From f4e224d29b5f513394385c67d741c3e125c01a36 Mon Sep 17 00:00:00 2001 From: Nicholas Mancuso Date: Fri, 30 Jun 2023 09:51:07 -0700 Subject: [PATCH] Update README.rst --- README.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.rst b/README.rst index 3304e47..6b653bc 100644 --- a/README.rst +++ b/README.rst @@ -77,7 +77,7 @@ where $N_i$ is the sample size for the $i^{th}$ GWAS , $\\mu$ is the intercept heterogeneity in statistical power across studies with precision scalar . Given $Z = \\{Z_i\\}^n_{i=1}$, and model parameters $L$, $F$, $\\mu$, $\\tau$, we can compute the likelihood as -$$\\mathcal{L}(L, F, \\mu, \\tau |Z) = \\prod_i \\mathcal{N}_p ( \\sqrt{N_i} (L f_i + \\mu), \\tau^{-1} I_p)$$ +$$\\mathcal{L}(L, F, \\mu, \\tau | Z) = \\prod_i \\mathcal{N}_p ( \\sqrt{N_i} (L f_i + \\mu), \\tau^{-1} I_p)$$ To model our uncertainty in $L$, $F$, $\\mu$, we take a full Bayesian approach in the lower dimension latent space similar to a Bayesian PCA model [1]_ as,