Non-parametric Bootstrap Resampling Research Articles

Inference on the common mean direction of several Fisher-von Mises-Langevin populations with unknown concentration parameters

The problem of combining information from several samples for estimating or testing a common mean for normal populations has been extensively studied in the statistical literature. In this paper, we take up this problem in the context of the common mean direction of several Fisher-von Mises-Langevin (FvML) distributions. The concentration parameters are taken to be unknown and heterogeneous. A non-iterative combined estimator is proposed and is seen to have substantially better risk performance than individual sample mean directions and a grand mean direction in a simulation study. Further, a test based on this non-iterative estimator is proposed, and nonparametric bootstrap and permutation resampling methods are developed for its implementation. Two more alternative tests are proposed and their implementation is carried out using nonparametric bootstrap resampling. A detailed simulation study shows that these test procedures achieve the nominal size and have good power performance. An ‘R’ package is developed for the implementation of the tests. A real data set is considered for illustrating the procedures.

Cost-effectiveness analysis of direct admission to acute geriatric unit versus admission after an emergency department visit for elderly patients

BackgroundElderly individuals represent an increasing proportion of emergency department (ED) users. In the Greater Paris University Hospitals (APHP) direct-admission study, direct admission (DA) to an acute geriatric unit (AGU) was associated with a shorter hospital length of stay (LOS), lower post-acute care transfers, and lower risk of an ED return visit in the month following the AGU hospitalization compared with admission after an ED visit. Until now, no economic evaluation of DA has been available.MethodsWe aimed to evaluate the cost-effectiveness of DA to an AGU versus admission after an ED visit in elderly patients. This was conducted alongside the APHP direct-admission study which used electronic medical records and administrative claims data from the Greater Paris University Hospitals (APHP) Health Data Warehouse and involved 19 different AGUs. We included all patients ≥ 75 years old who were admitted to an AGU for more than 24 h between January 1, 2013 and December 31, 2018. The effectiveness criterion was the occurrence of ED return visit in the month following AGU hospitalization. We compared the costs of an AGU stay in the DA versus the ED visit group. The perspective was that of the payer. To characterise and summarize uncertainty, we used a non-parametric bootstrap resampling and constructed cost-effectiveness accessibility curves.ResultsAt baseline, mean costs per patient were €5113 and €5131 in the DA and ED visit groups, respectively. ED return visit rates were 3.3% (n = 81) in the DA group and 3.9% (n = 160) in the ED group (p = 0.21). After bootstrap, the incremental cost-effectiveness ratio was €-4249 (95%CI= -66,001; +45,547) per ED return visit averted. Acceptability curves showed that DA could be considered a cost-effective intervention at a threshold of €-2405 per ED return visit avoided.ConclusionThe results of this cost-effectiveness analysis of DA to an AGU versus admission after an ED visit for elderly patients argues in favor of DA, which could help provide support for public decision making.

A Temporal Instability Measure for fMRI Quality Assurance.

There exist several fMRI quality assurance measures to assess scanner stability. Because they have practical and/or theoretical limitations, a different and more practical measure for instability would be desirable. To develop and test a sensitive, reliable and widely applicable temporal instability measure (TIM) for fMRI quality assurance. Technical development. Spherical gel phantom. A total of 120 datasets from a local Philips scanner with two different receive-only head coils (32ch and 8ch, 60 datasets per coil) were collected as well as 29 additional datasets with three different receive-only head coils (20ch, 32ch, and 64ch) from two additional sites with GE (seven runs with 32ch) and Siemens scanners (seven runs with 32ch and Multiband imaging, five runs with 20ch, 32ch, and 64ch) were borrowed. 2D Echo-planar-imaging (EPI). A new TIM was proposed that is based on the eigenratio of the correlation coefficient matrix, where each entry of the matrix is a correlation coefficient between two time-points of the time-series. Nonparametric bootstrap resampling was used twice to estimate confidence intervals (CI) of the TIM values and to assess the improved sensitivity of this measure. Differences in coil performance were assessed via a nonparametric bootstrap two-sample t-test. P-values <0.05 were considered significant. The TIM values ranged between 60 parts-per-million and 10,780 parts-per-million across all 149 experiments. The mean CI was 2.96% and 2.16% for the 120 and 29 fMRI datasets, respectively (the repeated bootstrap analysis gave 2.9% and 2.19%, respectively). The 32ch coils of the local Philips data provided more stable measurements than the 8ch coil (observed two-sample t-values = 26.36, -0.2 and -6.2 for TIM, tSNR, and RDC, respectively. PtSNR = 0.58). The proposed TIM is particularly useful for multichannel coils with spatially nonuniform receive sensitivity and overcomes several limitations of other measures. As such, it provides a reliable test for ascertaining scanner stability for fMRI experiments. 5. Stage 1.

