Category Archives: Exit Poll

2014 Danville Public Issues Survey data file now available

For interested parties, the full dataset from the 2014 Danville Public Issues Survey is now available for download. The data file can be accessed here:

http://web.centre.edu/benjamin.knoll/exitpoll.html#2014pollJan

As with other previously-released data files, this is available for examination and analysis by interested parties. Any public documents (blog posts, academic articles, conference papers, newspaper editorials, etc.) produced using this data should cite and reference the poll and its author. Also, the document should include a disclaimer that neither the author nor Centre College are responsible for the interpretations or conclusions of the analysis.

Commission voting and voter issue importance

In a recent letter to the editor, Danville Mayor Bernie Hunstad issued some corrections to a newspaper article that had recently been published about the upcoming Boyle County Republican Judge-Executive primary race.

First, he writes that “our commission has voted together 97-plus percent of the time.” He is generally correct in this assertion, although it’s not quite 97%+. An analysis that I published in 2011 shows that the commission voted unanimously on 80.7% of their votes during the summer of 2010 through summer of 2011. A year later that figure had changed to 82.6% for 2011-2012. The latest analysis published last year shows unanimous voting 87.3% of the time from 2012-2013. Regardless of the exact percentages, Mayor Hunstad is correct in that there is much more agreement than disagreement in the Danville City Commission under his tenure, at least measured in terms of roll call voting by commissioners.

He also writes that “the next board will not likely focus on the number one issue with the voters, which is the creation of better jobs and improvement in our local economy.” This is also correct, as evidenced by our 2012 Boyle County Exit Poll which showed a plurality (30%) of Boyle County voters listing “jobs” as the most important problem facing our local community. 38.3% said the same in the 2011 Exit Poll

Danville Public Issues Survey – January 2014

This January I have had the pleasure of teaching a class on “local politics” for Centre College’s annual three-week “CentreTerm” where students have the opportunity to engage in a number of high-impact experiential learning activities. We have covered a number of topics ranging from neighborhood design to federal grant activities to local city council politics to school board issues. We were also pleased to have several visitors from our local political community, including Danville Mayor Bernie Hunstad, Boyle Judge-Executive Harold McKinney, Danville Independent School Board Chairwoman Jean Crowley and Superintendent Carmen Coleman, and Boyle Economic Development Partnership representatives Jody Lassiter and Paula Fowler.

WHY DO A COMMUNITY SURVEY?

During the week of January 13th we had the opportunity to attend a number of public meetings, including the Danville City Commission meeting on the 13th, the Boyle County Fiscal Court meeting on the 14th, and the Danville Planning and Zoning Commission meeting on the 15th. We observed in several of these meetings that there were many community members who attended and provided their thoughts and input on a number of the issues currently facing our local community, including the proposed Fairness Ordinance, the proposed “Road Diet,” and how land should be used along the new 2168 connector road in Danville. In our class discussions we noted that while it’s great that there are citizens who are turning out to participate in the local political process by attending these meetings, writing letters to the editor in the local newspaper, and advocating for their positions and interests, it’s possible that these individuals do not represent the overall views of the community at large. Instead, they tend to be the more passionate and intense supporters or opponents of the various issues under discussion.

Given that reality, our Local Politics class partnered up with Prof. Bill Goodman’s “Politics and Journalism in the Age of Social Media” CentreTerm class and set out to obtain a more accurate picture of the views of Danville residents on these various issues. Specifically, we wanted to know what the residents of the community at large think on these issues (in contrast to those of the engaged minority who attend the public meetings and write letters to the editor). We did this by fielding a door-to-door survey to randomly selected Danville households over the course of a week. Conducting this survey required a significant amount of time and effort on the part of our students, who battled tight schedules as well as snow storms and below-freezing temperatures to go door-to-door and gather responses from members of the community. At Centre College we value engaged and experiential learning, as well as community engagement and service learning. This survey project provided students with an excellent opportunity to gain “real-life” experience with public opinion and local politics. It also gave them the opportunity to directly and immediately contribute to important community conversations about matters of public importance.

