similar to: MICE passive imputation formula

Hi all, I have a question and I do not know If I am at the right place to ask this question. But is there someone that has the formula of CKD-Epi in code in R? I have tried a lot of loops, but none of the approaches give me the right answer. Is there someone who has this formula coded? Thank you! [[alternative HTML version deleted]]

Often, when exploring a dataset, I'd like to plot several very different Y variables against the same X variable, in panels stacked one over the other. Is there an easy way to do this? I'd like to achieve an elegant look similar to the look achieved by lattice in conditioned plots--for instance no space between panels. But unlike in straightforward conditioned plot, each panel may be on a

Hello. I have run the command imp<-mice(mydata, im=c("","pmm","logreg","logreg"),m=5)  for a variable with no missing data, a numeric one and two variables with binary data. I got the following message: There were 37 warnings (use warnings() to see them) > warnings() Warning messages: 1: In any(predictorMatrix[j, ]) ... : coercing argument of

Dear friends. I wanted to reproduce a sheet of paper useful for plotting the reciprocal of some biochemical variable (creatinine) over time (Bleyer Am J Kidney Dis 34:576-578,1999). Time on X axis with units years and months. On Y axis, 1/creatinine, but with the original creatinine value indicated - to make it easier for people to use it. When using the graph, the linear decrease in 1/crea over

Dear Colleagues   I have the following code that generates a boxplot for one specific labtest:   boxplot.n(LBSTRESN~COHORT, main="Boxplot of laboratory data for XLXXX-XXX test=Creatinine", subset = LBTEST=="Creatinine", xlab = "Cohort Number", ylab = "Units = umol/L", varwidth=TRUE   I would like to know if there is a way to loop through the dataset and

Thank you to Peter Dalgaard, who provided help for some of this solution. It is still not ideal since the dots which are equidistant in the x-direction ideally should respect the reciprocal scale in the y-direction. op <- par("cex"= 0.7) x<-y<-NA plot(x,y,xlim=c(0,10),ylim=1/c(2000,70), axes=F) box() axis(1)

R 2.7.2 PPC Mac OS X 10.4.11 library mice 1.13.1 I try to use mice for multivariate data imputation. My variables are numeric, factors, count data, ordered factors. First I created a vector for the methods to use with each variable ImpMethMice<-c(rep("logreg", 62), rep("polyreg",1), rep("norm",12), rep("polyreg",12)) next step was

All, I've been using "sub" (subtitle) instead of "main" such that captions are below figures produced by xyplot. This works fine and captions are on a single line. However, when I try this for bar plots with error bars (altering the error.bars function form Crawley's The R Book, see below), the captions are split on more than 1 line. Is there a way to get the

I am running the sm.density.compare function amd I am getting the following error:   my code is  > sm.density.compare(LBSTRESN,COHORT,xlab="Units = umol/L"subset = LBTEST=="Creatinine")   Error in if (from == to) rep.int(from, length.out) else as.vector(c(from,  :   missing value where TRUE/FALSE needed   I do not understand the error and I have had no help when searching

Dear friends - We have 25 rats, 14 of these subjected to partial removal of kidney tissue, 11 to sham operation, and then followed for 6 weeks. So far we have data on 26 urine metabolites measured by NMR 7 times during the observation. I have smoothed the measurements by b.splines in fda including a roughness penalty, and inspecting the mean curves for nephrectomized and sham animals indicate

Dear friends. I have a paper (details below) examining the risk of renal failure after an operation. A logistic regression was done, and the coefficients to two regressors (age and creatinine) plus intercept with standard errors are given. These coefficients must be dependent in estimation, and when no details are given, I thought how I could most informatively get an impression as to how

Larry, You found a data set that kills coxph. I'll have to think about what to do since on the one hand it's your own fault for trying to fit a very bad model, and on the other I'd like the routine to give a nice error message before it dies. In the data set you sent me the predictor variable is very skewed: > quantile(anomaly1$CREAT, c(0, .5, .9, .999, 1)) 0% 50%

Hi I am unable to impute using the MICE command in R when imputing a binary variable using linear discriminant analysis. To illustrate my problem I have created a dataset, which consists of 1 continuous and 1 binary variable. The continuous variable is complete and the binary variable is partially observed. I am able to impute using the MICE command where the imputation methods is logistic

Hi, I'm trying to impute a large data set using mice but I keep getting this: Error in nnet.default(X, Y, w, mask = mask, size = 0, skip = TRUE, softmax = TRUE, : too many (2944) weights nnet.default uses the argument MaxNWts to set a maximum number of weights. I've tried to change nnet.default to get around this, but mice is somehow still passing an argument that sets the maximum

I am using -mice- for multiple imputation and would like to use the gelman diagnostic in -coda- to assess the convergence of my imputations. However, gelman.diag requires an mcmc list as input. van Buuren and Groothuis-Oudshoorn (2011) recommend running mice step-by-step to assess convergence (e.g. imp2 <- mice.mids(imp1, maxit = 3, print = FALSE) ) but this creates mids objects. How can I

Hi, I am trying to use mice() with an aov() model.I can fun mice() fine but when I try to pool the results it doesn't work. For example, I can run the following: fit=with(data=imp,exp=aov(Y~B*P*T + Error(S/(B*P*T)))) pool(fit) # doesn't work Where B, P, and T are within subject (S) factors. However, I can't go the next step to pool these results as I am guessing this hasn't been

# HG changeset patch # User Olaf Hering <olaf@aepfle.de> # Date 1316530721 -7200 # Node ID 56c7b8e10d3ba46e34d7a1be3b708da6f999b1a0 # Parent f4f25124b1b6d926b6e19a499bf4a3fdc97f0157 linux-2.6.18/Input: mousedev - handle mice that use absolute coordinates After commit 1083:211849d9d511 the mouse multiplexer /dev/input/mice does not receive updates because the base kernel lacks a change from

Dear all, I am trying to impute data for a range of variables in my data set, of which unfortunately most variables have missing values, and some have quite a few. So I set up the predictor matrix to exclude certain variables (setting the relevant elements to zero) and then I run the imputation. This works fine if I use predictive mean matching for the continous variables in the data set. When I

Hi all, How can I calculate the mean from several imputed data sets with the package mice? I know you can estimate regression parameters with, for example, lm and subsequently pool those parameters to get a point estimate using functions included in mice. But if I want to calculate the mean value of a variable over my multiple imputed data sets with fit <- with(data=imp, expr=mean(y)) and

Dear R-users, Version V2.0 of the package mice is now available on CRAN for Windows, Linux and Apple users. Multivariate Imputation by Chained Equations (MICE) is the name of software for imputing incomplete multivariate data by Fully Conditional Specifcation (FCS). MICE V1.0 appeared in the year 2000 as an S-PLUS library, and in 2001 as an R package. MICE V1.0 introduced predictor selection,