- Learn how to use variables and their indicators.
- Become familiar with searching out indicators for variables in codebooks.
- Social Research entails systematic observation and the understanding of patterns. Systematic observations are made using surveys, experiments, available data and field research. In this exercise we will use survey data. Patterns are understood by identifying and explaining variation in our observations. An essential aspect of social research is making certain that our observations exhibit some degree of variation. If there is little or no variation in our observations, they are regarded as constants. Constants are of limited value for most social research. So we try to look for variation.
- Variables are abstract concepts used to describe sets of attributes or characteristics. Some simple examples are gender, age and race, but social researchers are also interested in more complex variables such as ideological orientation or view of water use reduction policies.
- Indicators are used to measure variables. For example, to measure political identification we could use the indicator, “Do you consider yourself to be politically liberal, conservative, middle of the road … ?” To measure views of water use reduction policies we might use the indicator, “Do you think [mandatory water restrictions] do too much, the right amount, or not enough to respond to the current drought in California?”
- Hypotheses express an expected relationship between two variables. In causal explanations an independent variable (IV) is generally identified as X and a dependent variable (DV) is identified as Y. Symbolically, X→Y or X↔Y .
- Find a data set from either the 2015 or 2016 Statewide surveys made available by the Public Policy Institute of California (PPIC).
They are available at: http://www.ppic.org/main/datadepot.asp or through the data link on the DataArt.ca website.
- Download the .zip file containing the appropriate codebook & data. The example shown below uses the May 2015 data.
- Open the codebook, browse through the questions in the survey and select an indicator of a variable which interests you.
- Place the data file on your desktop or in another appropriate place such as a folder where you intend to keep your data sets.
- On a PC, right click on data set icon, select Properties and lock the dataset by clicking the box labeled “Read Only.” On a Mac right click (two finger click) on the icon and select Get Info and lock the dataset by clicking the box labeled locked
- Open the dataset using SPSS.
- Under the Analyze menu, select Descriptive Statistics and then Frequencies.
- Locate the item you have chosen for analysis and move it into the Variables area.
- Click Paste and review the syntax that has appeared in the syntax window
- Select the syntax.
- Go either to the Run menu and choose the green triangle or click on the green triangle in the row of icons.
- Review the results and ask yourself: Is there variation on this question? As a rough standard, no more than 85% of the cases should be in a single value category.
- If there is variation try to think of an explanation for the variation you observe by looking at the other available questions in the survey.
- Formulate a hypothesis in the form of X –>Y.
- Repeat steps 1-6 to examine variation on the hypothesized explanatory (X) variable.
EXAMPLE (using PPIC data)
- Statewide Survey May 2015
- Y Variable
- Drought Policy
- Indicator for Y
Q16. Governor Brown recently directed the State Water Resources Control Board to implement mandatory water reductions in cities and towns across California to reduce statewide water usage by 25 percent. Do you think this action does too much, the right amount, or not enough to respond to the current drought in California?
- Possible Explanation (X)
- Indicator for X
Q36. Next, would you consider yourself to be politically:
- SPSS Syntax
Fre var q16, q36.
- Formatted Tables Produced from Output
Mandatory water reductions of 25 percent. Too much, the right amount, or not enough?
Value Labels Frequency Percent Cumulative % Too much 227 13.3 13.3 Right Amount 780 45.7 59.3 Not enough 571 33.5 93.0 Don’t Know 119 7,0 100.0 Total 1697 100.0
Source: PPIC May 2015
Value Labels Frequency Percent Cumulative % Very liberal 201 11.9 11.9 Liberal 347 20.5 32.4 Middle of Road 509 30.1 62.5 Conservative 357 21.1 83.7 Very Conserv 242 14.3 98.0 DK 34 2.0 100.0 Total 1690 100
Source: PPIC May 2015
- QUESTION FOR REFLECTION
Is there variation on both the dependent and independent variables that form your hypothesis.
It is essential that there is variation of the indicators of both X and Y. Otherwise, they are not likely useful for further analysis.
- Give some thought to other possible IVs such as Gender of Language of Interview.