search for: do_cov

...6, 2006, at 11:29 AM, Ren? J.V. Bertin wrote: > Anyway, it has nothing to do with the G4 optimisations, as the > generic 2.4.0 on CRAN also shows the same performance drop. > Thanks for the example. I think I have a clarification on this. On a higher level it's happening in "do_cov", but the underlying issue is the use of "long double" computations. First the results: The timings I get (on 2xG5 2.7GHz) are: gcc3: 0.8s gcc4: 4.5s (dynamic libgcc) gcc4: 4.2s (static libgcc) Basically any calls that use long double will be affected: qadd: 4.5s (gcc3 opt), 6.7...

...cy; /* compute correlations if PRIMVAL(op) == 0, covariances if PRIMVAL(op) != 0 */ cor = 0; ansmat = 0; ncx = 1; ncy = 1; pair = TRUE; kendall = FALSE; cov_pairwise2(n, ncx, ncy, x, y, ans, &sd_0, cor, kendall); } replace SEXP do_cov(SEXP call, SEXP op, SEXP args, SEXP env) { ... } and we have cor.i which has /* File : cor.i */ %module cor extern cor ( int n, double *x, double *y, double *ans ); We have cor: cor.c swig -perl5 cor.i gcc -c cor.c cor_wrap.c -I. -I../../src/include -I/usr/local/include -I$...

I've noticed that the implementation of Kendall's Tau in R is O(N^2). The following reference describes how it can be done in O(N log N): A Computer Method for Calculating Kendall's Tau with Ungrouped Data William R. Knight Journal of the American Statistical Association, Vol. 61, No. 314, Part 1 (Jun., 1966), pp. 436-439 http://www.jstor.org/pss/2282833 I'm interested in