# Run this code to load the required packages suppressMessages(suppressWarnings(suppressPackageStartupMessages({ library(mosaic) library(supernova) library(Lock5withR) }))) # Adjust the plots to be a bit smaller options(repr.plot.width = 6, repr.plot.height = 4)

CensusSchool <- read.csv("https://docs.google.com/spreadsheets/d/e/2PACX-1vSVaWnM4odSxy0mlnhWvvGbeLtiKoZmsbqC6KLzXtBOjQfrF9EVKuX4RVh3XbP3iw/pub?gid=2100178416&single=true&output=csv", header = TRUE) str(CensusSchool)

In the data provided by the United States Census at school questionnaire, the dataset comes from a sample of 10,113 high school students at high schools in the United States. The students completed this questionnaire as part of their statistics course. And now a researcher named Anthony Gonzalez came across this data since he is a person that grew up spending alot of time with his family he wonders if people from the questionnaire also spent more time with their family if they prefer to be happy. So he claims that if a student chose that his preferred status was Happy then that means they were most likely to spend more time with their family. How much time a student spends doing things with their family model it can determine whether their preferred status should be happy rich, famous, or healthy. In this research I am using the explanatory variable of Preferred_Status to prove someones outcome variable which is Doing_Things_With_Family_Hours. This research questions is important because we are trying to figure out if someone that spends more time with their family is more likely to be happy according to my hypothesis. Doing_Things_With_Family_Hours = Preferred Status + Other Stuff

CensusSchool <- filter(CensusSchool, Doing_Things_With_Family_Hours <= 16*7) CensusSchool <- filter(CensusSchool, Preferred_Status!= "NA") gf_histogram(~Doing_Things_With_Family_Hours, data = CensusSchool)%>% gf_facet_grid(Preferred_Status ~ .)

Hours.Model <- lm(Doing_Things_With_Family_Hours ~ Preferred_Status, data = CensusSchool) Hours.Model

CensusSchool <- filter(CensusSchool, Doing_Things_With_Family_Hours <= 16*7) CensusSchool <- filter(CensusSchool, Preferred_Status!= "NA") lm(Doing_Things_With_Family_Hours ~ NULL, data = CensusSchool) -> Empty_model predict(Empty_model) -> CensusSchool$Empty.Pred head(CensusSchool) gf_jitter(Doing_Things_With_Family_Hours ~ Preferred_Status, data = CensusSchool) %>% gf_jitter(predict(Hours.Model ~ Preferred_Status, color = "dodgerblue", height = 0))

supernova(Hours.Model)