Sample Do-Your-Own Exercise
The Effects of Class and Race on Self-Reported Happiness
(Important: Do not use the same dependent variable (happy) for your exercise.
Also: use this sample exercise as a model, but be sure to use your own words.)

My Hypothesis: The higher a person's social class, the more likely the person is to report being very happy.

Higher social class is likely to be associated with greater access to resources to obtain the things that are important to a person.  These can be both tangible (commodities that money can buy) and intangible (respect, status).  It therefore seems reasonable to hypothesize that social class and happiness are positively correlated. The measure of happiness I am using is self-reported happiness, based on the respondent's answer to the following question: "Taken together, how would you say things are these days--would you say that you are very happy, pretty happy, or not too happy?" The variable number is #84.

Operationalizing Social Class: Education

I chose education (variable #24) as my measure of social class.  Education is a good measure of class because it is an important determinant of both occupation and income, which are key aspects of social class. Education also confers important social and cultural capital, which is important for both gaining and retaining social class position.

Note: As discussed in class, either family income (variable 43) or self-reported class (variable 234), are also acceptable measures of social class.  Use any one of these three choices to operationalize social class in your paper. Other choices are not acceptable for purposes of this exercise.

My Restated Hypothesis: The higher the level of education attained by a person, the more likely the person is to report being very happy.

Testing My Hypothesis

Running education as my independent variable with the variable, Happy, produces the following table:

My hypothesis is supported.  The data are statistically significant at the .01 level.  With each increasing level of education, the proportion of respondents reporting themselves to be "very happy" increases. Correspondingly, the proportion of respondents reporting themselves to be "not too happy" decreases with each ascending level of education. Cramer's V is .073, which indicates a statistically significant but weak relationship between the two variables.

Choosing a Control Variable: Race

I will now introduce race as a control variable.  I hypothesize that the relationship between social class and reported happiness should remain basically the same when whites and blacks are examined separately. Controlling for race produces the following tables:

Interpreting the Results

The table for whites is almost identical to the original table.  The data are statistically significant and show that the level of reported happiness for whites increases steadily with social class, as measured by education.  The original hypothesized relationship between class and happiness holds.

For blacks, however, my original hypothesis must be rejected, because the data do not meet the test of statistical significance. Blacks of all classes report relatively similar levels of happiness, and these levels are consistently below those reported by their white counterparts.  For blacks, race seems more important than class in determining the level of happiness. This may be because blacks at all social classes either anticipate or experience racial discrimination, and that the resulting stress lowers happiness across the board, particularly for those with higher education.

 

 

November 8, 2008