%0 Journal Article %1 patterson2006population %A Patterson, Nick %A Price, Alkes L %A Reich, David %D 2006 %I Public Library of Science %J PLoS Genet %K PCA Tracy-Widom eigenvectors random_matrices software spatial_statistics spatial_structure %N 12 %P e190 %R 10.1371/journal.pgen.0020190 %T Population Structure and Eigenanalysis %U http://dx.plos.org/10.1371%2Fjournal.pgen.0020190 %V 2 %X Current methods for inferring population structure from genetic data do not provide formal significance tests for population differentiation. We discuss an approach to studying population structure (principal components analysis) that was first applied to genetic data by Cavalli-Sforza and colleagues. We place the method on a solid statistical footing, using results from modern statistics to develop formal significance tests. We also uncover a general “phase change” phenomenon about the ability to detect structure in genetic data, which emerges from the statistical theory we use, and has an important implication for the ability to discover structure in genetic data: for a fixed but large dataset size, divergence between two populations (as measured, for example, by a statistic like $F_ST$) below a threshold is essentially undetectable, but a little above threshold, detection will be easy. This means that we can predict the dataset size needed to detect structure.

@article{patterson2006population, abstract = {Current methods for inferring population structure from genetic data do not provide formal significance tests for population differentiation. We discuss an approach to studying population structure (principal components analysis) that was first applied to genetic data by Cavalli-Sforza and colleagues. We place the method on a solid statistical footing, using results from modern statistics to develop formal significance tests. We also uncover a general “phase change” phenomenon about the ability to detect structure in genetic data, which emerges from the statistical theory we use, and has an important implication for the ability to discover structure in genetic data: for a fixed but large dataset size, divergence between two populations (as measured, for example, by a statistic like $F_{ST}$) below a threshold is essentially undetectable, but a little above threshold, detection will be easy. This means that we can predict the dataset size needed to detect structure.}, added-at = {2009-10-09T19:32:44.000+0200}, author = {Patterson, Nick and Price, Alkes L and Reich, David}, biburl = {https://www.bibsonomy.org/bibtex/211d3719065ef93be49aeebfba4e6c6bd/peter.ralph}, doi = {10.1371/journal.pgen.0020190}, interhash = {73776bdef3719e99f363736733b27b14}, intrahash = {11d3719065ef93be49aeebfba4e6c6bd}, journal = {PLoS Genet}, keywords = {PCA Tracy-Widom eigenvectors random_matrices software spatial_statistics spatial_structure}, month = {12}, number = 12, pages = {e190}, publisher = {Public Library of Science}, timestamp = {2012-07-13T19:31:18.000+0200}, title = {Population Structure and Eigenanalysis}, url = {http://dx.plos.org/10.1371%2Fjournal.pgen.0020190}, volume = 2, year = 2006 }