In our class we also discussed the role that public opinion ought to play in governmental decision-making. There are strong arguments to be made that in a democratic political system (such as ours) political leaders ought to try to carry out the views of the community on matters of public importance. There are, however, also compelling arguments that in a democratic republic (such as ours) public opinion should not always dictate public policy in every instance. Therefore, what our local leaders ultimately choose to do with this information is up to them. We consider it important, however, for there to be as much information as possible in the environment so that local leaders can be as well-informed as possible on the important decisions that they are responsible to decide on.

HOW THE SURVEY WAS CONDUCTED

The households that were surveyed were selected at random to ensure that everyone in the community would have an equal chance to be included in the survey. Random selection ensures that that the results are scientifically valid and representative of the population. Random selection also ensures that we can be confident that the survey results accurately reflect those of the community at large, within a particular margin of error.

Students fielded surveys beginning on Monday, January 20th and ending on Saturday, January 25th. For this survey, a total of 183 Danville residents over the age of 18 choose to participate. Given that the adult population of Danville is approximately 12,500 (as per the U.S. Census Bureau), a randomly-selected sample size of 183 gives us a margin of error of about 7%. (A sample size of 183 is certainly not ideal. It should be noted that sub-optimal temperatures and unpleasant weather this week prevented us from being able to collect more surveys which would have further decreased the margin of error.) In this case, a margin of error of 7% means that we can be very confident (95% confident, to be exact), that the true proportion of people in the community who have a particular opinion is within 7% up or down from the figure that is reported below, or a 14% margin total. In other words, the survey found that about 80% of Danville residents believe that Danville is “on the right track.” Given our sample size and margin of error, we can be 95% confident that the actual percentage of Danville residents who think that Danville is on the right track is somewhere between 73% and 87%. Ultimately, these results from our small sample size will not be able to give us a very precise measure of public opinion on these various questions. They will, however, allow us to give a confident “ballpark” figure within a 14% interval or so. All results reported here should be interpreted with that in mind.

(It should also be noted that these figures should not be directly compared to the results of the last two exit polls [here and here]. This survey sampled all residents in the Danville community while the exit polls sampled only voters throughout Boyle County. These are two different groups and thus can’t be directly compared in a meaningful fashion.)

To produce the household sample, we obtained a list of every residential address within Danville city limits from the county PVA. We then generated a randomized sub-sample of each address and assigned each of our students to distribute surveys to those addresses and only those addresses (this is to maintain the integrity of the random sample). If no one was at home, students were instructed to return to those same addresses up to three times to obtain a response. Students were further instructed to field surveys during the late afternoons/early evenings as well as some morning to try to maximize the amount of responses from households.

These surveys were completely anonymous and it is not possible to link any particular respondent with his or her answers after the survey is collected. Survey respondents were assured that participating was completely voluntary and that they could simply leave blank any question that they did not want to answer.

We also acknowledge the generous assistance of several students from Bill Goodman’s POL 438 “Politics and Journalism in the Age of Social Media” class who fielded dozens of surveys this last week. We also appreciate the contributions of Stephanie Lauderdale who provided several hours administrative assistance in preparing the survey and instruction packets.

A PDF copy of the complete survey questionnaire is available by clicking here

SURVEY RESULTS

The exact wording for each question and results of each question are shown below. Important reminder! There is a 7% margin of error associated with all these results unless otherwise indicated. This means that we can be 95% confident that the true proportion of people in the Danville community who have a particular opinion is within 7% up or down from the figure that is reported below.

Generally speaking, do you believe Danville is…?

  • Heading in the right direction: 79.8%
  • Off on the wrong track: 20.2%

Do you approve or disapprove of the way the following political leaders are handling their job?

