Replication Data for: Vote Expectations Versus Vote Intentions: Rival Forecasting Strategies

Are ordinary citizens better at predicting election results than conventional voter intention polls? We address this question by comparing eight forecasting models for British general elections: one based on voters’ expectations of who will win and seven based on who voters themselves intend to vote for (including “uniform national swing model” and “cube rule” models). The data come from ComRes and Gallup polls as well as the Essex Continuous Monitoring Surveys, 1950–2017, yielding 449 months with both expectation and intention polls. The large sample size allows us to compare the models’ prediction accuracy not just in the months prior to the election, but over the years leading up to it. In predicting both the winning party and parties’ seat shares, we find that vote expectations outperform vote intentions models. Vote expectations thus appear an excellent tool for predicting the winning party and its seat share.

普通民众是否比传统选民意向调查更擅长预测选举结果？我们通过对比英国大选的八种预测模型解答这一问题：其中一种基于选民对获胜者的预期，其余七种基于选民自身的投票意向（包括"统一全国摇摆模型（uniform national swing model）"与"立方法则模型（cube rule）"）。本次研究的数据来自1950年至2017年间的ComRes、盖洛普（Gallup）民调以及埃塞克斯郡持续监测调查（Essex Continuous Monitoring Surveys），共得到449个同时包含选民预期与投票意向民调的月份样本。得益于庞大的样本量，我们不仅可以对比选举前数月的模型预测精度，还能分析选举前数年的模型表现差异。在预测获胜政党以及各政党席位占比的任务中，我们发现选民预期模型的表现优于投票意向模型。由此可见，选民预期是预测获胜政党及其席位占比的优质工具。