@article{wang_li_2013, title={Estimation of Extreme Conditional Quantiles Through Power Transformation}, volume={108}, ISSN={["1537-274X"]}, DOI={10.1080/01621459.2013.820134}, abstractNote={The estimation of extreme conditional quantiles is an important issue in numerous disciplines. Quantile regression (QR) provides a natural way to capture the covariate effects at different tails of the response distribution. However, without any distributional assumptions, estimation from conventional QR is often unstable at the tails, especially for heavy-tailed distributions due to data sparsity. In this article, we develop a new three-stage estimation procedure that integrates QR and extreme value theory by estimating intermediate conditional quantiles using QR and extrapolating these estimates to tails based on extreme value theory. Using the power-transformed QR, the proposed method allows more flexibility than existing methods that rely on the linearity of quantiles on the original scale, while extending the applicability of parametric models to borrow information across covariates without resorting to nonparametric smoothing. In addition, we propose a test procedure to assess the commonality of extreme value index, which could be useful for obtaining more efficient estimation by sharing information across covariates. We establish the asymptotic properties of the proposed method and demonstrate its value through simulation study and the analysis of a medical cost data. Supplementary materials for this article are available online.}, number={503}, journal={JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION}, author={Wang, Huixia Judy and Li, Deyuan}, year={2013}, month={Sep}, pages={1062–1074} }
 @article{bernhardt_wang_zhang_2014, title={Flexible modeling of survival data with covariates subject to detection limits via multiple imputation}, volume={69}, ISSN={["1872-7352"]}, DOI={10.1016/j.csda.2013.07.027}, abstractNote={Models for survival data generally assume that covariates are fully observed. However, in medical studies it is not uncommon for biomarkers to be censored at known detection limits. A computationally-efficient multiple imputation procedure for modeling survival data with covariates subject to detection limits is proposed. This procedure is developed in the context of an accelerated failure time model with a flexible seminonparametric error distribution. The consistency and asymptotic normality of the multiple imputation estimator are established and a consistent variance estimator is provided. An iterative version of the proposed multiple imputation algorithm that approximates the EM algorithm for maximum likelihood is also suggested. Simulation studies demonstrate that the proposed multiple imputation methods work well while alternative methods lead to estimates that are either biased or more variable. The proposed methods are applied to analyze the dataset from a recently-conducted GenIMS study.}, journal={COMPUTATIONAL STATISTICS & DATA ANALYSIS}, author={Bernhardt, Paul W. and Wang, Huixia Judy and Zhang, Daowen}, year={2014}, month={Jan}, pages={81–91} }
 @article{jiang_wang_bondell_2013, title={Interquantile Shrinkage in Regression Models}, volume={22}, ISSN={["1537-2715"]}, DOI={10.1080/10618600.2012.707454}, abstractNote={Conventional analysis using quantile regression typically focuses on fitting the regression model at different quantiles separately. However, in situations where the quantile coefficients share some common feature, joint modeling of multiple quantiles to accommodate the commonality often leads to more efficient estimation. One example of common features is that a predictor may have a constant effect over one region of quantile levels but varying effects in other regions. To automatically perform estimation and detection of the interquantile commonality, we develop two penalization methods. When the quantile slope coefficients indeed do not change across quantile levels, the proposed methods will shrink the slopes toward constant and thus improve the estimation efficiency. We establish the oracle properties of the two proposed penalization methods. Through numerical investigations, we demonstrate that the proposed methods lead to estimations with competitive or higher efficiency than the standard quantile regression estimation in finite samples. Supplementary materials for the article are available online.}, number={4}, journal={JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS}, author={Jiang, Liewen and Wang, Huixia Judy and Bondell, Howard D.}, year={2013}, month={Dec}, pages={970–986} }