ALTERNATIVES TO THE CLASSICAL FREQUENTIST CONFIDENCE INTERVAL FOR DESCRIBING ZERO-INFLATED LEAF DISEASE SEVERITY

This paper presents the bootstrap percentile interval and the Bayesian credible interval as alternatives to the classical frequentist confidence interval for analysis of zero-inflated data. The indicated methods were applied to soybean downy mildew severity data obtained by stratified sampling in two municipalities in the state of São Paulo: Estiva Gerbi and Piracicaba. The amplitudes of the frequentist and bootstrap percentile confidence intervals were similar. For the Bayesian approach, the credible intervals of the posterior predictive distribution were considered using the zero-inflated beta distribution as likelihood. The credible intervals showed a wider range and included values in the upper bounds of the intervals greater than those observed in the data. We conclude that Bayesian inference is more complex, but allows incorporation of prior information regarding regional and seasonal aspects, contributing to better disease management in the field. When this information is not known, nonparametric bootstrap resampling is a simple alternative to construct intervals for zero-inflated data without assuming the distribution function.

A new active learning approach for adsorbate-substrate structural elucidation in silico.

Adsorbate interactions with substrates (e.g. surfaces and nanoparticles) are fundamental for several technologies, such as functional materials, supramolecular chemistry, and solvent interactions. However, modeling these kinds of systems in silico, such as finding the optimum adsorption geometry and energy, is challenging, due to the huge number of possibilities of assembling the adsorbate on the surface. In the current work, we have developed an artificial intelligence (AI) approach based on an active learning (AL) method for adsorption optimization on the surface of materials. AL uses machine learning (ML) regression algorithms and their uncertainties to make a decision (based on a policy) for the next unexplored structures to be computed, increasing, though, the probability of finding the global minimum with a small number of calculations. The methodology allows an accurate and automated structural elucidation of the adsorbate on the surface, based on the minimization of the total electronic energy. The new AL method for adsorption optimization was developed and implemented in the quantum machine learning software/agent for material design and discovery (QMLMaterial) program and was applied for C60@TiO2 anatase (101). It marks another software extension with a new feature in addition to the automatic structural elucidation of defects in materials and of nanoparticles as well. SCC-DFTB calculations were used to build the complex search surfaces with a reasonably low computational cost. An artificial neural network (NN) was employed in the AL framework evaluated together with two uncertainty quantification methods: K-fold cross-validation and non-parametric bootstrap (BS) resampling. Also, two different acquisition functions for decision-making were used: expected improvement (EI) and the lower confidence bound (LCB).

Transcatheter aortic valve implantation in patients with age ≤70 years: experience from two leading structural heart disease centers.

Transcatheter aortic valve implantation (TAVI) is emerging as an appealing management strategy for patients with severe aortic stenosis at intermediate, high or exceedingly high risk, but its risk-benefit profile in younger patients is less certain. We aimed to explore the outlook of patients aged 70 years or less and undergoing TAVI at 2 high-volume Italian institutions. We retrospectively collected baseline, imaging, procedural and outcome features of patients with age ≤70 years in whom TAVI was attempted at participating centers between 2012 and 2021. Non-parametric tests and bootstrap resampling were used for inferential purposes. A total of 39 patients were included, out of >3000 screened with heart team involvement and >1500 receiving TAVI. Most common or relevant indications for TAVI reduced life expectancy (e.g. cardiogenic shock or severe left ventricular systolic dysfunction), chronic obstructive pulmonary disease, morbid obesity, active or recent extra-cardiac cancer, porcelain aorta, neurologic disability, cirrhosis, or prior surgical aortic valve replacement, as well as extreme cachexia, and Hutchinson-Gilford progeria. At least two contemporary high-risk features were present in most cases. Transapical access was used in 5 (12.8%) cases, and a sheathless approach in 15 (38.5%). A variety of devices were used, including both balloon- and self-expandable devices. Clinical outcomes were satisfactory, despite the high-risk profile, at both short- and mid-term, with no in-hospital death, and 5.1% (95% confidence interval 0-12.8%) mortality at a median follow-up of 15 months (minimum 1; maximum 85). Notably, no case of significant valve deterioration requiring reintervention occurred. In carefully selected patients with 70 years or less of age and prohibitive risk for surgery or reduced life expectancy, TAVI represents a safe option with a favorable mid-term survival and low rate of adverse events.

A new active learning approach for global optimization of atomic clusters

In catalysis, an accurate structural elucidation of molecules, atomic clusters, nanoparticles and solid surfaces is required to understand chemical processes. Therefore, an efficient and automatic structure determination for these systems is of great benefit since it requires a global search within huge chemical spaces. In this work, we propose a new active learning (AL) method intended for atomic clusters that uses different supervised machine learning techniques and their uncertainties to decide the promising non-observed (virtual) structures to be evaluated from quantum calculations. The method was developed for structural elucidation of (I) clusters where all atomic coordinates are allowed to change in a continuous chemical space and (II) doped ones where the atoms exchange in a sufficiently rigid structure, thus, a discrete search space where all cluster descriptors are known. Particularly for case I, a genetic algorithm operator was used to create the unknown virtual structures (and then their descriptors) from the observed ones to improve the performance of the AL search. The proposed AL was applied to the global optimization of heteronuclear (Al4Si7 and 4Al@Si11) and homonuclear (Na20) clusters using self-consistent charge density-functional tight-binding (SCC-DFTB), where a new repulsion parameter was developed to reproduce isomers evaluated from high-level calculations. The performance of the Gaussian process and artificial neural network algorithms was evaluated together with several uncertainty quantification methods: from Gaussian process, K-fold cross-validation and nonparametric bootstrap (BS) resampling. The efficiency of the AL was compared to conventional global optimization methods, such as random search and a genetic algorithm. The results show that the AL can find efficiently the global minimum of atomic clusters.

Background Harmonic Probabilistic Model for Harmonic Responsibility Assessment Based on Nonparametric Methods

As the increasing integration of inverter‐interfaced renewable energy generators intensifies the volatility and uncertainty of background harmonics in the utility system, it is crucial to construct a precise background harmonic model and determine the harmonic responsibility to promote harmonic management. This paper proposes a probabilistic model of background harmonics for harmonic responsibility assessment based on nonparametric methods. First, the amplitude data of background harmonic voltage are segmented in chronological order considering the stochastic features. Then, the nonparametric Bootstrap resampling is introduced to handle the case of insufficient samples, and the Kernel density estimation with optimal bandwidth is used to depict the probability distribution characteristics in each time interval. For the sake of identifying the piecewise probability density function with optimal fitting effect, the goodness‐of‐fit test is subsequently applied. Finally, based on the proposed background harmonic probabilistic model, the harmonic responsibility assessment is conducted without the involvement of phase angle information. The detailed performance verification of the proposed model is carried out in light of the field‐measured data. The results validate that the proposed model outperforms the conventional parametric models in handling insufficient data and fitting accuracy and is helpful to achieve the effective quantification of the overall harmonic responsibility within a period of time. © 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Gonadotrophins or clomiphene citrate in couples with unexplained infertility undergoing intrauterine insemination: a cost-effectiveness analysis.

