search for: l_1

Hi all, I'm new with R (and S), and relatively new to statistics (I'm a computer scientist), so I ask sorry in advance if my question is silly. My problem is this: I have a (sample of a) discrete time stochastic process {X_t} and I want to estimate Pr{ X_t | X_{t-l_1}, X_{t-l_2}, ..., X_{t-l_k} } where l_1, l_2, ..., l_k are some fixed time lags. It will be enough for me to compute #{ X_t=a_t, X_{t-l_1}=a_{t-l_1}, X_{t-l_2}=a_{t-l_2}, ..., X_{t-l_k}=a_{t-l_k} } ---------------------------------------------------------------------------------- #{...

...widening uses more mul.lo.s64, add.s64, and setp.lt.s64 instructions which are more expensive than their 32-bit counterparts. Indeed, the SASS code (disassembly of the actual machine code running on GPUs) of the version with widening looks significantly longer. Without widening (7 instructions): .L_1: /*0048*/ IMUL R2, R0, R0; /*0050*/ IADD R0, R0, 0x1; /*0058*/ ST.E [R4], R2; /*0060*/ ISETP.NE.AND P0, PT, R0, c[0x0][0x140], PT; /*0068*/ IADD R4.CC, R4, 0x4; /*0070...

Hello! In the example below the Reduce() function by default assigns "a" to be the last accumulated value and "b" to be the current value in "x". I could not find this documented anywhere as the default settings for the Reduce() function. Does any sort of documentation for this behavior exist? x <- c(0,0,0,0,0,1,0,0,0,5,0,0,0,7,0,0,0,8,5,10)

Thank you, kcc. I am unsure if I misunderstand your reply. It seems that trace-bb, rather than trace-pc, fits better for my problem, given that my instrumentation is to put before each conditional statement. Do I misunderstand something here? " Tracing basic blocks <http://clang.llvm.org/docs/SanitizerCoverage.html#id11> With -fsanitize-coverage=trace-bb the compiler will insert

Vince Carey found this (thank you!). Since the fix to the problem is not entirely obvious, I post this to R-devel as RFC: help(dist) says: >> Missing values are allowed, and are excluded from all computations >> involving the rows within which they occur. If some columns are >> excluded in calculating a Euclidean, Manhattan or Canberra >> distance, the sum is

I saw a Help e-mail related to MLE. Does R have a probability weighted method (PWM) estimator function? I can't seem to find anything on PWM, unless my eyes are playing trick on me. [[alternative HTML version deleted]]

I am attempting to optimize a regression model's parameters to meet a specific target for the sum of positive errors over sum of the dependent variable (minErr below). I see two courses of action , 1) estimate a linear model then iteratively reduce the regressors to achieve the desired positive error threshold (naturally the regressors and predicted values are biased - but this is

Hi Duncan-- Nice simulation! The absolute difference in probabilities is small, but the maximum relative difference grows from something negligible to almost 2 as m approaches 2**31. Because the L_1 distance between the uniform distribution on {1, ..., m} and what you actually get is large, there have to be test functions whose expectations are quite different under the two distributions. Whether those correspond to commonly used statistics or not, I have no idea. Regarding backwards compatib...

...Philip B. Stark wrote: >> Hi Duncan-- >> >> Nice simulation! >> >> The absolute difference in probabilities is small, but the maximum >> relative difference grows from something negligible to almost 2 as m >> approaches 2**31. >> >> Because the L_1 distance between the uniform distribution on {1, ..., >> m} and what you actually get is large, there have to be test functions >> whose expectations are quite different under the two distributions. > > That is a mathematically true statement, but I suspect it is not very > r...

On 19/09/2018 3:52 PM, Philip B. Stark wrote: > Hi Duncan-- > > Nice simulation! > > The absolute difference in probabilities is small, but the maximum > relative difference grows from something negligible to almost 2 as m > approaches 2**31. > > Because the L_1 distance between the uniform distribution on {1, ..., m} > and what you actually get is large, there have to be test functions > whose expectations are quite different under the two distributions. That is a mathematically true statement, but I suspect it is not very relevant. Pseudo-ran...

...an-- > >> > >> Nice simulation! > >> > >> The absolute difference in probabilities is small, but the maximum > >> relative difference grows from something negligible to almost 2 as m > >> approaches 2**31. > >> > >> Because the L_1 distance between the uniform distribution on {1, ..., > >> m} and what you actually get is large, there have to be test functions > >> whose expectations are quite different under the two distributions. > > > > That is a mathematically true statement, but I suspect it...

No, the 2nd call only happens when m > 2**31. Here's the code: (RNG.c, lines 793ff) double R_unif_index(double dn) { double cut = INT_MAX; switch(RNG_kind) { case KNUTH_TAOCP: case USER_UNIF: case KNUTH_TAOCP2: cut = 33554431.0; /* 2^25 - 1 */ break; default: break; } double u = dn > cut ? ru() : unif_rand(); return floor(dn * u); } On Wed, Sep