 @article{jiang_bondell_wang_2014, title={Interquantile shrinkage and variable selection in quantile regression}, volume={69}, ISSN={["1872-7352"]}, DOI={10.1016/j.csda.2013.08.006}, abstractNote={Examination of multiple conditional quantile functions provides a comprehensive view of the relationship between the response and covariates. In situations where quantile slope coefficients share some common features, estimation efficiency and model interpretability can be improved by utilizing such commonality across quantiles. Furthermore, elimination of irrelevant predictors will also aid in estimation and interpretation. These motivations lead to the development of two penalization methods, which can identify the interquantile commonality and nonzero quantile coefficients simultaneously. The developed methods are based on a fused penalty that encourages sparsity of both quantile coefficients and interquantile slope differences. The oracle properties of the proposed penalization methods are established. Through numerical investigations, it is demonstrated that the proposed methods lead to simpler model structure and higher estimation efficiency than the traditional quantile regression estimation.}, journal={COMPUTATIONAL STATISTICS & DATA ANALYSIS}, author={Jiang, Liewen and Bondell, Howard D. and Wang, Huixia Judy}, year={2014}, month={Jan}, pages={208–219} }
 @article{wang_zhou_li_2013, title={Variable selection for censored quantile regresion}, volume={23}, number={1}, journal={Statistica Sinica}, author={Wang, H. J. and Zhou, J. H. and Li, Y.}, year={2013}, pages={145–167} }
 @article{tang_wang_zhu_song_2012, title={A unified variable selection approach for varying coefficient models}, volume={22}, number={2}, journal={Statistica Sinica}, author={Tang, Y. L. and Wang, H. J. and Zhu, Z. Y. and Song, X. Y.}, year={2012}, pages={601–628} }
 @article{wang_stefanski_zhu_2012, title={Corrected-loss estimation for quantile regression with covariate measurement errors}, volume={99}, ISSN={["0006-3444"]}, DOI={10.1093/biomet/ass005}, abstractNote={We study estimation in quantile regression when covariates are measured with errors. Existing methods require stringent assumptions, such as spherically symmetric joint distribution of the regression and measurement error variables, or linearity of all quantile functions, which restrict model flexibility and complicate computation. In this paper, we develop a new estimation approach based on corrected scores to account for a class of covariate measurement errors in quantile regression. The proposed method is simple to implement. Its validity requires only linearity of the particular quantile function of interest, and it requires no parametric assumptions on the regression error distributions. Finite-sample results demonstrate that the proposed estimators are more efficient than the existing methods in various models considered.}, number={2}, journal={BIOMETRIKA}, author={Wang, Huixia Judy and Stefanski, Leonard A. and Zhu, Zhongyi}, year={2012}, month={Jun}, pages={405–421} }
 @article{wang_li_he_2012, title={Estimation of High Conditional Quantiles for Heavy-Tailed Distributions}, volume={107}, ISSN={["1537-274X"]}, DOI={10.1080/01621459.2012.716382}, abstractNote={Estimation of conditional quantiles at very high or low tails is of interest in numerous applications. Quantile regression provides a convenient and natural way of quantifying the impact of covariates at different quantiles of a response distribution. However, high tails are often associated with data sparsity, so quantile regression estimation can suffer from high variability at tails especially for heavy-tailed distributions. In this article, we develop new estimation methods for high conditional quantiles by first estimating the intermediate conditional quantiles in a conventional quantile regression framework and then extrapolating these estimates to the high tails based on reasonable assumptions on tail behaviors. We establish the asymptotic properties of the proposed estimators and demonstrate through simulation studies that the proposed methods enjoy higher accuracy than the conventional quantile regression estimates. In a real application involving statistical downscaling of daily precipitation in the Chicago area, the proposed methods provide more stable results quantifying the chance of heavy precipitation in the area. Supplementary materials for this article are available online.}, number={500}, journal={JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION}, author={Wang, Huixia Judy and Li, Deyuan and He, Xuming}, year={2012}, month={Dec}, pages={1453–1464} }
