Search

Highlights • New diagnostic serial interval (DSI): time between diagnoses of infector & infectee. • DSI is defined regardless of symptoms and easy to obtain. • In South Korea, mean DSI was found to be short: 3.63 days (95% CI: 3.24, 4.01). • Mean DSI is a possible new indicator for effectiveness of epidemic surveillance., Background The clinical onset serial interval is often used as a proxy for the transmission serial interval of an infectious disease. For SARS-CoV-2/COVID-19, data on clinical onset serial intervals is limited, since symptom onset dates are not routinely recorded and do not exist in asymptomatic carriers. Methods We define the diagnostic serial interval as the time between the diagnosis dates of the infector and infectee. Based on the DS4C project data on SARS-CoV-2/COVID-19 in South Korea, we estimate the means of the diagnostic serial interval, the clinical onset serial interval and the difference between the two. We use the balanced cluster bootstrap method to construct 95% bootstrap confidence intervals. Results The mean of the diagnostic serial interval was estimated to be 3.63 days (95% CI: 3.24, 4.01). The diagnostic serial interval was shown to be significantly shorter than the clinical onset serial interval (estimated mean difference -1.12 days, 95% CI: -1.98, -0.26). Conclusions The relatively short diagnostic serial intervals of SARS-CoV-2/COVID-19 in South Korea are likely due to the country’s extensive efforts towards contact tracing. We suggest the mean diagnostic serial interval as a new indicator for the effectiveness of a country’s contact tracing as part of the epidemic surveillance.

Highlights • From March 17 to October 22, 2020, a total of 80,108 deaths from all causes were registered in Ecuador, of which 36,922 (95% bootstrap confidence interval: 32,314–42,696) were estimated to be in excess of expected levels. • The peak in all-cause excess mortality in Ecuador may have occurred on April 4, 2020, with 909 excess deaths. • The real impact of the pandemic in Ecuador was much worse than indicated by reports from national institutions. • Ecuador is among the worst-hit countries in the world by the COVID-19 pandemic., Objectives Ecuador is among the worst-hit countries in the world by the COVID-19 pandemic. In terms of confirmed deaths per million inhabitants, as of October 22, Ecuador ranks fourth in the Americas and ninth worldwide according to data from the World Health Organization. In this report we estimate excess deaths due to any cause in Ecuador since the start of the lockdown measures on March 17, 2020 until October 22, 2020. Methods Estimates of excess deaths were calculated as the difference between the number of observed deaths from all causes and estimates of expected deaths from all causes. Expected deaths were estimated for the period March 17 to October 22, 2020 from forecasts of an ARIMA model of order (3,0,1) with drift which was applied to daily mortality data for the period January 1, 2014 to March 16, 2020. Results The number of all-cause excess deaths in Ecuador was estimated to be 36,922 (95% bootstrap confidence interval: 32,314–42,696) during the study period. The peak in all-cause excess mortality in Ecuador may have occurred on April 4, 2020, with 909 excess deaths. Conclusions Our results suggest that the real impact of the pandemic in Ecuador was much worse than indicated by reports from national institutions. Estimates of excess mortality might provide a better approximation of the true COVID-19 death toll. These estimates might capture not only deaths directly attributable to the COVID-19 pandemic but also deaths from other diseases that resulted from indirect effects of the pandemic.

