Statistical Theory Commons^™

Loss-Based Cross-Validated Deletion/Substitution/Addition Algorithms In Estimation, Sandra E. Sinisi, Mark J. Van Der Laan

U.C. Berkeley Division of Biostatistics Working Paper Series

In van der Laan and Dudoit (2003) we propose and theoretically study a unified loss function based statistical methodology, which provides a road map for estimation and performance assessment. Given a parameter of interest which can be described as the minimizer of the population mean of a loss function, the road map involves as important ingredients cross-validation for estimator selection and minimizing over subsets of basis functions the empirical risk of the subset-specific estimator of the parameter of interest, where the basis functions correspond to a parameterization of a specified subspace of the complete parameter space. In this article we …

The Cross-Validated Adaptive Epsilon-Net Estimator, Mark J. Van Der Laan, Sandrine Dudoit, Aad W. Van Der Vaart

U.C. Berkeley Division of Biostatistics Working Paper Series

Suppose that we observe a sample of independent and identically distributed realizations of a random variable. Assume that the parameter of interest can be defined as the minimizer, over a suitably defined parameter space, of the expectation (with respect to the distribution of the random variable) of a particular (loss) function of a candidate parameter value and the random variable. Examples of commonly used loss functions are the squared error loss function in regression and the negative log-density loss function in density estimation. Minimizing the empirical risk (i.e., the empirical mean of the loss function) over the entire parameter space …

Multiple Imputation For Interval Censored Data With Auxiliary Variables, Chiu-Hsieh Hsu, Jeremy Taylor, Susan Murray

The University of Michigan Department of Biostatistics Working Paper Series

We propose a nonparametric multiple imputation scheme, NPMLE imputation, for the analysis of interval censored survival data. Features of the method are that it converts interval-censored data problems to complete data or right censored data problems to which many standard approaches can be used, and the measures of uncertainty are easily obtained. In addition to the event time of primary interest, there are frequently other auxiliary variables that are associated with the event time. For the goal of estimating the marginal survival distribution, these auxiliary variables may provide some additional information about the event time for the interval censored observations. …

Piecewise Constant Cross-Ratio Estimation For Association In Bivariate Survival Data With Application To Studying Markers Of Menopausal Transition, Bin Nan, Xihong Lin, Lynda D. Lisabet, Sioban Harlow

The University of Michigan Department of Biostatistics Working Paper Series

A question of significant interest in female reproductive aging is to identify bleeding criteria for the menopausal transition. Although various bleeding criteria, or markers, have been proposed for the menopausal transition, their validity has not been adequately examined. The Tremin Trust data are collected from a long-term cohort study that followed a group of women throughout their whole reproductive life, and provide a unique opportunity for assessing the association between age at onset of a bleeding marker and age onset of menopause. Formal statistical analysis of this dependence is challenging give the fact that both the marker event and menopause …

Optimal Sample Size For Multiple Testing: The Case Of Gene Expression Microarrays, Peter Muller, Giovanni Parmigiani, Christian Robert, Judith Rousseau

Johns Hopkins University, Dept. of Biostatistics Working Papers

We consider the choice of an optimal sample size for multiple comparison problems. The motivating application is the choice of the number of microarray experiments to be carried out when learning about differential gene expression. However, the approach is valid in any application that involves multiple comparisons in a large number of hypothesis tests. We discuss two decision problems in the context of this setup: the sample size selection and the decision about the multiple comparisons. We adopt a decision theoretic approach,using loss functions that combine the competing goals of discovering as many ifferentially expressed genes as possible, while keeping …

Calibrating Observed Differential Gene Expression For The Multiplicity Of Genes On The Array, Yingye Zheng, Margaret S. Pepe

UW Biostatistics Working Paper Series

In a gene expression array study, the expression levels of thousands of genes are monitored simultaneously across various biological conditions on a small set of subjects. One goal of such studies is to explore a large pool of genes in order to select a subset of genes that appear to be differently expressed for further investigation. Of particular interest here is how to select the top k genes once genes are ranked based on their evidence for differential expression in two tissue types. We consider statistical methods that provide a more rigorous and intuitively appealing selection process for k. We …

Multiple Testing. Part Iii. Procedures For Control Of The Generalized Family-Wise Error Rate And Proportion Of False Positives, Mark J. Van Der Laan, Sandrine Dudoit, Katherine S. Pollard

