search for: crp

Dear All, I faced the following problem. With the same data.frame the results are different under Linux and Windows. Could you help on this topic? Thanks in advance, Ildiko Linux: > d = read.csv("CRP.csv") > d$drugCode = as.numeric(d$drug) > cor(d, use="pairwise.complete.obs") PATIENT BL.CRP X24HR.CRP X48HR.CRP drug drugCode PATIENT NA NA NA NA NA NA BL.CRP NA 1.0000000 0.84324880 -0.05699590 NA -...

....packages("DMwR") library(robustbase) library(MASS) library(quantreg) library(RobPer) library(hbrfit) library("devtools") library("DMwR") bmi=c(23,43,12,1,23,4,3,4,5,5,6,5,5,34,67,87,32,12,23,19) glucose=c(98,34,21,13,2,43,16,43,28,93,11,14,16,43,23,65,42,16,54,32) crp=c(56,34,42,32,1,2,54,47,67,65,38,95,45,76,67,87,35,41,34,54) newdata=data.frame(bmi,glucose,crp) ? reg1 <- lm( crp ~ bmi+glucose,data=newdata) DMwR::regr.eval(newdata$crp,reg1$fitted.values) reg <- lmrob( crp ~ bmi+glucose,data=newdata) DMwR::regr.eval(newdata$crp,reg$fitted.values) Huber &...

Dear R-experts, I am trying to bootstrap (and average) the median squared error evaluation metric for a robust regression. I can't get it. What is going wrong ? Here is the reproducible example. ############################# install.packages( "quantreg" ) library(quantreg) crp <-c(12,14,13,24,25,34,45,56,25,34,47,44,35,24,53,44,55,46,36,67) bmi <-c(34,32,12,76,54,34,21,18,92,32,11,13,45,46,56,57,67,87,12,13) glucose <-c(23,54,11,12,13,21,32,12,45,54,65,87,21,23,12,12,23,23,43,54) # Create a list to store the results lst<-list() # Numbers of bootstrap sample...

...> > If you want to bootstrap a statistic, I suggest you use base package boot. > You would need the data in a data.frame, see how you could do it. > > > library(boot) > > bootMedianSE <- function(data, indices){ > ??? d <- data[indices, ] > ??? fit <- rq(crp ~ bmi + glucose, tau = 0.5, data = d) > ??? ypred <- predict(fit) > ??? y <- d$crp > ??? median(y - ypred)^2 > } > > dat <- data.frame(crp, bmi, glucose) > nboot <- 100 > > medse <- boot(dat, bootMedianSE, R = nboot) > > medse$t0 > mean(medse...

Hello, If you want to bootstrap a statistic, I suggest you use base package boot. You would need the data in a data.frame, see how you could do it. library(boot) bootMedianSE <- function(data, indices){ d <- data[indices, ] fit <- rq(crp ~ bmi + glucose, tau = 0.5, data = d) ypred <- predict(fit) y <- d$crp median(y - ypred)^2 } dat <- data.frame(crp, bmi, glucose) nboot <- 100 medse <- boot(dat, bootMedianSE, R = nboot) medse$t0 mean(medse$t) # This is the value you want Hope this helps, Rui...

...a, x3b, xm, 100), range(-100,y1a, y1b, y3a, y3b, ym, 100)) ln1 <- psp(x1a, y1a, x1b, y1b, window = win) ln3 <- psp(x3a, y3a, x3b, y3b, window = win) ? ppt <- crossing.psp(ln1, ln3) ? # find the radius of the second circle that has center at (ppt$x, ppt$y) and goes through B and H r.crp <- sqrt((pt2$x-ppt$x)^2 + (pt2$y-ppt$y)^2) r1.crp <- sqrt((xy$x[i]-ppt$x)^2 + (xy$y[i]-ppt$y)^2) ? # r.crp should be equal with r1.crp ? but there are some very little difference? but not enough in my opinion that the second circle not go through points H and B. > r.crp==r1.crp [1] FA...