 @article{wang_feng_2012, title={Multiple Imputation for M-Regression With Censored Covariates}, volume={107}, ISSN={["1537-274X"]}, DOI={10.1080/01621459.2011.643198}, abstractNote={We develop a new multiple imputation approach for M-regression models with censored covariates. Instead of specifying parametric likelihoods, our method imputes the censored covariates by their conditional quantiles given the observed data, where the conditional quantiles are estimated through fitting a censored quantile regression process. The resulting estimator is shown to be consistent and asymptotically normal, and it improves the estimation efficiency by using information from cases with censored covariates. Compared with existing methods, the proposed method is more flexible as it does not require stringent parametric assumptions on the distributions of either the regression errors or the covariates. The finite sample performance of the proposed method is assessed through a simulation study and the analysis of a c-reactive protein dataset in the 2007–2008 National Health and Nutrition Examination Survey. This article has supplementary material online.}, number={497}, journal={JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION}, author={Wang, Huixia Judy and Feng, Xingdong}, year={2012}, month={Mar}, pages={194–204} }
 @article{sun_wang_gilbert_2012, title={Quantile regression for competing risks data with missing cause of failure}, volume={22}, number={2}, journal={Statistica Sinica}, author={Sun, Y. Q. and Wang, H. J. and Gilbert, P. B.}, year={2012}, pages={703–728} }
 @article{tang_wang_zhu_2013, title={Variable selection in quantile varying coefficient models with longitudinal data}, volume={57}, ISSN={["1872-7352"]}, DOI={10.1016/j.csda.2012.07.015}, abstractNote={In this paper, we develop a new variable selection procedure for quantile varying coefficient models with longitudinal data. The proposed method is based on basis function approximation and a class of group versions of the adaptive LASSO penalty, which penalizes the Lγ norm of the within-group coefficients with γ≥1. We show that with properly chosen adaptive group weights in the penalization, the resulting penalized estimators are consistent in variable selection, and the estimated functional coefficients retain the optimal convergence rate of nonparametric estimators under the true model. We assess the finite sample performance of the proposed procedure by an extensive simulation study, and the analysis of an AIDS data set and a yeast cell-cycle gene expression data set.}, number={1}, journal={COMPUTATIONAL STATISTICS & DATA ANALYSIS}, author={Tang, Yanlin and Wang, Huixia Judy and Zhu, Zhongyi}, year={2013}, month={Jan}, pages={435–449} }
 @article{tang_wang_he_zhu_2012, title={An informative subset-based estimator for censored quantile regression}, volume={21}, ISSN={["1133-0686"]}, DOI={10.1007/s11749-011-0266-y}, number={4}, journal={TEST}, author={Tang, Yanlin and Wang, Huixia Judy and He, Xuming and Zhu, Zhongyi}, year={2012}, month={Dec}, pages={635–655} }
 @article{fung_he_hubert_portnoy_wang_2012, title={Editorial for the special issue on quantile regression and semiparametric methods}, volume={56}, ISSN={["0167-9473"]}, DOI={10.1016/j.csda.2011.12.012}, number={4}, journal={COMPUTATIONAL STATISTICS & DATA ANALYSIS}, author={Fung, Wing-Kam and He, Xuming and Hubert, Mia and Portnoy, Stephen and Wang, Huixia Judy}, year={2012}, month={Apr}, pages={753–754} }
