I’ve mentioned in the past that I’m not a big fan of twin studies, but it was a thrill to find one of my papers referenced in this particular one, published in the most recent edition of Political Psychology.
The study examined the biological (ie, based on genes) versus environmental (ie, based on experience) determinants of political views. The authors go as far as to suggest that a person’s political persuasion may be a stable personality trait – in addition to the Big 5. (For the non-psychology majors out there, or those who studied psychology any time prior to the 90s – the Myers Briggs Type Indicator, that many commercial psychometric tests are based on, is, shall we say, scientifically questionable. These days, scientific individual difference/personality researchers more commonly use the Big 5 – which are introversion-extroversion, agreeableness, conscientiousness, openness, and neuroticism).
Anyway… this article helps to emphasise why getting a representative sample of people for a survey is not just about getting the right number of people by age, gender, region, and ethnic group. Random sampling is basically an attempt to take a sample that is representative by the known and unknown factors that contribute to a person’s views. An earlier post about this is here.
UPDATE: Just corrected some very silly typos.