similar to: Sth better than cycle?

I want to maximize a conditional likelihood function that is basically logistic conditional on the number of successes within strata. What would be a good starting place for this? A complication is that the denominator includes a term that is the sum over all permutations. Although there is no time dimension to the problem, it's possible a degenerate use of the Cox proportional hazards

I think there are some missing words in "R Internals"'s description of the P_ macro. It currently has "A macro as a wrapper for ngettext", which I think ought to be something like "The macro P_ may be used as a wrapper for ngettext". The following patch also makes the 2 alternate definitions of P_ have the same argument names, StringS and StringP. Expanding the

I need to refresh my memory on Probability Theory, especially on conditional probability. In particular, I want to solve the following two problems. Can somebody point me some good books on Probability Theory? Thank you! 1. Z=X+Y, where X and Y are independent random variables and their distributions are known. Now, I want to compute E(X | Z = z). 2.Suppose that I have $I \times J$ random number

Ok, I think my first mail didn't get through so I'll try this again. Please disregard. I'm trying to use subscripts on plot text. The help files say this can be done and give several example. I'm trying to do: P_{2} (for example) and so I tried: text(5,2,expression(P_{2})) which doesn't work. There are no subscript examples. I recall someone telling me that latex-like

Hi, Can Someone inform me how to generate RV's using the below CDF, by inverse technique. Thanks for your help and time. My CDF is as follows \[ F(x)=0 \ \text{if} \ x < 0\]\[ F(x)=\{\frac{x-x_i}{x_{i+1}-x_{i}}*(p_{i+1}-p_{i})\}+p_{i}\ \forall \ x_{i}\leq x < x_{i+1} \] \[ F(x)=1 \ \text{if} \ x > x_{i+1} \] Regards Murthy

Dear all, Attached notunrolled.ll is a module containing reduction kernel. What I'm trying to do is to unroll it in such way, that partial reduction on unrolled iterations would be performed on register, and then stored to memory only once. Currently llvm's unroller together with all standard optimizations produce code, which stores value to memory after every unrolled iteration, which is

I tried to manually assign each of 3 arrays a unique TBAA node. But it does not seem to help: alias analysis still considers arrays as may-alias, which most likely prevents the desired optimization. Below is the sample code with TBAA metadata inserted. Could you please suggest what might be wrong with it? Many thanks, - D. marcusmae at M17xR4:~/forge/llvm$ opt -time-passes -enable-tbaa -tbaa

Hi all, I wanto to run a plot about the levels of a variable parting on an ols regression. The regression in done on the rate of return of the variable. Imagine R_{t}=a+b*R_{t-1} So If P, the "estimated" price would be P_{t}=P_{t-1}*R_{t} Imagine that I obtain lm fitted values and the original R_{t}, R_{t-1} are [1000,1] dimmension... How it is posible to obtain also 1000,1 fitted

I need to split a data frame into 3 columns. The column I want to split contains indices of lag (prefix L1 or L2 and suffix 01, 03, 04), station name (shown in the sample data as capitalized G, P and S) and pollutant name. Names with no ?L? prefix or 01/04 suffix are lag 0. Lag 01 is average of lag 0 and 1, and 04 is average of 0 to 4 days. How can one do that in R? I will ignore the other

Hi I'm starting to use R in windows. I need unzip some files. Each of them are in different folders and subfolders. Names of folders have the same beginning of the name. [example:( ~ / M_ /P_ (...)/ (...)R(...)/*.zip)] I do not know the expression (character) necessary to call this direction and to unzip files are in each subfolder. Thank you. -- View this message in context:

Got this in the log: rsync error: errors with program diagnostics (code 13) at log.c(340) [generator= 3.1.0dev] What could it be? I suspect it's triggered by a timeout or disconnect from the server side but I had never seen it.

Dear rsync people (particularly Wayne), I am finding that the CVS version of rsync hangs during most, but not all, local copies. The problem goes away if I pass --protocol=29, so I'm guessing it is related to the incremental file-list sending. The hanging seems to be timing-dependent. Increasing the verbosity level seems to increase the chance of a hang. If I run rsync repeatedly with the

Dear All Maybe the following is a stupid question. Assume I have 3 coordinate points (not limited to be in 2D or 3D space) a, b, c. It is known that these 3 points will define a plane. The problem is how to get the normal direction that is orthogonal to this plane. Is there an easy way to calculate it using the values of a, b, and c? Thanks for any point or help on this. Fred

Hi, I've tried to follow all helpful tips I've found in the mailing-list and I've applied these two utf-8 patches; http://article.gmane.org/gmane.comp.search.xapian.general/2324 http://article.gmane.org/gmane.comp.search.xapian.general/1927 Now the QueryParser works as I wants it to do, and creates the terms correctly. But sadly I can't find any documents. If I do this; $ quest

This is a follow-up to a question I asked a few years back. We have a pair of computers that share a common home directory (and therefor a common .Renviron) with identical hardware, but very different sets of libraries such that using a "shared" R_LIBS between two computers does not work. They both use this as the default library for user installations:

I am not sure where to begin so I will be as verbose as I can to explain the problem. I have 3 servers. Their specs are: Machine A: Redhat 7.1 kernel 2.4.9-34 openssh 3.1p1-5 Machine B: Redhat 7.3 kernel 2.4.9-31 openssh 3.1p1-5 Machine C: Debian Woody kernel 2.4.18-bf2.4 openssh 3.4p1 rsync 2.5.6 I am running an rsync over ssh from Machine C to Machine B with the following: rsync --verbose

Hi, I wanted to know if there existed an good implementation in R of the following classical subset Integers : $P_{n,m} = {k_1, \ldots, k_m \in \mathbb{N} : k_1 + \ldots + k_m = n }$ for any integers $m < n$. There is an obvious not optimal code which would be to run through $m$ sums and put a boolean condition to report if the integers respect these condition but it would take $m^n$

Dear R Gurus: I read somewhere that functions are considered vectors. Is this true, please? thanks Edna Bell

Hey guys, i want to calculate the continuasly compounded returns for stock prices. Formula for CCR: R_t = ln(P_t/P_{t-1})*100 With R: First i have to modify the vectors, so that they have the same length and we start at the second observation. log(GOOG1[-1]/GOOG1[1:length(GOOG1)-1])*100 That does work with normal vectors. My Questions: 1) I want to use this for stock prices. so i

>From: Jeff Cohen <jeffc at jolt-lang.org> >Date: Tue, 28 Sep 2004 13:05:16 -0700 > >They are part of the Platform SDK from Microsoft, part of Visual Studio. >They correspond to Window system DLLs dbghelp.dll and psapi.dll in Arrrggg, I forget this relation... >\winnt\system32. If you do not have these libs, then you are out of >luck. Mingw should have provided them