3. Research Methodology Within the NES 2012 Codebook, there are three questions I intend to examine. This first is labeled PRESVOTE2012_X in which the respondent specifies whether they voted for Obama, Romney, or other. The next question is labeled INCGROUP_PREPOST and asks the respondent to specify their level of family income beginning with under $5,000 going up to $250,000 or more. As a result of this question providing 28 different categories, for the purpose of my paper and tables, I recoded the INCGROUP_PREPOST variable to become income4 in which the results would be provided within four income categories, as opposed to the 28. The last question I will be looking at is labeled GENDER_RESPONDENT and asks the respondent to provide…show more content… Since 79.38 is larger than 12.592, I can reject the null hypothesis and conclude this data to be statistically significant. My P-value is 0.00 and with a significance level of 0.05, I am able to reject the null hypothesis that income does not influence vote choice and I am able to conclude that income does have an effect on vote choice.
2012 Presidential Vote by Prospective Family Income
Annual Family Income Less than 30,000 30,000-59,999 60,000-99,999 100,000+
Presidential Obama 62.7% 50.0% 45.3% 48.9%
Vote Romney 34.0% 47.2% 51.3% 48.2% Other 3.4% 2.8% 3.4% 2.9%
(1,311) (1,096) (953) (832) Chi-Square = 79.38 DF = 6 P = .000 My second table shows the percentage of individuals within the two genders that voted for Obama, Romney, and Other. This data shows that 48.7% of those in the male category voted for Obama, while 54.9% of those in the female category voted for Obama. The data does tend to support my hypothesis that females are more likely to vote for the Democratic candidate. There is a 6.2% difference between males that voted for Obama and females that voted for Obama, which is significant enough to observe a deviance but not to generalize all men and women, as there may be outliers. My Chi-square number is 30.95 and