SEARCH · PubMed Health

Results for “Bootstrap resampling”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 307 records · Page 17Linked to original sources

PubMed2005

Cluster randomized trials: another problem for cost-effectiveness ratios.

OBJECTIVES: This work has investigated under what conditions cost-effectiveness data from a cluster randomized trial (CRT) are suitable for analysis using a cluster-adjusted nonparametric bootstrap. The bootstrap's main advantages are in dealing with skewed data and its ability to take correlations between costs and effects into account. However, there are known theoretical problems with a commonly used cluster bootstrap procedure, and the practical implications of these require investigation. METHODS: Simulations were used to estimate the coverage of confidence intervals around incremental cost-effectiveness ratios from CRTs using two bootstrap methods. RESULTS: The bootstrap gave excessively narrow confidence intervals, but there was evidence to suggest that, when the number of clusters per treatment arm exceeded 24, it might give acceptable results. The method that resampled individuals as well as clusters did not perform well when cost and effectiveness data were correlated. CONCLUSIONS: If economic data from such trials are to be analyzed adequately, then there is a need for further investigations of more complex bootstrap procedures. Similarly, further research is required on methods such as the net benefit approach.

Cluster Analysis↗

PubMed1999

Validation procedures in radiologic diagnostic models. Neural network and logistic regression.

OBJECTIVE: To compare the performance of two predictive radiologic models, logistic regression (LR) and neural network (NN), with five different resampling methods. METHODS: One hundred sixty-seven patients with proven calvarial lesions as the only known disease were enrolled. Clinical and CT data were used for LR and NN models. Both models were developed with cross-validation, leave-one-out, and three different bootstrap algorithms. The final results of each model were compared with error rate and the area under receiver operating characteristic curves (Az). RESULTS: The NN obtained statistically higher Az values than LR with cross-validation. The remaining resampling validation methods did not reveal statistically significant differences between LR and NN rules. CONCLUSIONS: The NN classifier performs better than the one based on LR. This advantage is well detected by three-fold cross-validation but remains unnoticed when leave-one-out or bootstrap algorithms are used.

Adolescent↗

PubMed1990

Mitochondrial DNA evolution in primates: transition rate has been extremely low in the lemur.

Based on mitochondrial DNA (mt-DNA) sequence data from a wide range of primate species, branching order in the evolution of primates was inferred by the maximum likelihood method of Felsenstein without assuming rate constancy among lineages. Bootstrap probabilities for the maximum likelihood tree topology among alternatives were estimated without performing a maximum likelihood estimation for each resampled data set. Variation in the evolutionary rate among lineages was examined for the maximum likelihood tree by a method developed by Kishino and Hasegawa. From these analyses it appears that the transition rate of mtDNA evolution in the lemur has been extremely low, only about 1/10 that in other primate lines, whereas the transversion rate does not differ significantly from that of other primates. Furthermore, the transition rate in catarrhines, except the gibbon, is higher than those in the tarsier and in platyrrhines, and the transition rate in the gibbon is lower than those in other catarrhines. Branching dates in primate evolution were estimated by a molecular clock analysis of mtDNA, taking into account the rate of variation among different lines, and the results were compared with those estimated from nuclear DNA. Under the most likely model, where the evolutionary rate of mtDNA has been uniform within a great apes/human clade, human/chimpanzee clustering is preferred to the alternative branching orders among human, chimpanzee, and gorilla.

Animals↗

PubMed1997

Bootstrapping regression parameters in multivariate survival analysis.

Bootstrap methods are proposed for estimating sampling distributions and associated statistics for regression parameters in multivariate survival data. We use an Independence Working Model (IWM) approach, fitting margins independently, to obtain consistent estimates of the parameters in the marginal models. Resampling procedures, however, are applied to an appropriate joint distribution to estimate covariance matrices, make bias corrections, and construct confidence intervals. The proposed methods allow for fixed or random explanatory variables, the latter case using extensions of existing resampling schemes (Loughin, 1995), and they permit the possibility of random censoring. An application is shown for the viral positivity time data previously analyzed by Wei, Lin, and Weissfeld (1989). A simulation study of small-sample properties shows that the proposed bootstrap procedures provide substantial improvements in variance estimation over the robust variance estimator commonly used with the IWM.