Hello, Right! I copied from the OP's question without thinking about it. Corrected would be bootMedianSE <- function(data, indices){ d <- data[indices, ] fit <- rq(crp ~ bmi + glucose, tau = 0.5, data = d) ypred <- predict(fit) y <- d$crp median((y - ypred)^2) } Sorry, rui Barradas On 5/22/2018 11:32 AM, Daniel Nordlund wrote: > On 5/22/2018 2:32 AM, Rui Barradas wrote: >> bootMedianSE <- function(data, indices){ >> ?????...

...use I?m using longitudinal data? Even more. Is it possible to colour each one of the 15 lines with a different colour? library(ggplot2) library(reshape) library(lattice) library(gtable) library(grid) attach(mtcars) beta0 = rnorm (15, 1, .5) beta1 = rnorm (15, -1, .5) tempo = seq(1:5) CRP7raw = matrix(NA, 15, 5) CRP7 = matrix(NA, 15, 5) CRP98raw = matrix(NA, 15, 5) CRP98 = matrix(NA, 15, 5) crp <- for (i in 1:15) { CRP7raw[i,] = beta0[i] + beta1[i] * tempo CRP7[i,] = CRP7raw[i,] + rnorm(5, 0, 2.14) CRP98raw[i,] = beta0[i] + beta1[i] * tempo CRP98[i,] = CRP98ra...

On 5/22/2018 2:32 AM, Rui Barradas wrote: > bootMedianSE <- function(data, indices){ > ???? d <- data[indices, ] > ???? fit <- rq(crp ~ bmi + glucose, tau = 0.5, data = d) > ???? ypred <- predict(fit) > ???? y <- d$crp > ???? median(y - ypred)^2 > } since the OP is looking for the "median squared error", shouldn't the final line of the function be median((y - ypred)^2) Dan -- Dan...

Dear friends. I appreciate the help that plot.date is not yet fully developed but beautiful and efficient as is anyway. I attach again an example from a real patient and now the problem is how to represent a chemical C-reactive protein (CRP) on the plot together with concentration of vancomycin. CRP was 25-200 and vancomycin below about 20. I only could get it about right by dividing CRP by 10 and the plot is informative as is - but how could I make an axis for the CRP ? I've tried taking all axes away (but dates are not taken...

...) at /usr/src/sys/i386/i386/support.s:498 #8 0xc1f7267e in ?? () #9 0x8fb82d87 in ?? () #10 0x361fe9de in ?? () #11 0x39402686 in ?? () #12 0x00000fa0 in ?? () #13 0xc29cf380 in ?? () #14 0xc2ea9654 in ?? () #15 0x00000000 in ?? () #16 0xd61a095c in ?? () #17 0xc0700746 in crypto_invoke (cap=0x8, crp=0xd61a0950, hint=-1616994916) at cryptodev_if.h:53 Previous frame inner to this frame (corrupt stack?) (kgdb) ------------- Thansk, regards.

> Hi Rosa > something like > plot(1,1, sub=expression(lambda^"2")) > So with your example, do you want something like > plot(c(1:5), CRP7raw[1,], type = "n", xlim=c(1,5), ylim=c(-10,5) , > xlab="Day in ICU", > ylab="CRP (mg/dL)", > sub = mtext(expression(lambda^2))) OOps! Either plot( ..., sub = *) or plot( ... ) ; mtext(*) but not both! > CRP7graph <- ap...

...:19.90: [13507]: DELAY 70 ms Nov 05 11:10:19.97: [13507]: <-- [9:AT+FTH=3\r] Nov 05 11:10:20.02: [13507]: --> [7:CONNECT] Nov 05 11:10:20.02: [13507]: <-- data [3] Nov 05 11:10:20.02: [13507]: <-- data [2] Nov 05 11:10:21.33: [13507]: --> [2:OK] Nov 05 11:10:21.33: [13507]: SEND send CRP (command repeat) Nov 05 11:10:21.34: [13507]: <-- [9:AT+FRH=3\r] Nov 05 11:10:21.65: [13507]: --> [7:CONNECT] Nov 05 11:10:26.26: [13507]: --> [2:OK] Nov 05 11:10:26.26: [13507]: HDLC frame too short (0 bytes) Nov 05 11:10:26.26: [13507]: DELAY 70 ms Nov 05 11:10:26.33: [13507]: <-- [9:...

