summary.stepmented {segmented} | R Documentation |
Summarizing model fits for stepmented regression
Description
summary/print method for class stepmented
.
Usage
## S3 method for class 'stepmented'
summary(object, short = FALSE, var.diff = FALSE, p.df="p", .vcov=NULL, ...)
## S3 method for class 'summary.stepmented'
print(x, short=x$short, var.diff=x$var.diff,
digits = max(3, getOption("digits") - 3),
signif.stars = getOption("show.signif.stars"),...)
## S3 method for class 'stepmented'
print(x, digits = max(3, getOption("digits") - 3),
...)
Arguments
object , x |
Object of class "stepmented" or a |
short |
logical indicating if the ‘short’ summary should be printed. |
var.diff |
logical indicating if different error variances should be computed
in each interval of the stepmented variable, see Details. If |
p.df |
A character as a function of |
.vcov |
Optional. The full covariance matrix for the parameter estimates. If provided, standard errors are computed (and displayed) according to this matrix. |
digits |
controls number of digits printed in output. |
signif.stars |
logical, should stars be printed on summary tables of coefficients? |
... |
further arguments, notably |
Details
If short=TRUE
only coefficients of the stepmented relationships are printed.
If var.diff=TRUE
and there is only one stepmented variable, different error variances are
computed in the intervals defined by the estimated breakpoints of the stepmented variable.
For the jth interval with observations, the error variance is estimated via
,
where
is the residual sum of squares in interval j, and
is the number of model parameters. This number to be subtracted from
can be changed via argument
p.df
. For instance p.df="0"
uses , and
p.df="p/K"
leads to , where
is the number of groups (segments), and
can be interpreted as the average number of model parameter in that group.
Note var.diff=TRUE
only affects the estimates covariance matrix. It does not affect the parameter estimates, neither the log likelihood and relevant measures, such as AIC or BIC. In other words, var.diff=TRUE
just provides 'alternative' standard errors, probably appropriate when the error variances are different before/after the estimated breakpoints. Also are computed using the t-distribution with 'naive' degrees of freedom (as reported in
object$df.residual
).
If var.diff=TRUE
the variance-covariance matrix of the estimates is computed via the
sandwich formula,
where V is the diagonal matrix including the different group-specific error variance estimates. Standard errors are the square root of the main diagonal of this matrix.
Value
A list (similar to one returned by stepmented.lm
or stepmented.glm
) with additional components:
psi |
estimated break-points and relevant (approximate) standard errors |
Ttable |
estimates and standard errors of the model parameters. This is similar
to the matrix |
cov.var.diff |
if |
sigma.new |
if |
df.new |
if |
Warning
If type
is not specified in ...
(which means type="standard"
), no standard error will be computed (and returned) for the jumpoint.
Author(s)
Vito M.R. Muggeo
See Also
Examples
##continues example from stepmented()
# summary(stepmented.model,short=TRUE)
## an heteroscedastic example..
# set.seed(123)
# n<-100
# x<-1:n/n
# y<- -x+1.5*pmax(x-.5,0)+rnorm(n,0,1)*ifelse(x<=.5,.4,.1)
# o<-lm(y~x)
# oseg<-stepmented(o,seg.Z=~x,psi=.6)
# summary(oseg,var.diff=TRUE)$sigma.new