What is the cost-effectiveness of gonadotrophins compared with clomiphene citrate in couples with unexplained subfertility undergoing intrauterine insemination (IUI) with ovarian stimulation under strict cancellation criteria? A cost-effectiveness analysis alongside a randomized controlled trial (RCT). Between July 2013 and March 2016, 738 couples were randomized to gonadotrophins (369) or clomiphene citrate (369) in a multicentre RCT in the Netherlands. The direct medical costs of both strategies were compared. Direct medical costs included costs of medication, cycle monitoring, insemination and, if applicable, pregnancy monitoring. Non-parametric bootstrap resampling was used to investigate the effect of uncertainty in estimates. The cost-effectiveness analysis was performed according to intention-to-treat. The incremental cost-effectiveness ratio (ICER) between gonadotrophins and clomiphene citrate for ongoing pregnancy and live birth was assessed. The mean costs per couple were €1534 for gonadotrophins and €1067 for clomiphene citrate (mean difference of €468; 95% confidence interval [CI] €464-472). As ongoing pregnancy rates were 31% in women allocated to gonadotrophins and 26% in women allocated to clomiphene citrate (relative risk 1.16, 95% CI 0.93-1.47), the ICER was €21,804 (95% CI €11,628-31,980) per additional ongoing pregnancy with gonadotrophins and €17,044 (95% CI €8998-25,090) per additional live birth with gonadotrophins. Gonadotrophins are more expensive compared with clomiphene citrate in couples with unexplained subfertility undergoing IUI with adherence to strict cancellation criteria, without being significantly more effective.

Development and external validation of a logistic regression derived algorithm to estimate a 12-month post open defecation free slippage risk

Appropriate open defecation free (ODF) sustainability interventions are key to further mobilise communities to consume sanitation and hygiene products and services that enhance household’s quality of life and embed household behavioural change for heathier communities. This study aims to develop a logistic regression derived risk algorithm to estimate a 12-month ODF slippage risk and externally validate the model in an independent data set. ODF slippage occurs when one or more toilet adequacy parameters are no longer present for one or more toilets in a community. Data in the Zambia district health information software for water sanitation and hygiene management information system for Chungu and Chabula chiefdoms was used for the study. The data was retrieved from the date of chief Chungu and Chabula chiefdoms' attainment of ODF status in October 2016 for 12 months until September 2017 for the development and validation data sets respectively. Data was assumed to be missing completely at random and the complete case analysis approach was used. The events per variables were satisfactory for both the development and validation data sets. Multivariable regression with a backwards selection procedure was used to decide candidate predictor variables with p &lt; 0.05 meriting inclusion. To correct for optimism, the study compared amount of heuristic shrinkage by comparing the model’s apparent C-statistic to the C- statistic computed by nonparametric bootstrap resampling. In the resulting model, an increase in the covariates ‘months after ODF attainment’, ‘village population’ and ‘latrine built after CLTS’, were all associated with a higher probability of ODF slippage. Conversely, an increase in the covariate ‘presence of a handwashing station with soap’, was associated with reduced probability of ODF slippage. The predictive performance of the model was improved by the heuristic shrinkage factor of 0.988. The external validation confirmed good prediction performance with an area under the receiver operating characteristic curve of 0.85 and no significant lack of fit (Hosmer-Lemeshow test: p = 0.246). The results must be interpreted with caution in regions where the ODF definitions, culture and other factors are different from those asserted in the study.

Statistical Significance Assessment of Phase Synchrony in the Presence of Background Couplings: An ECoG Study.

