Featured Publications
SDPRX: A statistical method for cross-population prediction of complex traits
Zhou G, Chen T, Zhao H. SDPRX: A statistical method for cross-population prediction of complex traits. American Journal Of Human Genetics 2022, 110: 13-22. PMID: 36460009, PMCID: PMC9892700, DOI: 10.1016/j.ajhg.2022.11.007.Peer-Reviewed Original ResearchConceptsStatistical methodsJoint distributionWide association study (GWAS) summary statisticsNon-European populationsReal traitsSummary statisticsCross-population predictionPrediction accuracyGenome-wide association study summary statisticsLinkage disequilibrium differencesPrediction performancePolygenic risk scoresComplex traitsStatisticsSimulationsApplicationsTraits
2020
Leveraging effect size distributions to improve polygenic risk scores derived from summary statistics of genome-wide association studies
Song S, Jiang W, Hou L, Zhao H. Leveraging effect size distributions to improve polygenic risk scores derived from summary statistics of genome-wide association studies. PLOS Computational Biology 2020, 16: e1007565. PMID: 32045423, PMCID: PMC7039528, DOI: 10.1371/journal.pcbi.1007565.Peer-Reviewed Original ResearchConceptsEffect size distributionClass of methodsReal data applicationOnly summary statisticsTheoretical resultsSummary statisticsExtensive simulation resultsLD informationSimulation resultsData applicationsFirst methodImportant problemOptimal propertiesGenetic risk predictionAccurate predictionPrediction accuracyStandard PRSStatisticsPrediction method
2011
A permutation test approach to the choice of size k for the nearest neighbors classifier
Lai Y, Wu B, Zhao H. A permutation test approach to the choice of size k for the nearest neighbors classifier. Journal Of Applied Statistics 2011, 38: 2289-2302. DOI: 10.1080/02664763.2010.547565.Peer-Reviewed Original ResearchNearest neighbor classifierNeighbor classifierReal-world data setsCross-validation approachPrediction accuracyStatistical pattern recognitionHigh prediction accuracyMachine learningNumber of neighborsPattern recognitionMultiple sample groupsInformative featuresNumber of NNsSize k.Size kData setsClassifierPopular methodCross-validation procedureTest approachClassificationAccuracyLearningNeighborsNN