I’m finally reading the much-acclaimed “How Does Your Kindergarten Classroom Affect Your Earnings?”  There’s no denying that it’s an extremely impressive piece.  And unlike many of their fans, the authors are very careful.  Note well: Project STAR was designed to test the effect of class size, not teacher quality.  Now ponder these three quotes.

Quote #1 (from the abstract):

Class size does not have a significant effect on earnings at age 27, but this effect is imprecisely estimated.

Quote #2 (the actual magnitude):

Table V shows that without controls, students who were assigned to small classes are estimated to earn $4 more per year on average between 2005 and 2007. With controls for demographic characteristics, the point estimate of the earnings impact becomes -$124 (with a standard error of $336).

Quote #3 (the interpretation):

We conclude that the class size intervention, which raises test scores by 4.8 percentiles, is unfortunately not powerful enough to detect earnings increases of a plausible magnitude as of age 27.