SPSS Exercises

[GSS10SSDS] 

1. Create a frequency distribution, including any appropriate measures of central tendency, for HOMOSEX.

  1. Which measure of central tendency, mean or median, is most appropriate to summarize the dis­tribution of HOMOSEX? Explain why.
  2. Suppose we are interested in whether or not males and females have the same attitudes about homosexual relations. Create a frequency distribution, including any appropriate measures of cen­tral tendency, for HOMOSEX, this time separating results for men and women. (Use the Data–Split File command by clicking on Data, Split File, Organize Output by Groups, insert the variable SEX into the box labeled “Groups Based on” and click OK. Are there any differences in their measures of central tendency? Explain. (Remember, once you have completed this exercise, reset the Split File command to include all cases by clicking on Data, Split File, Analyze All Cases, Do Not Create Groups.)
  3. Repeat (b), this time using PREMARSX (acceptance of premarital sex) as your variable.

2. We are interested in investigating whether males and females have equal levels of education. Use the variable EDUC with the Frequencies procedure to produce frequency tables and the mean, the median, and the mode separately for males and females (as described in 1b).

  1. On average, do men and women have equal levels of education? Use all the available information to answer this question.
  2. When we use statistics to describe the social world, we should always go beyond merely using statistics to describe the condition of various social groups. Just as important is our interpretation of the statistics and some judgment as to whether any differences that we find between groups seem to be of practical importance; that is, do they make a practical differ­ence in the world? Do you think any differences you discovered between male and female educational levels are important enough to have an effect on such things as the ability to get a job or the salary that someone makes? Explain the reason for your answer.

3. Some people believe that social class influences the number of children that couples decide to have. Use SPSS to investigate this question with the GSS data file. (The variable CHILDS measures the respondent’s number of children.) To get the necessary information, have SPSS split the file by CLASS and then run Frequencies for CHILDS.

  1. What is the best measure of central tendency to represent the number of children in a household? Why?
  2. Which social class has more children per respondent?
  3. Rerun your analysis, this time with the variable CHLDIDEL (ideal number of children). Is there a difference among the social class categories? Explain.

4. Picking an appropriate statistic to describe the central tendency of a distribution is a critical skill. Based on the GSS10SSDS, determine the appropriate measure(s) of central tendency for the following variables:

  1. How often do respondents watch television? [TVHOURS]
  2. Respondents’ political views. [POLVIEWS]
  3. Number of hours a respondent worked last week. [HRS1]
  4. Whether respondents have a gun in their home. [OWNGUN]
  5. Number of brothers and sisters of those sampled. [SIBS]
  6. Does respondent support legalization of marijuana? [GRASS]

5. The educational attainment of American Indians, Alaska Natives, and Hispanic American respon­dents was compared in A Closer Look 4.1. You can use SPSS to do similar comparisons with other variables. For example, it may be interesting to look at levels of marital satisfaction and compare the number of hours that men and women spend watching TV per day. There is more than one method to get the frequency distributions of hours per day watching TV for these groups, but the easiest thing might be to use the Split File command (as described in 1b). Use the GSS10SSDS for this exercise. Click on Data, Split File, Organize Output by Groups, place the variables HAPMAR and SEX (in that order) in the “Groups Based on” box, and then click OK. HAPMAR has three categories of interest: 1 = very happy, 2 = pretty happy, 3 = not too happy. SEX has two valid values 1 = male and 2 = female. Essentially, you have told SPSS to create a separate set of output for each group defined by the combi­nation of the values of HAPMAR and SEX.

  1. Create a frequency distribution by clicking on Analyze, Descriptive Statistics, Frequencies. Select the variable TVHOURS, as well as all appropriate measures of central tendency under the Statistics option. Click OK. SPSS will create a great deal of output; all you need to do is find the appropriate frequency tables and measures of central tendency. For example, to find and report the frequency table for males who are pretty happy, look for the section with values of Happiness of Marriage = Pretty Happy and Respondent’s Sex = Male.
  2. Do you notice any gaps in hours spent watching TV between men and women at different levels of marital satisfaction?