 @article{ayers_moorman_deperno_yelverton_wang_2010, title={Effects of Mowing on Anthraquinone for Deterrence of Canada Geese}, volume={74}, ISSN={["0022-541X"]}, DOI={10.2193/2009-323}, abstractNote={ABSTRACT Anthraquinone (AQ)‐based repellents have been shown to reduce Canada goose (Branta canadensis) use of turfgrass; however, impacts of frequent mowing on efficacy of AQ have not been studied. Our objective was to determine efficacy and longevity of a rain‐fast AQ‐based avian repellent, FlightControl® PLUS (FCP), as a deterrent of free‐ranging resident Canada geese under 2 mowing frequencies. We conducted the study at 8 sites in the Triangle region (Raleigh, Durham, and Chapel Hill) of North Carolina, USA. We arranged our experiment in a randomized complete block design, with each of 8 sites containing 4 0.1‐ha treatment combinations: 1) treated with FCP and mowed every 4 days (T4), 2) treated with FCP and mowed every 8 days (T8), 3) untreated and mowed every 4 days, and 4) untreated and mowed every 8 days. We conducted 4 37‐day field sessions (Jun‐Jul 2007, Sep‐Oct 2007, Jun‐Jul 2008, and Sep‐Oct 2008), representing the summer molting phase and the full‐plumage phase. Resident goose use (measured by daily no. of droppings) was 41–70% lower on treated plots than on untreated plots, but use was similar between T4 and T8. Average FCP coverage on grass blades decreased in coverage from approximately 95% to 10% over the 30‐day posttreatment phase. Results indicate that resident Canada goose use of FCP‐treated turfgrass areas was lower than untreated areas even when chemical coverage on grass was 10%. Further, mowing frequency did not have a clear impact on the efficacy of FCP as a Canada goose repellent.}, number={8}, journal={JOURNAL OF WILDLIFE MANAGEMENT}, author={Ayers, Christopher R. and Moorman, Christopher E. and Deperno, Christopher S. and Yelverton, Fred H. and Wang, Huixia J.}, year={2010}, month={Nov}, pages={1863–1868} }
 @article{wang_zhu_2011, title={Empirical likelihood for quantile regression models with longitudinal data}, volume={141}, ISSN={["1873-1171"]}, DOI={10.1016/j.jspi.2010.11.017}, abstractNote={We develop two empirical likelihood-based inference procedures for longitudinal data under the framework of quantile regression. The proposed methods avoid estimating the unknown error density function and the intra-subject correlation involved in the asymptotic covariance matrix of the quantile estimators. By appropriately smoothing the quantile score function, the empirical likelihood approach is shown to have a higher-order accuracy through the Bartlett correction. The proposed methods exhibit finite-sample advantages over the normal approximation-based and bootstrap methods in a simulation study and the analysis of a longitudinal ophthalmology data set.}, number={4}, journal={JOURNAL OF STATISTICAL PLANNING AND INFERENCE}, author={Wang, Huixia Judy and Zhu, Zhongyi}, year={2011}, month={Apr}, pages={1603–1615} }
 @article{wang_zhou_2010, title={Estimation of the retransformed conditional mean in health care cost studies}, volume={97}, ISSN={["1464-3510"]}, DOI={10.1093/biomet/asp072}, abstractNote={We propose a new approach for analyzing skewed and heteroscedastic health care cost data through regression of the conditional quantiles of the transformed cost. Using the appealing equivariance property of quantiles to monotone transformations, we propose a distribution-free estimator of the conditional mean cost on the original scale. The proposed method is extended to a two-part heteroscedastic model to account for zero costs commonly seen in health care cost studies. Simulation studies indicate that the proposed estimator has competitive and more robust performance than existing estimators in various heteroscedastic models. Copyright 2010, Oxford University Press.}, number={1}, journal={BIOMETRIKA}, author={Wang, Huixia Judy and Zhou, Xiao-Hua}, year={2010}, month={Mar}, pages={147–158} }
 @article{wang_hu_2011, title={Identification of Differential Aberrations in Multiple-Sample Array CGH Studies}, volume={67}, ISSN={["0006-341X"]}, DOI={10.1111/j.1541-0420.2010.01457.x}, abstractNote={Summary Most existing methods for identifying aberrant regions with array CGH data are confined to a single target sample. Focusing on the comparison of multiple samples from two different groups, we develop a new penalized regression approach with a fused adaptive lasso penalty to accommodate the spatial dependence of the clones. The nonrandom aberrant genomic segments are determined by assessing the significance of the differences between neighboring clones and neighboring segments. The algorithm proposed in this article is a first attempt to simultaneously detect the common aberrant regions within each group, and the regions where the two groups differ in copy number changes. The simulation study suggests that the proposed procedure outperforms the commonly used single‐sample aberration detection methods for segmentation in terms of both false positives and false negatives. To further assess the value of the proposed method, we analyze a data set from a study that identified the aberrant genomic regions associated with grade subgroups of breast cancer tumors.}, number={2}, journal={BIOMETRICS}, author={Wang, Huixia Judy and Hu, Jianhua}, year={2011}, month={Jun}, pages={353–362} }
