Upload New File

FinalProj.Rmd

+---
+title: "finalproj403"
+author: "irisqlin"
+date: "11/13/2021"
+output: html_document
+---
+
+```{r setup, include=FALSE}
+knitr::opts_chunk$set(echo = TRUE)
+```
+
+## R Markdown
+
+```{r}
+library(stringr)
+data <- read.csv("IYSdata.csv")
+names(data)
+
+# predictor data cleaning
+
+data$X30.cig <- str_remove_all(data$X30.cig, " days")
+data$X30.cig <- str_remove_all(data$X30.cig, " day")
+data$X30.cig <- str_remove_all(data$X30.cig, " or more")
+data$X30.cig[data$X30.cig == "1-2"] <- 1.5
+data$X30.cig[data$X30.cig == "3-5"] <- 4
+data$X30.cig[data$X30.cig == "6-9"] <- 7.5
+data$X30.cig[data$X30.cig == "10-19"] <- 14.5
+data$X30.cig[data$X30.cig == "20-29"] <- 24.5
+data$X30.cig <- as.numeric(data$X30.cig)
+mean(data$X30.cig)
+
+data$X30drink <- str_remove_all(data$X30drink, " days")
+data$X30drink <- str_remove_all(data$X30drink, " day")
+data$X30drink <- str_remove_all(data$X30drink, " or more")
+data$X30drink[data$X30drink == "1-2"] <- 1.5
+data$X30drink[data$X30drink == "3-5"] <- 4
+data$X30drink[data$X30drink == "6-9"] <- 7.5
+data$X30drink[data$X30drink == "10-19"] <- 14.5
+data$X30drink[data$X30drink == "20-29"] <- 24.5
+data <- na.omit(data)
+data$X30drink <- as.numeric(data$X30drink)
+mean(data$X30drink)
+
+data$X30marijuana <- str_remove_all(data$X30marijuana, " days")
+data$X30marijuana <- str_remove_all(data$X30marijuana, " day")
+data$X30marijuana <- str_remove_all(data$X30marijuana, " or more")
+data$X30marijuana[data$X30marijuana == "1-2"] <- 1.5
+data$X30marijuana[data$X30marijuana == "3-5"] <- 4
+data$X30marijuana[data$X30marijuana == "6-9"] <- 7.5
+data$X30marijuana[data$X30marijuana == "10-19"] <- 14.5
+data$X30marijuana[data$X30marijuana == "20-29"] <- 24.5
+data <- na.omit(data)
+data$X30marijuana <- as.numeric(data$X30marijuana)
+mean(data$X30marijuana)
+```
+
+```{r}
+# response data cleaning
+data$times.moved[data$times.moved == "None"] <- 0
+data$times.moved[data$times.moved == "Once"] <- 1
+data$times.moved[data$times.moved == "Twice"] <- 2
+data$times.moved[data$times.moved == "Three times"] <- 3
+data$times.moved[data$times.moved == "Four times or more"] <- 4
+data <- na.omit(data)
+mean(as.numeric(data$times.moved))
+data$times.moved <- as.numeric(data$times.moved)
+
+data$pride[data$pride == "Strongly agree"] <- 4
+data$pride[data$pride == "Agree"] <- 3
+data$pride[data$pride == "Disagree"] <- 2
+data$pride[data$pride == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$pride))
+data$pride <- as.numeric(data$pride)
+
+data$truth[data$truth == "Strongly agree"] <- 4
+data$truth[data$truth == "Agree"] <- 3
+data$truth[data$truth == "Disagree"] <- 2
+data$truth[data$truth == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$truth))
+data$truth <- as.numeric(data$truth)
+
+data$responsibility[data$responsibility == "Strongly agree"] <- 4
+data$responsibility[data$responsibility == "Agree"] <- 3
+data$responsibility[data$responsibility == "Disagree"] <- 2
+data$responsibility[data$responsibility == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$responsibility))
+data$responsibility <- as.numeric(data$responsibility)
+
+data$friends[data$friends == "Strongly agree"] <- 4
+data$friends[data$friends == "Agree"] <- 3
+data$friends[data$friends == "Disagree"] <- 2
+data$friends[data$friends == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$friends))
+data$friends <- as.numeric(data$friends)
+
+data$fix.problems[data$fix.problems == "Strongly agree"] <- 4
+data$fix.problems[data$fix.problems == "Agree"] <- 3
+data$fix.problems[data$fix.problems == "Disagree"] <- 2
+data$fix.problems[data$fix.problems == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$fix.problems))
+data$fix.problems <- as.numeric(data$fix.problems)
+
+data$decision[data$decision == "Strongly agree"] <- 4
+data$decision[data$decision == "Agree"] <- 3
+data$decision[data$decision == "Disagree"] <- 2
+data$decision[data$decision == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$decision))
