Example of a Contingency Table
| Strong Democrat |
Weak Democrat |
Independent Democrat |
Independent | Independent Republican |
Weak Republican |
Strong Republican |
Total | |
|---|---|---|---|---|---|---|---|---|
| Obama | 98.1% (927.8) |
83.1% (522.6) |
88.0% (423.4) |
45.5% (171.3) |
8.7% (44.2) |
12.0% (61.8) |
2.7% (19.7) |
51.9% (2170.8) |
| Romney | 1.2% (11.6) |
14.9% (94.0) |
8.6% (41.1) |
39.8% (148.7) |
86.0% (434.6) |
85.6% (441.1) |
96.9% (706.4) |
44.9% (1877.6) |
| Other | 0.7% (6.5) |
2.0% (12.4) |
3.4% (16.4) |
14.4% (53.9) |
5.2% (26.5) |
2.4% (12.6) |
0.4% (2.8) |
3.1% (131.0) |
| Total | 100.0% (945.9) |
100.0% (629.0) |
100.0% (481.0) |
100.0% (373.9) |
100.0% (505.4) |
100.0% (515.5) |
100.0% (728.9) |
100.0% (4179.4) |
This contingency table is the cross tabulation of Party Identification (A07) with the presidential candidate the respondent voted for in the 2012 election (A02). People who did not vote for president in 2012 and those who did not express a party identification are excluded from the table.
The table demonstrates proper formatting. The independent variable is at the top and percentages total to 100 percent within each column. This is called percentaging by the independent variable. So, about 97% of Strong Republicans report voting for Mitt Romney, and about 99% of Strong Democrats report voting for Barrack Obama.
This table also shows one of the odd characteristics of working with weighted data in SDA. Weighting involves multiplying each respondent by a weight factor (typically lower or higher than 1.0) and then adding up the totals. SDA reports the weighted numbers in each cell to a single decimal place. This can result in some cells displaying a result like 927.8 respondents (the number of Strong Democrats who report voting for Obama). There is no such thing as eight-tenths of a respondent, but by multiplying each respondent by a weight factor, we can wind up with fractional respondents. Your instructor will explain how you should treat this when you write up your results.