Add analysis

.gitignore

@@ -0,0 +1,5 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
+.positai

Assignment 2.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

README.md

@@ -1,5 +1,14 @@
 # Assignment #2 Repository
 
-This repository includes the simulated data for Assignment #2. Fork this repository and add your analysis as described in the canvas assignment.
-
 The csv file for `cohort` in the `raw-data` folder includes 5,000 observations with variables `smoke`, `female`, `age`, `cardiac`, and `cost`.
+
+## Summary of findings:
+I modeled the association between the cost and cardiac variables using a logistic 
+regression and adjusted for age, sex, and smoke. Every 1 unit increase in cost is 
+associated with a 1 fold increase in odds of cardiac. While cost appears reasonably
+normally distributed, those with cardiac=1 have much higher cost on average.
+
+## AI statement:
+I did not use any generative AI technology to complete this assignment.
+
+![Alt Text](figures/Figure1.png)

code/analysis.R

@@ -0,0 +1,48 @@
+# Code for Assignment 2 - EPI 203
+# Author: Sylvie Dobrota Lai
+# Date: Apr 27, 2026
+
+library(tidyverse)
+library(tableone)
+
+#Load data 
+hw2_df <- read_csv("raw-data/cohort.csv")
+head(hw2_df)
+
+#Prepare variables
+clean_df <- hw2_df %>% 
+  mutate(
+    smoke=as.factor(smoke),
+    female=as.factor(female),
+    cardiac=as.factor(cardiac)
+  )
+
+#Table 1
+myVars<-c("smoke", "female", "age", "cardiac", "cost")
+catVars<-c("smoke", "female", "cardiac")
+
+table1<- CreateTableOne(vars=myVars, data=hw2_df, factorVars = catVars)
+
+print(table1, showAllLevels = TRUE)
+
+# Logistic model, cardiac as outcome
+model <- glm(cardiac~ cost + age + female + smoke, 
+             data=clean_df, 
+             family="binomial")
+
+summary(model)
+exp(coef(model))
+
+# Distribution of cost by cardiac status
+p <- clean_df %>% 
+  ggplot( aes(x=cost, fill=cardiac)) +
+  geom_histogram( color="#e9ecef", alpha=0.6, position = 'identity') +
+  scale_fill_manual(values=c("#69b3a2", "#404080")) +
+  theme_classic() +
+  labs(fill="cardiac",
+       title="Distribution of cost by cardiac")
+
+p
+
+ggsave("figures/Figure1.png", plot=p)
+