alexpkeil1

c(-38.3455, 0.54882, 5.19848, 0.492518, 0.566555, -0.0479212, 
0.333422, 8.85725, 0.450325, 0.277257, -148.454, 0.504147, 0.356457, 
0.341726, 0.405021, 0.28855, 0.972497, 0.605668, 0.539456, -136.618, 
-105.166, 1.49517, 0.707087, 0.0541961, 0.452244, 442.601, 0.288529, 
0.0149293, 48.3507, 606.591, 0.971479, 1.81285, 6.27816, 0.531303, 
0.874542, 16.5209, 0.446185, 0.76069, 12.3285, 0.629471, 0.719511, 
-0.061535, 0.828019, 0.233507, 0.170131, 0.682919, 0.880852, 
0.577185, 0.88224, 0.489173, 0.539035, 0.385609, 232.693, 0.504418, 
0.654281, 0.59836, 0.457291, 2.51278, 0.459031, 12366.9, 0.773534, 
6.5793, 1.02045, 0.451943, 0.176133, 463.412, 1549.17, 0.403163, 

alexpkeil1

# coding: utf-8
# python-2.7
# new yorker caption contest
import requests
import bs4 # beautifulsoup
import mechanize
import cookielib
import getpass

def ny_url(num=500, pr=False):

alexpkeil1

#! /usr/local/anaconda/bin/python

def bot():
  %magicstuff

alexpkeil1

######################################################################################################################
# Author: Alex Keil
# Program: weight_bias.R
# Language: R
# Date: Friday, February 21, 2020 at 3:18:41 PM
# Project: qgcomp
# Description: # addressing a conjecture that WQS will yield better estimates of weights than qgcomp
# when the assumptions of WQS hold in sample sizes of 500 in a scenario in which 
# exposures are all uncorrelated
#

alexpkeil1

# Example in which weighted quantile sums estimates a significant, positive effect of exposure due to pure confounding
#  even though there are no exposures that have a positive effect on the outcome



library(qgcomp)
library(gWQS)

dgm <- function(N = 100, b0=0, coef=c(1,0,0,0), family=gaussian(), ncor=0, corr=0.75, umc=FALSE){
  # simulate under data structure where WQS is the truth: e.g. an exposure with 

alexpkeil1

# simulation 1 from appendix of 
#  ”Per- and poly-fluoroalkyl substances and bone mineral density: 
#    Results from the Bayesian weighted quantile sum regression” by Colicino et al.
#
#  simulate data and run the BWQS model

library(rstan)
library(qgcomp)
parallel:::setDefaultClusterOptions(setup_strategy = "sequential") # kludge for bug in parallel package with r4.0
options(mc.cores = parallel::detectCores())

alexpkeil1

#!/usr/local/env R
# a way to base the quantiles off of weighted data

library(qgcomp)
library(DescTools) # need this to calculate weighted quantiles
data(metals)

# new function to calculate weighted quantiles
quantize.wtd <- function (data, expnms, q = 4, breaks = NULL, weights=NULL) 
{

alexpkeil1

# using qgcomp.cox.noboot in a nested case-control analysis as a way to fit a conditional logit qgcomp model
library(qgcomp)
library(survival)

# read in data from a nested case control study
data(infert, package = "datasets")
head(infert)


### 1) check that it works, part A

alexpkeil1

library(qgcomp)
library(mvtnorm)

Niter = 1000
seedvals = round(runif(Niter)*.Machine$integer.max)


truemod <- function(X,beta){
  X %*% beta
}

alexpkeil1

library(qgcomp)

msm.fit.noint <- function(f,
                          qdata,
                          intvals,
                          expnms,
                          rr=TRUE,
                          main=TRUE,
                          degree=1,
                          id=NULL,