Summary STA2020 coding

Week 2:

drywide <- read.csv("drying_times_wide.csv")
mean(drywide$Paint.1)
mean(drywide$Paint.2)
sd(drywide$Paint.1)

drylong <- read.csv("drying_times_long.csv")
View(drylong)
t <- aov(drying_time ~ paint , data= drylong)
summary( t)


Week 3:

oat_variety<-read.csv (‘oat_variety.csv’)
View(oat_variety)
variety <- as.factor(oat_variety$variety)
mean(oat_variety$yield [oat_variety$variety == "Golden.rain"])
mean(oat_variety$yield [oat_variety$variety == "Marvellous"])
mean(oat_variety$yield [oat_variety$variety == "Victory"])
sd(oat_variety$yield [oat_variety$variety == "Golden.rain"])
t <- aov(yield ~ variety + plot , data = oat_variety)
summary( t)


Week 4:

insects<-read.csv(‘insects_data.csv’)
mean(insects$counts [insects$species == "Megacrania" & insects$season == "Spring"])
mean(insects$counts [insects$species == "Extatosoma" & insects$season == "Autumn"]) spelificmean
t <- aov(counts ~ species + season + species*season, data = insects_data)
summary( t)
IwayAnova
Week 5:

Install readxl package
library(readxl)
calls<-read_excel(‘calls.xlsx’)
mean(calls$Calls)
t <- lm(Executions ~ Calls)
im independent dependent simple linear regression
summary( t)
cor(y=calls$Executions, x=calls$Calls)
regression <- lm(Executions~Calls, data=calls)
summary(regression)
con nt(regression)
plot(x=calls$Calls, y=calls$Executions)
xlab= “number of phone calls”, ylab= “number of executions”


Week 6:

View(multreg)
df <- read.csv("multreg.csv")
View(df)
mult.numeric <- df[ , c("Price", "PlotSize", "FloorArea", "Trees", "Distance")]
cor.multi.numeric <- cor(mult.numeric)
multiple linearregression
cor(mult.numeric)
df$Pool <- as.factor(df$Pool) convertingnumericvariables to fan or variables
contrasts(df$Pool)
t <- lm(Price ~ PlotSize + FloorArea + Trees + Distance + Pool + PlotSize*FloorArea, data = df)
summary( t)
imlynxdata
con nt( t)
predict( t)
torind estimateddependentvariable

Week 7:

log <- read.csv("logreg.csv")
View(log)
dep explanatory
t <- glm(cases ~ sex + income , data = log, family = "binomial" )
logistic regression
summary( t)

mb_data <- read.csv('step.csv')
str(mb_data)
mb_data$medschl <- as.factor(mb_data$medschl)
mb_data$region <- as.factor(mb_data$region)
t.full <- lm(length ~ . , mb_data) modelbuilding
summary( t.full)
t.empty <- lm(length ~ 1, mb_data) stepwiseregression
step.model <- step( t.empty, scope = formula( t.full), direction = 'forward')
summary(step.model)