  • President Barack Obama: 39.8% approve, 60.2% disapprove
  • Senator Mitch McConnell: 34.2% approve, 65.8% disapprove
  • Senator Rand Paul: 50.3% approve, 49.7% disapprove
  • Congressman Brett Guthrie: 50.8% approve, 49.2% disapprove
  • Judge-Exec Harold McKinney: 79% approve, 21% disapprove
  • Danville Mayor Bernie Hunstad: 50.3% approve, 49.7% disapprove
  • Danville City Commission: 68% approve, 32% disapprove

If we limit these responses only to those who report that they “always or nearly always vote,” most of these figures remain substantively unchanged except that Judge McKinney’s approval rating improves to 87.6% and Mayor Hunstad’s declines to 46.9%. (Given the smaller sample size the margin of error rises to about 10%.)

Thinking of the upcoming Kentucky Senate primary race, who do you currently plan to vote for? (JUST WRITE A NAME or “DON’T KNOW”)

  • Mitch McConnell: 8.2%
  • Matt Bevin: 2.7%
  • Alison Grimes: 12.6%
  • Don’t know / blank: 76.4%

Below is a list of some definite and some possible candidates running for Danville Mayor this fall. If the election were held today, which ONE candidate would you vote for?

  • J.H. Atkins: 16.7%
  • Kevin Caudill: 8.7%
  • Bernie Hunstad: 6.2%
  • Mike Perros: 10.6%
  • Paul Smiley: 6.2%
  • Paige Stevens: 14.9%
  • Undecided: 36%

Limiting these responses only to those who say that they “always or nearly always vote” gives us these results (margin of error 10%): J.H. Atkins: 14.9%, Kevin Caudill: 9.6%, Bernie Hunstad: 5.3%, Mike Perros: 9.6%, Paul Smiley: 5.3%, Paige Stevens: 23.4%, undecided 30.9%.

Recently there has been some discussion about possible changes along the new bypass 2168 connector road in Danville. In general, would you prefer that the land around the new connector road be used primarily for…?

  • Agriculture / green space: 66.5%
  • Residential housing: 15%
  • Commercial development: 18.5%

Recently there has been some consideration of a Danville city ordinance that would prohibit discrimination on the basis of sexual orientation when it comes to housing, employment, or other public accommodations. Would you support or oppose such a measure?

  • Strongly support: 51.7%
  • Somewhat support: 23.6%
  • Somewhat oppose: 8.6%
  • Strongly oppose: 16.1%

A reminder that the 7% margin of error means that we can be very confident (95% chance) that the true level of support for the Fairness Ordinance among Danville residents is somewhere between 68.3% and 82.3%.

The only demographic or political variables that consistently predicted opinion on the proposed Fairness Ordinance were ideology, partisanship, church attendance, and religious affiliation. 80.5% of liberals either strongly or somewhat support the proposed Fairness Ordinance while 49.1% of conservatives support. Approximately 89% of Democrats and 90% of Independents support the ordinance while about 60% of Republicans support the ordinance. Those who never attend church sometimes or never are 88.4% in favor of the ordinance while those who attend church once a week or more are only 60.3% in favor. There is also a difference among religious affiliation: 85.7% of Mainline Protestants, 75% of Catholics, and 48.6% of Evangelical Protestants support the Fairness Ordinance. No other demographic or political variables were significant predictors of attitudes on this issue.

How important would the issue described above [the proposed Fairness Ordinance] be to your vote for Mayor / City Commission election this fall?

  • Very important: 48%
  • Somewhat important: 39.7%
  • Somewhat unimportant: 6.7%
  • Very unimportant: 5.6%

Among those who see the proposed Fairness Ordinance as either somewhat or very important to their vote this fall, 77.1% either strongly or somewhat support the ordinance and 22.9% either strongly or somewhat oppose.

