[R] Plotting observed vs. Predicted values, change of symbols

[David Winsemius]

On Nov 29, 2009, at 8:51 AM, oscar linares wrote:

> Dear Wiz[R]ds,
>
> I am deeply grateful for the help from Duncan Murdoch, Gray Calhoun,  
> and
> others. We are almost there. For whatever reason, I can't change the  
> symbol
> from a circle to a triangle in the upright posture plots.

> Any ideas? I have
> included the problem in full.
>
> # tritiated (3H)-Norepinephrine(NE) disappearance from plasma
> # concentrations supine and upright
> # supine
> datasu <- data.frame(
> time=c(0,1,2,4,6,8,10,15,20),
> concsu=c(385.61,265.88,173.87,99.47,66.7,55.27,48.29,39.85,40.66)
> )
> # upright
> dataup <- data.frame(
> time=c(0,1,2,4,6,8,10,15,20),
> concup=c(767.27,529.03,328.13,225.94,164,151.1,132.02,121.15,70.88)
> )
>
> # fit supine
> wt.su<- function(resp, time,A1,a1,A2,a2)
> {
>    pred <- A1*exp(-a1*time)+A2*exp(-a2*time)
>    (resp - pred) / sqrt(pred)
> }
>
> fit.wt.su <- nls( ~ wt.su(concsu, time,A1,a1,A2,a2), data=datasu,
>              start=list(A1=500,a1=1,A2=100,a2=0.2),
>              trace = TRUE)
>
> summary(fit.wt.su)
>
> # fit upright
> wt.up<- function(resp, time,B1,b1,B2,b2)
> {
>    pred <- B1*exp(-b1*time)+B2*exp(-b2*time)
>    (resp - pred) / sqrt(pred)
> }
>
> fit.wt.up <- nls( ~ wt.up(concup, time,B1,b1,B2,b2), data=dataup,
>              start=list(B1=500,b1=1,B2=100,b2=0.1),
>              trace = TRUE)
>
> summary(fit.wt.up)
>
> # Function that returns predicted values and graphics
> # by Duncan Murdoch
>
> predictionssu <- function(fit, time) {
>  params <- summary(fit)$coefficients[, 1]
>  A1 <- params["A1"]
>  a1 <- params["a1"]
>  A2 <- params["A2"]
>  a2 <- params["a2"]
>
>  A1*exp(-a1*time)+A2*exp(-a2*time)
> }
>
> predictionsup <- function(fit, time) {
>  params <- summary(fit)$coefficients[, 1]
>  B1 <- params["B1"]
>  b1 <- params["b1"]
>  B2 <- params["B2"]
>  b2 <- params["b2"]
>
>  B1*exp(-b1*time)+B2*exp(-b2*time)
> }
>
> # plot observed and predicted values supine and upright in
> # each plot type (linear and smi-log)
>
> # Need upright in same plots (e.g., dashed line)
> par(cex.lab=1.2,cex.axis=1.3)
>
> par(mfrow=c(2,1))
> plot(c(datasu$concsu, dataup$concup) ~ c(datasu$time, dataup$time),  
> xlab =
> "Time (minutes)",
>     ylab = "3H-NE (dpm/ml)", main="3H-NE Post-infusion Plasma  
> Disappearance
> Curves", ylim=c(0,1000),cex=1.25, pch=16,col=1)
>
> lines(times, predictionssu(fit.wt.su, times))

I don't think this is a complete presentation. My system thinks  
"times" is a function from the chron package, so either you have a  
numeric object named "times" or you are putting in "times" when you  
meant "time". I did try dropping the "s" but still get the same  error:
lines(time, predictionssu(fit.wt.su, time))
Error in -a1 * time : non-numeric argument to binary operator

> lines(times, predictionsup(fit.wt.up, times), lty = "dashed")
>
> plot(c(datasu$concsu, dataup$concup) ~ c(datasu$time, dataup$time),  
> xlab =
> "Time (minutes)",
>     ylab = "3H-NE (dpm/ml)", log = "y", ylim=c(1,1000),cex=1.25,
> pch=16,col=1)
>
> lines(times, predictionssu(fit.wt.su, times))
> lines(times, predictionsup(fit.wt.up, times), lty = "dashed")
>
> Deeply grateful in advance...
> -- 
> Oscar
> Oscar A. Linares, MD
> Translational Medicine Unit
> LaPlaisance Bay, Bolles Harbor
> Monroe, Michigan 48161
>
> Department of Medicine,
> University of Toledo College of Medicine
> Toledo, OH 43606-3390
>
> Department of Internal Medicine,
> The Detroit Medical Center (DMC)
> Harper University Hospital
> Wayne State University School of Medicine
> Detroit, Michigan 48201
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org 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.

David Winsemius, MD
Heritage Laboratories
West Hartford, CT