Manipulating the output of mqgam

Contrary to qgam, mqgam does not output a standard gamObject, hence methods such as predict.gam or plot.gam cannot be used directly. qdo provides a simple wrapper for such methods.

qdo(obj, qu = NULL, fun = I, ...)

Arguments

obj	the output of a mqgam call.
qu	A vector whose elements must be in (0, 1). Each element indicates a quantile of interest, which should be an element of names(obj$fit). If left to NULL the function fun will be applied to each of the quantile fits in obj.
fun	The method or function that we want to use on the gamObject corresponding to quantile qu. For instance predict, plot or summary. By default this is the identity function (I), which means that the fitted model for quantile qu is returned.
...	Additional arguments to be passed to fun.

Value

A list where the i-th entry is the output of fun (whatever that is) corresponding to quantile qu[i].

Examples

library(qgam); library(MASS)

quSeq <- c(0.4, 0.6)
set.seed(737)
fit <- mqgam(accel~s(times, k=20, bs="ad"), data = mcycle, qu = quSeq)
#> Estimating learning rate. Each dot corresponds to a loss evaluation. 
#> qu = 0.4..........done 
#> qu = 0.6...........done 

qdo(fit, 0.4, summary)
#> 
#> Family: elf 
#> Link function: identity 
#> 
#> Formula:
#> accel ~ s(times, k = 20, bs = "ad")
#> 
#> Parametric coefficients:
#>             Estimate Std. Error z value Pr(>|z|)    
#> (Intercept)  -31.181      1.832  -17.02   <2e-16 ***
#> ---
#> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#> 
#> Approximate significance of smooth terms:
#>            edf Ref.df Chi.sq p-value    
#> s(times) 8.968  10.35  666.4  <2e-16 ***
#> ---
#> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
#> 
#> R-sq.(adj) =  0.781   Deviance explained = 69.9%
#> -REML = 609.58  Scale est. = 1         n = 133
invisible(qdo(fit, 0.4, plot, pages = 1))

# Return the object for qu = 0.6 and then plot it
tmp <- qdo(fit, 0.6)
plot(tmp)