diamonaj

#####################################
#####################################
#####################################

# Run a logistic regression and generate expected values of turnout, holding some predictors constant while others vary.


df <- read.csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSjMB6H07nhXmgdARkAMkUVWt7QPlzdD-RrDor2g_BSL9vil8V4efJ-iO-nQtZuqPE_klZPi6qNJ9Pw/pub?gid=921072292&single=true&output=csv")

glm2 <- glm(turnout ~ ., data = df, family = binomial)

diamonaj

## Step 1: Load the Training Data

#Download and inspect the training set using `read.csv()` from the URL provided:

# **Training data link:**  

training <- read.csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSUROPfTOZfUEpf6Ebby-vta5zWCwt9KK-KAwSvpToGQjQSKdhYsUfoHxYxvbOYxW8_IQxBD9FqWFJg/pub?gid=383144413&single=true&output=csv")
# View the first few rows using head()
head(training)

diamonaj

---
title: "CS130 Causal Inference Assignment Spring 2024"
output: html_document
date: "2024-04-01"
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

diamonaj

rm(list=ls())
training <- read.csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSUROPfTOZfUEpf6Ebby-vta5zWCwt9KK-KAwSvpToGQjQSKdhYsUfoHxYxvbOYxW8_IQxBD9FqWFJg/pub?gid=383144413&single=true&output=csv")

head(training)

# plot the data with big green dots
plot(training$x, training$y, main = "Training Data", pch = 16, cex = 3, col = "green")

################################################
#### RUN 3 DIFFERENT MODELS ON THE TRAINING SET

diamonaj

set.seed(432)

# imagine these are scores before a program:
before <- rnorm(50, mean = 0, sd = 10)

# imagine these are scores after a program
after <- before + rnorm(50, mean = 5, sd = 20)

# the scores are correlated, but not perfectly correlated
# correlation = 0.32... the program helps, 

diamonaj

simulate_raquetball = function(number_of_games, prob_win_serve,
                               prob_win_noserve, points_to_win)
{    
  # variable to track the number of wins
  wins = 0
 
  # variable to track the number of simulated games
  total_games = 1
 
  # list where we will store the number of volleys per game

diamonaj

install.packages("MASS")
library(MASS)
data(Pima.tr)
data(Pima.te)
#############


## STEP 1: Logistic regression, predict diabetes yes or no ##
logistic_reg <- glm(type ~ ., data = Pima.tr, family = binomial) # basic model 
predict_logistic.tr <- predict(logistic_reg, type = "response")  # predicted probabilities (TRAINING SET)

diamonaj

## This long coding example shows you how to obtain
## confidence intervals for logistic regression.
## The appendix at the very bottom also shows you how to obtain
## something analogous to prediction intervals
## for a logistic regression.  

## Here's a High-level summary of the basic procedure, step-by-step:

## Step 1:  Run desired logistic regression, including any desired interactions
##         

diamonaj

# Quiz 3 ANSWERS
#######

# Read the article:
#  https://www.menshealth.com/trending-news/a30894231/amazon-interview-sock-puzzle/
  
  
# 1. Write a function that will simulate the act of pulling 2 socks out of the drawer 
#    exactly as described in the Men's Health article. (i.e., selection without replacement)
  

diamonaj

###### Quiz 2 #######

# For this quiz you will analyze UN Peacekeeping data. 

# At any given time, the UN is involved with many peacekeeping missions around the world. 

# Almost all member-states contribute personnel to those missions. There are five types of personnel: 
# experts on mission, troops, staff officers, individual police, and formed police units.
# In its efforts to involve more women in its global operations, the UN reports, monthly, the
# gender of each person sent on a mission. You can read more about it here: