How To (Spot A) Lie With Economic Statistics

A nice little article. Good things for the non economist (and really and perhaps especially the economist too) to keep in mind when economic stats are tossed around.

(From Forbes)

A classic example of such lies are minimum wage studies that don’t account for other trends. For example, some studies have claimed raising the minimum wage increases does not reduce jobs because in cities or states that have raised the minimum wage, jobs in affected industries have still risen. What such studies often fail to account for is the preexisting trends in jobs. If a city that raises its minimum wage was adding 50,000 jobs per year in low-wage occupations before the wage hike and adds only 20,000 such jobs in the year after, that is evidence of lost jobs, not that minimum wage hikes cause no damage.

Similar examples of insufficient controls are found in the gender wage gap statistics that don’t account for differences in experience, education, and other similar factors that directly influence salary levels. The famous statistic of women earning $0.77 for every dollar men earn is exactly this sort of lie. It makes no attempt to correct for differences in experience, education, or even full versus part time status. Louis Jacobson of Politifact does a very nice job of walking a reader through different ways controls can be added that change that number, while also pointing out it can be a true statement as long as it doesn’t come with an implication this difference is due to discrimination against women working equivalent jobs.

Click here for the article.