Acquired Immunodeficiency Syndrome↗

PubMed2026

iMTSS: an integrated framework for biology- and patient-driven prognosis in myelofibrosis undergoing transplantation.

BACKGROUND: Allogeneic hematopoietic cell transplantation is the only curative treatment for myelofibrosis, but failure occurs by two mechanistically distinct routes: relapse of the neoplasm, which reflects its underlying genetics, and non-relapse mortality, which reflects whether the patient and graft tolerate the procedure. Established prognostic systems either lack molecular granularity or were derived in the non-transplant setting, and all collapse these two routes into a single survival estimate. None can indicate why an individual patient is at risk, or which class of intervention might reduce that risk. OBJECTIVE: To determine why an individual patient is at risk and to develop and validate an integrated framework that quantifies biology- and patient-driven prognosis. STUDY DESIGN: We analyzed 1,550 adults undergoing first allogeneic transplantation for primary or secondary myelofibrosis across international centers, the largest genomically annotated transplant cohort in this disease. The cohort was split into development (n=930) and validation (n=620) sets. Overall survival was modeled by Cox regression; relapse and non-relapse mortality were modeled as competing events by Fine-Gray subdistribution-hazard regression at 2 years. Discrimination was assessed by the concordance index with bootstrap confidence intervals. The molecular contribution was quantified by variance decomposition of, and robustness to the analytic choices was examined by resampling. RESULTS: A genetically defined disease-intrinsic axis, including TP53 allelic state, RAS pathway mutations, ASXL1 and driver genotype, blasts and blood counts, predicted 2 year relapse incidence (validation concordance 0.69, 95% CI 0.63 to 0.74), whereas a non-overlapping host and structural axis, including portal vein thrombosis, donor type, patients' performance status, and age predicted 2-year non-relapse mortality (0.63, 95% CI 0.59 to 0.68). The two scores shared only 3.4% of their variance, indicating that a patient's disease genetics carried almost no information about non-relapse mortality. Variance decomposition showed that TP53 allelic state alone accounted for 30% of the relapse score. Recombined, the framework discriminated overall survival (concordance 0.640, 95% CI 0.616 to 0.662) better than every established prognostic system. For proof of concept, 3 risk groups separated in the validation cohort, with 5 year survival of 72%, 58%, and 39% (P<0.001), and the models were well calibrated. CONCLUSIONS: Relapse and non-relapse mortality after transplantation for myelofibrosis are governed by distinct dimensions. Estimating both outcomes independently with genetic and clinical information, in addition to overall survival, establishes an individualized basis for transplant decision-making. The calculator is openly available (https://imtss-calculator.com).

mortality↗

PubMed1999

Resampling and multiplicity in cost-effectiveness inference.

We compare published methods for placing statistical confidence limits around incremental cost-effectiveness ratio statistics and show that only a nonparametric, bootstrap approach using polar angles gives completely reasonable results when neither treatment has significant advantages in cost or effectiveness. We also discuss alternative ways to report analytical results using plots, confidence or tolerance limits, and quadrant acceptability fractions. Finally, we use simulation to study the multiplicity bias that can be introduced into ICER confidence limits when only the most favorable results are reported over several possible choices of numerator cost measure and denominator effectiveness measure.

Confidence Intervals↗

PubMed2001

The psychometric function: II. Bootstrap-based confidence intervals and sampling.

The psychometric function relates an observer's performance to an independent variable, usually a physical quantity of an experimental stimulus. Even if a model is successfully fit to the data and its goodness of fit is acceptable, experimenters require an estimate of the variability of the parameters to assess whether differences across conditions are significant. Accurate estimates of variability are difficult to obtain, however, given the typically small size of psychophysical data sets: Traditional statistical techniques are only asymptotically correct and can be shown to be unreliable in some common situations. Here and in our companion paper (Wichmann & Hill, 2001), we suggest alternative statistical techniques based on Monte Carlo resampling methods. The present paper's principal topic is the estimation of the variability of fitted parameters and derived quantities, such as thresholds and slopes. First, we outline the basic bootstrap procedure and argue in favor of the parametric, as opposed to the nonparametric, bootstrap. Second, we describe how the bootstrap bridging assumption, on which the validity of the procedure depends, can be tested. Third, we show how one's choice of sampling scheme (the placement of sample points on the stimulus axis) strongly affects the reliability of bootstrap confidence intervals, and we make recommendations on how to sample the psychometric function efficiently. Fourth, we show that, under certain circumstances, the (arbitrary) choice of the distribution function can exert an unwanted influence on the size of the bootstrap confidence intervals obtained, and we make recommendations on how to avoid this influence. Finally, we introduce improved confidence intervals (bias corrected and accelerated) that improve on the parametric and percentile-based bootstrap confidence intervals previously used. Software implementing our methods is available.

