggest that the regional healthcare system efficiency can be affected by the ageing population, pay pressure, and liabilities.

Exploring the efficiency of primary health care provision in rural and sparsely populated areas: a case study from Mongolia.

Mongolia is facing serious challenges in the health sector and the macro-economic sphere that have important implications for health financing and the completion of universal health coverage. In this context, improving the efficiency of primary health care facilities is a critical issue. We study the efficiency of Soum Health Centres (SHCs) that provide primary care in rural Mongolia. Based on activity and resources data collected for all SHCs of Mongolia in 2017 and 2018 we estimate bias-adjusted efficiency scores. A double bootstrap truncated regression procedure is then used to study the factors associated with SHCs' efficiency. On average, SHCs could potentially engage in the same activity while reducing overall resource use by ∼23%. A comparatively higher population density and dependency ratio in the districts where they are located tend to favour SHCs' efficiency. Conversely, the higher the poverty rate in the soum, the lower the efficiency. We find a positive association between SHCs' efficiency and the proportion of doctors in the health workforce. The human resources allocation process and the capitation formula currently used to pay SHCs should be adjusted based on the size and socioeconomic/demographic characteristics of the population living in the catchment area of SHCs.

A new adaptive sampling algorithm for big data classification

The exponential growth of the quantity of data that circulates on the web led to the emergence of the big data phenomenon. This fact is a natural consequence of the proliferation of social media, mobile devices, the abundance of free online storage, and new technologies like the internet of things. Subsequently, big data has created several challenges to the computer science community, among which the large size of data is the most challenging. Traditional machine learning algorithms used mostly for insight extraction find themselves inadequate, even on high-performance computer architectures. For instance, big data analytics algorithms can overcome the size issue by either: (1) adapting the existing machine learning techniques to the scale of the big data; or, (2) by sampling big datasets, choosing randomly much smaller subsets of the data population, to meet what current algorithms can handle. In the present work, we aim to proceed through the second alternative to address the size challenge in the big data context. We propose intelligent sampling techniques based on Scalable Simple Random Sampling (ScaSRS) and Subsampled Double Bootstrap (SDB). Test results carried out on public generic datasets show that our proposal is able to address the size dimension efficiently. The proposed algorithms were evaluative on a classification task where the obtained results provided significant improvement compared to the state-of-the-art.

Technical efficiency of resource-poor maize farmers in northern Ghana

Abstract Farm productivity in most developing countries remains low, hence the need to enhance technical efficiency (TE) of producers. This study evaluates the TE of maize production in rural Ghana, using primary data from a survey of smallholder producers. A two-stage double bootstrap data envelopment analysis (DEA) approach was used to assess TE and its determinants. The results revealed a bias-corrected mean TE of 68% (as opposed to 81% using the traditional DEA approach). Hence, with the prevailing technology and current input levels, farmers can increase their TE of maize production by 32%. TE increased with adoption of improved varieties, weeding frequency, and herd size but decreased with producer’s age, household size, educational status, and group membership. Subsequently, these factors need to be carefully considered in targeting policies for increasing maize productivity. The study observed increased adoption of improved varieties and training in efficient methods of weed control as important measures to enhance TE of maize farmers.

Efficiency and management factors: finding the balance in Thalassaemia care centres

BackgroundOptimizing efficiency has become increasingly critical with the growing demand for finite healthcare resources driven by population growth and an ageing society. Hence, policymakers are urgently finding more efficient ways to deliver health services. Thalassemia is a complex inherited blood disorder with significant prevalence in Malaysia. The high number of patients put substantial strain on the healthcare system. This study aims to evaluate the technical efficiency of thalassaemia care centres throughout Malaysia and the determinants that affect the efficiency.MethodData from 30 public hospitals with thalassaemia care centres were collected. A double bootstrap data envelopment analysis (DEA) approach is used with the assumption of input-oriented and variable-to-scale DEA models to generate technical efficiency scores. Bootstrap truncated regression was later conducted to identify the factors affecting the efficiency scores.ResultsThe mean bias-corrected technical efficiency score has improved to 0.75 in 2017 from 0.71 in 2016. In both years, more than 50% of thalassaemia care centres showed good efficiency scores (0.8-1.0). Management factors that affect the efficiency scores include separation of patient management (β = 0.0653) and budget (β = 0.0843), where they are found to positively affect the efficiency scores. In contrast, having longer operating hours is found to inversely influence the performance levels (β = − 0.4023).ConclusionsThe study provides a pioneering framework to evaluate the technical efficiency of thalassaemia treatment centres in public healthcare settings and could provide a useful guide for policymaker and thalassaemia care centre managers to improve efficiency in service delivery to thalassaemia patients and their caregivers without compromising quality of care.

