N Parameters

Author

Ivy Spratt

Using data from a 2006 primary election in Michigan, which analyzes what extent people are motivated to vote by social pressure, we are trying to analyze if postcards influence whether people will vote or not in the upcoming Texas general election. A problem we encounter is that the voters in Michigan vote differently from voters in Texas because of their political landscapes. To calculate this, we are using a linear model which evaluates the difference that each postcard has on whether or not a person votes. We also modeled whether the respondent voted in the 2006 primary election, and found that people who have been voting in the past are more likely to vote again. We have calculated that the most effective way to get voters of all types to vote is by sending postcards that neighbors will have access to one’s voting status.

\[y_{i} = \beta_{0} + \beta_{1} age\_z + \beta_{2}male_i + \beta_{3}civic\_duty_i + \\ \beta_{4}hawthorne_i + \beta_{5}self_i + \beta_{6}neighbors_i + \\ \beta_{7}Sometimes\ vote_i + \beta_{8}Always\ vote_i + \\ \beta_{9}civic\_duty_i Sometimes\ vote_i + \beta_{10}hawthorne_i Sometimes\ vote_i + \\ \beta_{11}self_i Sometimes\ vote_i + \beta_{11}neighbors_i Sometimes\ vote_i + \\ \beta_{12}civic\_duty_i Always\ vote_i + \beta_{13}hawthorne_i Always\ vote_i + \\ \beta_{14}self_i Always\ vote_i + \beta_{15}neighbors_i Always\ vote_i + \epsilon_{i}\]

Characteristic Beta 95% CI1
(Intercept) 0.155 0.137, 0.174
age_z 0.036 0.031, 0.042
sex

    sexMale 0.004 -0.005, 0.014
treatment

    No Postcard
    treatmentCivicDuty 0.016 -0.027, 0.057
    Hawthorne 0.004 -0.037, 0.043
    Self -0.007 -0.049, 0.035
    Neighbors 0.084 0.041, 0.126
voter_class

    Rarely Vote
    voter_classSometimesVote 0.115 0.095, 0.135
    voter_classAlwaysVote 0.298 0.275, 0.321
treatment * voter_class

    treatmentCivicDuty * voter_classSometimesVote -0.005 -0.051, 0.043
    Hawthorne * voter_classSometimesVote 0.010 -0.033, 0.054
    Self * voter_classSometimesVote 0.059 0.012, 0.106
    Neighbors * voter_classSometimesVote -0.009 -0.057, 0.038
    treatmentCivicDuty * voter_classAlwaysVote -0.009 -0.061, 0.045
    Hawthorne * voter_classAlwaysVote 0.034 -0.017, 0.086
    Self * voter_classAlwaysVote 0.047 -0.007, 0.100
    Neighbors * voter_classAlwaysVote -0.002 -0.056, 0.050
1 CI = Credible Interval