Instantly share code, notes, and snippets.

Richard Moreyricharddmorey

• Sort options
Last active Feb 27, 2017
posterior for delta given only t and N
View delta_t.R
 ### Data t = 2 N = 20 rscale = sqrt(2)/2 ### Begin utility functions posterior = Vectorize(function(delta, t, N1, N2 = NULL, rscale = sqrt(2)/2, log = FALSE){
Created Dec 23, 2016
Using JAGS to sample missing values in both DVs and IVs in Bayesian regression
View missings_jags.R
 set.seed(123) # make reproducible M = 10000 # Number of posterior samples N = 20 # sample the IV x = rnorm(N, 10, 5) # regression model for DVs y = 100 + 3*x + rnorm(N,0,10) ## Delete missing data (3 in each)
Created Dec 21, 2016
View t1err-sim.R
 ### Utility functions # Do a single t test simulation # report the p value ttest.sim = function(n, func, true.mean = 0, alpha = 0.05){ x = func(n) - true.mean t.test(x)\$p.value } # Do a sequence of M t tests, report significance
Last active Oct 28, 2016
Spooky random numbers
View getSpookyNums.R
 getSpookyNums = function(M){ s = tempfile() # to ensure no caching my.url = paste0("http://richarddmorey.org/spooky.php?n=",M,"&",s) as.numeric(readLines(my.url)) } x = getSpookyNums(10)
Created Oct 28, 2016
example XML for distribution
View normal.xml
 Normal Normal Gaussian normal continuous
Last active Nov 17, 2016
Troubleshooting flexdashboard scrollbars
View solve.Rmd_
 --- title: "Generated data demo" output: flexdashboard::flex_dashboard: orientation: rows vertical_layout: scroll runtime: shiny --- ```{r setup, include=FALSE}
Last active Aug 11, 2016
Run the Essex Data Analysis Summer School JAGS demo in R
View runAll.R
 devtools::source_gist("2bd1b7a409fad3d71fc2d60884c85e50", filename = "runJAGSDemo.R")
Created Aug 10, 2016
example, Essex, beta/binomial
View beta.binomial.R
 y = 13 N = 35 a = 1 b = 1 theta = seq(0, 1, len = 100) likelihood = theta ^ y * (1-theta)^(N-y) #dbinom(y, N, theta) prior = theta ^ (a-1) * (1-theta)^(b-1) #dbeta(theta, a, b) posterior1 = prior * likelihood
Last active Aug 8, 2016
Comparison between normal and logistic priors for proportion Bayes factors
View do_plots.R
 devtools::source_gist("e49c345fcd6cfe8f32535eda4bd8c29b", filename='utility_functions.R') # Prior Setup p0 = .5 rscale = .5 interval = c(.5,1) # Do not change shift unless you want different prior shift # will cause deviation from BayesFactor package # (not that there's anything wrong with that, but changes demo) shift = qlogis(p0)
Created Jun 4, 2016
A demonstration of Bayes' theorem as "selecting subsets" using R markdown and interactive 3D plots
View binomial-beta.Rnw
 --- title: "Joint and conditional, binomial/beta example" author: "Richard D. Morey" date: "4 June 2016" output: html_document --- ```{r,echo=FALSE,warning=FALSE} library(rgl) library(knitr)
You can’t perform that action at this time.