Last updated on 2025-04-03 17:49:43 CEST.
| Flavor | Version | Tinstall | Tcheck | Ttotal | Status | Flags |
|---|---|---|---|---|---|---|
| r-devel-linux-x86_64-debian-clang | 1.23 | 32.68 | 145.11 | 177.79 | ERROR | |
| r-devel-linux-x86_64-debian-gcc | 1.23 | 22.39 | 95.58 | 117.97 | ERROR | |
| r-devel-linux-x86_64-fedora-clang | 1.23 | 168.78 | ERROR | |||
| r-devel-linux-x86_64-fedora-gcc | 1.23 | 309.52 | ERROR | |||
| r-devel-macos-arm64 | 1.23 | 73.00 | OK | |||
| r-devel-macos-x86_64 | 1.23 | 236.00 | OK | |||
| r-devel-windows-x86_64 | 1.23 | 31.00 | 158.00 | 189.00 | OK | |
| r-patched-linux-x86_64 | 1.23 | 30.93 | 153.32 | 184.25 | OK | |
| r-release-linux-x86_64 | 1.23 | 32.15 | 155.32 | 187.47 | NOTE | |
| r-release-macos-arm64 | 1.23 | 74.00 | NOTE | |||
| r-release-macos-x86_64 | 1.23 | 183.00 | NOTE | |||
| r-release-windows-x86_64 | 1.23 | 31.00 | 157.00 | 188.00 | NOTE | |
| r-oldrel-macos-arm64 | 1.23 | 70.00 | NOTE | |||
| r-oldrel-macos-x86_64 | 1.23 | 193.00 | NOTE | |||
| r-oldrel-windows-x86_64 | 1.23 | 40.00 | 198.00 | 238.00 | NOTE |
Version: 1.23
Check: examples
Result: ERROR
Running examples in ‘cgam-Ex.R’ failed
The error most likely occurred in:
> base::assign(".ptime", proc.time(), pos = "CheckExEnv")
> ### Name: cgam
> ### Title: Constrained Generalized Additive Model Fitting
> ### Aliases: cgam
> ### Keywords: cgam routine
>
> ### ** Examples
>
> # Example 1.
> data(cubic)
> # extract x
> x <- cubic$x
>
> # extract y
> y <- cubic$y
>
> # regress y on x with no restriction with lm()
> fit.lm <- lm(y ~ x + I(x^2) + I(x^3))
>
> # regress y on x under the restriction: "increasing and convex"
> fit.cgam <- cgam(y ~ incr.conv(x))
>
> # make a plot to compare the two fits
> par(mar = c(4, 4, 1, 1))
> plot(x, y, cex = .7, xlab = "x", ylab = "y")
> lines(x, fit.cgam$muhat, col = 2, lty = 2)
> lines(x, fitted(fit.lm), col = 1, lty = 1)
> legend("topleft", bty = "n", c("constrained cgam fit", "unconstrained lm fit"),
+ lty = c(2, 1), col = c(2, 1))
>
> # Example 2.
> ## Not run:
> ##D library(gam)
> ##D data(kyphosis)
> ##D
> ##D # regress Kyphosis on Age, Number, and Start under the restrictions:
> ##D # "concave", "increasing and concave", and "decreasing and concave"
> ##D fit <- cgam(Kyphosis ~ conc(Age) + incr.conc(Number) + decr.conc(Start),
> ##D family = binomial(), data = kyphosis)
> ## End(Not run)
>
> # Example 3.
