Displaying 3 results from an estimated 3 matches for "typetissue".
2009 Nov 12
0
writing selfStart models that can deal with treatment effects
...test for these treatment effects (they are quite
heterogenous), but when I try using the standard syntax for nls(), the
selfStart model only estimates a set of global values and these don't work
with nls()
> getInitial(Count ~ SSexpDecayAndConstantInflow(B0, Time, aL[Type], aN[Type],
T0[TypeTissue]), data = tissueData)
aL[Type] aN[Type] T0[TypeTissue]
4.600144e-02 1.000000e-04 1.082172e+03
> nls(Count ~ SSexpDecayAndConstantInflow(B0, Time, aL[Type], aN[Type],
T0[TypeTissue]), data = tissueData)
Error in numericDeriv(form[[3L]], names(ind), env) :
Missing value or...
2009 Oct 15
0
Setting random effects within a category using nlme
...d aL are from the same population, independent
of Type. I believe that this is doing what I want,
------------------------------------------
model1 = nlme(Count ~ quad.PBMC.model(aL, aN, T0),
data = tissueData,
start = list( fixed = c(rep(1000, 8), -2, -2) ),
fixed = list(T0 ~ TypeTissue-1, aL ~ 1, aN ~ 1),
random = aL + aN ~ 1|Tissue
)
Nonlinear mixed-effects model fit by maximum likelihood
Model: Count ~ quad.PBMC.model(aL, aN, T0)
Data: tissueData
Log-likelihood: -669.9258
Fixed: list(T0 ~ TypeTissue - 1, aL ~ 1, aN ~ 1)
T0.TypeTissueMemory/CLN T0....
2009 Oct 15
2
Proper syntax for using varConstPower in nlme
...ects models. Based on
this, I've tried using the syntax,
---------------------------------------------
> nlme(Count ~ quad.PBMC.model(aL, aN, T0),
+ data = tissueData,
+ weights = varConstPower(form =~ Count),
+ start = list( fixed = c(rep(1000, 8), -2, -2) ),
+ fixed = list(T0 ~ TypeTissue-1, aL ~ 1, aN ~ 1),
+ random = aL + aN ~ 1|Tissue
+ )
Error in MEestimate(nlmeSt, grpShrunk) :
Singularity in backsolve at level 0, block 1
>
>
---------------------------------------------
The above command clearly this doesn't work, but if I comment out the "weights
= ...&q...