Analysing drivers of efficiency in the leather industry: a two-stage double bootstrap DEA approach

PurposeThe Indian leather industry contributes to economic growth at a significant environmental cost. Due to the rising global demand for sustainable leather products, promoting efficient input utilisation has become vital. This study measures input efficiency and its determinants for leather industry in order for it to improve its future performance.Design/methodology/approachIn the first stage, bootstrap data envelopment analysis (DEA) approach is used for measuring efficiency and analysing firms' differences based on their geographical location, organisational structures, urban-rural location and sub-industrial groups. A second stage regression examines efficiency determinants using size, age, skill and capital-labour intensity as the explanatory variables.FindingsEfficiency result shows a significant potential of minimising inputs by 47% provided the firms adopt best practices. West Bengal firms, urban located firms, individual and proprietorship owned firms and leather consumer goods firms are found to be relatively efficient to their counterparts. Size, skilled managerial staff and labour-intensive firms positively affect efficiency.Practical implicationsConstruction of well-connected roads for accessing urban retail markets and provision of reliable electricity would improve efficiency of rural firms. Small-scale enterprises have a larger share in Indian leather industry; therefore, policy should focus on enhancing the firms' scale and investing in training facilities to skill employed labour for ensuring optimal use of inputs.Originality/valuePrevious studies on the leather industry have used the conventional DEA efficiency measurement approach. This study uses DEA bootstrapping model for robust efficiency estimates and provides consistent inferences about the determinants.

Level and determinants of county health system technical efficiency in Kenya: two stage data envelopment analysis

BackgroundImproving health system efficiency is a key strategy to increase health system performance and accelerate progress towards Universal Health Coverage. In 2013, Kenya transitioned into a devolved system of government granting county governments autonomy over budgets and priorities. We assessed the level and determinants of technical efficiency of the 47 county health systems in Kenya.MethodsWe carried out a two-stage data envelopment analysis (DEA) using Simar and Wilson’s double bootstrap method using data from all the 47 counties in Kenya. In the first stage, we derived the bootstrapped DEA scores using an output orientation. We used three input variables (Public county health expenditure, Private county health expenditure, number of healthcare facilities), and one outcome variable (Disability Adjusted Life Years) using 2018 data. In the second stage, the bias corrected technical inefficiency scores were regressed against 14 exogenous factors using a bootstrapped truncated regression.ResultsThe mean bias-corrected technical efficiency score of the 47 counties was 69.72% (95% CI 66.41–73.01%), indicating that on average, county health systems could increase their outputs by 30.28% at the same level of inputs. County technical efficiency scores ranged from 42.69% (95% CI 38.11–45.26%) to 91.99% (95% CI 83.78–98.95%). Higher HIV prevalence was associated with greater technical inefficiency of county health systems, while higher population density, county absorption of development budgets, and quality of care provided by healthcare facilities were associated with lower county health system inefficiency.ConclusionsThe findings from this analysis highlight the need for county health departments to consider ways to improve the efficiency of county health systems. Approaches could include prioritizing resources to interventions that will reduce high chronic disease burden, filling structural quality gaps, implementing interventions to improve process quality, identifying the challenges to absorption rates and reforming public finance management systems to enhance their efficiency.

THE DETERMINANTS OF MICROFINANCE INSTITUTIONS EFFICIENCY: THE ROLE OF WOMEN BORROWERS

Microfinance institutions (MFIs) are instrumental in enabling the economic empowerment of women. We examine the efficiency and performance of 84 Indian MFIs from 2016 to 2018 using a two-stage double bootstrap approach. Our results show that MFIs with increased outreach and actively target female borrowers achieve higher efficiency. Furthermore, we find larger MFIs and higher leverage intensity to be positively associated with efficiency. Government policies should be encouraged to support current MFIs to grow larger, actively target female borrowers and increase outreach to the poor to support India’s financial inclusion agenda and facilitate the economic empowerment of women whist revitalizing less efficient MFIs.

