Question

in R

For the iris dataset, store the 50 sepal lengths for the 50 versicolor rises in a vector x For the iris dataset, store the 50 sepal lengths for the 50 virginica irises in a vectory What are the means and the variances of x and y? The variances "seem" different. Perform Welch's t-test that is appropriate in such cases to check if the mean sepal lengths of Versicolor and Virginica irises are significantly different. What is the p-value for the test? Implement two modifications to the code from page 154 of my notes: a) sample only 40 uniform(0,1) random instances in x and b) change the intercept from 2 to 5 and the slope from 3 to-2 when creating the y. Hints: 1) y should also be of length 40 too so the normal noise that you add should be a vector of length 40.2) Yes, you are overwriting the x and y from 1-4, Produce a scatter plot with x and y from (5) and the blue line with the new intercept and slope (do not include the plot in your report yet). Fit a simple linear modely and print the summary of your fit. Plot a red line using the slope and the intercept estimated from your model fit in 7. Include the scatter plot with both lines in your report.

Answer 1

We have written a code in R

below is the code for R

#part a
z=data.frame(iris)

x=z[z$Species=="versicolor",which(names(z)=="Sepal.Length")]
#part b
y=z[z$Species=="virginica",which(names(z)=="Sepal.Length")]
#part c
mean(x);var(x)

mean(y);var(y)
#part d

var.test(x,y) # here signifies that the two variable x and y has equal variance

T=t.test(x,y) #perform welch t-test
#part e
T$p.value
#here p-value is < 0.05 we can say that the means are not equal.

as per HomeworkLib policy we have permission to answer first 4 subparts only