Statistical significance testing is a necessary step in connectivity analysis. Several statistical test methods have been employed to assess the significance of functional connectivity, but the performance of these methods has not been thoroughly evaluated. In addition, the effects of the intrinsic brain connectivity and background couplings on performance of statistical test methods in task-based studies have not been investigated yet. The background couplings may exist independent of cognitive state and can be observed on both pre- and post-stimulus time intervals. The background couplings may be falsely detected by a statistical test as task-related connections, which can mislead interpretations of the task-related functional networks. The aim of this study was to investigate the relative performance of four commonly used non-parametric statistical test methods-surrogate, demeaned surrogate, bootstrap resampling, and Monte Carlo permutation methods-in the presence of background couplings and noise, with different signal-to-noise ratios (SNRs). Using simulated electrocorticographic (ECoG) datasets and phase locking value (PLV) as a measure of functional connectivity, we evaluated the performances of the statistical test methods utilizing sensitivity, specificity, accuracy, and receiver operating curve (ROC) analysis. Furthermore, we calculated optimal p values for each statistical test method using the ROC analysis, and found that the optimal p values were increased by decreasing the SNR. We also found that the optimal p value of the bootstrap resampling was greater than that of other methods. Our results from the simulation datasets and a real ECoG dataset, as an illustrative case report, revealed that the bootstrap resampling is the most efficient non-parametric statistical test for identifying the significant PLV of ECoG data, especially in the presence of background couplings.

Metabolisable energy prediction in energy feedstuffs and evaluation of the stepwise validation procedure using bootstrapping

The use of predicted values of apparent metabolisable energy (AME), obtained from regression equations, can be useful for both research institutions and nutrition industries. However, there is a need to validate independent samples to ensure that the predicted equation for AME is reliable. In this study, data was collected in order to estimate the prediction equations of corn, sorghum and wheat bran for pig feed, based on the chemical composition, in addition to evaluating the validity of the stepwise selection procedure regressive method of non-parametric bootstrap resampling. Data from metabolism trials in pigs and the chemical composition of feedstuffs was collected from both Brazilian and international literature, expressed as dry matter. After the residue analysis, five models of multiple linear regression were adjusted to randomly generate 1000 bootstrap samples of equal size from the database via meta-analysis. The five estimated models were adjusted for all bootstrapped samples using the stepwise method. The highest percentage significance for regressor (PSR) value was observed for digestible energy (100%) in the AME1 model, and gross energy (95.7%) in the AME2 model, indicating high correlation of the regressive model with AME. The regressors selected for AME4 and AME5 resulted in a PSR of greater than 50%, and were validated for estimating the AME of pig feed. However, the percentage of joint occurrence of regressor models showed low reliability, with values between 2.6% (AME2) and 23.4% (AME4), suggesting that the stepwise procedure was invalid.

Generalized Lomb\u2013Scargle analysis of mathrm {^{90}Sr/^{90}Y} decay rate measurements from the Physikalisch\u2013Technische Bundesanstalt

We apply the generalized Lomb–Scargle (LS) periodogram to independently confirm the claim by Sturrock et al. (Astropart Phys 84:8. https://doi.org/10.1016/j.astropartphys.2016.07.005, 2016) of an oscillation at a frequency of 11/year in the decay rates of mathrm {^{90}Sr/^{90}Y} from measurements at the Physikalisch Technische Bundesanstalt (PTB), which however has been disputed by Kossert and Nahle (Astropart Phys 69:18. https://doi.org/10.1016/j.astropartphys.2015.03.003, 2015). For this analysis, we made two different ansatze for the errors. For each peak in the LS periodogram, we evaluate the statistical significance using non-parametric bootstrap resampling. We find using both of these error models evidence for 11/year periodicity in the mathrm {^{90}Sr/^{90}Y} data for two of the three samples, but at a lower significance than claimed by Sturrock et al. [1].

Applying causal mediation analysis to personality disorder research.

