LITMIR.BIZ

      1 Use the data in “results.txt” to develop boxplots of all the subjects on the same graph.

      2 Obtain a stem and leaf of each subject in “results.txt.” Are there patterns emerging?

      3 For the class of 50 students of computing detailed in Exercise 1.1, use R toform the stem‐and‐leaf display for each gender, and discuss the advantages of this representation compared to the traditional histogram;construct a box‐plot for each gender and discuss the findings.

      4 Plot the marks in Architecture 1 against those in Architecture 2 and obtain the line of best fit. In your opinion, is it a suitable model for predicting the results obtained in Architecture 2 from those obtained in Architecture 1?

      5 The following table gives the number of hours spent studying for the probability examination and the result obtained (%) by each of 10 students.Study hours548710610400Exam results73648070855086502025Plot the data and decide if there is a linear trend. If there is, use R to obtain the line of best fit.

      6 The percentage of households with access to the Internet in Ireland in each of the years 2010–2017 is given in the following table:Year20102011201220132014201520162017Internet access7278818282858789This set of data is to be used as a training set to estimate Internet access in the future.Plot the data and decide if there is a linear trend.If there is, obtain the line of best fit.Can you predict what the Internet access will be in 2019?

      1 In Appendix B, we show that the line of best fit is obtained whenandWrite a program in R to calculate and and use it to obtain the line that best fits the data in Exercise 5 above. Check your results using the lm(y˜x) function given in R.

      2 When plotting in Fig. 3.10, we used font.main = 1 to ensure the main titles are in plain font.Alternative fonts available are2 = bold,3 = italic,4 = bold italic5 = symbol.Fonts may also be changed on the ‐ and ‐axis labels, with font.lab. Explore the effect of changing the fonts in Fig. 3.7.

      1 Anscombe, F.J. (1973), Graphs in statistical analysis, American Statistician, 27, 1721.

      2 Girolami, M. (2015), A First Course in Machine Learning, CRC Press.