For electoral forecasting, we are currently using thirty-six pre-electoral and political survey results that were conducted after the 2016 parliamentarian elections. Besides, data analysis also includes numbers from the 2016 Parliamentarian and 2017 local government elections. As for the October 2020 wave of CRRC-Georgia’s omnibus survey, we did our version of nonresponse weighting. The corresponding STATA file is available here
The range of public opinion surveys is diverse in terms of fieldwork and data collections methodologies, as well as pollsters’ and commissioners’ political and institutional affiliations. The following circumstance makes it possible to capture the methodological and ideological variety characterizing Georgian society.
Polls used in our prediction models can be groups in three key categories. In the first category, polls conducted before the elections and pre-electoral period can be grouped. During that time, the specific date of the elections was not announced, electoral code was different from the current one, as well as political parties and elective block and unions were not formed. Polls conducted after the 2020 March 8th agreement are grouped in the second category. The March 8th agreement transformed the Georgian electoral system to the almost proportional representation. The last category unites the polls that were conducted during the electoral period, after finalizing electoral code and all key actors of the elections were registered and identified.
When it comes to the differentiation of polls based on the methodology, our analysis employs two major groups of surveys: face to face and telephone interviews. An important caveat in this regard is the comparability issue, as the mode of the survey can affect the poll outcome. It is also important to take into consideration the wording of the questions used in different surveys. In some waves voting intentions are asked, while in some surveys just party affiliation or party support was probed.