numeric: h parameter
(window size) in call to
locfit. The default value is
set to three hours assuming x given in seconds.
You can detect a better bandwidth by calling
bandwidthCV
locfit.deg
numeric: deg parameter
(polynomials degree) in call to
locfit
relative.height.at.lag
Parameter used by
guessCellGrowthParams
Details
For the non-parametric "locfit" model, local regression
is done by a call to locfit.
The returned maximum growth rate values the maximum value
of the fitted derivative over the data points. For the
parametric models "logistic", "gompertz", "rosso" and
"baranyi", the function does a non-least square fit by
calling nls. Initial parameters values are
generated by guessCellGrowthParams. The
returned maximum growth rate values the mu
parameter of these models.
Value
Fit as returned by locfit
for the "locfit" model and as returned by
nls for the "logistic", "gompertz", "rosso"
and "baranyi" models. The returned value also has an
attribute maxGrowthRate valueing the inferred
maximum growth rate as well as an attribute
pointOfMaxGrowthRate valuing the datapoint at
which the growth rate is maximal. Also, it has an
attribute max valuing the inferred maximum among
the time points as well as pointOfMax valuing the
datapoint of max fitted value. It gets the additional
class cellCurveFit assigned.
x = 1:1000
z = gompertz(x, mu=0.01, l=200, z0=1, zmax=5) + rnorm(length(x),sd=0.1)
f = fitCellGrowth(x, z, model = "gompertz")
floc = fitCellGrowth(x, z, model = "locfit", locfit.h=500)
plot(x,z, main="simulated data\nGompertz model")
lines(x, predict(f,x), lwd=2, col="red")
lines(x, predict(floc,x), lwd=2, col="blue")
legend( "right", legend=c("gompertz fit", "locfit"), lwd=1, col=c("red","blue") )
Results
R version 3.3.1 (2016-06-21) -- "Bug in Your Hair"
Copyright (C) 2016 The R Foundation for Statistical Computing
Platform: x86_64-pc-linux-gnu (64-bit)
R is free software and comes with ABSOLUTELY NO WARRANTY.
You are welcome to redistribute it under certain conditions.
Type 'license()' or 'licence()' for distribution details.
R is a collaborative project with many contributors.
Type 'contributors()' for more information and
'citation()' on how to cite R or R packages in publications.
Type 'demo()' for some demos, 'help()' for on-line help, or
'help.start()' for an HTML browser interface to help.
Type 'q()' to quit R.
> library(cellGrowth)
Loading required package: locfit
locfit 1.5-9.1 2013-03-22
> png(filename="/home/ddbj/snapshot/RGM3/R_BC/result/cellGrowth/fitCellGrowth.Rd_%03d_medium.png", width=480, height=480)
> ### Name: fitCellGrowth
> ### Title: Fit growth curves
> ### Aliases: fitCellGrowth
>
> ### ** Examples
>
> x = 1:1000
> z = gompertz(x, mu=0.01, l=200, z0=1, zmax=5) + rnorm(length(x),sd=0.1)
> f = fitCellGrowth(x, z, model = "gompertz")
> floc = fitCellGrowth(x, z, model = "locfit", locfit.h=500)
> plot(x,z, main="simulated data\nGompertz model")
> lines(x, predict(f,x), lwd=2, col="red")
> lines(x, predict(floc,x), lwd=2, col="blue")
> legend( "right", legend=c("gompertz fit", "locfit"), lwd=1, col=c("red","blue") )
>
>
>
>
>
> dev.off()
null device
1
>