> library(MASS)
> data(Rubber)
>
> # regress loss on hard and tens under the restrictions:
> # "decreasing" and "decreasing"
> fit.cgam <- cgam(loss ~ decr(hard) + decr(tens), data = Rubber)
> # "smooth and decreasing" and "smooth and decreasing"
> fit.cgam.s <- cgam(loss ~ s.decr(hard) + s.decr(tens), data = Rubber)
> summary(fit.cgam.s)
Call:
cgam(formula = loss ~ s.decr(hard) + s.decr(tens), data = Rubber)
Coefficients:
Estimate StdErr t.value p.value
(Intercept) 175.4333 5.9624 29.423 < 2.2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for gaussian family taken to be 606.8062)
Null deviance: 225011.4 on 29 degrees of freedom
Residual deviance: 17597.38 on 16.5 observed degrees of freedom
Approximate significance of constrained components:
edf mixture.of.Beta p.value
s.decr(hard) 7.5 0.8772 < 2.2e-16 ***
s.decr(tens) 4.5 0.8166 < 2.2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
CIC: 10.0851> anova(fit.cgam.s)
Family: gaussian
Link function: identity
Formula:
cgam(formula = loss ~ s.decr(hard) + s.decr(tens), data = Rubber)
Approximate significance of smooth terms:
edf mixture.of.Beta p.value
s.decr(hard) 7.5 0.8772 < 2.2e-16 ***
s.decr(tens) 4.5 0.8166 < 2.2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>
> # make a 3D plot based on fit.cgam and fit.cgam.s
> plotpersp(fit.cgam, th = 120, main = "3D Plot of a Cgam Fit")
> plotpersp(fit.cgam.s, tens, hard, data = Rubber, th = 120, main = "3D Plot of a Smooth Cgam Fit")
>
> # Example 4. monotonic variance estimation
> n <- 400
> x <- runif(n)
> sig <- .1 + exp(15*x-8)/(1+exp(15*x-8))
> e <- rnorm(n)
> mu <- 10*x^2
> y <- mu + sig*e
>
> fit <- cgam(y ~ s.incr.conv(x), var.est = s.incr(x))
> est.var <- fit$vh
> muhat <- fit$muhat
>
> par(mfrow = c(1, 2))
> plot(x, y)
> points(sort(x), muhat[order(x)], type = "l", lwd = 2, col = 2)
> lines(sort(x), (mu)[order(x)], col = 4)
>
> plot(sort(x), est.var[order(x)], col=2, lwd=2, type="l",
+ lty=2, ylab="Variance", ylim=c(0, max(c(est.var, sig^2))))
> points(sort(x), (sig^2)[order(x)], col=1, lwd=2, type="l")
>
> # Example 5. monotonic variance estimation with the lidar data set in SemiPar
> library(SemiPar)
> data(lidar)
>
> fit <- cgam(logratio ~ s.decr(range), var.est=s.incr(range), data=lidar)
Error in attr(x, "nm") <- deparse(pars$x) :
cannot set attribute on a 'builtin'
Calls: cgam -> cgam.fit -> s.incr
Execution halted
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc
Version: 1.23
Check: examples
Result: ERROR
Running examples in ‘cgam-Ex.R’ failed
The error most likely occurred in:
> ### Name: cgam
> ### Title: Constrained Generalized Additive Model Fitting
> ### Aliases: cgam
> ### Keywords: cgam routine
>
> ### ** Examples
>
> # Example 1.
> data(cubic)
> # extract x
> x <- cubic$x
>
> # extract y
> y <- cubic$y
>
> # regress y on x with no restriction with lm()
> fit.lm <- lm(y ~ x + I(x^2) + I(x^3))
>
> # regress y on x under the restriction: "increasing and convex"
> fit.cgam <- cgam(y ~ incr.conv(x))
>
> # make a plot to compare the two fits
> par(mar = c(4, 4, 1, 1))
> plot(x, y, cex = .7, xlab = "x", ylab = "y")
> lines(x, fit.cgam$muhat, col = 2, lty = 2)
> lines(x, fitted(fit.lm), col = 1, lty = 1)
> legend("topleft", bty = "n", c("constrained cgam fit", "unconstrained lm fit"),
+ lty = c(2, 1), col = c(2, 1))
>
> # Example 2.
> ## Not run:
> ##D library(gam)
> ##D data(kyphosis)
> ##D
> ##D # regress Kyphosis on Age, Number, and Start under the restrictions:
> ##D # "concave", "increasing and concave", and "decreasing and concave"
> ##D fit <- cgam(Kyphosis ~ conc(Age) + incr.conc(Number) + decr.conc(Start),
> ##D family = binomial(), data = kyphosis)
> ## End(Not run)
>
> # Example 3.