U.C. Berkeley Division of Biostatistics Working Paper Series

The accompanying articles by Dudoit et al. (2003b) and van der Laan et al. (2003) provide single-step and step-down resampling-based multiple testing procedures that asymptotically control the family-wise error rate (FWER) for general null hypotheses and test statistics. The proposed procedures fundamentally differ from existing approaches in the choice of null distribution for deriving cut-offs for the test statistics and are shown to provide asymptotic control of the FWER under general data generating distributions, without the need for conditions such as subset pivotality. In this article, we show that any multiple testing procedure (asymptotically) controlling the FWER at level alpha …

Robust Likelihood-Based Analysis Of Multivariate Data With Missing Values, Rod Little, An Hyonggin

The University of Michigan Department of Biostatistics Working Paper Series

The model-based approach to inference from multivariate data with missing values is reviewed. Regression prediction is most useful when the covariates are predictive of the missing values and the probability of being missing, and in these circumstances predictions are particularly sensitive to model misspecification. The use of penalized splines of the propensity score is proposed to yield robust model-based inference under the missing at random (MAR) assumption, assuming monotone missing data. Simulation comparisons with other methods suggest that the method works well in a wide range of populations, with little loss of efficiency relative to parametric models when the latter …

Multiple Testing. Part Ii. Step-Down Procedures For Control Of The Family-Wise Error Rate, Mark J. Van Der Laan, Sandrine Dudoit, Katherine S. Pollard

U.C. Berkeley Division of Biostatistics Working Paper Series

The present article proposes two step-down multiple testing procedures for asymptotic control of the family-wise error rate (FWER): the first procedure is based on maxima of test statistics (step-down maxT), while the second relies on minima of unadjusted p-values (step-down minP). A key feature of our approach is the test statistics null distribution (rather than data generating null distribution) used to derive cut-offs (i.e., rejection regions) for these test statistics and the resulting adjusted p-values. For general null hypotheses, corresponding to submodels for the data generating distribution, we identify an asymptotic domination condition for a null distribution under which the …

Multiple Testing. Part I. Single-Step Procedures For Control Of General Type I Error Rates, Sandrine Dudoit, Mark J. Van Der Laan, Katherine S. Pollard

U.C. Berkeley Division of Biostatistics Working Paper Series

The present article proposes general single-step multiple testing procedures for controlling Type I error rates defined as arbitrary parameters of the distribution of the number of Type I errors, such as the generalized family-wise error rate. A key feature of our approach is the test statistics null distribution (rather than data generating null distribution) used to derive cut-offs (i.e., rejection regions) for these test statistics and the resulting adjusted p-values. For general null hypotheses, corresponding to submodels for the data generating distribution, we identify an asymptotic domination condition for a null distribution under which single-step common-quantile and common-cut-off procedures asymptotically …

Loss-Based Estimation With Cross-Validation: Applications To Microarray Data Analysis And Motif Finding, Sandrine Dudoit, Mark J. Van Der Laan, Sunduz Keles, Annette M. Molinaro, Sandra E. Sinisi, Siew Leng Teng

U.C. Berkeley Division of Biostatistics Working Paper Series

Current statistical inference problems in genomic data analysis involve parameter estimation for high-dimensional multivariate distributions, with typically unknown and intricate correlation patterns among variables. Addressing these inference questions satisfactorily requires: (i) an intensive and thorough search of the parameter space to generate good candidate estimators, (ii) an approach for selecting an optimal estimator among these candidates, and (iii) a method for reliably assessing the performance of the resulting estimator. We propose a unified loss-based methodology for estimator construction, selection, and performance assessment with cross-validation. In this approach, the parameter of interest is defined as the risk minimizer for a suitable …

Kernel Estimation Of Rate Function For Recurrent Event Data, Chin-Tsang Chiang, Mei-Cheng Wang, Chiung-Yu Huang

Johns Hopkins University, Dept. of Biostatistics Working Papers

Recurrent event data are largely characterized by the rate function but smoothing techniques for estimating the rate function have never been rigorously developed or studied in statistical literature. This paper considers the moment and least squares methods for estimating the rate function from recurrent event data. With an independent censoring assumption on the recurrent event process, we study statistical properties of the proposed estimators and propose bootstrap procedures for the bandwidth selection and for the approximation of confidence intervals in the estimation of the occurrence rate function. It is identified that the moment method without resmoothing via a smaller bandwidth …

Unified Cross-Validation Methodology For Selection Among Estimators And A General Cross-Validated Adaptive Epsilon-Net Estimator: Finite Sample Oracle Inequalities And Examples, Mark J. Van Der Laan, Sandrine Dudoit

U.C. Berkeley Division of Biostatistics Working Paper Series

In Part I of this article we propose a general cross-validation criterian for selecting among a collection of estimators of a particular parameter of interest based on n i.i.d. observations. It is assumed that the parameter of interest minimizes the expectation (w.r.t. to the distribution of the observed data structure) of a particular loss function of a candidate parameter value and the observed data structure, possibly indexed by a nuisance parameter. The proposed cross-validation criterian is defined as the empirical mean over the validation sample of the loss function at the parameter estimate based on the training sample, averaged over …

