This preview shows page 1. Sign up to view the full content.
Unformatted text preview: 0.016]***[0.018]***
Yes Notes: The dependentvariablesare age left full-time education and log annualearnings.Each coefficient is from a separate
regression. Each regression includes controls for a birth cohort quarticpolynomial and indicatorwhether a cohort faced a
school leaving age of 15 at age 14. Columns 2, 3, 5, and 6 also include age controls:a quarticpolynomial and fixed effects
where indicated.Each regressionincludes the sample of 25- to 64-year-olds from the 1983 through 1998 GeneralHousehold
Surveys, who were aged 14 between 1935 and 1965. Data are first aggregatedinto cell means and weighted by cell size.
Regressions are clustered by birth cohort and region (Britain or N. Ireland). horts, there is a clear spike in mean attainment
after 1947. Average schooling increases by exactly half a year between the cohorts that were
age 14 in 1946 and in 1948. The figure also
plots the fittedvalues from regressingthe means
on a quarticpolynomial for year of birthand an
indicatorterm for whetheror not a cohort faced
a minimum school-leaving age of 15 (all 14year-olds in 1947 and after). The fit predicts an
increase in education attainmentbetween 1946
and 1947 of 0.44 years (R2 = 0.995)."1 This result, and the accompanying standard
error (0.065), can also be seen in column 1 of
Table 1, which was produced from the same
GHS data as the figures. The data were first
aggregatedinto cell means by birth cohort, region, and age. All regressions are weighted by
cell size and clustered by cohort and region
(Britain or Northern Ireland) using HuberWhite standarderrors.12Column 1 shows the " I also tried fitting the grouped means in several other
ways: with a quadratic,with a quadraticallowed to differ
before and after 1947, and by omitting 14-year-oldsin 1947,
since not all faced a higher school-leaving age that year.
These alternativespecifications generate similar results.
View Full Document
- Fall '13