Article published by José Alberto León Alonso in El Día on 12/13/15.
At Corporación 5 we have been conducting market research for more than eighteen years through our subsidiary SAO, and we have our own methodology for making electoral estimates. We use the survey aggregation technique to reduce the biases and errors introduced by the sampling methodology of each pollster, which allows us to reduce the volatility in the predictions and improve them substantially. Likewise, to reduce the systematic biases of each pollster, we weight the data according to the number of respondents, the proximity to election day, and the success of the pollster in the past. As we had promised, in this article we make a prediction of the seats that each of the national parties would obtain in Congress in the next general elections. In our current electoral system for Congress, 350 deputies are elected in 50 provincial constituencies, so to make reliable estimates of the number of seats, electoral simulations must be carried out in each of the provinces. In recent weeks, enough provincial polls have been published to be able to use the survey aggregation technique, although the provincial margin of error will necessarily be greater than the national one.
For this estimate we have decided to reduce the time period of the surveys to be considered to make our estimates, given that their volatility is enormous in recent months and their results “age” quickly. For this reason, we will only include those carried out during the last month, giving more weight to the most recent ones. Thus, it does not take into account the impact of the electoral campaign and debates which, although traditionally they do not have a great effect on the vote, on this occasion it is very likely that it will be greater. This volatility forces us to expand the seat prediction margin, as shown in the attached table. According to our estimates, the Popular Party would win the general elections with 28.5% of the votes, with more than eight percentage points difference compared to the second party, the PSOE, which would reach 20.4% of the votes. Ciudadanos would be third with 19.8%, just six tenths behind the PSOE, a situation of real technical tie between both forces. Podemos (along with its regional coalitions) would be the fourth political force with 16.8% and Unidad Popular (the coalition of which Izquierda Unida is a part) would add 3.7% of the votes. UPyD would not obtain parliamentary representation. We have assigned the vote to the different confluences and tides to Podemos, although it must be taken into account that IU participates together with Podemos (and others) in the electoral coalitions in Catalonia and Galicia, so some of the seats awarded to Podemos would foreseeably go to IU once the Congress is constituted.
In the last month, there has been a consolidation with an upward trend in the PP vote, which has gained 0.3 percentage points since November; a significant increase, of 3.5 p.p., from Podemos; the continuity of the upward trend of Ciudadanos, with 1.6 p.p. further; while the PSOE loses 1.7 p.p., and IU-UP drops 1 point. Nationalist parties lose parliamentary representation.
The PP would obtain between 114 and 137 seats; the PSOE from 67 to 85; Citizens from 57 to 76 seats; We can between 42 and 62; and IU between 1 and 4. With the current trend of voting for the different parties, of reducing the range of seats to be awarded to each one, we would be inclined to assign between 124 and 132 to the PP, from 67 to 74 to the PSOE, from 64 to 71 to Ciudadanos, from 50 to 56 to Podemos and from 2 to 3 to Unidad Popular-IU. Given the relative equality of votes between the main political forces, no less than about 45 seats are “up in the air” at the time of these estimates, and can change hands for a small number of votes, which is within the margin of error of any poll. Everything remains, therefore, to be decided.
The PP would win in thirteen CC.AA., the PSOE in two (Andalusia and Extremadura), Ciudadanos or Podemos in one (Catalonia) and the PNV in the Basque Country, although in Madrid the primacy is close between the PP and Ciudadanos. In the Canary Islands the party with the most votes would be the PP and in the province of Santa Cruz de Tenerife the PP would obtain 2 seats, the PSOE and Ciudadanos from 1 to 2, while Podemos and the Canary Coalition would obtain one each. That is, two parties (PSOE and Ciudadanos) would fight for a seat, replicating the same situation that occurs in numerous provinces. We are convinced of one thing: election night will be long and exciting.