This article is designed to address fundamental issues in the application of causal mediation analysis to research on personality disorders. Causal mediation analysis is used to identify mechanisms of effect by testing variables as putative links between the independent and dependent variables. As such, it would appear to have relevance to personality disorder research. It is argued that proper implementation of causal mediation analysis requires that investigators take several factors into account. These factors are discussed under 5 headings: variable selection, model specification, significance evaluation, effect size estimation, and sensitivity testing. First, care must be taken when selecting the independent, dependent, mediator, and control variables for a mediation analysis. Some variables make better mediators than others and all variables should be based on reasonably reliable indicators. Second, the mediation model needs to be properly specified. This requires that the data for the analysis be prospectively or historically ordered and possess proper causal direction. Third, it is imperative that the significance of the identified pathways be established, preferably with a nonparametric bootstrap resampling approach. Fourth, effect size estimates should be computed or competing pathways compared. Finally, investigators employing the mediation method are advised to perform a sensitivity analysis. Additional topics covered in this article include parallel and serial multiple mediation designs, moderation, and the relationship between mediation and moderation. (PsycINFO Database Record

Rethinking an ROC partial area index for evaluating the classification performance at a high specificity range

The area under a receiver operating characteristic (ROC) curve is valuable for evaluating the classification performance described by the entire ROC curve in many fields including decision making and medical diagnosis. However, this can be misleading when clinical tasks demand a restricted specificity range. The partial area under a portion of the ROC curve ( $${ pAUC}$$ ) has more practical relevance in such situations, but it is usually transformed to overcome some drawbacks and improve its interpretation. The standardized $${ pAUC}$$ ( $${ SpAUC}$$ ) index is considered as a meaningful relative measure of predictive accuracy. Nevertheless, this $${ SpAUC}$$ index might still show some limitations due to ROC curves crossing the diagonal line, and to the problem when comparing two tests with crossing ROC curves in the same restricted specificity range. This paper provides an alternative $${ pAUC}$$ index which overcomes these limitations. Tighter bounds for the $${ pAUC}$$ of an ROC curve are derived, and then a modified $${ pAUC}$$ index for any restricted specificity range is established. In addition, the proposed tighter partial area index ( $${ TpAUC}$$ ) is also shown for classifier when high specificity must be clinically maintained. The variance of the $${ TpAUC}$$ is also studied analytically and by simulation studies in a theoretical framework based on the most typical assumption of a binormal model, and estimated by using nonparametric bootstrap resampling in the empirical examples. Simulated and real datasets illustrate the practical utility of the $${ TpAUC}$$ .

Bioequivalence evaluation of sparse sampling pharmacokinetics data using bootstrap resampling method

ABSTRACTBioequivalence studies are an essential part of the evaluation of generic drugs. The most common in vivo bioequivalence study design is the two-period two-treatment crossover design. The observed drug concentration–time profile for each subject from each treatment under each sequence can be obtained. AUC (the area under the concentration–time curve) and Cmax (the maximum concentration) are obtained from the observed drug concentration–time profiles for each subject from each treatment under each sequence. However, such a drug concentration–time profile for each subject from each treatment under each sequence cannot possibly be available during the development of generic ophthalmic products since there is only one-time point measured drug concentration of aqueous humor for each eye. Instead, many subjects will be assigned to each of several prespecified sampling times. Then, the mean concentration at each sampling time can be obtained by the simple average of these subjects’ observed concentration. One profile of the mean concentration vs. time can be obtained for one product (either the test or the reference product). One AUC value for one product can be calculated from the mean concentration–time profile using trapezoidal rules. This article develops a novel nonparametric method for obtaining the 90% confidence interval for the ratio of AUCT and AUCR (or CT,max/CR,max) in crossover studies by bootstrapping subjects at each time point with replacement or bootstrapping subjects at all sampling time points with replacement. Here T represents the test product, and R represents the reference product. It also develops a novel nonparametric method for estimating the standard errors (SEs) of AUCh and Ch,max in parallel studies by bootstrapping subjects treated by the hth product at each time point with replacement or bootstrapping subjects treated by the hth product at all sampling time points with replacement, h = T, R. Then, 90% confidence intervals for AUCT/AUCR and CT,max/CR,max are obtained from the nonparametric bootstrap resampling samples and are used for the evaluation of bioequivalence study for one-time sparse sampling data.