Hi Rosa something like plot(1,1, sub=expression(lambda^"2")) So with your example, do you want something like plot(c(1:5), CRP7raw[1,], type = "n", xlim=c(1,5), ylim=c(-10,5) , xlab="Day in ICU", ylab="CRP (mg/dL)", sub = mtext(expression(lambda^2))) CRP7graph <- apply(CRP7, 1, lines, col="gray") Cheers Petr > -----Original Message----- > From: R-help...

...h different colours >> >> >> > Hi Rosa > something like >> >> > plot(1,1, sub=expression(lambda^"2")) >> >> > So with your example, do you want something like >> >> > plot(c(1:5), CRP7raw[1,], type = "n", xlim=c(1,5), >> ylim=c(-10,5) , > xlab="Day in ICU", > ylab="CRP >> (mg/dL)", > sub = mtext(expression(lambda^2))) >> >> OOps! Either plot( ..., sub = *) or plot( ... ) ; >> mtext(*)...

I try to use ColorRamp as ColorRampPalette (i.e. with the same gradient), but it seems there is a nuance that I've missed. pal.crp<-colorRampPalette( c("blue", "white", "red"), space = "rgb") plot(rep(0,40),pch=16,col=pal.crp(40)) # is great But, using the same gradient with colorRamp is giving erratic colors. pal.cr<-colorRamp( c("blue", "white", "red&qu...

...s and y-axis and > colour different subjects in longitudinal data with different colours > > > > Hi Rosa > > something like > > > plot(1,1, sub=expression(lambda^"2")) > > > So with your example, do you want something like > > > plot(c(1:5), CRP7raw[1,], type = "n", xlim=c(1,5), ylim=c(-10,5) , > > xlab="Day in ICU", > > ylab="CRP (mg/dL)", > > sub = mtext(expression(lambda^2))) > > OOps! Either plot( ..., sub = *) > or plot( ... ) ; mtext(*) > &gt...

Hi, My initial setup for receiving faxes worked as follows: fax call arrives on ISDN BRI connected to a BOSCH PBX, signal sent to ALCATEL PBX via PRI QSIG then finally sent to ASTERISK via PRI EUROISDN. The Asterisk server then forwarded the call to a iaxmodem and HylaFax received the data. All worked fine. Now I got rid of both BOSCH and ALCATEL in the "fax path" and it's as

Hi, everyone, Before everything, thanks. Lots of thanks ;)!!!! I don?t think you understood everything I need to do. I want to write t_i instead of "Day in ICU? [i subscript for t] and y_ij instead of "CRP (mg/dL)? [ij superscript for y]. The label of the axis? :( Can you help me on that task? Thanks!!!!! Best, Rosa Oliveira > On 31 Jul 2017, at 10:28, Martin Maechler <maechler at stat.math.ethz.ch> wrote: > >>>>>> PIKAL Petr <petr.pikal at precheza.cz <ma...

...y suggested plot(c(1:5), type = "n", xlab=expression("t"[i]), ylab=expression("y"^ij)) mtext(expression(lambda^2)) which by my humble opinion is precisely what you wanted. I want to write t_i instead of "Day in ICU? [i subscript for t] and y_ij instead of "CRP (mg/dL)? [ij superscript for y]. If it is not you need to express yourself more clearly. My crystal ball is broken. Cheers Petr On 31 Jul 2017, at 13:44, PIKAL Petr <petr.pikal at precheza.cz<mailto:petr.pikal at precheza.cz>> wrote: Hi From: Rosa Oliveira [mailto:rosita21 at gmai...