Background Saying the words “Itadakimasu” and “Gochisosama” is a common Japanese ritual at the beginning and end of a meal. Many Japanese parents and educators communicate to children to express appreciation for food on a daily basis through these words, and they habitually connect these rituals to further education to avoid food waste to children. Objective This study aimed to examine whether appreciation for food mediates the association of meal-related rituals learned in childhood with the avoidance of food waste behavior among Japanese adults. Study Design, Setting, Participants Four hundred Japanese adults participated in the web-based cross-sectional questionnaire survey. Measurable Outcome/Analysis The following information was included in the questionnaire: participants’ background (age, sex, BMI, household size, subjective social status, and dietary change from a year ago), present avoiding food waste behaviors (measured by a sub-scale of validated “sustainable and healthy eating behaviors” questionnaire; 3 items), present appreciation for food (measured by a sub-scale of the Mindful Eating Inventory; 3 items), rituals before and after the meal in childhood (1 item), and advice from parents or educators to refrain from leaving food in childhood (1 item). Mediation analyses with percentile-corrected bootstrap confidence intervals were conducted to calculate the indirect effects adjusted for participants’ background. Results The participants’ mean (SD) age and BMI were 40.0 (11.6) years and 21.9 (3.9) kg/m2, respectively (female = 50.0%). The mean (SD) score of avoiding food waste was 16.0 (4.08; range: 7–21). Appreciation for food mediated the association between meal-related rituals before and after the meal (indirect effects fully adjusted models: B = 0.085, 95% CI = 0.009–0.184) and advice by parents or educators to refrain from leaving food (B = 0.101, 95% CI = 0.016–0.221) and avoiding food waste behavior. Conclusion Learning experiences from childhood seem to have an influence on present food waste behavior and are mediated by appreciation for food.

The purpose of this study is to examine the social impacts of events on participants’ satisfaction and whether loyalty is a result of this satisfaction when taking attendance to event into consideration. This study uses data from a sample of 542 participants who participated in the Kirkpinar Oil Wrestling Festival. Factor analysis was performed, and the data was sorted into seven different categories: community benefits, cultural and educational benefits, quality of life concerns, community resource concerns, attendance to event, satisfaction, and loyalty. Structural equation modeling was performed, and the hypotheses were tested using bootstrap confidence intervals in addition to classical testing procedures. The hypothesis results showed a direct effect on quality of life concerns and attendance to event. In events on satisfaction, there was also a direct effect on loyalty. In addition, there was an indirect effect on quality of life concerns and attendance to events on loyalty through satisfaction.

Rationale Peer victimization in children and adolescents is a serious public health concern. Growing evidence exists for negative consequences of peer victimization, but research has mostly been short term and little is known about the mechanisms that moderate and mediate the impacts of peer victimization on subsequent antisocial behavior. Objective The current study intended to examine the longitudinal relationship between peer victimization in adolescence and antisocial behavior in young adulthood and to determine whether sleep problems influence this relationship. Methods In total, 2006 adolescents participated in a prospective study from 2009 to 2013. The moderating role of sleep problems was examined by testing the significance of the interaction between peer victimization and sleep problems. The mediating role of sleep problems was tested by using bootstrapping mediational analyses. All analyses were conducted using SAS 9.3 software. Results We found that peer victimization during adolescence was positively and significantly associated with antisocial behavior in young adulthood (β = 0.10, p

This study demonstrates a bootstrap interval estimation of both OD flow and link traffic flows and its application. Although the causes of OD flow fluctuation are various, we focus the sampling error due by travel survey. We made a trial case study using Kumamoto Metropolitan Area person trip survey. We demonstrate an example of interval estimation of OD and link flow and discuss its implications.

The paper is a potpourri of short sections. There will be some reminiscences about Evarist (from the early 1970s), then some on infinite-dimensional limit theorems from 1950 through 1990. A section reviews a case of slow convergence in the central limit theorem for empirical processes (Beck, 1985) and another the “fast” convergence of Komlos–Major–Tusnady. The paper does an experimental exploration of bootstrap confidence intervals for the mean (of Pareto distributions) and (as less commonly seen) for the variance, of normal and Pareto distributions.

The aquaculture plant with a mooring system is a relatively novel concept compared with the traditional offshore structures and plenty of numerical models have been proposed to investigate its hydrodynamic behavior. In this study, the model uncertainty in hydrodynamic characteristics by several existing numerical models is estimated based on the validation data in the published researches. The traditional method is employed to calculate the statistics of the model bias factor and the bootstrap method is used to estimate the statistical uncertainty in the model bias factor due to the small sample size. In addition, the reliability analysis of mooring line is conducted considering the model uncertainty for a case study. The results indicate that the bootstrap method can effectively predict the uncertainty of the mean value and the standard deviation of the model bias factor and the model uncertainty can significantly affect the reliability of the mooring line. The bootstrap confidence interval of the reliability index can be calculated to achieve a more reasonable assessment of the failure probability for the designers. Therefore, the characterization of the statistical uncertainty in the model bias factor is of paramount importance for the reliability-based design of the aquaculture plant and its mooring system.