Confidence Intervals↗

PubMed2001

Application of resampling techniques to the statistical analysis of the Brier score.

We investigated the application of resampling techniques to the statistical analysis of the Brier score (B), and extended them to the statistical comparison of two Bs derived from the same set of patients. The resampling techniques are helpful in the statistical analysis of B, and there are almost no differences between the jackknife method and the bootstrap method in this analysis. Thus, we believe that B should be used more often as an index to evaluate probabilistic judgments in the case in which the data sets for the assessment are "degenerate" as the "receiver operating characteristic data sets."

Case-Control Studies↗

PubMed1999

Statistical evaluation of bud development theories: application to bud burst of Betula pendula leaves.

Resampling methods were used to evaluate models based on alternative bud development theories applied to Betula pendula Roth data. Statistical testing based on the bootstrap method showed that the mean square errors (MSE) of the predicted bud-burst dates of two models, in which the start of ontogenetic development depended on dormancy development only, did not differ significantly. However, the MSE of the model in which the start of ontogenesis depended on a signal from light climate, indicated by using a fixed calendar date, was significantly smaller than that of the models depending on dormancy development. Model parameters were highly multi-collinear; i.e., sensitive to changes in the data. The cross-validation method was used to determine the prediction error of the models. The predictive ability of the models was not much less for an independent data set than for the original data.

Journal Article↗

PubMed2000

Effect of mortality rate on the performance of the Acute Physiology and Chronic Health Evaluation II: a simulation study.

OBJECTIVE: To evaluate the impact of case mix variation on the performance of the Acute Physiology and Chronic Health Evaluation (APACHE) II using measures of calibration and discrimination. DESIGN: APACHE II data were collected prospectively at the surgical intensive care unit of the University of Vermont on all adult admissions over an 8-yr period (excluding cardiac surgical patients, burn patients, and patients < 16 yrs of age). The original case mix was systematically varied to create 2,000 different case mixes ranging in mortality between 5% and 18% using a computer-intensive resampling algorithm. The area under the receiver operating characteristic curve and the Hosmer-Lemeshow C statistic were derived for each of the simulated case mixes with bootstrapping. SETTING: The surgical intensive care unit at a 450-bed teaching hospital. PATIENTS: A group of 6,806 adult surgical patients excluding cardiac surgical patients and burn patients. MEASUREMENTS AND RESULTS: Simulated data sets were created from a database of patients treated at a single institution to test the hypothesis that the performance of APACHE II is stable across a clinically reasonable range of mortality rates. The discrimination and calibration of APACHE II varied with case mix. CONCLUSION: The discrimination of APACHE II is not independent of case mix. However, the variability of the Hosmer-Lemeshow statistic as a function of the case mix may simply reflect the limitations of this goodness of fit statistic to assess model calibration. Because the discrimination of APACHE II is a function of case mix, caution should be exercised when using APACHE II-based adjusted mortality rates to compare intensive care units with widely divergent case mixes.

APACHE↗

PubMed2003

Bagging to improve the accuracy of a clustering procedure.