Thinking about your day yesterday, did you get your news in any of the following ways? (CHECK ALL THAT APPLY)

  • Newspaper: 41.8%
  • Network news on TV (ABC, CBS, NBC): 59.6%
  • Cable news on TV (Fox, MSNBC, CNN, etc.): 42.1%
  • Radio: 31.5%
  • Traditional news site on computer: 27.1%
  • Facebook, Twitter, or other social media site on computer: 34.6%
  • News/social media app on a mobile device: 23.2%

Do you consider yourself: Liberal: 24.9%, Moderate: 43.5%, Conservative: 31.6%

Do you think of yourself as a (an): Democrat: 34.8%, Independent, lean Democrat: 10.1%, Independent: 10.7%, Independent, lean Republican: 10.7%, Republican: 28.1%, Other: 5.6%.

Additionally, 52% of survey respondents were female, 48% male; 42% report an income over $50K/year while 10% report an income under $20K/year; 12% report never attending church, 43.2% report attending sometimes, and 44.8% report attending once a week or more; 5.6% report being a “Tea Party supporter; 84.3% report white ethnicity with 11.2% reporting African-American ethnicity; 33% report a high school education, 46.4% report college level of education, and 20.7% report a post-graduate level of education. The age of the average survey respondent is 48 with a range of 18 to 90 years of age.

Demographic voting patterns in the 2012 Danville City Commission election

The following table presents percentages of various sub-groups of the population and how votes for the various 2012 Danville City Commission candidates were distributed among these various population groups. The data is collected from the 2012 Boyle County Exit Poll.

The table should be interpreted like this: the first row indicates that among those who self-identify as liberal, 35% cast a vote for Smiley (first column), 21% for Montgomery (second column), 23% for Louis (third column), etc. Among those who self-identify as conservative (second row), 48% voted for Smiley (first column), 35% for Montgomery (second column), etc.

Meaningful differences should be interpreted by comparing up and down across rows, instead of between columns. Those on the right side of the table have higher values because they got more votes overall and won the election. To see if there is an advantage for any single candidate among different groups, compare the candidate in the same column with figures in different rows. (For example, examining Stevens on the far right column, we see that liberals were 10% more likely to vote for her than conservatives (71% to 61%), while conservatives were 13% more likely to vote for Smiley (48% to 35%).)

  % Smiley % Montgomery % Louis % Hamner % Atkins % Caudill % Stevens
Liberal 35% 21% 23% 58% 71% 64% 71%
Conservative 48% 35% 43% 38% 50% 50% 61%
Democrat 33% 19% 27% 54% 69% 59% 70%
Republican 51% 35% 36% 41% 52% 54% 63%
Income < $20K/year 42% 43% 40% 45% 58% 40% 57%
Income between $20K-$50K/year 48% 32% 35% 46% 53% 50% 61%
Income > $50K/year 39% 24% 27% 51% 65% 60% 69%
Never attend church 33% 21% 23% 62% 64% 60% 74%
Attend church more than 1 per week 42% 26% 33% 44% 58% 56% 66%
High school education 49% 31% 38% 41% 54% 44% 58%
College education 37% 26% 34% 50% 57% 55% 62%
White 44% 26% 32% 50% 61% 58% 68%
Non-white 28% 33% 30% 39% 65% 33% 53%
Female 42% 23% 34% 48% 62% 53% 67%
Male 39% 31% 29% 50% 61% 57% 64%
Under age 30 47% 30% 28% 49% 57% 49% 65%
Age 30-49 40% 32% 31% 54% 57% 54% 64%
Age 50-64 46% 20% 37% 45% 72% 60% 69%
Over age 65 43% 28% 32% 49% 61% 55% 66%
Tea Party supporter 51% 40% 40% 43% 46% 57% 65%
Evangelical 49% 30% 44% 39% 51% 52% 63%
Mainline 39% 19% 23% 55% 69% 69% 74%
Black Protestant 24% 35% 6% 41% 82% 47% 65%
Catholic 46% 37% 31% 46% 59% 56% 62%
Approve Mayor Hunstad 45% 45% 54% 40% 47% 42% 56%
Approve City Commission 42% 41% 46% 45% 53% 41% 59%

How did minorities vote in the 2012 Danville City Commission election?

