@article {Shchur145599,
author = {Shchur, Vladimir and Nielsen, Rasmus},
title = {On the Number of Siblings and p-th Cousins in a Large Population Sample},
elocation-id = {145599},
year = {2018},
doi = {10.1101/145599},
publisher = {Cold Spring Harbor Laboratory},
abstract = {The number of individuals in a random sample with close relatives in the sample is a quantity of interest when designing Genome Wide Association Studies (GWAS) and other cohort based genetic, and non-genetic, studies. In this paper, we develop expressions for the distribution and expectation of the number of p-th cousins in a sample from a population of size N under two diploid Wright-Fisher models. We also develop simple asymptotic expressions for large values of N. For example, the expected proportion of individuals with at least one p-th cousin in a sample of K individuals, for a diploid dioecious Wright-Fisher model, is approximately 1 - e-(22p-1)K/N. Our results show that a substantial fraction of individuals in the sample will have at least a second cousin if the sampling fraction (K/N) is on the order of 10-2. This confirms that, for large cohort samples, relatedness among individuals cannot easily be ignored.},
URL = {https://www.biorxiv.org/content/early/2018/05/03/145599},
eprint = {https://www.biorxiv.org/content/early/2018/05/03/145599.full.pdf},
journal = {bioRxiv}
}