acoppock

library(rvest)
library(tidyverse)
library(stringr)
library(lubridate)
library(ggrepel)

pres_terms <- 
  read_html("https://www.presidentsusa.net/presvplist.html") %>%
  html_nodes("table") %>%
  pluck(1) %>%

acoppock

library(tidyverse)
library(rvest)

pew_tables <-
  read_html("http://www.pewforum.org/fact-sheet/changing-attitudes-on-gay-marriage/") %>%
  html_nodes("table") %>%
  html_table

gg_df <-
  pew_tables[-1] %>%

acoppock

rm(list = ls())
library(tidyverse)

fate <-
  function(stopping_rule) {
    # the order you meet people
    the_shuffle = sample(1:100)
    # everybody you've met
    the_exes <- the_shuffle[1:stopping_rule]
    # how good was the best so far

acoppock

# This script shows how to make blocks with blockTools, then randomize with randomizr
# Alex Coppock
# declaredesign.org

library(randomizr)
library(blockTools)
library(tidyverse)

# Prepare data with dplyr + tidyr -----------------------------------------

acoppock

# Gelman and Hill 2007: Chapter 3 Regression Examples 
# Using ggplot and estimatr

rm(list = ls())
# Uncomment to install
# install.packages("ggplot2")
# install.packges("haven")
# install.pacakges("estimatr")

library(ggplot2)

acoppock

library(DeclareDesign)
proportion_shy <- .06

population <- declare_population(
  N = 5000,
  # true trump vote (unobservable)
  truthful_trump_vote = draw_binary(.45, N),
  
  # shy voter (unobservable)  
  shy = draw_binary(proportion_shy, N),

acoppock

rm(list = ls())

library(tidyverse)
library(estimatr)

N <- 1000

dat <-
  data.frame(
    Y = rnorm(N),

acoppock

library(fabricatr)
library(randomizr)
library(estimatr)
library(ggplot2)

dat <- fabricate(N = 200,
                 Z = complete_ra(N, conditions = c("Control", "Treatment")),
                 X = sample(c("A", "B"), size = N, replace = TRUE),
                 Y = (X == "A") + (Z == "Treatment") + rnorm(N, sd = 1 + (Z == "Treatment")))

acoppock

library(DeclareDesign)
library(tidyverse)

set.seed(343)

design <-
  declare_population(N = N) +
  declare_potential_outcomes(
    # Difference 1: 0.6 - 0.4 = 0.2
    Y_Z_1 = draw_binary(prob = 0.4, N = N),