Double Bootstrap Research Articles

On Bootstrap Algorithms in Survey Sampling

Objective: The aim of this paper is to present bootstrap algorithms for measuring the accuracy of estimation and prediction in design-based and model-based approaches in survey sampling and small area estimation. Three proposals of prediction-mean squared error estimators are also examined. Research Design & Methods: Various bootstrap procedures are shown and used to estimate the design- and prediction-mean squared errors based on real data. Computations are supported by two R packages. Findings: Three prediction-mean squared error estimators are proposed. Implications / Recommendations: The bootstrap algorithms used in the design-based approach give similar results for the considered data for the variance estimates of the considered estimator, implying that the speed of the algorithms may be important for practitioners in cases of similar properties. The proposed estimators of the prediction mean squared error produce higher estimates than other estimators in the model-based approach, indicating a positive bias that can be interpreted as a pessimistic accuracy estimate. Contribution: All the presented bootstrap algorithms are easily applicable using two R packages available at R CRAN and GitHub. Three double bootstrap prediction-MSE estimators are proposed and analysed in the real-data application.

A double bootstrap data envelopment analysis model with stochastic reducible outputs and expandable inputs: An application to power plants

Clean production of electricity is not only cost-effective but also effective in reducing pollutants. Toward this end, the use of clean fuels is strongly recommended by environmentalists. Benchmarking techniques, especially data envelopment analysis, are an appropriate tool for measuring the relative efficiency of firms with environmental pollutants. In classic data envelopment analysis models, decision-makers are faced with production processes in which reducible inputs are used to produce expandable outputs. In this contribution, we consider production processes when the input and output data are given in stochastic form and some throughputs are reducible and some others are expandable. A stochastic directional distance function model is proposed to calculate the relative technical efficiency of firms. In order to evaluate firm-specific technical efficiency, we apply bootstrap DEA. We first calculate the technical efficiency scores of firms by classic DEA model. Then, the double bootstrap DEA model is applied to determine the impact of explanatory variables on firm efficiency. To demonstrate the applicability of the procedure, we present an empirical application wherein we employ power plants.

Research on the Validity of Bootstrap LM-Error Test in Spatial Random Effect Models

Under the condition of non-classical distributed errors, the test for spatial dependence in spatial panel data models is still a problem waiting to be solved. In this paper, we apply the FDB (Fast Double Bootstrap) method to spatial panel data models to test spatial dependence. In order to research the validity of the Bootstrap LM-Error test in spatial random effect models under the condition that the error term obeys a normal distribution, heteroscedasticity, or time-series correlation, we construct Bootstrap LM-Error statistics and make use of Monte Carlo simulation from size distortion and power aspects to carry out our research. The Monte Carlo simulation results show that the asymptotic LM-Error test in the spatial random effects model has a large size of distortion when the error term disobeys classical distribution. However, the FDB LM-Error test can effectively correct the size distortion of the asymptotic test with the precondition that there is nearly no loss of power in the FDB test. Obviously, compared to the asymptotic LM-Error test, the FDB LM-Error test is a more valid method to test spatial dependence in a spatial random effects model.

Portuguese Banks Efficiency: A Data Envelopment Analysis

This paper analyses the determinants of Portuguese Banking efficiency using a sample of 45 banks from 2005 to 2019. Simar and Wilson's two-stage approach [1] has been applied. Data envelopment analysis (DEA) was used in the first stage to estimate efficiency scores. In the second stage, a truncated regression was estimated with a double bootstrap to test the significance of the relationship between bank efficiency and its determinants.The results obtained indicate that, in general, Portuguese banking shows good levels of pure technical efficiency but poor results in scale efficiency, thus deteriorating the levels of total technical efficiency. After a decrease in total technical efficiency between 2005 and 2011, from 2012 onwards, it shows a positive trend. Our results also show that larger banks, better-capitalised, more profitable, with less credit risk and less diversified sources of income, are the most efficient.These results have implications for public policies adopted by the government and regulated by the competent authorities for the sector studied. Namely, creating large, well-capitalized banks should be promoted, preventing excess credit risk.

