Quantcast

logistic growth model

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

logistic growth model

magushi
I want to Fit a logistic growth model for
y = k *eb0+b1(age)/1 + eb0+b1(age), can some one help on how to get the
initial coefficients b0 and b1? I need to estimate in order to do the
regression analysis. When I run using b0=0.5 and b1=3.4818, I get the
following error

397443.8 :  0.5 3.4818
Error in nls(Height ~ k * exp(b1 + b2 * Age)/(1 + exp(b1 + b2 * Age)),  :
   singular gradient
"please tell me what is wrong with my initials values, and how to get
the initial values"

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: logistic growth model

Rubén Roa

Write the growth formula in an R script.
Define initial par values.
Input the size and age data.
Plot the size and age data as points.
Plot the growth model with the initial par values as a line.
Play with the initial par values until you see a good agreement between the model (the line) and the data (the points).
Optimise.
Re-plot.
Plot a residual histogram.
Plot a residual scatterplot.
Plot a Q-Q residual plot.

HTH

Rubén
____________________________________________________________________________________

Dr. Rubén Roa-Ureta
AZTI - Tecnalia / Marine Research Unit
Txatxarramendi Ugartea z/g
48395 Sukarrieta (Bizkaia)
SPAIN



> -----Mensaje original-----
> De: [hidden email]
> [mailto:[hidden email]] En nombre de Renalda
> Enviado el: sábado, 04 de junio de 2011 6:17
> Para: [hidden email]
> Asunto: [R] logistic growth model
>
> I want to Fit a logistic growth model for y = k
> *eb0+b1(age)/1 + eb0+b1(age), can some one help on how to get
> the initial coefficients b0 and b1? I need to estimate in
> order to do the regression analysis. When I run using b0=0.5
> and b1=3.4818, I get the following error
>
> 397443.8 :  0.5 3.4818
> Error in nls(Height ~ k * exp(b1 + b2 * Age)/(1 + exp(b1 + b2
> * Age)),  :
>    singular gradient
> "please tell me what is wrong with my initials values, and
> how to get the initial values"
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: logistic growth model

Walmes Zeviani-3
If you use RStudio (www.rstudio.org) you can find good initial start values
by interactive plot using manipulate() function. Look the simple code below.

age <- 1:20
k <- 3; b0 <- -5; b1 <- .5
y <-  k*exp(b0+b1*age)/(1+exp(b0+b1*age))+rnorm(age,0,0.1)
plot(y~age)
start <- list()

require(manipulate)
manipulate(
           {
             plot(y~age)
             k <- kk; b0 <- b00; b1 <- b10
             curve(k*exp(b0+b1*x)/(1+exp(b0+b1*x)), add=TRUE)
             start <<- list(k=k, b0=b0, b1=b1)
           },
           kk=slider(0,5,step=0.1,initial=2.7),
           b00=slider(-5,0,step=0.1,initial=-2.5),
           b10=slider(0,1,step=0.1,initial=0.5))

start

n0 <- nls(y~k*exp(b0+b1*age)/(1+exp(b0+b1*age)), start=start)
summary(n0)

If you don't use RStudio you can follow the procedures in this blog (that
uses gWidgetsRGtk2).

http://ridiculas.wordpress.com/2011/04/09/metodo-grafico-interativo-para-valores-iniciais-em-regressao-nao-linear/

Bests.
Walmes.

==========================================================================
Walmes Marques Zeviani
LEG (Laboratório de Estatística e Geoinformação, 25.450418 S, 49.231759 W)
Departamento de Estatística - Universidade Federal do Paraná
fone: (+55) 41 3361 3573
VoIP: (3361 3600) 1053 1173
e-mail: [hidden email]
twitter: @walmeszeviani
homepage: http://www.leg.ufpr.br/~walmes
linux user number: 531218
==========================================================================


On Mon, Jun 6, 2011 at 4:20 AM, Rubén Roa <[hidden email]> wrote:

>
> Write the growth formula in an R script.
> Define initial par values.
> Input the size and age data.
> Plot the size and age data as points.
> Plot the growth model with the initial par values as a line.
> Play with the initial par values until you see a good agreement between the
> model (the line) and the data (the points).
> Optimise.
> Re-plot.
> Plot a residual histogram.
> Plot a residual scatterplot.
> Plot a Q-Q residual plot.
>
> HTH
>
> Rubén
>
> ____________________________________________________________________________________
>
> Dr. Rubén Roa-Ureta
> AZTI - Tecnalia / Marine Research Unit
> Txatxarramendi Ugartea z/g
> 48395 Sukarrieta (Bizkaia)
> SPAIN
>
>
>
> > -----Mensaje original-----
> > De: [hidden email]
> > [mailto:[hidden email]] En nombre de Renalda
> > Enviado el: sábado, 04 de junio de 2011 6:17
> > Para: [hidden email]
> > Asunto: [R] logistic growth model
> >
> > I want to Fit a logistic growth model for y = k
> > *eb0+b1(age)/1 + eb0+b1(age), can some one help on how to get
> > the initial coefficients b0 and b1? I need to estimate in
> > order to do the regression analysis. When I run using b0=0.5
> > and b1=3.4818, I get the following error
> >
> > 397443.8 :  0.5 3.4818
> > Error in nls(Height ~ k * exp(b1 + b2 * Age)/(1 + exp(b1 + b2
> > * Age)),  :
> >    singular gradient
> > "please tell me what is wrong with my initials values, and
> > how to get the initial values"
> >
> > ______________________________________________
> > [hidden email] mailing list
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> > http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
> >
>
> ______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
        [[alternative HTML version deleted]]


______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: logistic growth model

subhrodip
This post has NOT been accepted by the mailing list yet.
In reply to this post by magushi
Is the data self generated? NLS relies on a glm algo that throws error if the errors were not sufficiently random.
Loading...