(This article was originally published at Statistical Modeling, Causal Inference, and Social Science, and syndicated at StatsBlogs.)
Jeff points me to this news article and asks, Can this be right?
Hmmm . . . the article defines “wealthier smokers” as “those earning 60,000 or more.” So suppose a “low-income smoker” makes $20K, then 25% is $5000, which is $100 a week, or $14/day, which according to the article is roughly the cost of a pack of cigarettes. So I guess it’s possible. It just depends where you put the cutoff for “low-income” and where you put the cutoff for “smoker.” I also wonder whether the numerator and denominator are comparable. It might be that if you add up all of these people’s expenses and divide by their income, you’ll get a ratio of more than 100%.
Please comment on the article here: Statistical Modeling, Causal Inference, and Social Science