Hybrid Goldstone Modes from the Double Copy Bootstrap

We perform a systematic classification of scalar field theories whose amplitudes admit a double copy formulation and identify two building blocks at four-point and 13 at five-point. Using the four-point blocks simultaneously as bootstrap seeds, this naturally leads to a single copy theory that is a gauged nonlinear sigma model. Moreover, its double copy includes a novel theory that can be written in terms of Lovelock invariants of an induced metric, and includes Dirac-Born-Infeld and the special Galileon in specific limits. The amplitudes of these Goldstone modes have two distinct soft behavior regimes, corresponding to a hybrid of nonlinear symmetries. Published by the American Physical Society 2024

A firm-specific Malmquist productivity index model for stochastic data envelopment analysis: an application to commercial banks

In the data envelopment analysis (DEA) literature, productivity change captured by the Malmquist productivity index, especially in terms of a deterministic environment and stochastic variability in inputs and outputs, has been somewhat ignored. Therefore, this study developed a firm-specific, DEA-based Malmquist index model to examine the efficiency and productivity change of banks in a stochastic environment. First, in order to estimate bank-specific efficiency, we employed a two-stage double bootstrap DEA procedure. Specifically, in the first stage, the technical efficiency scores of banks were calculated by the classic DEA model, while in the second stage, the double bootstrap DEA model was applied to determine the effect of the contextual variables on bank efficiency. Second, we applied a two-stage procedure for measuring productivity change in which the first stage included the estimation of stochastic technical efficiency and the second stage included the regression of the estimated efficiency scores on a set of explanatory variables that influence relative performance. Finally, an empirical investigation of the Iranian banking sector, consisting of 120 bank-year observations of 15 banks from 2014 to 2021, was performed to measure their efficiency and productivity change. Based on the findings, the explanatory variables (i.e., the nonperforming loan ratio and the number of branches) indicated an inverse relationship with stochastic technical efficiency and productivity change. The implication of the findings is that, in order to improve the efficiency and productivity of banks, it is important to optimize these factors.

Cost Efficiency and its Determinants of Cane and Bamboo Enterprise in Assam: a Double Bootstrap DEA Approach

Cost Efficiency and its Determinants of Cane and Bamboo Enterprise in Assam: a Double Bootstrap DEA Approach

Healthcare system efficiency and drivers: Re-evaluation of OECD countries for COVID-19

The Covid-19 pandemic has raised concerns about the resilience of health systems. The aim of this study is twofold: i) to measure and compare the resilience of health system efficiency of OECD countries before and during Covid-19 and ii) to determine the healthcare efficiency drivers (e.g., socio-economic) of health system performance. Using a dataset of 31 OECD countries for 2018 and 2020, we first estimate bias-adjusted efficiency scores, followed by a double bootstrap truncated regression procedure to study the drivers associated with health system efficiency. We find that the health system efficiency overall score decreased among OECD countries during the Covid-19 pandemic compared to before Covid-19. Estonia and Japan retained their full efficiency scoreduring Covid-19. We find a negative association between health system efficiency and unemployment rate, share of health expenditure in GDP, and share of population over 65. Conversely, high vaccination rates contribute positively to health system efficiency during the Covid-19 period.

BANK EFFICIENCY AND GOVERNANCE: EVIDENCE FROM JOINT VENTURE AND FOREIGN COMMERCIAL BANKS IN VIETNAM

In this paper, we intend to examine the influence of national governance on the bank efficiency of joint venture and foreign commercial banks in Vietnam. Joint venture and foreign commercial banks have been instrumental in introducing new financial products to the Vietnamese market (e.g., mortgage services and medium-term certificates of deposit). At the same time, they have also penetrated the retail market through automobile and housing loans, and international credit card services. We use the DEA double bootstrap method to develop a bank network function to evaluate bank efficiency. The findings from our random-effects model demonstrate that world governance indicators as proposed by the World Bank independently determine the bank efficiency of the joint venture and foreign commercial banks in Vietnam. There are important implications to be highlighted for policymakers and stakeholders of joint venture and foreign commercial banks and other types of banks in the banking industry elsewhere around the world.

Estimation and bootstrapping under spatiotemporal models with unobserved heterogeneity

Proposed herein is a novel spatiotemporal model to characterize the unobserved heterogeneity across individuals using quantile-function-based correlated random effects and heteroscedastic innovations in a general framework. This model can be used to explore the influence of space-specific factors on latent effects at different quantile levels by controlling for spatiotemporal effects. A two-stage estimation procedure is introduced in which (i) the method of moments is used to estimate spatiotemporal effects then (ii) quantile regression is used for individual effects. A hybrid double bootstrapping procedure is then proposed to approximate the asymptotic distributions of coefficient estimators. The validity of the estimation and bootstrapping is established theoretically and then confirmed by simulation studies, and the usefulness of the proposed model is demonstrated with a real example involving city air quality.