Weighting Adjustments For Unit Nonresponse With Multiple Outcome Variables, Sonya L. Vartivarian, Rod Little

The University of Michigan Department of Biostatistics Working Paper Series

Weighting is a common form of unit nonresponse adjustment in sample surveys where entire questionnaires are missing due to noncontact or refusal to participate. Weights are inversely proportional to the probability of selection and response. A common approach computes the response weight adjustment cells based on covariate information. When the number of cells thus created is too large, a coarsening method such as response propensity stratification can be applied to reduce the number of adjustment cells. Simulations in Vartivarian and Little (2002) indicate improved efficiency and robustness of weighting adjustments based on the joint classification of the sample by two …

Estimating Predictors For Long- Or Short-Term Survivors, Lu Tian, Wei Wang, L. J. Wei

Harvard University Biostatistics Working Paper Series

No abstract provided.

Smooth Quantile Ratio Estimation With Regression: Estimating Medical Expenditures For Smoking Attributable Diseases, Francesca Dominici, Scott L. Zeger

Johns Hopkins University, Dept. of Biostatistics Working Papers

In this paper we introduce a semi-parametric regression model for estimating the difference in the expected value of two positive and highly skewed random variables as a function of covariates. Our method extends Smooth Quantile Ratio Estimation (SQUARE), a novel estimator of the mean difference of two positive random variables, to a regression model.

The methodological development of this paper is motivated by a common problem in econometrics where we are interested in estimating the difference in the average expenditures between two populations, say with and without a disease, taking covariates into account. Let Y1 and Y2 be two positive …

A Nonparametric Comparison Of Conditional Distributions With Nonnegligible Cure Fractions, Yi Li, Jin Feng

Harvard University Biostatistics Working Paper Series

No abstract provided.

Survival Analysis With Heterogeneous Covariate Measurement Error, Yi Li, Louise Ryan

Harvard University Biostatistics Working Paper Series

No abstract provided.

Loss Function Based Ranking In Two-Stage, Hierarchical Models, Rongheng Lin, Thomas A. Louis, Susan M. Paddock, Greg Ridgeway

Johns Hopkins University, Dept. of Biostatistics Working Papers

Several authors have studied the performance of optimal, squared error loss (SEL) estimated ranks. Though these are effective, in many applications interest focuses on identifying the relatively good (e.g., in the upper 10%) or relatively poor performers. We construct loss functions that address this goal and evaluate candidate rank estimates, some of which optimize specific loss functions. We study performance for a fully parametric hierarchical model with a Gaussian prior and Gaussian sampling distributions, evaluating performance for several loss functions. Results show that though SEL-optimal ranks and percentiles do not specifically focus on classifying with respect to a percentile cut …

Statistical Inference For Infinite Dimensional Parameters Via Asymptotically Pivotal Estimating Functions, Meredith A. Goldwasser, Lu Tian, L. J. Wei

Harvard University Biostatistics Working Paper Series

No abstract provided.

Joint Modeling And Estimation For Recurrent Event Processes And Failure Time Data, Chiung-Yu Huang, Mei-Cheng Wang

Johns Hopkins University, Dept. of Biostatistics Working Papers

Recurrent event data are commonly encountered in longitudinal follow-up studies related to biomedical science, econometrics, reliability, and demography. In many studies, recurrent events serve as important measurements for evaluating disease progression, health deterioration, or insurance risk. When analyzing recurrent event data, an independent censoring condition is typically required for the construction of statistical methods. Nevertheless, in some situations, the terminating time for observing recurrent events could be correlated with the recurrent event process and, as a result, the assumption of independent censoring is violated. In this paper, we consider joint modeling of a recurrent event process and a failure time …

Model Comparisons Using Information Measures, C. Mitchell Dayton

Journal of Modern Applied Statistical Methods

Methodologists have criticized the use of significance tests in the behavioral sciences but have failed to provide alternative data analysis strategies that appeal to applied researchers. For purposes of comparing alternate models for data, information-theoretic measures such as Akaike AIC have advantages in comparison with significance tests. Model-selection procedures based on a min(AIC) strategy, for example, are holistic rather than dependent upon a series of sometimes contradictory binary (accept/reject) decisions.

