Statistically Testing the Representative Capacity

Abstract

A statistical test of the representative capacity of a candidate, party or coalition is developed. As observations, we consider how well the candidate (coalition) positions on several policy issues, such as ‘Introduce nationwide minimum wage’ (Yes/No), ‘Privatize railways’ (Yes/No), etc., match up with the prevailing public opinion on these issues. If the issues are few and the candidates are numerous, then even a perfect match says little about the representative capacity, because it is always possible that one candidate, or one coalition out of many, will align with public opinion on a couple of topics. To perform the test, the probability of the observed match of the candidate/ coalition position with the prevailing public opinion is found under the null hypothesis, assuming no representative capacity but coincidence by chance. If this probability is small, then the null hypothesis is rejected and the alternative hypothesis (existence of representative capacity) is accepted. The test developed is applied to the five German parties and their coalitions considered in Chapter 8.

I gather, young man, that you wish to be a Member of Parliament. The first lesson that you must learn is that, when I call for statistics about the rate of infant mortality, what I want is proof that fewer babies died when I was Prime Minister than when anyone else was Prime Minister. That is a political statistic.

Winston Churchill (1874–1963)