𝔽ind the class notes here […] Notice that the estimated effect size divided by the standard error behaves like a normal(0,1) random variable when the sample size is large enough: […] \[ Z = \frac{\hat\beta}{\text{se}(\hat\beta)}\] \[Z \approx N(0,1) ~~~~~~ \text{as } n \rightarrow … Read more →

𝕚f(!file.exists(glue::glue("~/Downloads/analysis_population_structure.tgz"))) { system(glue::glue("wget -O ~/Downloads/analysis_population_structure.tgz https://uchicago.box.com/shared/static/zv1jyevq01mt130ishx25sgb1agdu8lj.tgz")) ## tar -xf file_name.tar.gz --directory … Read more →

𝕊ee the full vignette here ## simulate two independent, normally distributed random variables X and epsi ## set seed to make simulations reproducible set.seed(20210108) ## parameter definition nsamp = 100 beta = 2 h2 = 0.6 sig2X = h2 sig2epsi = (1 - sig2X) * beta^2 sigX = sqrt(sig2X) sigepsi = … Read more →