crplot {PSEA} | R Documentation |
Component-plus-residual (CR) plot for quantitative variables and group-specific effects.
crplot(lm,quantv,g=NULL,newplot=TRUE,col=c(1,2,4),xlab=NULL,ylab='CR',...)
lm |
object of class "lm". Fitted model. |
quantv |
character. Name of the quantitative independent variable ("component" to be plotted). |
g |
character vector. Interaction regressors coding for group-specific effects in the model. |
newplot |
logical. If TRUE (default) a new plot (graphics device) is opened. |
col |
integer vector. Colors of groups. Defaults to 1 (black), 2 (red) and 4 (blue) for group 1, 2 and 3, respectively. |
xlab |
character. x-axis label. Absent by default. |
ylab |
character. y-axis label. "CR" by default. |
... |
Further arguments passed to plot() |
In the fitted model (lm), group-specific effects are specified by interaction regressors. In this case, an interaction regressor is a quantitative variable multiplied by a binary variable (i.e. where 0s represent samples of group 1 and 1s represent samples of group 2).
Predicted components are not centered and the intercept of the CR is 0 by definition. This function thus differs from cr.plot in the car package.
NULL |
This function is used for plotting. |
Alexandre Kuhn alexandre.m.kuhn@gmail.com
Kuhn A, Thu D, Waldvogel HJ, Faull RL, Luthi-Carter R. Population-specific expression analysis (PSEA) reveals molecular changes in diseased brain. Nat Methods 2011, 8(11):945-7
## Load example expression data (variable "expression") ## for 23 transcripts and 41 samples, and associated ## phenotype (i.e. group) information (variable "groups") data("example") ## The group data is encoded as a binary vector where ## 0s represent control samples (first 29 samples) and ## 1s represent disease samples (last 12 samples) groups ## Neuronal reference signals (i.e. quantitative variable) ## and group-specific change in neuronal expression ## (i.e. interaction regressor) neuron_probesets <- list(c("221805_at", "221801_x_at", "221916_at"), "201313_at", "210040_at", "205737_at", "210432_s_at") neuron_reference <- marker(expression, neuron_probesets) neuron_difference <- groups * neuron_reference ## Fit an expression model containing neuronal expression and ## neuron-specific change in expression between control and ## disease samples model <- lm(expression["202429_s_at",] ~ neuron_reference + neuron_difference) ## Visualize the dependence on the neuronal reference signal and ## the group-specific effect (decreased neuronal expression in ## disease samples). Black and red dots represent control and ## disease samples, respectively. crplot(model, "neuron_reference", g="neuron_difference")