POL242 LAB MANUAL: EXERCISE 2A
PURPOSE
To identify the meaning of descriptive terms for each type of variable: nominal, ordinal, and interval.
To acquaint students with Webstats and recoding.
MAIN POINTS
Types of Variables
Nominal: The categories of the variable have no inherent rank or order. The categories are nevertheless mutually exclusive and exhaustive. Example, Gender.
Ordinal: The categories of the variable are ordered or ranked, from less to more or more to less, but there is not an equivalent distance between them. E.g. “How much do you like Paul Martin: very much, moderately, very little, or not at all.”
Interval: The categories of the variable are ordered and have an uniform distance between them. E.g., Income
Any interval variable can be transformed into an ordinal variable by recoding it. For example, we could divide income into categories of income groups such as $0-10,000, $10,000-20,000...etc.
Descriptive Statistics
Mean: Computed by adding all the values and dividing this sum by the number of cases
Standard deviation: Expresses the degree of variation within a variable on the basis of the average deviation from the mean.
Variance: The squared value of the std. deviation. Hence the standard deviation is the square-root of the variance.
Median: The value of the middle case, i.e, the one with the same number of cases above and below it.
Mode: The most frequent value.
Skew: This measures the symmetry of the distribution
Kurtosis: This measures the peakedness of the distribution
INSTRUCTIONS
Enter the Codebooks website from the POL242 home site.
Select one of the following datasets for this exercise: CRIC2002, GMF(Euro2002), Macleans or CCFRpop/elites.
Choose any variable from the Questionnaire according to the following criteria. The first variable must be nominal, the second ordinal, and the last one must be an interval variable. Make note of the question numbers and keep the Questionnaire window open.
In a new window, Enter the Webstats website.
Set the type of Analysis as Frequencies. Then click on Proceed.
Select the Variable you have chosen from the Questionnaire. In order to know how to code the missing values and how to recode the values you will need to perform a trial run of the frequencies. To perform the trial run, press Run without entering anything for the Missing Values or the Recoding elements.
Based on the Output of the trial run, identify the Missing Values and decide whether and how to Recode the data. Without the proper recodes, the summary measures may be misleading.
Return to Webstats and select the respective dataset. Press Proceed to continue.
Select the respective variable once again. Select the appropriate summary measures and enter the missing values and recode as needed. It is essential to re-label the recoded values as the old labels will not be automatically changed..
In separate windows, repeat steps 4 to 9 for the other two variables.
Finally, where relevant, identify the MEANING of the summary measures for each type of variable.
EXAMPLES
Example #1
Example #2
Please
note that the recode makes the high score indicate thinking the Charter is a
good thing which would be useful if you understand your variable as
"support for the Charter" .
Example #3
Note that the mean is -78 if the missing values are not declared.
QUESTIONS FOR REFLECTION
Why aren't all of the descriptive statistics appropriate to describe all three variables?
Can we ever learn something from measures appropriate for another level of data?
Discussion
Not all summary measures are appropriate for every variable.
With nominal variables, the mode is the only truly useful descriptive statistic and the range can be used for dispersion. For dichotomous variables coded between 0 and1 (dummy variables), the mean is useful to indicate the proportions.