Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Johnsen, Pål Vegard"'
We investigate saddlepoint approximations applied to the score test statistic in genome-wide association studies with binary phenotypes. The inaccuracy in the normal approximation of the score test statistic increases with increasing sample imbalance
Externí odkaz:
http://arxiv.org/abs/2110.04025
Autor:
Johnsen, Pål Vegard, Strümke, Inga, Riemer-Sørensen, Signe, DeWan, Andrew Thomas, Langaas, Mette
Estimating feature importance is a significant aspect of explaining data-based models. Besides explaining the model itself, an equally relevant question is which features are important in the underlying data generating process. We present a Shapley v
Externí odkaz:
http://arxiv.org/abs/2109.00855
Autor:
Johnsen, Pål Vegard1,2 (AUTHOR) pal.johnsen@sintef.no, Strümke, Inga3,4 (AUTHOR), Langaas, Mette2 (AUTHOR), DeWan, Andrew Thomas5 (AUTHOR), Riemer-Sørensen, Signe1 (AUTHOR)
Publikováno v:
PLoS Computational Biology. 3/14/2023, Vol. 19 Issue 3, p1-22. 22p. 1 Diagram, 3 Charts, 3 Graphs.
