{"id":23415,"date":"2025-01-29T10:57:09","date_gmt":"2025-01-29T08:57:09","guid":{"rendered":"https:\/\/www.stem.cz\/?post_type=metodologie&p=23415"},"modified":"2025-02-14T15:55:12","modified_gmt":"2025-02-14T13:55:12","slug":"the-2025-weekly-election-model-for-cnn-prima-news","status":"publish","type":"metodologie","link":"https:\/\/www.stem.cz\/en\/?metodologie=the-2025-weekly-election-model-for-cnn-prima-news","title":{"rendered":"The 2025 weekly election model for CNN Prima News"},"content":{"rendered":"\n

Introduction:<\/strong><\/p>\n\n\n\n

From January 2025 until the autumn election for the Czech Chamber of Deputies, STEM, Institute for Empirical Research will continuously monitor the electoral preferences of the Czech public. The project is commissioned by CNN Prima News. Each week we will conduct a survey of Czech voters and calculate a pre-election model. This level of almost continuous polling is an innovation and a novelty in the Czech public debate and will allow us to monitor the pre-election developments in unique detail, especially due to the weekly publication of updated results. Our approach allows us to capture the impact of possible unexpected events, such as the emergence of a new party, the merging of existing groupings, the dynamics of the election campaigning, and the main affairs of politicians. The model will be run weekly up until the moratorium before this year\u2019s parliamentary elections (due to be held in autumn).<\/p>\n\n\n\n

Sampling and data collection method:<\/strong><\/p>\n\n\n\n

The data collection is done through an online survey (CAWI method). Interviewing and data collection is provided by the STEM\/MARK agency. The participants are people registered in the Czech National Panel. STEM, STEM\/MARK, and the Czech National Panel are members of the SIMAR association of research agencies and follow its professional standards. The rules for being contacted by and registering with the Czech National Panel are described in more detail on its website: https:\/\/www.narodnipanel.cz\/homepage\/faq<\/a>.<\/p>\n\n\n\n

Each data collection round includes at least 500 participants \u2013 always on Friday, Saturday, Sunday, Monday, and Tuesday. Attention is given to ensure that participants are included evenly in the sample, that is, to ensure that responses are not concentrated on any one day. In addition, we check the attention of respondents when filling out the survey, check the logical link between the answers, and we exclude survey answers that were completed suspiciously quickly.<\/p>\n\n\n\n

The sample for a given data collection round is always representative of the 18+ Czech population. Quota sampling is used; the quotas regard the participants\u2019 gender, age, education, region of residence, and the population size of their municipality. To further enhance the sample\u2019s representativeness, we further follow the cross-quotas of gender\u2013age and gender\u2013education. The quotas are based on data published by the Czech Statistical Office. We also pay particular attention to ensure that the sample is representative in terms of voting behaviour in the previous election to the Czech Chamber of Deputies (which took place in 2021).<\/p>\n\n\n\n

We further strengthen the representativeness of the sample by weighting for deviations from the main quota characteristics, as well as weighting for past voting behaviour in the October 2021 Chamber of Deputies election, the January 2023 second round of the presidential election, and for social\/employment status.<\/p>\n\n\n\n

Note: The data are thus representative of the Czech adult population, but they have inherent limitations due to the nature of online surveying \u2013 a portion of the public is reached only to a limited extent or not at all (e.g., people who are homeless or have limited online accessibility). The more active part of the public is therefore slightly over-represented in the data; however, these people still make up the vast majority of the Czech electorate.<\/em><\/p>\n\n\n\n

The data used for calculating the model and other indicators are put together by combining the last three polling waves. The resulting sample includes at least 1,500 participants and is representative of the adult (age 18+) Czech population. During data processing, we assign different weights to each wave so that the most recent data have the largest importance, while the two previous waves serve to smooth out the estimate (i.e., to account for possible random bias in the data). The statistical error of the sample is around \u00b11 percentage point for the smallest parties, and around \u00b13 percentage points for the larger parties.<\/p>\n\n\n\n

Note: In order to be able to start publishing the model at the beginning of January, the first data collection was done, as an exception, on a single sample of 1,500 people, therefore, the first model captures the situation about six days before its publication. Starting with the second data collection round, each wave consists of 500 participants. In the second and third rounds of the model, the initial wave of 1,500 respondents will remain a part of the data, but starting with the fourth wave, the data will regularly consist of three waves of 500 respondents each.<\/em><\/p>\n\n\n\n

Model construction:<\/strong><\/p>\n\n\n\n

The method for drawing up the continuous STEM model for CNN Prima News is almost the same as for the standard STEM model. The cornerstone of the model is an open-ended question on the participants\u2019 party preferences in a hypothetical election for the Chamber of Deputies that would have been held the following week. The participant writes down their spontaneous answer; they do not choose from any provided list.<\/p>\n\n\n\n

The model itself is based on a probabilistic approach, where one participant\u2019s answer does not necessarily translate to one vote in the model. For sporadic or hesitant voters or voters who state they are considering more than one party, we account for this uncertainty. Still, such participants do enter the model to some extent.<\/p>\n\n\n\n

We follow a three-step process while calculating the STEM election model. First, we identify the main groups within the public based on their motivation to vote. We construct an indicator of motivation to vote based on three questions:<\/p>\n\n\n\n

    \n
  1. willingness to vote in the upcoming election,<\/li>\n\n\n\n
  2. general interest in political events,<\/li>\n\n\n\n
  3. the strength of the relationship with the preferred party or movement (if the participants does prefer any).<\/li>\n<\/ol>\n\n\n\n

    In this way, the Czech public can be divided into three groups in terms of electoral motivation:<\/p>\n\n\n\n

