From the friends of Stephan Lewandowsky, and upside-down Mann department
Ralph Dave Westfall submits this story:
Here’s an interesting example of possibly politicized research findings getting blown out of the water: Conservative political beliefs not linked to psychotic traits, as study claimed.
Researchers have fixed a number of papers after mistakenly reporting that people who hold conservative political beliefs are more likely to exhibit traits associated with psychoticism, such as authoritarianism and tough-mindedness.
As one of the notices specifies, now it appears that liberal political beliefs are linked with psychoticism. That paper also swapped ideologies when reporting on people higher in neuroticism and social desirability (falsely claiming that you have socially desirable qualities); the original paper said those traits are linked with liberal beliefs, but they are more common among people with conservative values.
The interpretation of the coding of the political attitude items in the descriptive and preliminary analyses portion of the manuscript was exactly reversed. Thus, where we indicated that higher scores in Table 1 (page 40) reflect a more conservative response, they actually reflect a more liberal response. Specifically, in the original manuscript, the descriptive analyses report that those higher in Eysenck’s psychoticism are more conservative, but they are actually more liberal; and where the original manuscript reports those higher in neuroticism and social desirability are more liberal, they are, in fact, more conservative.
Andrew Gelman, a statistician at Columbia not involved with the work … said:
‘I don’t find this paper at all convincing, indeed I’m surprised it was accepted for publication by a leading political science journal. The causal analysis doesn’t make any sense to me, and some of the things they do are just bizarre, like declaring that correlations are “large enough for further consideration” if they are more than 0.2 for both sexes. Where does that come from? The whole thing is a mess.’
Pete Hatemi, a political scientist at Penn State University and co-author on three of the papers, explained why the swapped political beliefs and personality traits do not affect the conclusions:
We only cared about the magnitude of the relationship and the source of it … None of our papers actually give a damn about whether it’s plus or minus.
When we asked Hatemi to elaborate on what that magnitude was — how much more likely were people who held conservative or liberal views to exhibit certain traits? — he said:
[T]he correlations are spurious, so the direction or even magnitude is not suitable to elaborate on at all- that’s the point of all our papers and the general findings.
The reversal reminds me of the Alfred Kinsey research which initially indicated that more-educated females were less likely to be orgasmic. Later Kinsey said they had gotten the relationship backward due to calculation and sample size problems. (As reported in The Feminine Mystique (50th Anniversary Edition) by Betty Friedan, pp. 282-283).
Note by Anthony: This episode reminds me exactly of another Penn-State researcher, Michael Mann, who famously used the Tiljander proxy data upside down in one of his hockey stick papers, and then claimed the sign of the data doesn’t matter, and then after a year of stonewalling, grudgingly corrected it. Must be something in the water at State College, perhaps also in Mt. Beauty, Victoria, Australia. 😉