In total, 1,461 Boyle County voters completed the 2012 Boyle County Exit Poll. Of those, 1,038 reported being Danville residents of whom 120 reported non-white race/ethnicity, or a total of 12.1% of Danville voters. Here is a summary of how minority voters in Danville voted in the city commission race compared to those reporting “white” race/ethnicity. (See here for more information about the poll, response rates, margin of error, etc.)

Note: the following figures should be interpreted by % vote for candidate or % indicating approval for each particular issue. For example, the first row indicates that 27.6% of minorities voted for Paul Smiley while 43.9% of non-minorities voted for Smiley.

  Minority Non-minority
Voted for Smiley 27.6% 43.9%
Voted for Montgomery 32.7% 25.6%
Voted for Louis 29.9% 31.9%
Voted for Hamner 39.2% 50.1%
Voted for Atkins 64.9% 60.6%
Voted for Caudill 32.7% 58.4%
Voted for Stevens 52.6% 68.0%
     
MOST IMPORTANT PROBLEM    
Jobs 30.2% 35.3%
Education 21.7% 13.5%
Racial/ethnic tension 13.2% 1.0%
     
Danville on the right track 70.2% 70.3%
Approve Mayor Hunstad 47.7% 40.2%
Approve City Commission 60.8% 39.1%
Approve of water plant expansion 68.4% 73.1%
Approve of Tony Gray appointment 86.3% 88.0%
Approve of Ron Scott appointment 57.0% 44.8%
Approve of city budget process 45.9% 39.8%
Approve of VP debate preparations 86.6% 93.3%
Approve of BISCO building purchase 52.4% 35.9%

 

Results published from 2011 Boyle County Exit Poll

To all my GOV 110 and GOV 336 Centre College students who helped design and field Boyle County exit polls on Election Day in 2011: some of the results from this project were finally published in an academic journal! I used the social desirability and immigration attitudes questions from the 2011 exit poll as part of the empirical analysis in an article that was published online today in Social Science Research. And I made sure to include a “shout out” to you all in the Acknowledgements section of the article.

Thank you to my students who have been participating in this project over the last two years. The Exit Poll project simply can’t run without you! In addition to providing valuable information to the community, these surveys gather valuable data that can eventually become part of the world of scholarly knowledge.

For those who participated in the Fall 2012 exit poll, I’ll be presenting a paper that discusses the results from this survey next spring and hopefully sometime in late 2014 or 2015 it will see the light of day in an academic article. (The peer review process is agonizingly slow sometimes!)

So thank you all again for your assistance with these exit polling projects. Slowly but surely, your efforts definitely pay off!

2012 Boyle County Exit Poll data file available for download

For interested parties, the data file of the 2012 Boyle County Exit Poll is now publicly available. It can be downloaded here:

http://web.centre.edu/benjamin.knoll/2012bcep_public.zip

Happy number crunching! 

Cross-tabulation percentages in 2012 Danville City Commission voting

I previously posted the correlational relationships between voting for pairs of Danville City Commission members. Here is the same information, but presenting percentages instead of correlation figures. This should hopefully be a little easier to intuitively interpret.

The graph should be interpreted like this: Find the candidate in the rows going down, then find another candidate in the columns going across. The percentage figure where those two candidate intersect can be interpreted: “x% of Danville voters who choose the candidate from the row also voted for the candidate from the candidate in the corresponding column.” For example, the row Smiley corresponds column Montgomery at 28%, which means that 28% of those who voted for Smiley also voted for Montgomery (but not vice-versa, as 44% of those who voted for Montgomery also voted for Smiley).

