1 These are findings from Ipsos polling conducted for Thomson Reuters from September 8-12, 2014. State-specific sample details are below. The data are weighted to Kentucky s current population voter data (CPS) by gender, age, education, ethnicity, and a political values scale. Ipsos Likely Voter model (applied to Voting Intention questions only) uses a seven-item summated index, including questions on voter registration, past voting behavior, likelihood of voting in the upcoming election, and interest in following news about the campaign. Statistical margins of error are not applicable to online polls. All sample surveys and polls may be subject to other sources of error, including, but not limited to coverage error and measurement error. Figures marked by an asterisk (*) indicate a percentage value of greater than zero but less than one half of one per cent. Where figures do not sum to 100, this is due to the effects of rounding. KENTUCKY A sample of 1,755 Registered Voters (RVs) and 944 Likely Voters (LVs), age 18 and over in Kentucky was interviewed online. Data below has a credibility interval of plus or minus 2.7 percentage points for RVs and 3.6 for LVs. Data below is among registered voters unless otherwise specified. Q1. Generally speaking, would you say things in this country are heading in the right direction, or are they off on the wrong track? Right direction 18% Wrong track 72% Don t know 10% Q2. Generally speaking, would you say the following things are heading in the right direction, or are they off on the wrong track? Right Wrong Direction Direction Don t know The national economy 18% 74% 8% Employment and jobs 25% 68% 7% Healthcare system 27% 64% 8% Immigration policy 12% 72% 16% National deficit 10% 76% 13% Education system 24% 62% 14% National politics 9% 74% 17% American foreign policy 13% 68% 19% Fuel and gas prices 13% 80% 7% Your cost of living 15% 78% 7% Q3. Thinking about the upcoming general election in November of this year, if the election for U.S. Senator from Kentucky were held today, for whom would you vote? All Likely Voters (LV) All Registered Democrats Republicans Independents Mitch McConnell, Republican 46% 36% 8% 70% 24% Alison Lundergan Grimes, Democrat 42% 38% 74% 12% 29% Another candidate 5% 9% 5% 7% 16% Will not/do not plan to vote *% 4% 3% 1% 8% Don t know / Refused 6% 13% 9% 9% 23%
2 Q4. Thinking about the elections in 2014, if the election for U.S. Congress were held today, would you vote for the Democratic candidate or the Republican candidate in your district where you live? All Likely Voters (LV) All Registered Democrats Republicans Independents Democratic candidate 37% 33% 76% 8% 13% Republican candidate 44% 34% 6% 72% 17% Candidate from another political party 5% 7% 2% 4% 18% Will not/do not plan to vote *% 3% 2% 1% 7% Don t know / Refused 14% 23% 15% 14% 45% Q5. How familiar are you with the following public figures, taking into account all the ways you may have heard about them? Very Familiar Somewhat familiar Not very familiar Have heard of them; but that s it Have not heard of them TOTAL FAMILIAR President Barack Obama 68% 26% 4% 1% 1% 98% Senator Rand Paul, senator from Kentucky Senator Mitch McConnell, senator form Kentucky Kentucky Secretary of State Alison Lundergan Grimes Kentucky Governor Steve Beshear 38% 42% 13% 4% 2% 93% 54% 35% 7% 3% 1% 96% 26% 44% 19% 8% 3% 89% 40% 42% 12% 5% 2% 93% Q6. Would you say you are generally favorable or unfavorable towards these public figures? (Asked of those aware of the figure at Q5) Very favorable Somewhat favorable Lean towards favorable Lean towards unfavorable Somewhat unfavorable Very unfavorable TOTAL FAVORABLE TOTAL UNFAVORABLE President Barack Obama 12% 13% 13% 13% 10% 39% 38% 62% Senator Rand Paul, senator from Kentucky 16% 19% 25% 19% 7% 14% 60% 40% Senator Mitch McConnell, senator form Kentucky 13% 18% 18% 17% 9% 25% 48% 52% Kentucky Secretary of State Alison Lundergan 16% 17% 23% 18% 11% 15% 56% 44% Grimes Kentucky Governor Steve Beshear 13% 21% 35% 18% 7% 5% 70% 30%
3 [ASKED OF THOSE AWARE OF MITCH MCCONNELL AT Q5, n=1,743] Q7. Which of the following words best describe Mitch McConnell? (Please select up to three) Experienced 39% Arrogant 33% Washington insider 33% Intelligent 17% Respected 17% Entitled 16% Hard-working 13% Effective 12% Real Kentuckian 11% Extremist 8% Inexperienced 4% None of these 10% [ASKED OF THOSE AWARE OF ANGELA LUNDERGAN GRIMES AT Q5, n=1,721] Q8. Which of the following best describe Alison Lundergan Grimes? (Please select up to three) Inexperienced 36% Intelligent 32% Hard-working 25% Respected 18% Real Kentuckian 18% Arrogant 17% Effective 10% Entitled 10% Extremist 10% Washington insider 9% Experienced 7% None of these 14% [ASKED OF THOSE WHO WOULD VOTE FOR MITCH MCCONNELL AT Q3, n=598] Q9. You said earlier that if the election for U.S. Senate were held today, you would vote for Mitch McConnell over Alison Lundergan Grimes. Would you vote that way more because? You support Mitch McConnell 57% You oppose Alison Lundergan Grimes 29% Neither 12% Don t know 2%