MOTIVATION: The microarray technology is increasingly being applied in biological and medical research to address a wide range of problems such as the classification of tumors. An important statistical question associated with tumor classification is the identification of new tumor classes using gene expression profiles. Essential aspects of this clustering problem include identifying accurate partitions of the tumor samples into clusters and assessing the confidence of cluster assignments for individual samples. RESULTS: Two new resampling methods, inspired from bagging in prediction, are proposed to improve and assess the accuracy of a given clustering procedure. In these ensemble methods, a partitioning clustering procedure is applied to bootstrap learning sets and the resulting multiple partitions are combined by voting or the creation of a new dissimilarity matrix. As in prediction, the motivation behind bagging is to reduce variability in the partitioning results via averaging. The performances of the new and existing methods were compared using simulated data and gene expression data from two recently published cancer microarray studies. The bagged clustering procedures were in general at least as accurate and often substantially more accurate than a single application of the partitioning clustering procedure. A valuable by-product of bagged clustering are the cluster votes which can be used to assess the confidence of cluster assignments for individual observations. SUPPLEMENTARY INFORMATION: For supplementary information on datasets, analyses, and software, consult http://www.stat.berkeley.edu/~sandrine and http://www.bioconductor.org.

Algorithms↗

PubMed2004

Detection of power changes between conditions using split-half resampling of synthetic aperture magnetometry data.

Synthetic Aperture Magnetometry (SAM) measures changes in task-related power using pseudo-t values which are affected by changes in both signal and noise. Detecting significant signal power changes between two separate experimental conditions should not be done directly due to possible fluctuation in the noise as well as the response. This study proposes a method to estimate the noise within a single condition, which is then used to test the null hypothesis of no difference between the conditions. The noise estimation is based on a split-half resampling technique. For each resampling, the data of a given condition is divided into two halves. The difference of the pseudo-t volumes between the pair of the datasets is calculated. After multiple resamplings, the confidence limits of the differences within this single condition are computed for a given p-value so that one can test the null hypotheses that the second condition is within the same distribution as the first. The limits are calculated using a bootstrap technique to correct for any bias in the estimated threshold. Power changes between the two conditions are considered significantly different if the difference of the pseudo-t value is larger than expected within conditions. To demonstrate the effectiveness of the technique, the proposed method was applied to MEG responses to two distinct visual stimuli recorded from a single subject. Major differences of brain activity between the two conditions were found in the occipital region. These results were validated using four pairs of split-half datasets, generated from either the odd or even trials in each condition. The method of split-half resampling should therefore be useful for localizing significant differences in brain activity between conditions within individual subjects.

Brain Mapping↗

PubMed1996

Confirmatory P-technique analyses of therapist discourse: high-versus low-quality child therapy sessions.

From a sample of 35 child therapy sessions, 3 of the highest and 3 of the lowest quality sessions (HQS and LQS) were identified by independent ratings on the Loyola Child Psychotherapy Process Scales. Each of the 535 therapist-utterances in the HQS and the 372 therapist-utterances in the LQS were rated on 15 language interaction scales. Principal-components P-technique analyses were applied separately to the HQS and LQS, revealing 3 factors, Responsive Informing (RI), Initiatory Questioning (IQ), and Positive Regard (PR), that seemed to correspond across session types. Using confirmatory P-technique, a general measurement model with acceptable goodness-of-fit was determined for HQS. Two factors emerged: RI and IQ but not PR. Using a bootstrap procedure, random halves of the HQS were repeatedly sampled and compared via multigroup confirmatory factor analysis to create a reference distribution of the magnitudes of their difference chi-squares. Random resamples of HQS and LQS were then compared, resulting in a second reference distribution. Statistical tests and effect-size measures revealed replicable and large differences between sessions types.

Child↗

PubMed1992

Inference of horizontal genetic transfer from molecular data: an approach using the bootstrap.

Inconsistencies in taxonomic relationships implicit in different sets of nucleic acid sequences potentially result from horizontal transfer of genetic material between genomes. A nonparametric method is proposed to determine whether such inconsistencies are statistically significant. A similarity coefficient is calculated from ranked pairwise identities and evaluated against a distribution of similarity coefficients generated from resampled data. Subsequent analyses of partial data sets, obtained by the elimination of individual taxa, identify particular taxa to which the significance may be attributed, and can sometimes help in distinguishing horizontal genetic transfer from inconsistencies due to convergent evolution or variation in evolutionary rate. The method was successfully applied to data sets that were not found to be significantly different with existing methods that use comparisons of phylogenetic trees. The new statistical framework is also applicable to the inference of horizontal transfer from restriction fragment length polymorphism distributions and protein sequences.

Animals↗

PubMed2005

A resampling approach for adjustment in prediction models for covariate measurement error.