      \n
    1. Stable voters:<\/strong> about less than half of the people go to the parliamentary elections regularly, their participation in the parliamentary elections is very likely, and they are mostly clear about who they would vote for.<\/li>\n\n\n\n
    2. Undecided: <\/strong>about one-third of the population is unsure about going to the polls at all or they are unclear about their party choice.<\/li>\n\n\n\n
    3. Non-voters:<\/strong> between one-fifth and one-quarter of the population consists of non-voters whose motivation to vote is negligible.<\/li>\n<\/ol>\n\n\n\n

      The sum of the share of Stable voters and Undecided voters can be considered the theoretical maximum possible turnout that could be achieved in the actual election. The motivation to vote serves as a starting point for the construction of the turnout and voting model.<\/p>\n\n\n\n

      We do not take into account the answers of survey participants identified as Non-voters, and for the remaining two groups (Stable voters and Undecided) we estimate their probability of participation in a hypothetical parliamentary election. We calculate the likelihood of participation in the election based on the participants\u2019 answers to questions related to their long-term, past, and expected voting behaviour:<\/p>\n\n\n\n

        \n
      1. long-term tendency to vote,<\/li>\n\n\n\n
      2. participation in past parliamentary elections,<\/li>\n\n\n\n
      3. declared participation in a hypothetical general election the following week.<\/li>\n<\/ol>\n\n\n\n

        This probability ranges from 0 to 1, depending on how strong the participant\u2019s voting motivation is. The weight of each participant\u2019s vote in the model then corresponds to the probability of them turning up to the polls.<\/p>\n\n\n\n

        The turnout probability values are used to recalculate the data for the Stable voters group. This yields a new data set, which we refer to as Loyal voters. We treat these as the bottom threshold for the hypothetical support for the respective electoral groupings (parties and movements). In other words, these are the supporters that an electoral grouping is very unlikely to lose in the medium term, and whose support would likely only be shaken by some major scandal. Loyal voters form the basis of the STEM electoral model, as they represent about two-thirds of the votes in the model.<\/p>\n\n\n\n

        Undecided voters contribute the remaining third of the votes in the model. These votes are weighed not only based on the participant\u2019s probability of turnout but also based on the probability of them voting for the parties they are seriously considering \u2013 i.e., the participants\u2019 expressed willingness to vote for each party is used as a weight, as well as the number of parties the participant is considering. Again, this probability takes a value between 0 and 1, depending on how (un)clearly the undecided voter expresses a willingness to vote for the mentioned parties. In the model, it is combined with the probability of turnout and applied to the group of Undecided voters.<\/p>\n\n\n\n

        Figure of the process of selecting participants for the model<\/strong><\/p>\n\n\n\n

        \"\"<\/figure>\n\n\n\n

        In addition to openly stating direct support for a party or movement, the study also inquires about the participants\u2019 willingness to vote for major Czech electoral groupings. On a seven-point scale, participants can express the degree of \u201cacceptability\u201d for each of the parties, movements or electoral coalitions. The maximum amount of theoretical support for a given electoral grouping, the so-called potential<\/em>, is then calculated as the sum of the size of the votes of those who chose one of the top three answers to the \u201cacceptability\u201d question (Definitely would vote, Rather would vote and Maybe would vote) for this electoral grouping, and who also belong to the group of Stable or Undecided voters.<\/p>\n\n\n\n

        We believe that these three data points should be taken into account when interpreting the STEM survey results in a responsible and meaningful way:<\/p>\n\n\n\n

          \n
        1. Probable result (the electoral model itself)<\/li>\n\n\n\n
        2. Loyal voters (the bottom threshold of support for an electoral grouping)<\/li>\n\n\n\n
        3. Potential (upper theoretical threshold of support for an electoral grouping)<\/li>\n<\/ol>\n\n\n\n

          Seat projection based on the election model:<\/strong><\/p>\n\n\n\n

          We can estimate the number of seats for each political grouping if we apply the legal rules (\u00a748 to \u00a751 of the Electoral Act) for converting vote shares (as given by the STEM model) into seats in the Chamber of Deputies and estimate voter behaviour patterns in the respective electoral constituencies and the national turnout level.<\/p>\n\n\n\n

          It is important to note that even small changes in the calculated percentage gains of respective parties \u2013 even near the margin of statistical error \u2013 can have a major impact on the hypothetical composition of the Chamber of Deputies. The most important changes in this respect take place near the legal threshold for entering the Chamber. A single party or movement needs at least 5% of the vote, a two-member coalition at least 8%, and a multi-member coalition at least 11%. The modelled composition of the Chamber then differs significantly if a grouping with a gain just around the relevant threshold is calculated to gain a little above or little under this threshold. A party crossing the 5% result affects the \u201cfate\u201d of some 10 to 15 seats that are either awarded to this party if it gains more than 5% or are distributed to other groupings if it does not.<\/p>\n\n\n\n

          The Czech electoral system traditionally favours the grouping with the largest vote gains. This \u201cwinner\u2019s bonus\u201d is usually greater the more significant the difference between the first party and the runners-up. Parties with evenly distributed support across constituencies (regions) also see an advantage, as well as those that succeed significantly in the four most populous regions (Moravian-Silesian, South Moravian, Central Bohemia, and Prague) where almost half (94) of all seats are contested.<\/p>\n\n\n\n

          <\/p>\n","protected":false},"template":"","class_list":["post-23415","metodologie","type-metodologie","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.stem.cz\/en\/wp-json\/wp\/v2\/metodologie\/23415","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.stem.cz\/en\/wp-json\/wp\/v2\/metodologie"}],"about":[{"href":"https:\/\/www.stem.cz\/en\/wp-json\/wp\/v2\/types\/metodologie"}],"wp:attachment":[{"href":"https:\/\/www.stem.cz\/en\/wp-json\/wp\/v2\/media?parent=23415"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}