viniciusmss

set.seed(20181001)
### LOOCV 

# Load packages and data
library(Matching)
library(boot)
data(lalonde)

# Train your model on ALL the data -- Use glm instead of lm

viniciusmss

library(haven)
library(arm)
df <- read_dta("C:/Users/Vinic/Downloads/turnout.dta")
View(df)
df[1,1]
df[1,]

lm2 <- glm(turnout ~ ., data = df, family = binomial)
summary(lm2)

viniciusmss

library(boot)

#estimate the mean via bootstrapping
boot.mean <- function(data,index) return(mean(data[index]))

#calculate the CI via t-distribution
t.dist.ci <- function(samp) {
  df <- length(samp) - 1
  factors <- qt(c(0.025, 0.975), df = df)
  samp.mean <- mean(samp) 

diamonaj

# EXERCISE TO BUILD INTUITION FOR CORRELATED VS. UNCORRELATED DATA
# PLEASE FOCUS ON UNDERSTANDING THE BELOW
### DO NOT JUST EXECUTE ALL THE CODE IN ONE BATCH--RUN IT LINE BY LINE...

### Simulation of analysis on correlated data

set.seed(1314)

nsims <- 10000

diamonaj

################ PRELIMINARIES
library(MASS)
data(Pima.tr)
library(tree)
library(randomForest)

## STEP 1: Logistic regression ##
logistic_reg <- glm(type ~ ., data = Pima.tr, family = binomial) # basic model
predict_logistic.tr <- predict(logistic_reg, type = "response")  # predicted probabilities (TRAINING SET)

diamonaj

storage.vector <- NA

# Function that assigns treatment/control depending on 
# propensity scores (assignment probabilities)
experiment <- function(vector.of.probabilities = NULL) {
  k = 0
  for (i in 1:length(vector.of.probabilities)) {
    if(
      sample(x = c(1,0), size = 1, prob = c(vector.of.probabilities[i], 
                                            1 - vector.of.probabilities[i])) == 1) {

viniciusmss

viniciusmss

# An addition
5 + 5 

# A subtraction
5 - 5 

# A multiplication
3 * 5

# A division

viniciusmss

diamonaj

PEACEKEEPING WORKOUT (based on  King, Gary;Zeng, Langche, 2007, 
                      "Replication data for: When Can History be Our Guide? 
                      The Pitfalls of Counterfactual Inference", 
                      https://hdl.handle.net/1902.1/DXRXCFAWPK, 
                      Harvard Dataverse, V4, 
                      UNF:3:DaYlT6QSX9r0D50ye+tXpA== [fileUNF] )
# CONSIDER USING THE JUPYTER NOTEBOOK WITH R-SERVER KERNEL (NEVER R-SAGE KERNEL)
foo <- read.csv("https://course-resources.minerva.kgi.edu/uploaded_files/mke/00086677-3767/peace.csv")
                
# extract relevant columns