Programming Assignment 2

CSC323 - Data Analysis and Statistical Software
Due: Section 801 - 3/2/2004; Section 501 - 3/3/2004

 

The pervasiveness of mobile communication technologies has led to considerable recent interest in methods of efficient text entry for these devices. Your colleague is interested in this issue and has asked you to help with a usability experiment that evaluates the T9 text entry method for novice users. She is particularly interested in this experiment since several of her co-workers claim that, on average, the 12-Key Keypad method is just as efficient as the T9 method.
Note: For more details on usability see Jakob Nielsens useit.com site. In particular, the Usability Metrics essay, the Novice vs. Expert Users essay, and the Graceful Degradation of Scalable Internet Services essays are relevant and interesting.

The T9 method is a relatively new text entry method that uses a built-in dictionary to look up words for a key entry sequence. For example, to enter the character sequence abc, the user would press the key sequence 2-2-2. Similarly, for the word phone, the user would press the key sequence 7-4-6-6-3. The T9 method uses the key sequence entered, and its built-in dictionary, to identify word possibilities. Where multiple words are possible for the entered key sequence, T9 retrieves the most common word. If necessary, users have the option of scrolling through a list of candidate words.

Note that the T9 method differs from the widely used 12-Key Keypad method in that, for the 12-Key Keypad method, each key must be pressed one or more times by the user to specify a character. For example, pressing the 2 key, results in the character a. Pressing the 2 key two times, in rapid succession, results in the character b. Pressing the 2 key three times, in rapid succession, results in the character c.
Note: For comments on mobile communication issues see the paper Designing the next generation of mobile communication by Christina James the chief designer of the T9 method.

Your colleague explains that she believes that the T9 method is more efficient than the 12-Key Keypad method. She further explains that to investigate this issue, she selected a random sample of novice mobile phone users and trained each user with the T9 method. Each user was then allowed extensive practice time over several days. The users were then observed completing a standard task suite that involved 3 tasks. The time required to correctly enter the text specified for each task was observed. Your colleague points out that by measuring time until correct completion, both speed and accuracy are taken into account. She also explains that, from previously published reports, novice users require, on average, 165 seconds to complete this standard task suite when using the 12-Key Keypad method.

You have been provided with this data file. Each observation consists of the following values:

Notice that the times provided are for the individual tasks in the suite. You are interested in total task time. Notice that a Status indicator has been provided. You are only interested in observations where Status is C. Several users did not complete the task suite and so the task times for these users should be ignored.

Note: Do not edit the data in any way. You must code your SAS program to read each observation as defined above and ignore those observations that are not needed.

Conduct a thorough analysis of these data. You will need to conduct a test of hypotheses and submit a report summarizing your findings. See additional details below.

  1. Write a SAS program to analyze the data provided at the link above. (50%)

    Your program should do the following:

    1. Read your data from an external file.
    2. Compute the total task time for each observation.
      Note: You will need an assignment statement in your data step.
    3. Analyze observations where Status is C only.
    4. Execute the PRINT procedure.
    5. Use the appropriate SAS procedures to produce the statistics needed to conduct your hypothesis test.

    Note: For PROC PRINT, be sure to use defined labels for column headings rather than variable names. Use names for data sets and variables that are meaningful. You should generate an appropriate title for the output of these procedures.

  2. Write a short analysis (no more than two pages) of the output of your SAS program. (50%)

    Remember that your analysis is a test of hypotheses and so should at least address the following:

    1. State the primary hypotheses. That is, the NULL and ALTERNATIVE hypotheses for the experiment described above.
    2. Given your hypotheses, complete the following:
      1. Address the normality issue. That is, is do you need to establish normality in order to address your primary hypotheses? Justify your answer.
        i.e. If you think normality must be established, do not assume normality. Instead, state and address the normality hypotheses. To do this you will need to write SAS code to provide a p-value for the normality hypotheses. This p-value will allow you to detemine if normality is reasonable.
      2. Determine the p-value for your primary hypotheses (i.e. compute the p-value as outlined in Step 3 of the Hypothesis Testing lecture notes). Remember to discuss the significance of the p-value obtained for the primary hypotheses.
        Note: Your SAS output will not provide the p-value for your primary hypotheses and so this p-value must be computed manually.
    3. Given your findings, briefly explain why you should (or should not) provide a point estimate for the parameter in question. If you argue that a point estimate for the parameter is appropriate you must provide it as well as a 90% confidence interval for the parameter (with an interpretation).