4 [ASKED OF THOSE WHO WOULD VOTE FOR ALISON LUNDERGAN GRIMES AT Q3, n=752] Q9. You said earlier that if the election for U.S. Senate were held today, you would vote for Alison Lundergan Grimes over Mitch McConnell. Would you vote that way more because..? (Those who are voting for Mitch McConnell) You support Alison Lundergan Grimes 43% You oppose Mitch McConnell 48% Neither 8% Don t know 1% Q10. In your own words, why would you vote that way in the U.S. Senate election between Mitch McConnell and Alison Lundergan Grimes? (Those who are voting for Alison Lundergan Grimes)
5 Q11. What is the most important issue affecting how you plan to vote in the U.S. Senate election between Mitch McConnell and Alison Lundergan Grimes? (Select one) Economy generally 23% Unemployment / lack of jobs 19% Coal and Energy issues 14% Healthcare 8% Morality 6% Education 5% Immigration 3% War / foreign conflicts 2% Terrorism / terrorist attacks 2% Crime 1% Environment 1% Other 6% Don t know 11% Q12. How often, if at all, are you seeing TV advertising for the U.S. Senate election between Mitch McConnell and Alison Lundergan Grimes that does the following? Several times a day About once a day Several times a week Several times a month Never, have not seen TV ads like this Criticizes or attacks Alison Lundergan Grimes 21% 18% 23% 19% 19% Supports Alison Lundergan Grimes 22% 18% 24% 18% 18% Criticizes or attacks Mitch McConnell 24% 18% 24% 19% 15% Supports Mitch McConnell 19% 18% 23% 18% 23% Q13. Overall, do you approve or disapprove about the way Barack Obama is handling his job as President? Q13a. Is that strongly (approve/disapprove) or somewhat (approve/disapprove)? (Asked of those who selected approve or disapprove ) Q2b. If you had to choose, do you lean more towards approve or disapprove? (Asked of those who selected don t know ) All RVs Democrats Republicans Independents Strongly approve 11% 25% 3% 5% Somewhat approve 14% 26% 4% 13% Lean towards approve 3% 5% 1% 2% Lean towards disapprove 3% 3% 2% 3% Somewhat disapprove 16% 17% 14% 19% Strongly disapprove 49% 21% 75% 51% Not sure 4% 3% 1% 7% Total approve 28% 56% 8% 20% Total disapprove 69% 41% 91% 73%
6 Q14. Thinking about politics and government, do you consider yourself: All Registered Very conservative 11% Moderately conservative 27% Lean conservative 18% Lean liberal 11% Moderately liberal 12% Very liberal 5% Don t know/refuse 16% All PARTY ID Registered Democrat 35% Republican 38% Independent 24% None/Don t Know 2%
7 How to Calculate Bayesian Credibility Intervals The calculation of credibility intervals assumes that Y has a binomial distribution conditioned on the parameter θ\, i.e., Y θ~bin(n,θ), where n is the size of our sample. In this setting, Y counts the number of yes, or 1, observed in the sample, so that the sample mean (y ) is a natural estimate of the true population proportion θ. This model is often called the likelihood function, and it is a standard concept in both the Bayesian and the Classical framework. The Bayesian 1 statistics combines both the prior distribution and the likelihood function to create a posterior distribution. The posterior distribution represents our opinion about which are the plausible values for θ adjusted after observing the sample data. In reality, the posterior distribution is one s knowledge base updated using the latest survey information. For the prior and likelihood functions specified here, the posterior distribution is also a beta distribution (π(θ/y)~β(y+a,n-y+b)), but with updated hyper-parameters. Our credibility interval for θ is based on this posterior distribution. As mentioned above, these intervals represent our belief about which are the most plausible values for θ given our updated knowledge base. There are different ways to calculate these intervals based on π(θ/y). Since we want only one measure of precision for all variables in the survey, analogous to what is done within the Classical framework, we will compute the largest possible credibility interval for any observed sample. The worst case occurs when we assume that a=1 and b=1 and y=n/2. Using a simple approximation of the posterior by the normal distribution, the 95% credibility interval is given by, approximately: For this poll, the Bayesian Credibility Interval was adjusted using standard weighting design effect 1+L=1.3 to account for complex weighting 2 Examples of credibility intervals for different base sizes are below. Ipsos does not publish data for base sizes (sample sizes) below 100. Sample size Credibility intervals 2,000 2.5 1,500 2.9 1,000 3.5 750 4.1 500 5.0 350 6.0 200 7.9 100 11.2 1 Bayesian Data Analysis, Second Edition, Andrew Gelman, John B. Carlin, Hal S. Stern, Donald B. Rubin, Chapman & Hall/CRC ISBN: 158488388X 2003 2 Kish, L. (1992). Weighting for unequal Pi. Journal of Official, Statistics, 8, 2, 183200.