Using Zero-Inflated Count Regression Models To Estimate The Fertility Of U. S. Women, Dudley L. Poston Jr., Sherry L. Mckibben

Journal of Modern Applied Statistical Methods

In the modeling of count variables there is sometimes a preponderance of zero counts. This article concerns the estimation of Poisson regression models (PRM) and negative binomial regression models (NBRM) to predict the average number of children ever born (CEB) to women in the U.S. The PRM and NBRM will often under-predict zeros because they do not consider zero counts of women who are not trying to have children. The fertility of U.S. white and Mexican-origin women show that zero-inflated Poisson (ZIP) and zero-inflated negative binomial (ZINB) models perform better in many respects than the Poisson and negative binomial models. …

Test Of Homogeneity For Umbrella Alternatives In Dose-Response Relationship For Poisson Variables, Chengjie Xiong, Yan Yan, Ming Ji

Journal of Modern Applied Statistical Methods

This article concerns the testing and estimation of a dose-response effect in medical studies. We study the statistical test of homogeneity against umbrella alternatives in a sequence of Poisson distributions associated with an ordered dose variable. We propose a test similar to Cochran-Armitage’s trend test and study the asymptotic null distribution and the power of the test. We also propose an estimator to the vertex point when the umbrella pattern is confirmed and study the performance of the estimator. A real data set pertaining to the number of visible revertant colonies associated with different doses of test agents in an …

Alphabet Letter Recognition And Emergent Literacy Abilities Of Rising Kindergarten Children Living In Low-Income Families, Stephanie Wehry

Journal of Modern Applied Statistical Methods

Alphabet letter recognition item responses from 1,299 rising kindergarten children from low-income families were used to determine the dimensionality of letter recognition ability. The rising kindergarteners were enrolled in preschool classrooms implementing a research-based early literary curriculum. Item responses from the TERA-3 subtests were also analyzed. Results indicated alphabet letter recognition was unitary. The ability of boys and younger children was less than girls and older children. Child-level letter recognition was highly associated with TERA-3 measures of letter knowledge and conventions of print. Classroom-level mean letter recognition ability accounted for most of variance in classroom mean TERA-3 scores.

A Note On Mles For Normal Distribution Parameters Based On Disjoint Partial Sums Of A Random Sample, W. J. Hurley

Journal of Modern Applied Statistical Methods

Maximum likelihood estimators are computed for the parameters of a normal distribution based on disjoint partial sums of a random sample. It has application in the disaggregation of financial data.

Fitting Generalized Linear Mixed Models For Point-Referenced Spatial Data, Armin Gemperli, Penelope Vounatsou

Journal of Modern Applied Statistical Methods

Non-Gaussian point-referenced spatial data are frequently modeled using generalized linear mixed models (GLMM) with location-specific random effects. Spatial dependence can be introduced in the covariance matrix of the random effects. Maximum likelihood-based or Bayesian estimation implemented via Markov chain Monte Carlo (MCMC) for such models is computationally demanding especially for large sample sizes because of the large number of random effects and the inversion of the covariance matrix involved in the likelihood. We review three fitting procedures, the Penalized Quasi Likelihood method, the MCMC, and the Sampling-Importance-Resampling method. They are assessed in terms of estimation accuracy, ease of implementation, and …

Conventional And Robust Paired And Independent-Samples T Tests: Type I Error And Power Rates, Katherine Fradette, H. J. Keselman, Lisa Lix, James Algina, Rand R. Wilcox

Journal of Modern Applied Statistical Methods

Monte Carlo methods were used to examine Type I error and power rates of 2 versions (conventional and robust) of the paired and independent-samples t tests under nonnormality. The conventional (robust) versions employed least squares means and variances (trimmed means and Winsorized variances) to test for differences between groups.

Jmasm9: Converting Kendall’S Tau For Correlational Or Meta-Analytic Analyses, David A. Walker

Journal of Modern Applied Statistical Methods

Expanding on past research, this study provides researchers with a detailed table for use in meta-analytic applications when engaged in assorted examinations of various r-related statistics, such as Kendall’s tau (τ) and Cohen’s d, that estimate the magnitude of experimental or observational effect. A program to convert from the lesser-used tau coefficient to other effect size indices when conducting correlational or meta-analytic analyses is presented.

P* Index Of Segregation: Distribution Under Reassignment, Charles F. Bond, F. D. Richard

Journal of Modern Applied Statistical Methods

Students of intergroup relations have measured segregation with a P^* index. In this article, we describe the distribution of this index under a stochastic model. We derive exact, closed-form expressions for the mean, variance, and skewness of P^* under random segregation. These yield equivalent expressions for a second segregation index: η². Our analytic results reveal some of the distributional properties of these indices, inform new standardizations of the indices, and enable small-sample significance testing. Two illustrative examples are presented.