My model takes into account five things: the vote share a party received in the by - election constituency at the preceding general election;
changes in public opinion towards the party since the last general election; whether the party won the seat at the last election; whether the party is in government; and whether there are «party effects» on by - election outcomes.
Finally, to its credit, this lengthy, propaganda - spiked article does contain one nugget of (almost) serious analysis worthy of further discussion — there has, sadly, been an upturn of
public opinion change in the UK
in recent years
towards the denialist camp.