Perspectives, News & Opinions From The Researchers At Edison

Edison Research Tbilisi Exit Poll Results

Entry by Tom Webster | Sunday, May 30th, 2010 | Permalink

Tbilisi Exit Poll – Final Results

Conducted by Edison Research, May 30, 2010

FINAL RESULTS

An exit poll conducted by Edison Research in today’s local elections in Tbilisi, Georgia, shows the incumbent mayor, Giorgi Ugulava, leading over several opposition candidates and that Ugulava will win a majority of the vote. In the party slate voting for Tbilisi City Council, the United National Movement was leading with 59% of the vote followed by the Alliance for Georgia (17%), the Christian-Democratic Movement (10%), the National Council (7%) and the Industry Saves Georgia Party (5%).
The Edison Research exit poll was conducted for Rustavi 2 and Imedi television stations. These results are based upon 12,951 interviews of voters randomly selected from a sample of 72 polling locations in Tbilisi. The response rate of voters who were selected to participate in the exit poll was 49%. The final results are based upon interviews conducted as of poll closing, at 8PM local time.
The estimate for the vote for mayor based upon the exit poll is:

Giorgi Ugulava 60%
Irakli Alasania 17%
Giorgi Chanturi 10%
Zviad Dzidziguri 6%
Gogi Topadze 5%
Nikoloz Ivanishvili Less Than 1%
Giorgi Laghidze Less Than 1%
Tamaz Vashadze Less Than 1%
David Iakobidze Less Than 1%

The exit poll estimate is based on exit poll survey results and there is potential for error based upon sampling and non-response. The calculated sampling error based upon 12,951 interviews is +/- 2%.
Voters also reported that jobs and unemployment (44%) is the most important issue facing the country followed by health care (13%), tensions with Russia (10%) and pensions (8%).
The exit poll found that most voters had decided on their chosen candidate for mayor before the last week of the campaign.

DEMOGRAPHICS

Gender

Male 42%
Female 58%

Age

18-29 23%
30-44 26%
45-64 36%
65+ 15%

Education Level

Incomplete primary school 1%
Incomplete secondary school 3%
Complete secondary school 18%
College/professional-technical school 13%
University/academy 60%
Post-graduate 5%

Children under 18 year old living in household

Yes 46%
No 54%

How long voter has lived in Tbilisi

Born in Tbilisi 58%
More than 10 years 34%
Less than 10 years 6%
No Answer 2%

Download the complete presentation graphs of the exit poll results:
Edison Research Tbilisi Georgia Exit Poll 30 May 2010 Final Results.pdf

METHODS STATEMENT

Edison Research conducted this exit poll for Rustavi 2 and Imedi. The poll should be referred to as the “Edison Research Exit Poll conducted for Rustavi 2 and Imedi.
The exit poll was conducted at 72 polling places among 12,951 Election Day voters.
The polling places are a stratified probability sample of Tbilisi, Georgia. Within each polling place an interviewer approached every nth voter as the voter exited the polling place. A target was set at 100 voters completing a questionnaire at each polling place. The exact number of questionnaires depends on voter turnout and their cooperation.
All samples are approximations. A measure of the approximation is called the sampling error. Sampling error is affected by the design of the sample, the characteristic being measured and the number of people who have the characteristic. If a characteristic is found in roughly the same proportions in all precincts the sampling error will be lower. If the characteristic is concentrated in a few precincts the sampling error will be larger. Gender would be a good example of a characteristic with a lower sampling error.
For this exit poll the table below lists typical sampling errors for given size subgroups for a 95% confidence interval. The values in the table should be added and subtracted from the characteristic’s percentage in order to construct an interval. Ninety-five percent of the intervals created this way will contain the value that would be obtained if all voters were interviewed using the same procedures. Other non-sampling factors, including nonresponse, are likely to increase the total error.

sampling_error.png

Comments are closed.