32,757 year old survey participant skews Lewandowsky paper – Defective data, demonstrably defective conclusion

Guest essay by Eric Worrall.

JoNova reports on a hilarious error in Lewandowsky’s paper “The Role of Conspiracist Ideation and Worldviews in Predicting Rejection of Science” . The calculated age of survey respondents has reportedly been skewed by one “outlier” who claimed to have been born in the palaeolithic, 32,757 years ago.

Raw data – line 607, http://websites.psychology.uwa.edu.au/labs/cogscience/documents/PLOSONE2013Data.csv

Lewandowsky was informed of this error over a year ago – and has reportedly done nothing to address this glaring problem with his calculations and conclusion.

According to Jo Nova;

“Lewandowsky, Gignac and Oberauer put out a paper in 2013 which was used to generate headlines like ‘Climate sceptics more likely to be conspiracy theorists’. The data sample is not large, but despite that, it includes the potential Neanderthal, as well as a precocious five year old and some underage teenagers too. The error was reported on Lewandowsky’s blog over a year ago by Brandon Shollenberger, then again by Jose Duarte in August 2014. Nothing has been corrected. The ages are not just typos, they were used in the calculations, correlations and conclusions. The median age was 43 but the mean age was a flaming neon 76. One wildly old person in the data skewed the correlation for age with nearly everything:

That one data point – the paleo-participant – is almost single-handedly responsible for knocking out all the correlations between age and so many other variables. If you just remove the paleo-participant, leaving the minors in the data, age lights up as a correlate across the board. Further removing the kids will strengthen the correlations.”

Full story: http://joannenova.com.au/2015/01/lewandowsky-peer-reviewed-study-includes-someone-32757-years-old/#more-40327

Worst of all, the bad data has apparently led to a demonstrably erroneous conclusion. According to Jose Duarte,

“This would be a serious problem in any context. We cannot have minors or paleo-participants in our data, in the data we use for analyses, claims, and journal articles. It’s even more serious given that the authors analyzed the age variable, and reported its effects. They state in their paper:

— “Age turned out not to correlate with any of the indicator variables.”

This is grossly false. It can only be made true if we include the fake data. If we remove the fake data, especially the 32,757-year-old, age correlates with most of their variables. It correlates with six of their nine conspiracy items, and with their “conspiracist ideation” combined index. It also correlates with views of vaccines – a major variable in their study. See the graph below.”

http://www.joseduarte.com/blog/how-one-paleo-participant-can-change-the-outcome-of-a-study

Lets hope that Lewandowsky finally takes action to correct the error, and amends the erroneous conclusion of his paper, which is inferred from Lewandowsky’s analysis of the grossly defective data. Of course, while he’s at it, I’m sure we could suggest a few other defects with Lewandowsky’s work which he could correct.