Stats Seasonality and calendar Calendar anomalies

The weekend effect's t statistic fell from -8.86 to -1.37

1953-1977: -8.86-8.861953-19771978-2002: -1.37-1.371978-2002

A t statistic of minus 8.86 is overwhelming. Minus 1.37 is nothing. The paper was published in 1980. Source: Schwert, Anomalies and Market Efficiency, NBER working paper 9277.

Researchers kept finding returns tied to the calendar, then published them. Kenneth French's weekend effect had a t statistic of minus 8.86 before 1980 and minus 1.37 after. Across 97 published predictors, returns fell 58 per cent once the paper was out.

-8.86Weekend t, 1953 to 1977
-1.37Weekend t, 1978 to 2002
97Predictors tested
58% lowerReturn after publication

Members only

The rest of this page is for members

Below this point there are 8 sections, 1 chart and 4 named sources, roughly 1200 words of it. Every figure carries the source it came from and the date the data is from.

You can keep browsing every statistic in the library for free. The intro and the summary are always open.