a. Comment on what the dot plot at the start of Assignment Data reveals. [2 marks] b. Comment why we are not particularly concerned about the lack of Normality in this data when carrying out the t-test? [1 mark] c. Would using a log transform improve this data with respect to Normality and equal variability? Briefly justify your answer. [1 mark] d. Give a brief Executive Summary of the main conclusions of the analysis of the Assignment Data in Appendix A. [4 marks e. Referencing the original plot of the data, why would giving a single measure of centre (mean or median) not give a clear picture of what is happening with this data? [1 marks) A course administrator had received numerous questions/comments just before or more worryingly, just after) an assignment was due such as "where can we find assistance to help with our assignment" or "shouldn't you provide tutors who can help us work on the assignments". He decided to see how many students accessed this information on Canvas and discovered that only two thirds of students had actually accessed information regarding the help available for the course assistance room, lab or targeted assistance). Discussing this with the lecturer and tutors, he wondered if students who didn't access help were students who were doing well and didn't need extra support or were less pre- pared students who could use the extra help. He decided to see if there was any difference in average assignment 1 marks between students who did access assistance information and students who did not. He took a random sample of 50 students from each group and recorded their assignment 1 marks. The resulting data contains the variables: A1Mark the students assignment 1 mark (out of a maximum of 46) Assist Info did the student access assistance information on Canvas?, either Yes or No. > stripchart (A1Mark Assist Info,method="stack",pch=1, data=Assignment.df, main="A1 marks by whether or not accessed assistance information") A1 marks by whether or not accessed assistance information Yes o 8.0000888888b.l.ob. o ON 00000 00000 0000000 COD o 88.88 8 Oo 08 o o 8 0 8 000 10 20 40 A1 Mark > summaryStats (A1Mark Assist Info,data=Assignment.df) Sample Size Mean Median Std Dev Midspread No 50 28.14 33.0 10.30159 17.75 Yes 50 33.62 34.5 6.19048 6.75 > fit1=lm (A1Mark Assist Info,data=Assignment.df) > plot (fiti, which=1) Residuals vs Fitted 10 T o Residuals GOOOO OMD O OCLOCOLAGEDEOCOD -20 8,2 570 03 28 29 30 31 32 33 Fitted values Im(A1Mark - Assistinfo) > cooks20x(fit1) Cook's Distance plot 12 57 20 80 100 40 60 observation number > normcheck(fit) Sample Quantiles dananna 0000000 o Theoretical Quantiles Residuals from im(A1 Mark - Assistinfo) > summary(fiti) Call: Im(formula - A1Mark Assist Info, data - Assignment.df) Residuals: Min 1Q Median 30 Max -24.14 -5.75 1.86 5.99 12.86 Coefficients: (Intercept) Assist InfoYes Estimate Std. Error t value Pr>It!) 28.140 1.202 23.414 confint (fit) 2.5 % 97.5 % (Intercept) 25.754963 30.525037 Assist Info Yes 2.107049 8.852951