The System Usability Scale (SUS) is commonly employed for usability testing. This ten-question survey is applicable to a variety of technology products including graphical user interfaces, web sites, and hardware devices.
Review the articles An Empirical Evaluation of the System Usability Scale (Bangor, Kortum, & Miller, 2008) and Determining What Individual SUS Scores Mean: Adding An Adjective Rating Scale (Bangor, Kortum, & Miller, 2009). Then, respond to the following questions:
1. Page 578 of the first article, An Empirical Evaluation of the System Usability Scale (Bangor, Kortum, & Miller, 2008), shows the distributions of scores for individual surveys and for overall studies. Describe the distribution for individual surveys. Describe the distribution for overall studies. Explain using the Central Limit Theorem why the data for the overall studies is approximately normally distributed when that of the individual surveys is not.
2. You are assessing a new user interface for a point of sale web system. Forty randomly selected individuals complete the SUS after utilizing the interface. The data file SUSpointofsaletest.cvs gives the scores for these surveys. Import this data into Excel and find the average score for your product. What is the average score? What percentage of systems score higher than the average? Assuming a normal distribution, what is the z-statistics for this value? (specifically identify the average and standard deviation for the distribution you are utilizing to calculate z). What mark would it receive on the grade scale? What adjective would best describe it? Please explain and justify all of your answers.
3. Explain why the authors want to develop a consistent adjective ratings when there are already accepted numeric scores and grade equivalents for the SUS. Do you agree that the adjective ratings is necessary or valuable? Why or why not?
4.Pages 118-119 of the second article, Determining What Individual SUS Scores Mean: Adding An Adjective Rating Scale (Bangor, Kortum, & Miller, 2009) provide descriptive statistics for the adjective rating and show a chart of the averages with standard error bars. In the descriptive statistics, “Best Imaginable” has a standard deviation less than the standard deviation for “OK”. However on the chart, the standard error bars are much larger for “Best Imaginable” than for “OK”. Explain what standard error means, and utilize this definition to explain why the adjective with smaller standard deviation has larger standard error. Use the descriptive statistics given to calculate the standard error for “Best Imaginable” and for “OK” (show your work) to demonstrate that the chart is accurate.