+data$decision <- as.numeric(data$decision)
+
+data$excite[data$excite == "Strongly agree"] <- 4
+data$excite[data$excite == "Agree"] <- 3
+data$excite[data$excite == "Disagree"] <- 2
+data$excite[data$excite == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$excite))
+data$excite <- as.numeric(data$excite)
+
+data$hard.work[data$hard.work == "Strongly agree"] <- 4
+data$hard.work[data$hard.work == "Agree"] <- 3
+data$hard.work[data$hard.work == "Disagree"] <- 2
+data$hard.work[data$hard.work == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$hard.work))
+data$hard.work <- as.numeric(data$hard.work)
+
+data$safe[data$safe == "Strongly agree"] <- 4
+data$safe[data$safe == "Agree"] <- 3
+data$safe[data$safe == "Disagree"] <- 2
+data$safe[data$safe == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$safe))
+data$safe<- as.numeric(data$safe)
+
+data$best.school[data$best.school == "Strongly agree"] <- 4
+data$best.school[data$best.school == "Agree"] <- 3
+data$best.school[data$best.school == "Disagree"] <- 2
+data$best.school[data$best.school == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$best.school))
+data$best.school <- as.numeric(data$best.school)
+
+data$talk.adult[data$talk.adult == "Strongly agree"] <- 4
+data$talk.adult[data$talk.adult == "Agree"] <- 3
+data$talk.adult[data$talk.adult == "Disagree"] <- 2
+data$talk.adult[data$talk.adult == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$talk.adult))
+data$talk.adult <- as.numeric(data$talk.adult)
+
+data$grades[data$grades == "Excellent"] <- 5
+data$grades[data$grades == "Above average"] <- 4
+data$grades[data$grades == "Average"] <- 3
+data$grades[data$grades == "Below average"] <- 2
+data$grades[data$grades == "Failing"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$grades))
+data$grades <- as.numeric(data$grades)
+
+data$Wpdrink[data$Wpdrink == "Very wrong"] <- 4
+data$Wpdrink[data$Wpdrink == "Wrong"] <- 3
+data$Wpdrink[data$Wpdrink == "Dont know"] <- 2.5
+data$Wpdrink[data$Wpdrink == "A little wrong"] <- 2
+data$Wpdrink[data$Wpdrink == "Not wrong at all"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$Wpdrink))
+data$Wpdrink <- as.numeric(data$Wpdrink)
+
+data$N.safe[data$N.safe == "Strongly agree"] <- 4
+data$N.safe[data$N.safe == "Agree"] <- 3
+data$N.safe[data$N.safe == "Disagree"] <- 2
+data$N.safe[data$N.safe == "Strongly disagree"] <- 1
+data <- na.omit(data)
+mean(as.numeric(data$N.safe))
+data$N.safe <- as.numeric(data$N.safe)
+
+```
+
+```{r}
+# response data exploration
+
+# hist(as.numeric(data$X30.5drinks))
+hist(as.numeric(data$X30.cig))
+hist(as.numeric(data$X30drink))
+hist(as.numeric(data$X30marijuana))
+
+summary(data)
+
+# TODO: as numeric all the predictor variables
+round(cor(data[, -c(1, 2, 3, 4, 6)], 3))
+
+```
+
+## Drinks Model(s)
+```{r}
+# making models
+drinks_threshold <- mean(data$X30drink)
+data$drinks_var <- ifelse(data$X30drink >= drinks_threshold, 1, 0)
+
+# total model
+drinks_total_mod <- glm(drinks_var ~ pride + truth + responsibility + friends + fix.problems + decision + excite + hard.work + safe + best.school + talk.adult +grades + Wpdrink + N.safe, data = data, family = "binomial")
+summary(fiveDrinks_mod)
+
+# dropped p > 0.1
+drinks_mod_1 <- glm(drinks_var ~ truth + decision + excite + safe + best.school + grades + Wpdrink, data = data, family = "binomial")
+summary(drinks_mod_1)
+
+# dropped p > 0.1
+drinks_mod_2 <- glm(drinks_var ~ truth + decision + excite + safe + best.school + Wpdrink, data = data, family = "binomial")
+summary(drinks_mod_2)
+
+#likelihood ratio test to test whether the observed difference in model fits is statistically significant
+# source: https://www.listendata.com/2016/07/insignificant-levels-of-categorical-variable.html
+
+anova(drinks_total_mod, drinks_mod_1, test="LRT")
+anova(drinks_mod_1, drinks_mod_2, test = "LRT")
+#Both of these are not significant, which means dropping the variables we did was not significant. 
