ELECTORAL MODEL BY EL ESPAÑOL

Who will win the next Spanish elections?

Our statistical model estimates the seats that each party will win and with which probability. It aggregates dozens of polls and historical data to perform 15.000 simulations of the electoral results.

The following graph shows the evolution of our 'poll of polls' —which includes dozens of polls weighted by date, sample size and house effects.

PP would be first, with around 29.5% vote share. Unidos Podemos, the coalition between Podemos and IU, will get around 24,9%, PSOE 20.8%, and Ciudadanos, 14.6%.

The next graph shows the total seats for each party.

PP would win between 112 and 130 seats. Unidos Podemos would get 90±9 seats, PSOE around 79±9, and Ciudadanos around 39±8. Five other parties would also get seats.

The following table summarizes these results.

Note: Unidos Podemos results include seats won by Podemos’ coalitions with other parties in Cataluña, Comunidad Valenciana and Galicia.

WHICH PARTY WILL BE SECOND?

Notice that predictions are relatively uncertain. This uncertainty has two sources: the intrinsic error of public polls and last-moment changes on public opinion.

Parties still could change their relative positions.

Right now, Unidos Podemos seems to be second both in votes and seats. It is second in 68% of the simulations. PSOE is second in 29%.

PSOE has an advantage because it is stronger in the less populated districts, where seats are 'cheaper' in terms of votes. According to our statistical model, Unidos Podemos needs one or two extra points in vote share than PSOE to get more seats.

THE DEPUTIES IN EACH DISTRICT

The following table shows the seats that each party may get in each district. The "likely seats" (those with more than a 75% chance) are represented in a darker color. The "possible seats" are represented in a lighter color: "Possible seats" have a 50% chance, between 25% and 75%.

THE KEY: WHO CAN FORM A COALITION TO ELECT THE PRESIDENT?

As in December, several parties will need to reach an agreement to elect the next president. Our model calculates which coalitions are (arithmetically) possible. We have calculated the likelihood that different combinations of parties will reach the 176 seats that make up the majority.

No simple coalition has a majority right now. PP and C's have a 16% chance of reaching a majority of seats. UP and PSOE have a 30% chance. PSOE and C's has near zero chance. A coalition between PP and PSOE will probably get those 176 seats, but is politically difficult.

All these coalitions gain viability if the objective is put on 170 seats instead of 176. That may be the 'magic number' to elect the next president —supported by a regional party–. PP and C's have a 28% chance of reaching 170 seats. UP and PSOE have a 45% chance.

If none of those coalitions is viable after 26J, the scenario will be the same as in December. The available options would be a 'Gran coalición' with PP and PSOE, a coalition of three to replace Mariano Rajoy —with UP, PSOE, C's—, or a left coalition with UP, PSOE and several regional parties. There is a new factor: now UP is likely to be second instead of PSOE.

METHODOLOGY

Our model estimates the seats in each district. It uses dozens of polls and historical results to perform 15.000 simulations of the 20D elections. This way it estimates the seats that each party will win and with which probability.

The model follows a four-step procedure.

Step 1. Calculate a weigthed average of national polls. These polls are provided by Metroscopia, My Word, Celestetel, Sigma Dos, Invymark, Simple Lógica, NC Report, Encuestamos, Demoscopia Servicios, DYM, GESOP, GETS, TNS Demoscopia, CIS, etc.

Step 2. Approximate the votes shares in each district. We use the results of past elections and polls to do this. This distribution is perfomed in a way that guarantees that the total votes are those estimated by the weigthed average of polls at a national level.

Step 3. Incorporate uncertainty into the model. We have calibrated the degree of uncertainty by evaluating the results of polls in eight elections of the last five years.

Step 4. Simulate: The last step is to run the model to perform 15.000 simulations of electoral results at each district. The we compute agregates, majorities, etc.

You can read more details about the methodology here (Spanish).