One data pattern, many interpretations

David Pittelli points us to this paper: “When Is Higher Neuroticism Protective Against Death? Findings From UK Biobank,” and writes:

They come to a rather absurd conclusion, in my opinion, which is that neuroticism is protective if, and only if, you say you are in bad health, overlooking the probability that neuroticism instead makes you pessimistic when describing your health.

Here’s the abstract of the article, by Catharine Gale, Iva Cukic, G. David Batty, Andrew McIntosh, Alexander Weiss, and Ian Deary:

We examined the association between neuroticism and mortality in a sample of 321,456 people from UK Biobank and explored the influence of self-rated health on this relationship. After adjustment for age and sex, a 1-SD increment in neuroticism was associated with a 6% increase in all-cause mortality (hazard ratio = 1.06, 95% confidence interval = [1.03, 1.09]). After adjustment for other covariates, and, in particular, self-rated health, higher neuroticism was associated with an 8% reduction in all-cause mortality (hazard ratio = 0.92, 95% confidence interval = [0.89, 0.95]), as well as with reductions in mortality from cancer, cardiovascular disease, and respiratory disease, but not external causes. Further analyses revealed that higher neuroticism was associated with lower mortality only in those people with fair or poor self-rated health, and that higher scores on a facet of neuroticism related to worry and vulnerability were associated with lower mortality. Research into associations between personality facets and mortality may elucidate mechanisms underlying neuroticism’s covert protection against death.

The abstract is admirably modest in its claims; still, Pittelli’s criticism seems reasonable to me. I’m generally suspicious of reading too much into this sort of interaction in observational data. The trouble is that there are so many possible theories floating around, so many ways of explaining a pattern in data. I think it’s a good thing that the Gale et al. paper was published: they found a pattern in data and others can work to understand it.

4 thoughts on “One data pattern, many interpretations

  1. I found the article’s title and Discussion (excerpt below) more problematic than the Abstract.

    “The findings of this study raise the question of why neuroticism becomes protective against mortality from
    all causes and cancer in people with fair or poor self-rated health.” (Goes on to list a bunch of possible reasons, not including neurotic people’s possible exaggeration of health problems.)

  2. The abstract raises these issues for me: (a) observational data (b) they are asserting a tiny effect (hazard ratio 0.92) due to a big intervention (1 SD change is big) (c) “self-rated health” is a silly covariate; so if a neurotic knows of this effect, then he/she only has to rate his/her own health lower to reduce mortality rate?

  3. I have no problem using observational data to make inferences like these, because there are important benefits with observational data that can be difficult or impossible to gain with experiments. The problem is when, like this paper, the alternative explanation that cannot be definitely ruled out by the data seems *more* likely than what the authors are arguing. Seems far more likely neuroticism interferes with accurate self-perception than that neuroticism makes one more resilient against illness.

  4. “…overlooking the probability that neuroticism instead makes you pessimistic when describing your health.”

    Maybe I’m missing something here. Even if neuroticism inclines a person to rate his/her own health as poorer than it is (a likelihood that the authors acknowledge at the very beginning of the paper), how does that discount the idea that “neuroticism is protective if, and only if, you say you are in bad health”?

    Obviously, self-rated health is an imperfect proxy for actual health. But if neurotic people in general tend to rate their health as worse than it is—including those who rate themselves as better than “bad”—then examining the interaction between neuroticism and self-rated health seems fairly reasonable, if not ideal, given the data they had to work with.

    p.s. – I am not a scientist, and I welcome any illumination as to why this judgment is misguided.

Leave a Reply

Your email address will not be published. Required fields are marked *