I show how results from the United Kingdom’s referendum on membership of the European Union can be remapped from local authority level to parliamentary constituency level through the use of a scaled Poisson regression model which incorporates demographic information from lower level geographies. I use these estimates to show how the geographic distribution of signatures to a petition for a second referendum was strongly associated with how constituencies voted in the actual referendum.
|Number of pages||18|
|Journal||Journal of Elections, Public Opinion and Parties|
|Early online date||17 Mar 2017|
|Publication status||Published - 2017|