A search for evidence of solar rotation in Super-Kamiokande solar neutrino dataset

We apply the generalized Lomb–Scargle (LS) periodogram, proposed by Zechmeister and Kurster, to the solar neutrino data from Super-Kamiokande (Super-K) using data from its first five years. For each peak in the LS periodogram, we evaluate the statistical significance in two different ways. The first method involves calculating the False Alarm Probability (FAP) using non-parametric bootstrap resampling, and the second method is by calculating the difference in Bayesian Information Criterion (BIC) between the null hypothesis, viz. the data contains only noise, compared to the hypothesis that the data contains a peak at a given frequency. Using these methods, we scan the frequency range between 7–14 cycles per year to look for any peaks caused by solar rotation, since this is the proposed explanation for the statistically significant peaks found by Sturrock and collaborators in the Super-K dataset. From our analysis, we do confirm that similar to Sturrock et al, the maximum peak occurs at a frequency of 9.42/year, corresponding to a period of 38.75 days. The FAP for this peak is about 1.5% and the difference in BIC (between pure white noise and this peak) is about 4.8. We note that the significance depends on the frequency band used to search for peaks and hence it is important to use a search band appropriate for solar rotation. However, The significance of this peak based on the value of BIC is marginal and more data is needed to confirm if the peak persists and is real.

Is IVF-served two different ways-more cost-effective than IUI with controlled ovarian hyperstimulation?

What is the cost-effectiveness of in vitro fertilization (IVF) with conventional ovarian stimulation, single embryo transfer (SET) and subsequent cryocycles or IVF in a modified natural cycle (MNC) compared with intrauterine insemination with controlled ovarian hyperstimulation (IUI-COH) as a first-line treatment in couples with unexplained subfertility and an unfavourable prognosis on natural conception?. Both IVF strategies are significantly more expensive when compared with IUI-COH, without being significantly more effective. In the comparison between IVF-MNC and IUI-COH, the latter is the dominant strategy. Whether IVF-SET is cost-effective depends on society's willingness to pay for an additional healthy child. IUI-COH and IVF, either after conventional ovarian stimulation or in a MNC, are used as first-line treatments for couples with unexplained or mild male subfertility. As IUI-COH is less invasive, this treatment is usually offered before proceeding to IVF. Yet, as conventional IVF with SET may lead to higher pregnancy rates in fewer cycles for a lower multiple pregnancy rate, some have argued to start with IVF instead of IUI-COH. In addition, IVF in the MNC is considered to be a more patient friendly and less costly form of IVF. We performed a cost-effectiveness analysis alongside a randomized noninferiority trial. Between January 2009 and February 2012, 602 couples with unexplained infertility and a poor prognosis on natural conception were allocated to three cycles of IVF-SET including frozen embryo transfers, six cycles of IVF-MNC or six cycles of IUI-COH. These couples were followed until 12 months after randomization. We collected data on resource use related to treatment, medication and pregnancy from the case report forms. We calculated unit costs from various sources. For each of the three strategies, we calculated the mean costs and effectiveness. Incremental cost-effectiveness ratios (ICER) were calculated for IVF-SET compared with IUI-COH and for IVF-MNC compared with IUI-COH. Nonparametric bootstrap resampling was used to investigate the effect of uncertainty in our estimates. There were 104 healthy children (52%) born in the IVF-SET group, 83 (43%) the IVF-MNC group and 97 (47%) in the IUI-COH group. The mean costs per couple were €7187 for IVF-SET, €8206 for IVF-MNC and €5070 for IUI-COH. Compared with IUI-COH, the costs for IVF-SET and IVF-MNC were significantly higher (mean differences €2117; 95% CI: €1544-€2657 and €3136, 95% CI: €2519-€3754, respectively).The ICER for IVF-SET compared with IUI-COH was €43 375 for the birth of an additional healthy child. In the comparison of IVF-MNC to IUI-COH, the latter was the dominant strategy, i.e. more effective at lower costs. We only report on direct health care costs. The present analysis is limited to 12 months. Since we found no evidence in support of offering IVF as a first-line strategy in couples with unexplained and mild subfertility, IUI-COH should remain the treatment of first choice. The study was supported by a grant from ZonMw, the Netherlands Organization for Health Research and Development, (120620027) and a grant from Zorgverzekeraars Nederland, the Netherlands' association of health care insurers (09-003). Current Controlled Trials ISRCTN52843371; Nederlands Trial Register NTR939.

