vod vos
2017-Feb-26 07:51 UTC
[R] Why the slope and intercept of 95% CI varies at each calculation when using package mcr?
Hi Everybody,
aa<-
c(1,5,10,20,50,40,50,60,70,80,90,100,150,200,250,300,350,400,450,500,550,600,650,700,750,800,850,900,950,1000)
bb<-
c(8,16,30,24,39,54,40,68,72,62,122,80,181,259,275,380,320,434,479,587,626,648,738,766,793,851,871,957,1001,960)
library(mcr)
pbreg<- mcreg(aa,bb, method.reg = "PaBa")
pbreg at para
EST SE LCI UCI
Intercept 7.081869 NA -2.824761 20.169193
Slope 1.055312 NA 1.024968 1.096982
but when you calculate again,
pbreg<- mcreg(aa,bb, method.reg = "PaBa")
pbreg at para
EST SE LCI UCI
Intercept 7.081869 NA -1.834744 20.598912
Slope 1.055312 NA 1.025339 1.095888
pbreg at para show different values of LCI and UCI compared to the first time,
how does this happen?
Thanks.
Rui Barradas
2017-Feb-26 10:54 UTC
[R] Why the slope and intercept of 95% CI varies at each calculation when using package mcr?
Hello, I know nothing about package mcr but by reading the help page for function mcreg I conclude that CI's are calculated using a bootstrap resampling technique and therefore you should expect different values every time the function runs unless you set the random generator seed using ?set.seed. Hope this helps, Rui Barradas Em 26-02-2017 07:51, vod vos escreveu:> > Hi Everybody, > > aa<- c(1,5,10,20,50,40,50,60,70,80,90,100,150,200,250,300,350,400,450,500,550,600,650,700,750,800,850,900,950,1000) > bb<- c(8,16,30,24,39,54,40,68,72,62,122,80,181,259,275,380,320,434,479,587,626,648,738,766,793,851,871,957,1001,960) > > library(mcr) > > pbreg<- mcreg(aa,bb, method.reg = "PaBa") > > pbreg at para > > EST SE LCI UCI > Intercept 7.081869 NA -2.824761 20.169193 > Slope 1.055312 NA 1.024968 1.096982 > > but when you calculate again, > > pbreg<- mcreg(aa,bb, method.reg = "PaBa") > > pbreg at para > > EST SE LCI UCI > Intercept 7.081869 NA -1.834744 20.598912 > Slope 1.055312 NA 1.025339 1.095888 > > pbreg at para show different values of LCI and UCI compared to the first time, how does this happen? > > Thanks. > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. >
peter dalgaard
2017-Feb-26 10:57 UTC
[R] Why the slope and intercept of 95% CI varies at each calculation when using package mcr?
Because they are bootstrap based. -pd> On 26 Feb 2017, at 08:51 , vod vos <vodvos at zoho.com> wrote: > > > Hi Everybody, > > aa<- c(1,5,10,20,50,40,50,60,70,80,90,100,150,200,250,300,350,400,450,500,550,600,650,700,750,800,850,900,950,1000) > bb<- c(8,16,30,24,39,54,40,68,72,62,122,80,181,259,275,380,320,434,479,587,626,648,738,766,793,851,871,957,1001,960) > > library(mcr) > > pbreg<- mcreg(aa,bb, method.reg = "PaBa") > > pbreg at para > > EST SE LCI UCI > Intercept 7.081869 NA -2.824761 20.169193 > Slope 1.055312 NA 1.024968 1.096982 > > but when you calculate again, > > pbreg<- mcreg(aa,bb, method.reg = "PaBa") > > pbreg at para > > EST SE LCI UCI > Intercept 7.081869 NA -1.834744 20.598912 > Slope 1.055312 NA 1.025339 1.095888 > > pbreg at para show different values of LCI and UCI compared to the first time, how does this happen? > > Thanks. > > ______________________________________________ > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code.-- Peter Dalgaard, Professor, Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Office: A 4.23 Email: pd.mes at cbs.dk Priv: PDalgd at gmail.com