DBKGrad (version 1.7)

plot.dbkGrad: Plot Method for dbkGrad objects

Description

Plotting the dbkGrad object produces a few different plots that are of interest. The different plots, created from various plottype options, are described below:

Usage

# S3 method for dbkGrad
plot(x, plottype = c("obsfit", "fitted", "observed", "exposure",
    "residuals", "checksd"), plotstyle = c("mat", "level", "persp"),
    restype = c("working", "proportional", "response", "deviance", "pearson"), 
    byage = TRUE, columns, rows, CI = TRUE, CBBonf = FALSE, CBSidak = FALSE,
    logscale = TRUE, alphares = 0.05, col, …)

Arguments

x

a dbkGrad object

plottype

an optional character string. It specifies the type of plot to display and must be one of:

• "observed" to plot observed values;

• "fitted" to plot fitted values;

• "obsfit" to plot observed and fitted values (default);

• "exposure" to plot the exposed to the risk of death;

• "residuals" to display plots related to residuals: density of residuals, residuals versus fitted values, and residuals versus the discrete variable of interest;

• "checksd" to plot autocorrelogram and autodependogram (see Bagnato, Punzo, Nicolis, 2012) of residuals, only for the unidimensional case.

plotstyle

an optional character string. It specifies the style of plot; it has no effect when plottype=checksd. It must be:

• "mat" for a matplot (default for the unidimensional case);

• "level" for a levelplot (default for the bidimensional case);

• "persp" for a perspective plot.

restype

an optional character string.When plottype=residuals or plottype=checksd, it specifies the type of residuals displayed. It must be:

• "working" to use working residuals: o-f (default);

• "proportional" to use working residuals: o/f-1;

• "response" to use response residuals: e*(o-f);

• "deviance" to use deviance residuals: sign(o-f) * sqrt(2*e*o*log(o/f) + 2*e*(1-o)*log((1-o)/(1-f)));

• "pearson" to use Pearson residuals: e*(o-f)/sqrt(e*f*(1-f)),

where e=exposures, o=observed values and f=fitted values.

rows, columns

an optional numeric vector. It specifies the rows (columns) to plot.

byage

an optional logical. It selects the discrete variable of interest: TRUE (default) for the variable in rows (typically age) and FALSE for the other variable (years or duration).

logscale

an optional logical;when TRUE (default), rates are plotted on log scale.

CI

an optional logical; if TRUE, 1-alpha*100% confidence intervals for the fitted values are displayed in plottype="obsfit" and plottype="fitted". When the alpha argument is not provided in dbkGrad(), 95% pointwise confidence intervals are displayed. Default value is TRUE.

CBBonf

an optional logical; does the same as CI but Bonferroni correction is applied to obtain confidence bands. Default is FALSE.

CBSidak

an optional logical; does the same as CI but Sidak correction is applied to obtain confidence bands. Default is FALSE.

alphares

an optional scalar. When plottype=residuals the boundaries of the (alphares)*100% critical region are displayed. Default value is 0.05.

col

a scalar or a vector with plotting colors.

…

additional arguments to be passed to or from methods.

Value

No values are returned from the plot function.

References

Bagnato L, Punzo A, Nicolis O (2012). The autodependogram: a graphical device to investigate serial dependences. Journal of Time Series Analysis, 33(2), 233-254.

Bagnato L, De Capitani L, Punzo A (2013a). Detecting Serial Dependencies with the Reproducibility Probability Autodependogram. Advances in Statistical Analysis. doi:10.1007/s10182-013-0208-y.

Bagnato L, De Capitani L, Punzo A (2013b). Testing Serial Independence via Density-Based Measures of Divergence. Methodology and Computing in Applied Probability. doi:10.1007/s11009-013-9320-4.

Mazza A, Punzo A (2014) DBKGrad: An R Package for Mortality Rates Graduation by Discrete Beta Kernel Techniques. Journal of Statistical Software, Code Snippets, 572, 1-18.

See Also

DBKGrad-package, dbkGrad, ItalyM, TSA:acf, SDD:ADF

Examples

# NOT RUN {
data("ItalyM")

# unidimensional analysis

res1 <- dbkGrad(obsq=obsq, limx=c(6,71), limy=104, exposure=population, bwtypex="EX", adaptx="ab")
plot(res1, plottype="obsfit", CI=FALSE, CBBonf=TRUE)
plot(res1, plottype="residuals", restype="pearson")
plot(res1, plottype="checksd", restype="pearson")
residuals(res1, type="pearson")

# bidimensional analysis

res2 <- dbkGrad(obsq=obsq, limx=c(6,46), limy=c(60,80), exposure=population, 
transformation="logit", bwtypex="VC", bwtypey="EX", hx=0.01, hy=0.008, adaptx="ab", adapty="b")
plot(res2, plottype="obsfit")
plot(res2, plottype="obsfit", plotstyle="persp", col="black")


# }