Statistic 10C

install.packages(“rmarkdown”)

# set seed replace 12345678 with your student ID
seed = 17069600

# loads in data for the full population
pop<-read.csv("HW1.csv", head = TRUE)
names(pop) <- c("X", "Y")

# sets the seed for the random number generator
set.seed(seed)

# assigns a "random" sample of 12 from the population to 'data'
data<-pop[sample(nrow(pop), 12, replace=FALSE),]

# use this data
data

##      X  Y
## 658  9  8
## 610  7  6
## 794 10  7
## 369 10  7
## 381  8 10
## 624  4  4
## 188  8  6
## 485  7  6
## 914 11  7
## 64  10  7
## 654 10  8
## 531  7  6

# regression
model <- lm(Y ~ X, data=data)
summary(model)

## 
## Call:
## lm(formula = Y ~ X, data = data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -0.9670 -0.5587 -0.3699 -0.0408  3.3495 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)  
## (Intercept)   3.1398     1.6342   1.921   0.0836 .
## X             0.4388     0.1894   2.316   0.0430 *
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 1.241 on 10 degrees of freedom
## Multiple R-squared:  0.3492, Adjusted R-squared:  0.2841 
## F-statistic: 5.366 on 1 and 10 DF,  p-value: 0.04303

# creates plot
plot(data$X, data$Y, main=c(paste("Scatterplot")), xlim=c(0,15), ylim=c(0,15), xaxs = "i", yaxs = "i", xlab="X", ylab="Y")
abline(lm(Y ~ X, data=data))