+
+# TODO: idk what this does
+anova(drinks_total_mod, drinks_mod_1, test="Chisq")
+
+#drop in deviance test compares residual deivances from two models
+# source: https://bookdown.org/roback/bookdown-BeyondMLR/ch-poissonreg.html#cs-philippines
+# source: https://bookdown.org/roback/bookdown-BeyondMLR/ch-logreg.html
+anova(drinks_mod_1, drinks_mod_2, test = "Chisq")
+
+
+```
+## Cig model
+
+```{r}
+# making models
+cig_threshold <- mean(data$X30.cig)
+data$cig_var <- ifelse(data$X30.cig >= cig_threshold, 1, 0)
+
+# total model
+cig_total_mod <- glm(cig_var ~ pride + truth + responsibility + friends + fix.problems + decision + excite + hard.work + safe + best.school + talk.adult + grades + Wpdrink + N.safe, data = data, family = "binomial")
+summary(cig_total_mod)
+
+# dropped p > 0.1
+cig_mod_1 <- glm(cig_var ~ friends + fix.problems + decision + excite + hard.work + safe + best.school + grades + Wpdrink, data = data, family = "binomial")
+summary(cig_mod_1)
+
+# dropped p > 0.1
+cig_mod_2 <- glm(cig_var ~ truth + decision + excite + best.school + Wpdrink, data = data, family = "binomial")
+summary(cig_mod_2)
+
+cig_mod_3 <- glm(cig_var ~ + decision + excite + best.school + Wpdrink, data = data, family = "binomial")
+summary(cig_mod_3)
+
+#likelihood ratio test to test whether the observed difference in model fits is statistically significant
+# source: https://www.listendata.com/2016/07/insignificant-levels-of-categorical-variable.html
+
+anova(cig_total_mod, cig_mod_1, test="LRT")
+anova(cig_mod_1, cig_mod_2, test = "LRT")
+anova(cig_mod_2, cig_mod_3, test="LRT")
+#Both of these are not significant, which means dropping the variables we did was not significant. 
+
+# TODO: idk what this does
+anova(drinks_total_mod, drinks_mod_1, test="Chisq")
+
+#drop in deviance test compares residual deivances from two models
+# source: https://bookdown.org/roback/bookdown-BeyondMLR/ch-poissonreg.html#cs-philippines
+# source: https://bookdown.org/roback/bookdown-BeyondMLR/ch-logreg.html
+anova(drinks_mod_1, drinks_mod_2, test = "Chisq")
+```
+
+
+
+```{r}
+# Extra code
+fiveDrinks_mod_3 <- glm(fiveDrinks_var ~ Wpdrink + friends, data = data, family = "binomial")
+#summary(fiveDrinks_mod_3)
+
+fiveDrinks_mod_4 <- glm(fiveDrinks_var ~ Wpdrink, data = data, family = "binomial")
+#summary(fiveDrinks_mod_4)
+```
+
+