search for: carrieandstat

Hi, dear R-helpers, I have a simple question regarding selecting subset of a variable based on another variable. Here is the example: xx=rnorm(10) id=sample(1:10, 10) temp=c(6, 1, 8, 2) Now, all I want is xx's that their id are 6, 1, 8, 2, instead of the position. Any suggestions ? Thank you all your help !! Carrie [[alternative HTML version deleted]]

Hello, everyone, I have a question about integration of product of two densities. Here is the sample code; however the mean of first density is a function of another random variable, which is to be integrated. ## f=function(x) {dmvnorm(c(0.6, 0.8), mean=c(0.75, 0.75/x))*dnorm(x, mean=0.6, sd=0.15)} integrate(f, lower=-Inf, upper=Inf) ## error message Error in dmvnorm(c(0.6, 0.8), mean = c(0.75,

Hello everyone, I have a question about integration of two density function Intuitively, I think the value after integration should be 1, but they are not. Am I missing something here ? > t=function(y){dnorm(y, mean=3)*dnorm(y/2, mean=1.5)} > integrate(t, -Inf, Inf) 0.3568248 with absolute error < 4.9e-06 Also, is there any R function or package could do multivariate integration ?

Hello R-helpers, I have a question about counting numbers. Here is a simple example. a=c(2, 3, 3,4) > table(a) a 2 3 4 1 2 1 so, I can to create another variables that has the corresponding counting numbers. In this case, I want to have: b=c(1,2,2,1) Is there any way coding for this ? Thanks for helps! Carrie-- [[alternative HTML version deleted]]

Hi everyone, I am confused regarding the function "density". suppose that there is a sample x of 100 data points, and plot(density(x)) gives it's pdf ? or it's more like histogram only ? thanks for any answering Carrie [[alternative HTML version deleted]]

Dear R-helpers, I am using the package "gee" to run a marginal model. Here is the output. In my simulated data, both x and z are time-varying, so I include their interaction terms with time indicator (i.e. tind=0, if time 1, and 1 if time 2) The data is simulated, so the true parameter of z both at time 1 and time 2 is 5, which is very close from the model output for time 1, z =

Dear R-helpers , I have a simple loop as follows, however, to be more efficient, I would like to use any apply functions (tapply, I suppose) But how can I do this ? I am not very clear about this. # Z is a P * Q matrix # so for each row of Z, I would like to pull out only some of the elements, and save as a separate matrix under a list # index is a vector with length smaller than Q, but the

Dear r-helpers, I have a small dataset (n<50), and I want to compute the Hodges Lehmann exact confidence interval. So far, I know that "pairwiseCI" has the function "HL.diff". The description is as follows : HL.diff calculates the Hodges-Lehmann confidence interval for the difference of locations by calling wilcox.exact in package exactRankTests ; But when I check

Dear R-helpers, I would like to generate a binary random variable within a stratum's stratum. Here is a simple example. ## x is the first level strata index, here I have 3 strata. x=c(rep(1,5), rep(2,5), rep(3,5)) ## within x, there is a second strata indexed by t=0 and t=1 t=rep(c(0,0,1,1,1),3) ## and within strata i and t=0 and t=1, I generate the random binomial variable respectively,

Hi, all I am doing a optimization problem using nlminb. It seems to me that the result is kind of sensitive to the starting value. (It happened that the resulting parameter doesn't change from the starting value.) Any suggestions on giving the starting value ? or any other function that can do optimization but not being sensitive to the initial guess ? Thanks for any helps. Carrie

Hi, R-helpers, I am working on a problem of measurement error modeling. (I am new to this filed) The model I am dealing with is simple. Consider a linear regression y= beta0 + beta1 * x + error, in which x is measured with errors. (the variance of errors are known. ) I looked up the package simex, and the method is simulation-extrapolation estimation. So I was wondering that if there is any

Dear r-help group, I am creating a package that has some FORTRAN code under windows. I have read through "Writing R Extension" but still not so clear about the steps. Before R CMD build, how can I create a dynamic library and later in my R function using dyn.load ("xxx.dll") ? If I already have a .dll file, can I build the package with the dll file directly ? Does any one

Dear R-helpers, I would like to generate a variable that takes 0 or 1, and each subject has different probabilities of taking the draw. So, which of the following code I should use ? suppose there are 5 subjects, and their probabilities of this Bernoulli variable is p=c(0.2, 0.9, 0.15, 0.8, 0.75) n<-5 Ber.var <- rbimon(n,1,p) ## I doubt if this will take the first probability, which is

Dear R-helpers, I have a question about giving index. Suppose that I have a vector say, id=1:5, and each of them have some given index but some of them may share the same index Now, I have another vector, and I want to give it a index based what just defined. # 5 subjects test1=1:5 # corresponding index, so here, subject 2 and subject 4 share the common index "1" index=c(3,1,2,1,4) #

Hi all, I have some questions about the predicted HR in coxph function including psline covariate. If just fitting covariate as linear form, by default, the reference value for each of predictions type (linear predictor, risk and terms) is the mean covariate within strata. If the psline is specified for the covariate, what's the reference value for the predictions? I did some test code

Hello R helpers, I have a quick question about loop and next In my loop, I have some random generation of data, but if the data doesn't meet some condition, then I want it to go next, and generate data again for next round. # just an example.. # i want to generate the data again, if the sum is smaller than 25 temp=rep(NA, 10) for(i in 1:10) { dt=sum(rbinom(10, 5, 0.5)) while (dt<25) next