@article{xu_martin_muir_1995, title={Multistage selection for maximum economic return with an application to beef cattle breeding}, volume={73}, number={3}, journal={Journal of Animal Science}, author={Xu, S. and Martin, T. G. and Muir, W. M.}, year={1995}, pages={699} }
 @article{xu_kobak_smouse_1994, title={CONSTRAINED LEAST-SQUARES ESTIMATION OF MIXED POPULATION STOCK COMPOSITION FROM MTDNA HAPLOTYPE FREQUENCY DATA}, volume={51}, ISSN={["0706-652X"]}, DOI={10.1139/f94-043}, abstractNote={Nuclear allozymes have provided the markers of choice for genetic stock identification, especially for Pacific salmonids. For other species, a dearth of allozyme variation has led workers to pursue mtDNA markers. Haploid mtDNA markers obviate methods based on Hardy–Weinberg equilibrium; all mtDNA markers are rigidly linked, violating the independence assumption; and mtDNA sample sizes are small. Based on a conditional weighted least squares approach for the case of known source population genotype frequencies, we develop an unconditional method for estimated genotype frequencies. We compare the methods with Monte Carlo simulation, evaluating effects of source population and mixed harvest sample sizes and those of source population divergence and mixture composition. When genetic resolution is poor or sample sizes are inadequate, the conditional method works better, but with larger sample sizes and reasonable population resolution, the unconditional method is superior.}, number={2}, journal={CANADIAN JOURNAL OF FISHERIES AND AQUATIC SCIENCES}, author={XU, SZ and KOBAK, CJ and SMOUSE, PE}, year={1994}, month={Feb}, pages={417–425} }
 @article{xu_atchley_muir_1994, title={PARTIAL AND CONDITIONAL MAXIMUM-LIKELIHOOD FOR VARIANCE-COMPONENT ESTIMATION}, volume={111}, ISSN={["0931-2668"]}, DOI={10.1111/j.1439-0388.1994.tb00456.x}, abstractNote={SummaryPatterson and Thompson's idea of ‘error contrasts’ (or restricted maximum likelihood) (1971) was extended to multiple sets of linear contrasts for variance component estimtion. The error contrasts were established in such a way that only errors are retained in the model. The error variance was then estimated by maximizing the likelihood function obtained from the error contrasts. More sets of linear contrasts were then progressively established such that each set of linear contrasts contains only one class of random effects and the errors. A likelihood function was constructed and maximized for each variance of random effects given the error variance held at its estimated value. The likelihood function for estimating the covariance component between two classes of random effects was established such that all other random effects are treated as fixed effects. The likelihood function was then maximized with respect to the covariance given the two variance components fixed at their estimated values. The multidimensional optimization problem in the traditional restricted maximum‐likelihood problem was then turned into several one‐dimensional optimization problems by using this technique. Inasmuch as the error variance was estimated using a partial likelihood function and the other variance components are estimated using likelihood functions conditional on the estimated error variance, the method is referred to as partial and conditional maximum likelihood (PCML).}, number={3}, journal={JOURNAL OF ANIMAL BREEDING AND GENETICS-ZEITSCHRIFT FUR TIERZUCHTUNG UND ZUCHTUNGSBIOLOGIE}, author={XU, S and ATCHLEY, WR and MUIR, WM}, year={1994}, month={Jul}, pages={178–188} }
 @article{xu_atchley_fitch_1994, title={Phylogenetic inference under the pure drift model}, volume={11}, number={6}, journal={Molecular Biology and Evolution}, author={Xu, S. and Atchley, W. R. and Fitch, W. M.}, year={1994}, pages={949} }
 @article{xu_1994, title={WEIGHTED LEAST-SQUARES ESTIMATION OF DNA FRAGMENT LENGTHS}, volume={85}, ISSN={["0022-1503"]}, DOI={10.1093/oxfordjournals.jhered.a111417}, abstractNote={A new weighted least squares method, which fits the reciprocal mobility model and directly minimizes the sum of squares of percentage deviations, is introduced for estimating DNA fragment lengths. Results are illustrated for data analysis using published data.}, number={2}, journal={JOURNAL OF HEREDITY}, author={XU, S}, year={1994}, pages={151–152} }
 @article{xu_1993, title={INDUPDAT - A SAS/IML PROGRAM FOR SELECTION INDEX UPDATING}, volume={84}, ISSN={["0022-1503"]}, DOI={10.1093/oxfordjournals.jhered.a111347}, abstractNote={Journal Article INDUPDAT: A SAS/IML Program for Selection Index Updating Get access S. Xu S. Xu Department of Genetics, North Carolina State UniversityRaleigh, NC 27695-7164 Address reprints requests to Dr. Xu at the address above, or sxgn@unity.ncsu.edu. Search for other works by this author on: Oxford Academic PubMed Google Scholar Journal of Heredity, Volume 84, Issue 4, July 1993, Page 316, https://doi.org/10.1093/oxfordjournals.jhered.a111347 Published: 01 July 1993}, number={4}, journal={JOURNAL OF HEREDITY}, author={XU, S}, year={1993}, pages={316–316} }