lqnorm: Minimizing the L-q norm Family Function

Description

Minimizes the L-q norm of residuals in a linear model.

Usage

lqnorm(qpower=2, link="identity", earg=list(),
       method.init=1, imu=NULL, shrinkage.init=0.95)

Arguments

qpower

A single numeric, must be greater than one, called $q$ below. The absolute value of residuals are raised to the power of this argument, and then summed. This quantity is minimized with respect to the regression coefficients.

link, earg

Link function applied to the `mean' $\mu$, and extra argument optionally used by the link function. See Links for more details.

method.init

Must be 1, 2 or 3. See CommonVGAMffArguments for more information. Ignored if imu is specified.

imu

Numeric, optional initial values used for the fitted values. The default is to use method.init=1.

shrinkage.init

How much shrinkage is used when initializing the fitted values. The value must be between 0 and 1 inclusive, and a value of 0 means the individual response values are used, and a value of 1 means the median or mean is used. This argument is used i

Value

An object of class "vglmff" (see vglmff-class). The object is used by modelling functions such as vglm, and vgam.

Warning

Convergence failure is common, therefore the user is advised to be cautious and monitor convergence!

Details

This function minimizes the objective function

\sum_{i = 1}^{n} w_{i} (| y_{i} - μ_{i} |)^{q}

where $q$ is the argument qpower, $\eta_i = g(\mu_i)$ where $g$ is the link function, and $\eta_i$ is the vector of linear/additive predictors. The prior weights $w_i$ can be inputted using the weights argument of vlm/vglm/vgam etc.; it should be just a vector here since this function handles only a single vector or one-column response.

Numerical problem will occur when $q$ is too close to one. Probably reasonable values range from 1.5 and up, say. The value $q=2$ corresponds to ordinary least squares while $q=1$ corresponds to the MLE of a double exponential (Laplace) distibution. The procedure becomes more sensitive to outliers the larger the value of $q$.

References

Yee, T. W. and Wild, C. J. (1996) Vector generalized additive models. Journal of the Royal Statistical Society, Series B, Methodological, 58, 481--493.

Examples

Run this code

set.seed(123)
ldat = data.frame(x = sort(runif(nn <- 10 )))
realfun = function(x) 4 + 5*x
ldat = transform(ldat, y = realfun(x) + rnorm(nn, sd=exp(1)))
# Make the first observation an outlier
ldat = transform(ldat, y = c(4*y[1], y[-1]), x=c(-1, x[-1]))
fit = vglm(y ~ x, fam = lqnorm(qpower=1.2), data=ldat)
coef(fit, matrix=TRUE)
head(fitted(fit))
fit@misc$qpower 
fit@misc$objectiveFunction 

# Graphical check
with(ldat, plot(x, y, main=paste("LS=red, lqnorm=blue (qpower = ",
             fit@misc$qpower, "), truth=black", sep=""), col="blue"))
lmfit = lm(y ~ x, data=ldat)
with(ldat, lines(x,  fitted(fit), col="blue"))
with(ldat, lines(x, lmfit$fitted, col="red"))
with(ldat, lines(x,  realfun(x),  col="black"))

Run the code above in your browser using DataLab

Get 50% off unlimited learning