CLUSTER FAST DOUBLE BOOTSTRAP APPROACH WITH RANDOM EFFECT SPATIAL MODELING

Panel data is a combination of cross-sectional and time series data. Spatial panel analysis is an analysis to obtain information based on observations affected by the space or location effects. The effect of location effects on spatial analysis is presented in the form of weighting. The use of panel data in spatial regression provides a number of advantages, however, the spatial dependence test and parameter estimators generated in the spatial regression of data panel will be inaccurate when applied to areas with a small number of spatial units. One method to overcome the problem of small spatial unit size is the bootstrap method. This study used the fast double bootstrap (FDB) method by modeling the poverty rate in the Flores islands. The data used in the study was sourced from the BPS NTT Province website. The results of Hausman test show that the right model is Random effect. The spatial dependence test concludes that there is a spatial dependence and the poverty modeling in the Flores islands tends to use the SAR model. SAR random effect model R2 shows the value of 77.38 percent and it does not meet the assumption of normality. Spatial Autoregressive Random effect model with the Fast Double Bootstrap approach is able to explain the diversity of poverty rate in the Flores Island by 99.83 percent and fulfilling the assumption of residual normality. The results of the analysis using the FDB approach on the spatial panel show better results than the common spatial panel.

A framework for mediation analysis with massive data

During the past few years, mediation analysis has gained increasing popularity across various research fields. The primary objective of mediation analysis is to examine the direct impact of exposure on outcome, as well as the indirect effects that occur along the pathways from exposure to outcome. There has been a great number of articles that applied mediation analysis to data from hundreds or thousands of individuals. With the rapid development of technology, the volume of avaliable data increases exponentially, which brings new challenges to researchers. Directly conducting statistical analysis for large datasets is often computationally infeasible. Nonetheless, there is a paucity of findings regarding mediation analysis in the context of big data. In this paper, we propose utilizing subsampled double bootstrap and divide-and-conquer algorithms to conduct statistical mediation analysis on large-scale datasets. The proposed algorithms offer a significant enhancement in computational efficiency over traditional bootstrap confidence interval and Sobel test, while simultaneously ensuring desirable confidence interval coverage and power. We conducted extensive numerical simulations to evaluate the performance of our method. The practical applicability of our approach is demonstrated through two real-world data examples.

Spatial Modeling of Fixed Effect and Random Effect with Fast Double Bootstrap Approach

Spatial Modeling of Fixed Effect and Random Effect with Fast Double Bootstrap Approach

The effect of crop insurance in Ecuadorian rice farming: a technical efficiency approach

PurposeThe aim of this study is to estimate the technical efficiency of the massive and economically important crop of rice in Ecuador, and then conduct a comparison between groups of farmers with and without insurance.Design/methodology/approachThe authors use an input-oriented data envelopment analysis approach (DEA) to estimate technical efficiency scores. The DEA is combined with the double bootstrap approach in Simar and Wilson (2007) to study factors that may affect technical efficiency. This method overcomes the traditional two-stage DEA approach frequently used in the efficiency literature. The authors thus research the role of insurance on rice efficiency production using this technique and sizeable field-level survey data from 376 rice farmers distributed in five provinces during the 2019 winter cycle in Ecuador.FindingsMost uninsured rice farmers operate with increasing returns to scale, which means that farms improve their resource use efficiency by increasing their size. However, since scale efficiencies are relatively high, it appears that inefficiencies are explained by inadequate input use. Also, the authors find evidence that insured farmers have a negative relationship with technical efficiency in rice production. In other results, when exploring the influence of additional variables on efficiency, the authors find that parameters related to transplanting, high education, farm size and some locations are positive and statistically significant.Social implicationsThe results of this work are relevant for policymakers interested in evaluating technology performance, risk management instruments and farm efficiency in an industry in a developing country such as rice production in Ecuador.Originality/valueThis paper is the first attempt to estimate farm-level technical efficiency employing the double bootstrap approach to assess the efficiency and its determinants of Ecuadorian rice producers.

The influence of organisational and staff characteristics on local governments’ efficiency: the case of Mexican municipalities

ABSTRACT Administrative capacity depends on organisational and human factors that can enhance or diminish the performance of local governments. To analyse the effect of these factors, efficiency scores of municipal governments were calculated and regressed against organisational and staff characteristics, using double bootstrap data envelopment analysis, on a sample of 1470 Mexican municipalities. Of the variables related to staff characteristics, the proportion of employees with college education, and remunerations, have a positive and statistically significant effect on efficiency. Of the organisational characteristics of local governments, the number of computers per employee was the main variable explaining the efficiency of municipal governments.

