Gd. Whitten et Hd. Palmer, HEIGHTENING COMPARATIVISTS CONCERN FOR MODEL CHOICE - VOTING-BEHAVIORIN GREAT-BRITAIN AND THE NETHERLANDS, American journal of political science, 40(1), 1996, pp. 231-260
Theory: As the research methodology more closely approximates the caus
al process being analyzed, the inferences and predictions derived from
that methodology will better represent actual behavior. Statistical m
odels were specified on the basis of accepted theories of voting behav
ior and political cleavages in the Netherlands and Great Britain. Hypo
theses: We hypothesize that multinomial models provide a more accurate
characterization of voting behavior in countries with more than two p
olitical parties competing for votes. Method: Binomial legit, multinom
ial legit, and nested multinomial legit models of voting behavior are
estimated on Dutch and British National Election Study data. Results:
Compared to binomial methods, we find that multinomial models of votin
g behavior produce results that are more congruent with accepted theor
ies of Dutch and British politics.