# Chow breakpoint test for all series points

How appropriate would be, if you perform Chow breakpoint test for all points within series (without the very beginning and very ending), then find out where test suggest possible breakpoints (e.g. there are 4-5 points) and analyze them from visual and common-sense point of view - whether it is a real structural break or not?

The test is appropriate and was suggested by Quandt (1960) right after Chow (1960) had introduced it. However the correct asymptotic distribution for computing critical values and p-values was unknown until Andrews (1993) rigorously derived the required theory. An R implementation is available in R package strucchange (Zeileis et al. 2002) based on the p-values from Hansen (1997). The package also emphasizes visualizations of the sequence of test statistics to accompany the final significance tests.
This analysis can also be extended to multiple change points along with formal breakpoint estimation (Bai and Perron 2003). See Zeileis et al. (2003) for the implementation in strucchange.