The impact of provincial port integration on port efficiency: Empirical evidence from China's Coastal Provinces

Port integration with the provincial territory as the primary spatial carrier has become an important initiative to implement port reform in China. Objectively evaluating and verifying its effectiveness is essential for refining and promoting this policy. This study empirically examines the effect of provincial port integration (PPI) on port efficiency from a provincial perspective by constructing the multi-period difference-in-differences (DID) model with the panel dataset of China's 9 coastal provinces from 2004 to 2019. The results show that: (1) Implementing PPI can significantly improve provincial port efficiency (PPE), but its impact on green provincial port efficiency (GPPE) is not significant, implying a lack of coordination between port integration and regional ecological protection. This conclusion remains robust to multiple scenarios, including truncated double bootstrapping approach test, placebo test, and endogeneity check. (2) The heterogeneity analysis demonstrates that PPI has a more significant incentive effect on PPE in smaller-scale provinces, provinces with lower levels of port specialization, provinces with larger port size, and provinces that implemented PPI after 2015. (3) Moderate administrative participation is more conducive to exerting the effect of PPI on PPE, and this effect presents an “inverted U-shaped” change characteristic as PPE increases.

Comparison of type I error and statistical power between state trace analysis and analysis of variance

State-Trace Analysis (STA) is a methodology for investigating the number of latent variables. Recently, a quantitative STA technique based on conjoint monotonic regression and double bootstrap method (STA-CMR) has been proposed. More discussion is needed on the type I error and the statistical power of this technique, as it adopts null hypothesis significance testing (NHST) to draw statistical inference. Because the results of STA are comparable with analysis of variance (ANOVA) in a three-factor experiment with linearity assumption, it is necessary to compare STA-CMR with ANOVA accordingly. This study investigated the type I error and the statistical power of STA-CMR and ANOVA in specific linear and nonlinear models using simulated data. Results demonstrated that both techniques were effective in the linear models, where ANOVA had a greater statistical power and STA-CMR had a more rigorous control of type I error. In the nonlinear models, although STA-CMR worked just as well as in the linear models, ANOVA completely lost its effectiveness. Besides, we found that the estimated type I error rate of STA-CMR was always smaller than the preset significance level in both linear and non-linear models. We suggest that the suppressed type I error rate may be caused by the bootstrap procedure, but the exact causes need further investigation. In conclusion, despite the suppressed type I error rate, STA-CMR can be a useful tool for determining the number of latent variables, particularly in non-linear models.

Estimating the Efficiency Gain of Covariate-Adjusted Analyses in Future Clinical Trials Using External Data.

We present a framework for using existing external data to identify and estimate the relative efficiency of a covariate-adjusted estimator compared to an unadjusted estimator in a future randomized trial. Under conditions, these relative efficiencies approximate the ratio of sample sizes needed to achieve a desired power. We develop semiparametrically efficient estimators of the relative efficiencies for several treatment effect estimands of interest with either fully or partially observed outcomes, allowing for the application of flexible statistical learning tools to estimate the nuisance functions. We propose an analytic Wald-type confidence interval and a double bootstrap scheme for statistical inference. We demonstrate the performance of the proposed methods through simulation studies and apply these methods to estimate the efficiency gain of covariate adjustment in Covid-19 therapeutic trials.

A Glimpse of Nonparametric Single and Double Residual Bootstrap Method with Outliers

A Glimpse of Nonparametric Single and Double Residual Bootstrap Method with Outliers

The effects of provider contract types and fiscal decentralization on the efficiency of the Polish hospital sector: A data envelopment analysis across 16 health regions

BackgroundExpenditures on hospitals constitute a large proportion of total health expenditures. In Poland the share of hospital spending is higher than the European Union average. The efficiency of the Polish hospital sector merits investigation. Research goalThe goal of this study is to estimate the relative technical efficiencies of Polish hospital regions, and to measure the impacts of provider contract types, fiscal decentralization, and the 2017 reform on the relative efficiencies. MethodsUsing data from 16 hospital regions in Poland for the years 2007 to 2019, we estimate relative technical efficiencies and their determinants using a two-stage approach. In the first stage, we apply Data Envelopment Analysis, in which we assume variable returns to scale and an output orientation. In the second stage we use a truncated regression with double bootstrapping. ResultsOur findings are threefold. First, fiscal decentralization may reduce technical efficiency, but the results was not statistically significant. Second, efficiency tended to be higher in regions where a greater proportion of nurses and midwives were offered employment as opposed to consulting contracts. Contract types offered to physicians were not statistically significant. Third, the 2017 reforms seem to have had a positive impact on efficiency to date. ConclusionPolicy makers may wish to consider offering less fiscal autonomy and control to regions and encouraging employment contracts with nurses and midwives.