 @article{bondell_reich_wang_2010, title={Noncrossing quantile regression curve estimation}, volume={97}, ISSN={["0006-3444"]}, DOI={10.1093/biomet/asq048}, abstractNote={Since quantile regression curves are estimated individually, the quantile curves can cross, leading to an invalid distribution for the response. A simple constrained version of quantile regression is proposed to avoid the crossing problem for both linear and nonparametric quantile curves. A simulation study and a reanalysis of tropical cyclone intensity data shows the usefulness of the procedure. Asymptotic properties of the estimator are equivalent to the typical approach under standard conditions, and the proposed estimator reduces to the classical one if there is no crossing. The performance of the constrained estimator has shown significant improvement by adding smoothing and stability across the quantile levels.}, number={4}, journal={BIOMETRIKA}, author={Bondell, Howard D. and Reich, Brian J. and Wang, Huixia}, year={2010}, month={Dec}, pages={825–838} }
 @article{pang_lu_wang_2012, title={Variance estimation in censored quantile regression via induced smoothing}, volume={56}, ISSN={["1872-7352"]}, DOI={10.1016/j.csda.2010.10.018}, abstractNote={Statistical inference in censored quantile regression is challenging, partly due to the unsmoothness of the quantile score function. A new procedure is developed to estimate the variance of Bang and Tsiatis's inverse-censoring-probability weighted estimator for censored quantile regression by employing the idea of induced smoothing. The proposed variance estimator is shown to be asymptotically consistent. In addition, numerical study suggests that the proposed procedure performs well in finite samples, and it is computationally more efficient than the commonly used bootstrap method.}, number={4}, journal={COMPUTATIONAL STATISTICS & DATA ANALYSIS}, author={Pang, Lei and Lu, Wenbin and Wang, Huixia Judy}, year={2012}, month={Apr}, pages={785–796} }
 @article{reich_bondell_wang_2010, title={Flexible Bayesian quantile regression for independent and clustered data}, volume={11}, ISSN={["1465-4644"]}, DOI={10.1093/biostatistics/kxp049}, abstractNote={Quantile regression has emerged as a useful supplement to ordinary mean regression. Traditional frequentist quantile regression makes very minimal assumptions on the form of the error distribution and thus is able to accommodate nonnormal errors, which are common in many applications. However, inference for these models is challenging, particularly for clustered or censored data. A Bayesian approach enables exact inference and is well suited to incorporate clustered, missing, or censored data. In this paper, we propose a flexible Bayesian quantile regression model. We assume that the error distribution is an infinite mixture of Gaussian densities subject to a stochastic constraint that enables inference on the quantile of interest. This method outperforms the traditional frequentist method under a wide array of simulated data models. We extend the proposed approach to analyze clustered data. Here, we differentiate between and develop conditional and marginal models for clustered data. We apply our methods to analyze a multipatient apnea duration data set.}, number={2}, journal={BIOSTATISTICS}, author={Reich, Brian J. and Bondell, Howard D. and Wang, Huixia J.}, year={2010}, month={Apr}, pages={337–352} }