Multiple Comparisons for a Psychophysical Test in Bootstrap Logistic Regression

We propose an algorithm of multiple comparisons with a control for a psychophysical test. Our algorithm is based on the step-down procedure and is applicable to the bootstrap test in logistic regression. We use logistic regression combined with guessing rate and log-likelihood ratio test statistics of multiple samples in order to test hypotheses by using non-parametric bootstrap resampling. We apply our algorithm to visual acuity measurement, and show that bootstrap resampling can be used to resolve problems with multiple comparisons especially when the numbers of observations among samples are not identical.

Regional frequency analysis of extreme precipitation with consideration of uncertainties to update IDF curves for the city of Trondheim

Summary Regional frequency analysis based on the method of L -moments is performed from annual maximum series of extreme precipitation intensity to update Intensity–Duration-Frequency (IDF) curves for the city of Trondheim. The main problems addressed are (1) reduction of uncertainties of different sources for reliable estimation of quantiles: (i) testing of trend patterns and stationarity of the data series from the target site and demonstrating the dependency of results on the data used; (ii) testing regional homogeneity of extreme precipitation events for the climate regime in the study area and “pooling” of regional data for data augmentation and reduction of uncertainty due to short length of data series; and (iii) selection of distributions for extreme precipitation events of different durations to reduce the uncertainty due to choice of distributions; and (2) assessment and quantification of sampling uncertainty in terms of interval estimates (confidence bounds) of quantiles. Trend patterns and check for stationarity were demonstrated for a data from a target site based on both non-parametric Mann–Kendall and parametric regression tests. Selection of distributions was performed based on Z -statistics and L -moment ratio diagrams. Non-parametric balanced bootstrap resampling was used to quantify the sampling uncertainty. For extreme precipitation events of shorter durations (5–30 min) there are statistically significant increasing trend patterns for the data series with start years of 1992–1998 while there are no significant trend patterns for recent extremes and there are no statistically significant trend patterns for longer durations (45–180 min). The results of the analyses indicate that: (1) significance tests for trend patterns and stationarity are dependent on the data series used but the stationarity assumption is valid for the data series used from the target site. (2) the extreme precipitation events from four sites in Trondheim are homogeneous and can be “pooled” for regional analysis; (3) different types of distributions fit to extreme precipitation events of different durations which shows that thorough selection of distributions is indispensable rather than fitting a single distribution for the whole durations; (4) interval estimates from balanced bootstrap resampling indicated that there is huge sampling uncertainty in quantile estimation that needs to be addressed in any frequency analysis; and (5) large differences are observed between the IDF curves from this study and the existing IDF curves (i.e. Imetno). The IDF curves from this study are from data augmented through regional analysis, based on thorough procedures for selection of distributions and also include uncertainty bounds and hence are more reliable than the existing one. Hence, the methods and procedures followed in this study are expected to contribute to endeavors for estimating reliable IDF curves.