Political scientists often use public opinion polls to test their theories. Yet these data present some difficulties. First, they are noisy. Second, they occur at irregular intervals. Third, they measure both public preferences and pollsters’ survey design choices. We introduce a new dataset, PollBasePro, that accounts for these issues. It includes voting intention estimates for each of Britain’s three largest parties on each day between the 1955 general election and the present. As the dataset covers 24,106 days in total, it is perhaps more comprehensive than any other existing time series of British political opinion. We then use our estimates to test a question of pressing importance: how daily deaths attributable to COVID-19 have influenced support for the governing Conservative Party.
Public preferences about who should be prioritized in receiving the COVID-19 vaccine: people with or without Alzheimer’s disease?