 
Smiley
Montgomery
Louis
Atkins
Caudill
Stevens
Hamner
Smiley
100%
28%
37%
58%
50%
66%
30%
Montgomery
44%
100%
52%
39%
40%
46%
37%
Louis
49%
45%
100%
39%
34%
57%
38%
Atkins
39%
17%
20%
100%
65%
74%
52%
Caudill
38%
19%
19%
73%
100%
76%
54%
Stevens
42%
19%
27%
69%
64%
100%
55%
Hamner
26%
27%
24%
66%
60%
73%
100%

We see the strongest relationship between Hamner and Stevens, as 73% who voted for Hamner also supported Stevens. The weakest relationship is between Atkins and Montgomery, as only 17% of Atkins voters also selected Montgomery.

Exit poll results on Kentucky’s 54th District House Race: Mike Harmon (R) vs. Barry Harmon (D)

This week, Boyle County’s incumbent state legislator Mike Harmon (R) won a tight reelection race against challenger Barry Harmon (D), 54.8% to 45.2%. The 54th district includes Boyle and Washington counties. Mike Harmon (R) won Boyle County with 51.5% of the vote and Washington County with 62.8% of the vote. Boyle County accounted for 70.5% of the total vote for the 54th district seat.

Below are the exit poll results for Boyle County’s share of the 54th district election, broken down by relevant demographic and political groups. The cross-tabulations read across, meaning for example that the first line reports that among those who self-identified as “liberals,” 17% voted for Mike Harmon while 83% voted for Barry Harmon.

Mike Harmon (R) Barry Harmon (D)
Liberal 17% 83%
Moderate 41% 59%
Conservative 76% 24%
     
Democrat 14% 86%
Ind-lean-Democrat 20% 80%
Independent 48% 52%
Ind-lean-Republican 74% 26%
Republican 85% 15%
     
Below $20K/year 41% 59%
$20-$50K/year 50% 50%
Over $50K/year 49% 51%
     
Church never 29% 71%
Church sometimes/once per week 46% 54%
More than once per week 55% 45%
     
High School 51% 49%
College graduate 50% 50%
Postgraduate 39% 61%
     
White 51% 49%
African-American 15% 85%
     
Female 46% 54%
Male 51% 49%
     
18-29 42% 58%
29-44 50% 50%
45-64 50% 50%
65+ 51% 49%
     
Pres: voted for Obama 12% 88%
Pres: voted for Romney 76% 24%
     
Congress: voted for Williams (D) 13% 87%
Congress: voted for Guthrie (R) 74% 26%
     
Approve Boyle Judge McKinney (D) 44% 56%
Disapprove McKinney (D) 58% 42%

Ideological and partisan patterns in Danville’s city commission election

More from the 2012 Boyle County Exit Poll:

Among Danville voters:

% calling themselves “conservative” – % calling themselves “liberal”:

13% Smiley
13% Montgomery
19% Louis
15% Hunstad approval
13% City Commission approval

In other words, you could say that Paul Smiley had a 13% advantage among self-reported conservatives as compared to self-reported liberals. Use a similar interpretation for all of the following graphs: 

% calling themselves “liberal” – % calling themselves “conservative”:

20% Hamner
20% Atkins
14% Caudill
10% Stevens

 % calling themselves Republican (and independent-lean-Republican) – % calling themselves Democrats (and independent-lean-Democrat):

18% Smiley
16% Montgomery
9% Louis
9% Hunstad approval

 % calling themselves Democrat (and independent-lean-Democrat) – % calling themselves Republican (and independent-lean-Republican):

13% Hamner
17% Atkins
3% Caudill
7% Stevens

It looks like there was a clear partisan/ideological difference in voting patterns for the various city commission candidates and in approval/disapproval of Mayor Hunstad. Smiley, Montgomery, and Louis had anywhere from a 9%-19% advantage among conservatives and Republicans. Atkins, Caudill, Stevens, and Hamner had between a 3%-20% advantage among liberals and Democrats (especially Hamner and Atkins), although Stevens and Caudill seemed to have a smaller ideological/partisan advantage amongst liberals and Democrats.