 @article{wang_fygenson_2009, title={INFERENCE FOR CENSORED QUANTILE REGRESSION MODELS IN LONGITUDINAL STUDIES}, volume={37}, ISSN={["0090-5364"]}, DOI={10.1214/07-AOS564}, abstractNote={We develop inference procedures for longitudinal data where some of the measurements are censored by fixed constants. We consider a semi-parametric quantile regression model that makes no distributional assumptions. Our research is motivated by the lack of proper inference procedures for data from biomedical studies where measurements are censored due to a fixed quantification limit. In such studies the focus is often on testing hypotheses about treatment equality. To this end, we propose a rank score test for large sample inference on a subset of the covariates. We demonstrate the importance of accounting for both censoring and intra-subject dependency and evaluate the performance of our proposed methodology in a simulation study. We then apply the proposed inference procedures to data from an AIDS-related clinical trial. We conclude that our framework and proposed methodology is very valuable for differentiating the influences of predictors at different locations in the conditional distribution of a response variable.}, number={2}, journal={ANNALS OF STATISTICS}, author={Wang, Huixia Judy and Fygenson, Mendel}, year={2009}, month={Apr}, pages={756–781} }
 @article{wang_2009, title={Inference on quantile regression for heteroscedastic mixed models}, volume={19}, number={3}, journal={Statistica Sinica}, author={Wang, H. J.}, year={2009}, pages={1247–1261} }
 @article{thomas_wang_tsai_langford_fosmire_jubala_getzy_cutter_modiano_breen_2009, title={Influence of genetic background on tumor karyotypes: Evidence for breed-associated cytogenetic aberrations in canine appendicular osteosarcoma}, volume={17}, ISSN={["1573-6849"]}, url={http://www.scopus.com/inward/record.url?eid=2-s2.0-67349167237&partnerID=MN8TOARS}, DOI={10.1007/s10577-009-9028-z}, abstractNote={Recurrent chromosomal aberrations in solid tumors can reveal the genetic pathways involved in the evolution of a malignancy and in some cases predict biological behavior. However, the role of individual genetic backgrounds in shaping karyotypes of sporadic tumors is unknown. The genetic structure of purebred dog breeds, coupled with their susceptibility to spontaneous cancers, provides a robust model with which to address this question. We tested the hypothesis that there is an association between breed and the distribution of genomic copy number imbalances in naturally occurring canine tumors through assessment of a cohort of Golden Retrievers and Rottweilers diagnosed with spontaneous appendicular osteosarcoma. Our findings reveal significant correlations between breed and tumor karyotypes that are independent of gender, age at diagnosis, and histological classification. These data indicate for the first time that individual genetic backgrounds, as defined by breed in dogs, influence tumor karyotypes in a cancer with extensive genomic instability.}, number={3}, journal={CHROMOSOME RESEARCH}, author={Thomas, Rachael and Wang, Huixia J. and Tsai, Pei-Chien and Langford, Cordelia F. and Fosmire, Susan P. and Jubala, Cristan M. and Getzy, David M. and Cutter, Gary R. and Modiano, Jaime F. and Breen, Matthew}, year={2009}, month={Apr}, pages={365–377} }
 @article{wang_wang_2009, title={Locally Weighted Censored Quantile Regression}, volume={104}, ISSN={["0162-1459"]}, DOI={10.1198/jasa.2009.tm08230}, abstractNote={Censored quantile regression offers a valuable supplement to Cox proportional hazards model for survival analysis. Existing work in the literature often requires stringent assumptions, such as unconditional independence of the survival time and the censoring variable or global linearity at all quantile levels. Moreover, some of the work uses recursive algorithms, making it challenging to derive asymptotic normality. To overcome these drawbacks, we propose a new locally weighted censored quantile regression approach that adopts the redistribution-of-mass idea and employs a local reweighting scheme. Its validity only requires conditional independence of the survival time and the censoring variable given the covariates, and linearity at the particular quantile level of interest. Our method leads to a simple algorithm that can be conveniently implemented with R software. Applying recent theory of M-estimation with infinite dimensional parameters, we establish the consistency and asymptotic normality of the proposed estimator. The proposed method is studied via simulations and is illustrated with the analysis of an acute myocardial infarction dataset.}, number={487}, journal={JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION}, author={Wang, Huixia Judy and Wang, Lan}, year={2009}, month={Sep}, pages={1117–1128} }