Recent works on covariate measurement errors focus on the possible biases in model coefficient estimates. Usually, measurement error in a covariate tends to attenuate the coefficient estimate for the covariate, i.e., a bias toward the null occurs. Measurement error in another confounding or interacting variable typically results in incomplete adjustment for that variable. Hence, the coefficient for the covariate of interest may be biased either toward or away from the null. This paper presents a new method based on a resampling technique to deal with covariate measurement errors in the context of prediction modeling. Prediction accuracy is our primary parameter of interest. Prediction accuracy of a model is defined as the success rate of prediction when the model predicts new response. We call our method bootstrap regression calibration (BRC). We study logistic regression with interacting covariates as our prediction model. We measure the prediction accuracy of a model by receiver operating characteristic (ROC) method. Results from simulations show that bootstrap regression calibration offers consistent enhancement over the commonly used regression calibration (RC) method in terms of improving prediction accuracy of the model and reducing bias in the estimated coefficients.

Calibration↗

PubMed1990

Estimation and inference in pharmacokinetic models: the effectiveness of model reformulation and resampling methods for functions of parameters.

It is well known that high parameter estimate correlations and asymptotic variance estimates can cause estimation and inference problems in the analysis of pharmacokinetic models. In this paper we show that analysis of three important functions of pharmacokinetic parameters, the half-life, mean residence time, and the area under the curve, can sometimes be greatly improved by reformulating the model to address collinearity and by using the bootstrap to form confidence intervals. The resultant estimators can be more accurate than the original ones, and resultant confidence intervals can be narrower. Of the three measures, the half-life estimator is much better behaved than the estimators of mean residence time and area under the curve under collinearity, suggesting that it (or measures like it) should be used more often.

Analysis of Variance↗

PubMed2005

Stability of response characteristics of a Delphi panel: application of bootstrap data expansion.

BACKGROUND: Delphi surveys with panels of experts in a particular area of interest have been widely utilized in the fields of clinical medicine, nursing practice, medical education and healthcare services. Despite this wide applicability of the Delphi methodology, there is no clear identification of what constitutes a sufficient number of Delphi survey participants to ensure stability of results. METHODS: The study analyzed the response characteristics from the first round of a Delphi survey conducted with 23 experts in healthcare quality and patient safety. The panel members had similar training and subject matter understanding of the Malcolm Baldrige Criteria for Performance Excellence in Healthcare. The raw data from the first round sampling, which usually contains the largest diversity of responses, were augmented via bootstrap sampling to obtain computer-generated results for two larger samples obtained by sampling with replacement. Response characteristics (mean, trimmed mean, standard deviation and 95% confidence intervals) for 54 survey items were compared for the responses of the 23 actual study participants and two computer-generated samples of 1000 and 2000 resampling iterations. RESULTS: The results from this study indicate that the response characteristics of a small expert panel in a well-defined knowledge area are stable in light of augmented sampling. CONCLUSION: Panels of similarly trained experts (who possess a general understanding in the field of interest) provide effective and reliable utilization of a small sample from a limited number of experts in a field of study to develop reliable criteria that inform judgment and support effective decision-making.

Consensus Statements as Topic↗

PubMed2007

Appropriateness of some resampling-based inference procedures for assessing performance of prognostic classifiers derived from microarray data.

The goal of many gene-expression microarray profiling clinical studies is to develop a multivariate classifier to predict patient disease outcome from a gene-expression profile measured on some biological specimen from the patient. Often some preliminary validation of the predictive power of a profile-based classifier is carried out using the same data set that was used to derive the classifier. Techniques such as cross-validation or bootstrapping can be used in this setting to assess predictive power, and if applied correctly, can result in a less biased estimate of predictive accuracy of a classifier. However, some investigators have attempted to apply standard statistical inference procedures to assess the statistical significance of associations between true and cross-validated predicted outcomes. We demonstrate in this paper that naïve application of standard statistical inference procedures to these measures of association under null situations can result in greatly inflated testing type I error rates. Under alternatives of small to moderate associations, confidence interval coverage probabilities may be too low, although for very large associations coverage probabilities approach their intended values. Our results suggest that caution should be exercised in interpreting some of the claims of exceptional prognostic classifier performance that have been reported in prominent biomedical journals in the past few years.

Clinical Trials as Topic↗