Turnover among the child welfare workforce has been linked to workforce demographics, individual-level work attitudes, and organizational conditions. It is relatively understudied how organizational and individual factors may be related to each other in predicting turnover among the voluntary (i.e., private, non-profit) child welfare workforce. The main purpose of this study was to investigate the indirect effects of organizational climate on turnover through voluntary child welfare workers’ job satisfaction. The sample consisted of 849 direct care and clinical workers in 13 voluntary agencies under contract with the public child welfare system in a northeastern state in the United States. Paper-and-pencil surveys were sent out to the agencies. Structural equation modeling was used to examine the relationship between organizational climate, job satisfaction, and turnover intentions. To examine the indirect effects of interest, bias-corrected and accelerated bootstrap confidence intervals based on 20,000 replications were obtained. Results suggested that the effect of organizational climate on intent to leave the agency was fully mediated by job satisfaction (β = -0.16, SE = 0.09, 95% CI = [−0.342, −0.002]), while its effect on intent to stay in child welfare was partially mediated (β = 0.15, SE = 0.06, 95% CI = [0.024, 0.280]). Voluntary child welfare agencies should consider redirecting their resources and focus on how their efforts into organizational changes may impact workers’ job satisfaction in pay, benefits, and promotion opportunities. Given that job satisfaction has a more immediate effect on turnover, it is worth investing in programs specifically designed to enhance job satisfaction. Limitations of our study and directions for future research are discussed.

I propose a nonparametric iid bootstrap procedure for the empirical likelihood, the exponential tilting, and the exponentially tilted empirical likelihood estimators that achieves asymptotic refinements for t tests and confidence intervals, and Wald tests and confidence regions based on such estimators. Furthermore, the proposed bootstrap is robust to model misspecification, i.e., it achieves asymptotic refinements regardless of whether the assumed moment condition model is correctly specified or not. This result is new, because asymptotic refinements of the bootstrap based on these estimators have not been established in the literature even under correct model specification. Monte Carlo experiments are conducted in dynamic panel data setting to support the theoretical finding. As an application, bootstrap confidence intervals for the returns to schooling of Hellerstein and Imbens (1999) are calculated. The result suggests that the returns to schooling may be higher.

In this paper, progressive Type-II hybrid censoring based on maximum product spacing method is introduced. Parameters estimation for the Power Lomax (PL) distribution are discussed under the progressive Type-II hybrid censoring based on maximum likelihood estimation and maximum product spacing method. A comparison studies with classical methods as maximum likelihood is discussed. Also, asymptotic confidence intervals and bootstrap confidence intervals are obtained. A numerical study using two real data and Monte Carlo simulation are performed to compare between the different methods.

Freight transport studies require, as a preliminary step, a survey to be conducted on a sample of the universe of agents, vehicles and/or companies of the transportation system. The statistical reliability of the data determines the goodness of the outcomes and conclusions that can be inferred from the analyses and models generated. The methodology contained herein, based on bootstrapping techniques, allows us to generate the confidence intervals of origin-destination pairs defined by each cell of the matrix derived from a freight transport survey. To address this study a data set from a statistically reliable freight transport study conducted in Spain at the level of multi-province inter-regions has been used.

For a number of researchers a number of publications for each author is simulated using the zeta distribution and then for each publication a number of citations per publication simulated. Bootstrap confidence intervals indicate that the difference between the average of ratios and the ratio of averages are not significant. It was found that the log–logistic distribution which is a general form for the ratio of two correlated Pareto random variables, give a good fit to the estimated ratios.

Is there a positive impact of intelligence on religious disbelief after we account for the fact that both average intelligence and religious disbelief tend to be higher in more developed countries? We carry out four beta regression analyses and conclude that the answer is yes. We also compute impact curves that show how the effect of intelligence on atheism changes with average intelligence quotients. The impact is stronger at lower intelligence levels, peaks somewhere between 100 and 110, and then weakens. Bootstrap standard errors for our point estimates and bootstrap confidence intervals are also computed.