 @article{wang_zhu_zhou_2009, title={QUANTILE REGRESSION IN PARTIALLY LINEAR VARYING COEFFICIENT MODELS}, volume={37}, ISSN={["0090-5364"]}, DOI={10.1214/09-AOS695}, abstractNote={Semiparametric models are often considered for analyzing longitudinal data for a good balance between flexibility and parsimony. In this paper, we study a class of marginal partially linear quantile models with possibly varying coefficients. The functional coefficients are estimated by basis function approximations. The estimation procedure is easy to implement, and it requires no specification of the error distributions. The asymptotic properties of the proposed estimators are established for the varying coefficients as well as for the constant coefficients. We develop rank score tests for hypotheses on the coefficients, including the hypotheses on the constancy of a subset of the varying coefficients. Hypothesis testing of this type is theoretically challenging, as the dimensions of the parameter spaces under both the null and the alternative hypotheses are growing with the sample size. We assess the finite sample performance of the proposed method by Monte Carlo simulation studies, and demonstrate its value by the analysis of an AIDS data set, where the modeling of quantiles provides more comprehensive information than the usual least squares approach.}, number={6B}, journal={ANNALS OF STATISTICS}, author={Wang, Huixia Judy and Zhu, Zhongyi and Zhou, Jianhui}, year={2009}, month={Dec}, pages={3841–3866} }
 @article{thomas_duke_wang_breen_higgins_linder_ellis_langford_dickinson_olby_et al._2009, title={‘Putting our heads together’: insights into genomic conservation between human and canine intracranial tumors}, volume={94}, ISSN={0167-594X 1573-7373}, url={http://dx.doi.org/10.1007/s11060-009-9877-5}, DOI={10.1007/s11060-009-9877-5}, abstractNote={Numerous attributes render the domestic dog a highly pertinent model for cancer-associated gene discovery. We performed microarray-based comparative genomic hybridization analysis of 60 spontaneous canine intracranial tumors to examine the degree to which dog and human patients exhibit aberrations of ancestrally related chromosome regions, consistent with a shared pathogenesis. Canine gliomas and meningiomas both demonstrated chromosome copy number aberrations (CNAs) that share evolutionarily conserved synteny with those previously reported in their human counterpart. Interestingly, however, genomic imbalances orthologous to some of the hallmark aberrations of human intracranial tumors, including chromosome 22/NF2 deletions in meningiomas and chromosome 1p/19q deletions in oligodendrogliomas, were not major events in the dog. Furthermore, and perhaps most significantly, we identified highly recurrent CNAs in canine intracranial tumors for which the human orthologue has been reported previously at low frequency but which have not, thus far, been associated intimately with the pathogenesis of the tumor. The presence of orthologous CNAs in canine and human intracranial cancers is strongly suggestive of their biological significance in tumor development and/or progression. Moreover, the limited genetic heterogenity within purebred dog populations, coupled with the contrasting organization of the dog and human karyotypes, offers tremendous opportunities for refining evolutionarily conserved regions of tumor-associated genomic imbalance that may harbor novel candidate genes involved in their pathogenesis. A comparative approach to the study of canine and human intracranial tumors may therefore provide new insights into their genetic etiology, towards development of more sophisticated molecular subclassification and tailored therapies in both species.}, number={3}, journal={Journal of Neuro-Oncology}, publisher={Springer Science and Business Media LLC}, author={Thomas, Rachael and Duke, Shannon E. and Wang, Huixia J. and Breen, Tessa E. and Higgins, Robert J. and Linder, Keith E. and Ellis, Peter and Langford, Cordelia F. and Dickinson, Peter J. and Olby, Natasha J. and et al.}, year={2009}, month={Mar}, pages={333–349} }