> library(MASS)
> data(Rubber)
>
> # regress loss on hard and tens under the restrictions:
> # "decreasing" and "decreasing"
> fit.cgam <- cgam(loss ~ decr(hard) + decr(tens), data = Rubber)
> # "smooth and decreasing" and "smooth and decreasing"
> fit.cgam.s <- cgam(loss ~ s.decr(hard) + s.decr(tens), data = Rubber)
> summary(fit.cgam.s)
Call:
cgam(formula = loss ~ s.decr(hard) + s.decr(tens), data = Rubber)
Coefficients:
Estimate StdErr t.value p.value
(Intercept) 175.4333 5.9624 29.423 < 2.2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
(Dispersion parameter for gaussian family taken to be 606.8062)
Null deviance: 225011.4 on 29 degrees of freedom
Residual deviance: 17597.38 on 16.5 observed degrees of freedom
Approximate significance of constrained components:
edf mixture.of.Beta p.value
s.decr(hard) 7.5 0.8772 < 2.2e-16 ***
s.decr(tens) 4.5 0.8166 < 2.2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
CIC: 10.0851> anova(fit.cgam.s)
Family: gaussian
Link function: identity
Formula:
cgam(formula = loss ~ s.decr(hard) + s.decr(tens), data = Rubber)
Approximate significance of smooth terms:
edf mixture.of.Beta p.value
s.decr(hard) 7.5 0.8772 < 2.2e-16 ***
s.decr(tens) 4.5 0.8166 < 2.2e-16 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>
> # make a 3D plot based on fit.cgam and fit.cgam.s
> plotpersp(fit.cgam, th = 120, main = "3D Plot of a Cgam Fit")
> plotpersp(fit.cgam.s, tens, hard, data = Rubber, th = 120, main = "3D Plot of a Smooth Cgam Fit")
>
> # Example 4. monotonic variance estimation
> n <- 400
> x <- runif(n)
> sig <- .1 + exp(15*x-8)/(1+exp(15*x-8))
> e <- rnorm(n)
> mu <- 10*x^2
> y <- mu + sig*e
>
> fit <- cgam(y ~ s.incr.conv(x), var.est = s.incr(x))
> est.var <- fit$vh
> muhat <- fit$muhat
>
> par(mfrow = c(1, 2))
> plot(x, y)
> points(sort(x), muhat[order(x)], type = "l", lwd = 2, col = 2)
> lines(sort(x), (mu)[order(x)], col = 4)
>
> plot(sort(x), est.var[order(x)], col=2, lwd=2, type="l",
+ lty=2, ylab="Variance", ylim=c(0, max(c(est.var, sig^2))))
> points(sort(x), (sig^2)[order(x)], col=1, lwd=2, type="l")
>
> # Example 5. monotonic variance estimation with the lidar data set in SemiPar
> library(SemiPar)
> data(lidar)
>
> fit <- cgam(logratio ~ s.decr(range), var.est=s.incr(range), data=lidar)
Error in attr(x, "nm") <- deparse(pars$x) :
cannot set attribute on a 'builtin'
Calls: cgam -> cgam.fit -> s.incr
Execution halted
Flavors: r-devel-linux-x86_64-fedora-clang, r-devel-linux-x86_64-fedora-gcc
Version: 1.23
Check: package dependencies
Result: NOTE
Depends: includes the non-default packages:
'coneproj', 'svDialogs', 'statmod', 'lme4', 'Matrix', 'splines2'
Adding so many packages to the search path is excessive and importing
selectively is preferable.
Flavors: r-release-linux-x86_64, r-release-macos-arm64, r-release-macos-x86_64, r-release-windows-x86_64, r-oldrel-macos-arm64, r-oldrel-macos-x86_64, r-oldrel-windows-x86_64
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.