Second, to summarize my position on using these data to test the theory that saturated fat is good for your health. We know that there are many ways in which richer, more developed countries differ from poorer, less developed countries: they’re healthier in various ways, more educated, do less physical labor, have higher gender equality, eat more meat, have more political freedom, use more energy, etc. So when you’re interested in looking at some variable between countries, it’s important to check whether it’s one of the many variables that are associated with development level. If it is, then it’s a safe bet that it will be correlated any of the other variables that goes with development level, regardless of whether or not there’s any causal relationship between them, since they are both part of the same package (development). As a first step to see if there is a causal relationship between them, you can run a regression controlling for some measure of development (such as GDP per capita) to see if their relationship still holds up – are they related to each other beyond what you’d expect from them both being features of developed countries? There are limitations to that analysis (you want to think about whether you’re using the best measures of the variables, and whether there’s something more you should be controlling for), but if your predicted relationship holds up in the regression then that’s some evidence that it’s a real causal relationship. If it doesn’t then that’s some evidence that the there isn’t much of a causal relationship between them, and the correlation between them is just due to them both being part of the development package.

Deal?

I really appreciate you going to that work.

Listen, the las thing I — and Alex, I’m pretty sure — want is to fool ourselves or others. And, I think you can see from the first post, then Seth’s objections and Alex’s own anticipation of objections and subsequent crunching that everyone is being as objective as possible.

I’ve also read Seth’s response to your analysis over at his place.

http://www.blog.sethroberts.net/2009/11/07/saturated-fat-epidemiology/#comment-359647

I tend to agree with that, at least in the sense that I think it’s perfectly sensible to _presume_ that saturated fat, particularly in the context of a whole foods diet with minimal neolithic foods (grains, sugar, vegetable oils and derivatives), out to be perfectly healthful. As I said at the end of the post:

“Go figure. I mean, should this be a surprise? Are predatory animals who eat other animals and prize the [saturated] fat dropping dead of strokes and heart disease? No, and why? Because they’re less arrogant than humans. They don’t, because they can’t, eat in any way other than how they evolved to eat.”

This, I think, is what we ought to expect at a very fundamental level and ought to really demand extraordinary proof in the contrary.

What we have is some confirmation based on the raw correlations that what actually makes perfect sense is likely the case.

All the numbers that I needed except for GDP per capita were in Alex’s first post. His first graph has labels with the SatFat% for 45 countries, and his last graph has labels with the DALY figures for those countries*. I copied those numbers into a spreadsheet, and then added the GDP Per Capita numbers (from the IMF, 2008). If anyone is interested, I could email them the spreadsheet.

GDP/person correlated strongly with both SatFat% (r = .86) and DALY (r = -.84). And in a linear regression predicting DALY from both SatFat% and GDP/person, only GDP/person was a significant predictor (F(1,42) = 33.9, p less than .0001); SatFat% was nowhere near significant (F(1,42) = .49, p = .49). This model explains 71% of the variance in DALY (R^2 = .710). The regression equation says that every additional $1000 in GDP/person is associated with 98 fewer DALYs, and each 1 percentage point increase in SatFat% is associated with 54 additional DALYs (but this is not significantly different from zero).

I tried a few variations on this analysis, seeing if transforming the variables made for a better model. Using the log of DALY instead of DALY is an improvement: the pairwise correlations are stronger (-.75 and -.89 instead of -.69 and -.84), R^2 for the regression model goes up (.787 instead of .710), and Norway is no longer predicted to have a negative number of DALY. The pattern of regression results remains the same: GDP/person is a strong predictor of log(DALY) (F = 43.7), and SatFat% has a very slight positive association with log(DALY) that is not close to being statistically significant (F = .05, p = .83).

These analyses suggest that wealth (or something closely correlated with wealth) has a big impact on saturated fat consumption and on health, and that whatever impact saturated fat consumption has on health is too small to show up in this data set.

*Two countries, Moldova and Macedonia, were missing from the last graph, so I used their approximate DALY from the first graph, which plots DALY on the y-axis but doesn’t label the exact number.