 @article{wang_he_2008, title={An enhanced quantile approach for assessing differential gene expressions}, volume={64}, ISSN={["0006-341X"]}, DOI={10.1111/j.1541-0420.2007.00903.x}, abstractNote={Summary Due to the small number of replicates in typical gene microarray experiments, the performance of statistical inference is often unsatisfactory without some form of information‐sharing across genes. In this article, we propose an enhanced quantile rank score test (EQRS) for detecting differential expression in GeneChip studies by analyzing the quantiles of gene intensity distributions through probe‐level measurements. A measure of sign correlation, δ, plays an important role in the rank score tests. By sharing information across genes, we develop a calibrated estimate of δ, which reduces the variability at small sample sizes. We compare the EQRS test with four other approaches for determining differential expression: the gene‐specific quantile rank score test, the quantile rank score test assuming a common δ, a modified t‐test using summarized probe‐set‐level intensities, and the Mack–Skillings rank test on probe‐level data. The proposed EQRS is shown to be favorable for preserving false discovery rates and for being robust against outlying arrays. In addition, we demonstrate the merits of the proposed approach using a GeneChip study comparing gene expression in the livers of mice exposed to chronic intermittent hypoxia and of those exposed to intermittent room air.}, number={2}, journal={BIOMETRICS}, author={Wang, Huixia and He, Xuming}, year={2008}, month={Jun}, pages={449–457} }
 @article{wang_he_2007, title={Detecting differential expressions in GeneChip microarray studies: A quantile approach}, volume={102}, ISSN={["1537-274X"]}, DOI={10.1198/016214506000001220}, abstractNote={In this article we consider testing for differentially expressed genes in GeneChip studies by modeling and analyzing the quantiles of gene expression through probe level measurements. By developing a robust rank score test for linear quantile models with a random effect, we propose a reliable test for detecting differences in certain quantiles of the intensity distributions. By using a genomewide adjustment to the test statistic to account for within-array correlation, we demonstrate that the proposed rank score test is highly effective even when the number of arrays is small. Our empirical studies with real experimental data show that detecting differences in the quartiles for the probe level data is a valuable complement to the usual mixed model analysis based on Gaussian likelihood. The methodology proposed in this article is a first attempt to develop inferential tools for quantile regression in mixed models.}, number={477}, journal={JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION}, author={Wang, Huixia and He, Xuming}, year={2007}, month={Mar}, pages={104–112} }
 @article{wang_huang_2007, title={Mixture-model classification in DNA content analysis}, volume={71A}, ISSN={["1552-4922"]}, DOI={10.1002/cyto.a.20443}, abstractNote={AbstractDNA abundance provides important information about cell physiology and proliferation activity. In a typical in vitro cellular assay, the distribution of the DNA content within a sample is comprised of cell debris, G0/G1‐, S‐, and G2/M‐phase cells. In some circumstances, there may be a collection of cells that contain more than two copies of DNA. The primary focus of DNA content analysis is to deconvolute the overlapping mixtures of the cellular components, and subsequently to investigate whether a given treatment has perturbed the mixing proportions of the sample components. We propose a restricted mixture model that is parameterized to incorporate the available biological information. A likelihood ratio (LR) test is developed to test for changes in the mixing proportions between two cell populations. The proposed mixture model is applied to both simulated and real experimental data. The model fitting is compared with unrestricted models; the statistical inference on proportion change is compared between the proposed LR test and the Kolmogorov–Smirnov test, which is frequently used to test for differences in DNA content distribution. The proposed mixture model outperforms the existing approaches in the estimation of the mixing proportions and gives biologically interpretable results; the proposed LR test demonstrates improved sensitivity and specificity for detecting changes in the mixing proportions. © 2007 International Society for Analytical Cytology}, number={9}, journal={CYTOMETRY PART A}, author={Wang, Huixia and Huang, Shuguang}, year={2007}, month={Sep}, pages={716–723} }
 @article{wang_huang_shou_su_onyia_liao_li_2006, title={Comparative analysis and integrative classification of NC160 cell lines and primary tumors using gene expression profiling data}, volume={7}, journal={BMC Genomics}, author={Wang, H. X. and Huang, S. G. and Shou, J. Y. and Su, E. W. and Onyia, J. E. and Liao, B. R. and Li, S. Y.}, year={2006} }