R strucchange RSS and BIC for one breakpoint -


the reference manual r strucchange package states:

as maximum of sequence of f statistics equivalent minimum ols estimator of breakpoint in 2-segment partition can extracted breakpoints object of class "fstats" computed fstats.

is breakpoint extracted above approach same breakpoint extracted applying coeftest object of class "breakpointsfull" when "breaks" option 1? in other words, breakpoint extracted calling breakpoints on fstats object (minimum rss) equal breakpoint extracted calling coeftest on breakpointsfull object (minimum bic) when breaks = 1?

library(lmtest) library(strucchange)  data("nile")  fs.nile <- fstats(nile ~ 1) breakpoints(fs.nile)  bp.nile <- breakpoints(nile ~ 1) coeftest(bp.nile, breaks = 1) 

essentially yes. breakpoint associated supf statistic (supwald or suplr) , minimum rss breakpoint in linear regression model identical.

of course, trimming/minimal segment size needs same. default 15% in both breakpoints() (argument h) , fstats() (arguments from , to). also, no alternative covariance matrix estimator (vcov) must used in fstats().

however, breakpoints(fstats(formula, ...)) extracts simple object of class "breakpoints" while breakpoints(formula, ...) sets whole "breakpointsfull" object confidence intervals, coefficient tests, information criteria etc. can computed.


Comments

Popular posts from this blog

angularjs - ADAL JS Angular- WebAPI add a new role claim to the token -

php - CakePHP HttpSockets send array of paramms -

node.js - Using Node without global install -