Bootstrap confidence intervals on fixed-effects efficiency estimates in micro panels exhibit low coverage probabilities. We propose an alternative efficiency measure involving the mean of the firm effects. With the same estimated efficiency ranks as the traditional measure, its corresponding bootstrap confidence intervals have better coverage probabilities.

In general, poverty measures are estimated by applying income information. However, only using income data for calculating relative poverty might lead to an incomplete view. For example, a household can be under a poverty threshold even if a household member owns real estate or equity. In this thesis, at risk of income poverty in Germany is estimated. In order to get a more complete picture of at risk of poverty, a multidimensional approach is applied. Not only at risk of income poverty, also at risk of wealth poverty is measured. Moreover, households that are both at risk of income and wealth poor are analyzed. Furthermore, several poverty groups are identified: twice-poor which are households that are, at risk of income and wealth poverty; protected-poor, households that are at risk of income poverty but not at risk of wealth poverty; vulnerable-poor, households which are at risk of wealth poverty but not at risk of income poverty; non-poor, households which are either at risk of income poverty nor at risk of wealth poverty. Poverty profiles in Germany and their changes over time are analyzed for the years 2002, 2007 and 2012. In fact, it is investigated to which degree at risk of poverty rates differ in socio-economic characteristics. A logit regression is applied for each dimension and each wave for estimation. For robustness checks, 95 percent bootstrap confidence intervals are calculated for all results. Findings suggest that young age, region East Germany, single, lone parent, unemployment and low education are factors that condition the at risk of poverty rates. The definition of a certain rate influences the percentage of households that are affected by at risk of poverty, however, has a limited effect on poverty profiles. Poverty profiles have not changed over time but some factors such as unemployment and low education have significantly increased.

Constructing bootstrap confidence intervals for impulse response functions (IRFs) from structural vector autoregression (SVAR) models has become standard practice in empirical macroeconomic research. The accuracy of such confidence intervals can deteriorate severely, however, if the bootstrap IRFs are biased. We document an apparently common source of bias in the estimation of the VAR error covariance matrix which can be easily reduced by a scale adjustment. This bias is generally unrecognized because it only affects the bootstrap estimates of the error variance, not the original OLS estimates. Nevertheless, as we illustrate here, analytically, with sampling experiments, and in an example from the literature, the bootstrap error variance bias can have significant distorting effects on bootstrap IRF confidence intervals. We also show that scale-adjusted bootstrap confidence intervals can be expected to exhibit improved coverage accuracy.

We propose an adaptive importance resampling algorithm for estimating bootstrap quantiles of general statistics. The algorithm is especially useful in estimating extreme quantiles and can be easily used to construct bootstrap confidence intervals. Empirical results on real and simulated data sets show that the proposed algorithm is not only superior to the uniform resampling approach, but may also provide more than an order of magnitude of computational efficiency gains.

We propose an estimator for the expected busy period (denoted by β) of a controllable M/G/1 queueing system in which the server applies a bicriterion 〈p, N〉 policy during his idle period. Using this estimator, we construct new confidence intervals for β, which are based on five bootstrap methods; standard bootstrap (SB), percentile bootstrap (PB), bootstrap pivotal (BP), bias-corrected percentile bootstrap (BCPB), bias-corrected and accelerated bootstrap (BCa). A numerical simulation study is conducted in order to demonstrate performance of the proposed estimator β ˆ and bootstrap confidence intervals for β. From the simulation results, we show that β ˆ is a consistent estimator for β, which agrees with the theoretical results. In addition, we also investigate the accuracy of the five bootstrap confidence intervals by calculating the coverage percentage and the relative coverage (defined as the ratio of coverage percentage to average length of confidence interval). Detailed discussions of simulation results for three queueing models are presented.

This paper first studies the performance of the Lee–Carter [J. Am. Stat. Assoc. 419 (87) (1992) 659–675] model for mortality forecasting on the Nordic countries. Three approaches for computing the model parameters are compared: Singular Value Decomposition, Weighted Least Square and Maximum Likelihood Estimation. Hypothetical projections are also made, based on variable period intervals. Secondly, the paper addresses an extension to the Lee–Carter method: a residual bootstrapped technique is used to construct confidence intervals for forecasted life expectancies. Uncertainties produced with this method incorporate the variability from all parameters in the model, while the original Lee–Carter method focuses on the variability in the time-varying parameter.

