There were 1491 respondents who gave their age in this survey, the youngest is 18 years old and the oldest is 89. Click Options and make the following selections:įor the variable “age” in the 2008 GSS data set, your output will look like this: Move your variables into the Variable box. To obtain descriptive statistics from continuous variables, click Analyze, Descriptive Statistics, Descriptives. S, the percent and valid percent in the frequency distribution differ slightly from one another.Ĭontinuous Variables (called “Scale” by SPSS) Notice that there were 1495 valid responses and 5 missing cases for this variable. Here is an the output for the variable “happy” from the 2008 GSS data set: If you use all of these statistics, your statistics box will look like this:
In contrast to what you do for nominal variables, you may choose the median, range, and interquartile range as additional statistics for ordinal variables. Here is the difference from nominal variables. Move the ordinal variables that you want to examine into the Variables box. The process of obtaining descriptive statistics is very similar to the process for nominal variables: click Analyze, Descriptive Statistics, Frequencies. The variable “Happy” in the General Social Survey is one of these types of variables. One of the more common forms of ordinal variables are Likert scale responses. Ordinal variables are those variables that are ranked. As you can see from the Statistics box, there are no missing data for this variable, therefore the percent and valid percent are the same. The valid percent adjusts for missing data. The percent is the attribute’s percentage of the total N. The second box above is called a “frequency distribution.” The frequency is the number of responses for each attribute (or category) of the variable. Here is the output for the variable “sex” from the 2008 GSS data set: Check the following boxes:Ĭlick Continue, OK. Move the nominal variables that you want to examine into the Variables box. To obtain descriptive statistics for nominal variables, click Analyze, Descriptive Statistics, Frequencies. Scale*: Range, Interquartile Range, Variance, Standard Deviation You can examine dispersion by using the following: In addition to knowing the “center” of your data, you will also want to know its dispersion (how far it is spread out around your “center”).
*SPSS uses the term “Scale” for Interval and Ratio levels of measurement. Here are the central tendencies that are appropriate for different levels of measurement: The mode is the value that occurs most frequently. The median is the datum that is in the middle of the data when it is rank-ordered (from lowest to highest). The mean is a statistical average (the summation of all data values divided by the number of data). Although you could add up all of the 1s (males) and 2s (females) and then divide by 25, the average, 1.4, makes no sense. Assume you have 25 people in your dataset: 15 have identified as male and 10 people have identified as female. Be aware that SPSS will calculate statistics even if the measure of central tendency and dispersion are not appropriate. What do I mean by inappropriate descriptive statistics? The General Social Survey includes two attributes for the variable SEX: male or female. (Whether or not this is exhaustive is another discussion). Descriptive statistics are statistics that describe a variable’s central tendency (the ‘middle’ or expected value) and dispersion (the distribution of the variable’s responses).