ManualRivas
summary
Uses Stan and BRMS to fit mixture models to summary GWAS statistics from the UK Biobank (~500,000), estimating genetic correlation, scale and the fraction pi of nonzero effects. Shows a two‑component multivariate normal and a four‑component sex model, finds >50 sex‑specific variants for waist‑hip ratio, cites PCSK9 loss‑of‑function lowering LDL ~80% and MI risk ~50%, reports Rhat near 1 for correlations, and flags heavy computation for full Bayesian fits.
AI-written summary · about
chapters (8)
- 0:00Start
- 4:10What a Genetic Association Study Is
- 7:16The Manhattan Plot
- 12:06Why the Need for Stan in Human Genetics
- 13:56Dna Sequencing
- 17:13Data from Genetic Study
- 21:36Estimate Genetic Parameters
- 31:37Genetic Variants That Have Sex Specific Effects
related talks
17mPrecision Medicine for All: Using Tidymodels to Validate PRS in Brazil
29mBreaking the Winner's Curse in Mendelian Randomization: Rerandomized Inverse Variance...
38mMixed and Covariate-Dependent Graphical Models
01h 27mFlexible Statistical Modeling
29mDeveloping and Delivering Personalized Polygenic Scores at Scale
01h 24mIntroductory tutorial on data exploration and statistical models
34mFast, beautiful and easy Bayesian modelling: Can you have it all?
31mBayesian Risk Analysis For Large Multi-Modal Data