Different estimators of high quantiles, such as x"p^c proposed in [N.M. Markovitch, U.R. Krieger, The estimation of heavy-tailed probability density functions, their mixtures and quantiles. Computer Networks 40 (3) (2002) 459-474], Weissman's estimator x"p^w and the POT-method are considered. Regarding the estimators x"p^c and x"p^w the asymptotic normality of the logarithms of ratios of these estimators to the true value of the quantile is proved. These estimators are applied to real data of Web sessions and pages. Furthermore, bootstrap confidence intervals of x"p^c and x"p^w are constructed for modelled data of different heavy-tailed distributions as well as for Web-traffic data.

We discuss the problem of comparing two estimates of Prevosti's genetic distance as an extension of the theory developed by the same authors in a previous study (Biometrics (1995) 51 (4) 1216). The asymptotic distribution of the difference between distances is established in some situations. For practical purposes the comparison is performed by building bootstrap confidence intervals for the difference between the distances. A simulation study to choose between competing methods shows a greater performance of those with better theoretical properties. As an example to show the possibilities of the method, and only for illustrative purposes, some data on the colonization of America by the fruit fly Drosophila subobscura are analyzed.

Some applications of the bootstrap involve smoothing the estimated distribution that is resampled, a method known as the smoothed bootstrap. Recently, the effect of resampling a kernel smoothed distribution was evaluated through expansions for the coverage of bootstrap percentile confidence intervals. It was shown that under a smooth function model, a bandwidth of order n−1/4 can accomplish a first-order correction for the one-sided percentile method. This paper proposes and investigates the performance of some data-based methods for selecting this bandwidth. The methods are studied through asymptotic comparisons and the resulting intervals are compared in the finite sample case to other well-known bootstrap confidence interval methods through a simulation study.

It is shown by an example that in general, the rate of bootstrap approximation to the studentized sample mean of lattice data is not better than the rate in the case of the normalized sample mean. A modified bootstrap method is proposed and shown to be second-order correct. Unlike the conventional "smoothed" bootstrap methods, the proposed procedure smooths the estimator rather than the resampling distribution. It is observed that irrespective of the lattice or nonlattice character of the data, confidence intervals based on this procedure have more accurate coverage probabilities than the usual bootstrap confidence intervals.

Following the comments of Schenker (1985), Efron (1987) introduced the BCa methodology to construct confidence intervals. In this article we demonstrate that the BCa confidence intervals can degenerate with a very high probability if a ⩾ 0.4. On the other hand, if a is small it is not necessary that the BCa intervals perform better in the sense of the size of the confidence interval and/or the coverage probability. This is illustrated by considering the estimation of confidence intervals for the variance components in a two way analysis of variance model.

The interpretation of C pk , a common measure of process capability and confidence limits for it, is based on the assumption that the process is normally distributed. The non-parametric but computer intensive method called Bootstrap is introduced and the standard Bootstrap confidence interval estimate for C pk is defined. An initial simulation of two processes (one normal and the other highly skewed) is presented and discussed.

The authors regret that the following changes should be made to this article. The caption for Fig. 3 should read: “Fig 3. Line graph showing the effect sizes, d, and their 95% bootstrap confidence interval for CT treatment (CT and CT+) at pre-intervention post-intervention and 6and 12-month follow-up relative to the pre-intervention control groupmean (and SD).” Lines 385–6, currently “included in a subsequent, longitudinal analysis of follow-up data, since they contained such data” should be “included in a subsequent analysis of clinical significance, since they contained such data.” Line 389, currently “(plus two additional studies in thewithin-group analysis)” should be “(plus two additional studies in the analysis of clinical significance).” Line 391, currently “and an additional 12 in the within-group analysis,” should be removed.

Nonparametric confidence bounds are obtained for a wide class of statistics using bootstrap. These results improve the errors in the probability estimates of the confidence intervals over the ones obtained by the normal approximation theory unconditionally.