josealvarez97

# If you are copy/pasting this to an R Notebook, select "Raw" from the GitHub page before you copy.

# Replication file of Section 5 in
# Iacus, King, Porro (2011), Multivariate Matching Methods 
# That Are Monotonic Imbalance Bounding, JASA, V 106, N. 493,
# p. 345-361

foo <- read.csv(url("https://course-resources.minerva.kgi.edu/uploaded_files/mke/00089202-1711/daughters.csv"))

# Table 1 in Ebonya

josealvarez97

# Logistic Regression and lalonde data set

library(Matching)
data(lalonde)
head(lalonde)
summary(lalonde)
View(lalonde)
??lalonde

# Note: For simplicity, all operations will be performed over the training model.

josealvarez97

# Produce model from training set
LinearRegression.1 <- lm(clickperview ~ timeofday + Post_type + promotion + target_audience, data=Lironne_DataSet_Training) 
summary(LinearRegression.1)


predict(LinearRegression.1,Lironne_DataSet_Training) == Lironne_DataSet_Training

# Calculate RMSE for training set
RMSE.trainingset <- sqrt(mean( (Lironne_DataSet_Training$clickperview - predict(LinearRegression.1, Lironne_DataSet_Training))^2 ))
RMSE.trainingset

josealvarez97

# READ DATA
DataSet <- read.csv("datasetforCS112-TA.csv", stringsAsFactors = FALSE)

# FIX DATA TYPES IN DATA FRAME
# Factors
DataSet$status <- as.factor(DataSet$status)
DataSet$project.type <- as.factor(DataSet$project.type)
# Dates
DataSet$approval.date <- as.Date(DataSet$approval.date, format = "%d-%B-%y")
DataSet$implementation.start.date <- as.Date(DataSet$implementation.start.date, format="%d-%B-%y")