Integration in banking efficiency: a comparative analysis of the European Union, the Eurozone, and the United States banks

PurposeThis paper investigates the development of efficiency and the progress of banking integration in the European Union by checking for convergence among banks of European and Eurozone countries as well as contrasting the results with those of United States banks.Design/methodology/approachInitially, we employ the two-stage semi-parametric double bootstrap DEA method, which absorbs the effects of possible integration barriers in the measurement of efficiency. Afterwards, we apply a panel data model, in order to investigate the process of banking integration by testing for convergence and for convergent clusters in banking efficiency.FindingsOur main findings show that the bank efficiency of the US is considerably higher than that of the Eurozone and the European Union. Although there is no evidence of convergence across the banking groups, our results indicate the presence of club convergence. We also conclude that the US banking system is closer to convergence than the Eurozone and the European Union banks. Nevertheless, this outcome is subject to change in the future due to the fact that Eurozone and European Union banks' speed of convergence is higher than that of US banks.Originality/valueOur survey is unique in trying to check for convergence while controlling for country-specific and bank-specific factors that affect the efficiency of European and Eurozone banks. Moreover, recent literature does not compare the convergence of efficiency of Eurozone, European and US banking. Finally, in our paper special consideration was given to the comparison of commercial, cooperative and savings banks, as subsets of our banking groups.

Efficiency of South African water utilities: a double bootstrap DEA analysis

ABSTRACT Although the efficiency of the water sector has been studied extensively utilizing data envelopment analysis (DEA), most of the literature tends to use the conventional DEA model to compute efficiency scores. In addition, there are many studies that undertake a second stage regression of the efficiency scores against a set of covariates. However, such second-stage analyses are problematic due to potential serial correlation inherent in the estimated efficiency scores. To determine the bias-corrected efficiency scores of rural and urban water utilities in South Africa, this study uses a robust, non-parametric DEA bootstrapping model to generate them. Moreover, little is known about relative performance of the conventional DEA versus bias-corrected DEA. In addition, the truncated double-bootstrap regression results provide insights into the drivers of efficiency, including how water policies and the political and institutional contexts of water utilities can impact relative efficiencies. We found that there are significant differences between the rankings and efficiency scores generated by the conventional DEA model compared to the double-bootstrap DEA model, for both urban and rural samples. The regression model found the location and the ratio of metered to unmetered connections to be significant determinants of efficiency for both urban and rural water utilities.

Statistical inference in massive datasets by empirical likelihood

In this paper, we propose a new statistical inference method for massive data sets, which is very simple and efficient by combining divide-and-conquer method and empirical likelihood. Compared with two popular methods (the bag of little bootstrap and the subsampled double bootstrap), we make full use of data sets, and reduce the computation burden. Extensive numerical studies and real data analysis demonstrate the effectiveness and flexibility of our proposed method. Furthermore, the asymptotic property of our method is derived.

Technical and resource-use efficiencies of cashew production in Ghana: implications on achieving sustainable development goals

The expansion of Ghana’s cashew industry is expected to be a watershed moment in the country’s diversification of agricultural export commodity trade. In Ghana’s cashew farms, however, there is a significant difference between observed and potential farm yield. As a result, empirical study is required to serve as policy guidelines in order to improve farmer’s productive efficiency and, as a necessary consequence, contribute to the achievement of the Sustainable Development Goals (SDGs) of no poverty and zero hunger. The study explores farm-level productive efficiency and factors that can lead to variations in farmer’s technical efficiency in the Bono East region of Ghana. The single-stage double bootstrap Data Envelopment Analysis (DEA) was used to estimate technical efficiency and its determinants. The estimated results indicate that the average bias-corrected technical efficiency score (33%) was lower than the original average score (51%), suggesting that the original efficiency scores had been skewed upwards. Some of the primary factors that have been reported as having a significant effect on technical efficiency include the gender of respondents, educational attainment, and membership of farmer groups. Results of the resource-use efficiency analysis suggest that cashew farmers in Ghana do not escape the criticisms of inefficient resource allocation. Farm-level policies should be skewed towards enhancing resource-use efficiency through effective capacity-building to improve farmer’s management and technical capabilities, improve farm productivity, and consequently contribute to Ghana's quest to meet the sustainable development goals.