jump to navigation

Prolonged vacation and the dangers of diet soda July 25, 2007

Posted by Johan in Links, Rants, You Make Pearson Cry.

The blog has been idle for long enough for the spam bots to kick in properly – I can only surmise that they specifically target blogs with no recent post since there is less risk of moderation that way.

My vacation is still on, now in Budapest, Hungary. What little time I have for science is spent re-learning high school maths for the GRE and reading up for a literature review on face processing in Schizophrenia.

I was going to post a quick rant about the recently hyped-up story on how diet soda is linked with ‘metabolic syndrome’ (heart disease, diabetes and other consequences of poor eating), just like regular soda. There are some obvious problems with how the media has interpreted the correlational, non-causal relationship between metabolic syndrome and diet soda consumption, e.g., could it be that people who drink a lot of diet soda do so at fast food restaurants and in other contexts where you might eat unhealthy foods?

However, Shelley at Retrospectacle already posted an excellent critique of the study. I really have nothing to add, so go read about it at Retrospectacle instead.


You Make Pearson Cry #3: Daycare Correlates March 28, 2007

Posted by Johan in Developmental Psychology, You Make Pearson Cry.

A recent report on the NICHD study on early childcare argues that time spent in daycare is associated with disruptive behaviour:

keeping a preschooler in a day care center for a year or more increased the likelihood that the child would become disruptive in class — and that the effect persisted through the sixth grade.

The effect was slight, and well within the normal range for healthy children, the researchers found. And as expected, parents’ guidance and their genes had by far the strongest influence on how children behaved.

But the finding held up regardless of the child’s sex or family income, and regardless of the quality of the day care center. With more than two million American preschoolers attending day care, the increased disruptiveness very likely contributes to the load on teachers who must manage large classrooms, the authors argue.

On the positive side, they also found that time spent in high-quality day care centers was correlated with higher vocabulary scores through elementary school.

Controlling for genetics, parenting, family income, and gender is probably a good start, but even with such controls it’s not exactly difficult to think of other interpretations of the data:

  1. Disruptive children get put in daycare more because their parents need time off.
  2. Children in daycare have parents who generally have less time for them, in and out of daycare.
  3. Parents who put their children in daycare differ from stay-at-home parents on some other third variable

I’m also a bit curious about how they controlled for parenting, since I imagine a pretty crucial factor in parenting styles is going to be whether you believe in daycare or not. But before I spend too much time trying to make sense of the data, what does it look like, exactly?

In 2001, the authors reported that children who spent most of their day in care not provided by a parent were more likely to be disruptive in kindergarten. But this effect soon vanished for all but those children who spent a significant amount of time in day care centers.

Every year spent in such centers for at least 10 hours per week was associated with a 1 percent higher score on a standardized assessment of problem behaviors completed by teachers, said Dr. Margaret Burchinal, a co-author of the study and a psychologist at the University of North Carolina.

The statistical trick of creating extreme groups and then testing for significance tells me that they failed to find a significant correlation between time in daycare and scores on the test. By taking the extreme cases you can squeeze out a significant result, but unfortunately, you’re no longer just comparing daycare to no daycare. You’re comparing a lot of daycare to no daycare at all, and this may make your groups less comparable on other variables since you’re looking at extreme groups only, without considering the bulk of the sample that is somewhere in-between.

The effect size is a bit of a joke. a 1 percent different in scores on a test? And this is a cause for concern? Even while admitting that there were positive correlations with vocabulary scores? Making the unlikely assumption that daycare is the cause of both these effects, perhaps scoring 1 percent higher in this disruptive behaviour measure is actually a worthwhile trade-off for improved vocabulary scores?

While a large sample is always better, I think this study raises the question of how small a significant effect can be to be considered meaningful. This $200 million project (no exaggeration) could obviously afford a huge sample, to be able to get significance on a 1 percent difference. But what does this mean? Should parents take this into consideration? It’s quite possible that there is a 1 percent difference in scores on this measure for disruptive behaviour linked to a whole pile of other, less politically loaded factors that we know nothing about, because no one is looking for them.

Ultimately, a major part of why so much of basic sociology is open to interpretation is the reliance on correlational measures. Sociology, at its best, should be able to inform policy – to tell us what the best option is, for parents and for policy-makers. In this case, with a $200 million budget, I could easily see how experimental measures could be employed instead: get a sample of lower-income families and offer them free day-care in exchange for participation in the study. Out of the people who volunteer, assign half to day-care, and half as a control group. The study wouldn’t generalise beyond that part of the socioeconomic spectrum, but at least you would be able to show causation.

You Make Pearson Cry #2: Deadly Mobiles? February 8, 2007

Posted by Johan in Rants, You Make Pearson Cry.
add a comment

While international media appears to have been spared so far, Swedish media decided to go creative when interpreting results from studies by IARC (the International Agency for Research on Cancer) on the possible dangers of mobile phone use. National tabloid Expressen goes for the big guns with a headline that roughly translated goes “cell phones damage your child’s brain.” In the article, it is claimed that the risk of “brain tumour” increases by 39 percent if you have used your mobile phone regularly for over 10 years. There’s no mention of children being at risk, so I presume this bit of the story was inspired by the fact that the risk only appears over the long term.

So is there truth to this? Yes, and no. If you go to the source, it turns out that people who have used cell phones for over 10 years do have an increased risk of cancer, and the difference is on the order of 40 percent.

But the increase is not for brain tumours in general. Rather, there is an increased risk of acoustic neurinoma, which IARC describes as “slowly growing benign tumours that generally have a good prognosis, as they only rarely undergo malignant change.” Now that’s interesting enough in itself, but wait, it gets better: the IARC report also states that the incidence of acoustic neurinoma in adults is on the order of 1 per 100 000 per year.

 Let’s do some numbers on that. If the incidence for the normal population is 1/100 000, or a risk of 0.00001 percent per year, and regular mobile phone use over 10 years increases the risk by 39 percent, the incidence for these people is 1.39/100 000, and the risk grows to a whooping 0.0000139 percent.

So to summarise, heavy mobile phone use over a long period of time increases the risk that you will catch a benign, slow-growing tumour by a number that is, in real terms, somewhere on the order of being struck by lightning in your pinky.

The real, undiscovered danger in mobiles lies in their use as throwing weapons. I’m willing to bet that the risk of getting a mobile thrown at your head with deadly results is at least 39 percent greater than the risk of the mobile causing you cancer. Of course, such an argument relies on treating proportions as absolutes…. and that would just be silly, wouldn’t it?

By the way, this particular case has nothing to do with misinterpreting correlations, so from now on, I guess You Make Pearson Cry will concern rants on any bad science reporting, correlational or not.

You Make Pearson Cry #1: Stay Together for the Money December 11, 2006

Posted by Johan in Off Topic, Rants, You Make Pearson Cry.
add a comment

The British Conservative Party launched a report today, which inspired me to create a new feature for this blog: you make Pearson cry, named after the man who did the first work on correlation, and whom the Pearson correlation coefficient is named after. Of course, I have no idea what Pearson might have thought about inappropriate use of his measure of effect size. After all, the man was a eugenicist, for whom confusing correlation and causation is par for the course. It’s that very confusion which will be the topic of this feature.

The report seems to be quite wonderful in its blatant disregard for what might be inferred from a correlation. Case in point:

Iain Duncan Smith’s report for the Tories on poverty, found family splits caused social problems costing £20bn.” (BBC)

So, you’ve figured out that divorced parents have more social problems, and that their kids get into more trouble. So far so good. Next, you conclude that if they stayed together, you wouldn’t have a problem. Umm, no. There are a million other variables with also differ between people who have problems and people who don’t, and it seems a bit idiotic to believe that of all those, it isn’t a family history of poverty and social problems; it isn’t drug use; it isn’t screwing up school. No. Instead, marital status is the underlying cause of all these! So what do we do?

“Couples should be “encouraged to get together and stay together” – possibly with the help of changes to taxation to support marriage, Mr Cameron said” (BBC)

We buy them off. Clearly some of these couples that split up, thus causing, in essence, the downfall of the British Empire, would stay together for purposes of taxation. We all know how great it is when parents stay together for the kids. Now parents who don’t care about the kids can still stay together for the money, which is likely to result in everyone living happily ever after, according to Mr Cameron.

Just to be clear: this proposal is really looking out for the poor. It has absolutely nothing to do with the Conversative constituency being made up of married couples who like tax breaks.