>From a practitioner perspective. Parametric methods have more power. If
assumptions are here - use formulas. On the other hand my usual
recommendation to colleagues: "If you don't know what to do - use
bootstrap."
Regards,
Sergiy
On Mon, 5 May 2025, 17:06 Gregg Powell via R-help,
wrote:
> Hi K
Chris,
In all likelihood, if computers had been invented, "traditional" statistics
would have been invented, but it would be less fully developed than it
currently is.
While resampling, simulations, etc. can give answers, they have at least two
drawbacks. First, compared to "traditional" metho
I've often wondered how the field of statistics, and statistical
education, would have evolved if modern-day computers and software and
programming were available in the early years. Would the "traditional"
methods, requiring simplifying assumptions, have been developed at all?
--Chris Ryan
avi.e
A brief answer to this OT question is that many disciplines do the same
thing and teach multiple methods, including some that are historical and are
no longer really used.
But since you say this was an intro course, it would not prepare you well if
later courses and the real world expose you to us
Heh. I suspect you'll get some interesting responses, but I won't try to
answer your questions. Instead, I'll just say:
(All just imo, so caveat emptor)
1. What you have been taught is mostly useless for addressing "real"
statistical issues;
2. Most of my 40 or so years of statistical practice i
(adding slightly to Gregg's answer)
Why do professionals use both? Computer intensive methods (bootstrap,
randomization, jackknife) are data hungry. They do not work well if I have a
sample size of 4. One could argue that the traditional methods also have
trouble, but one could also think of the
Hi Kevin,
It might seem like simulation methods (bootstrapping and randomization) and
traditional formulas (Normal or t-distributions) are just two ways to do the
same job. So why learn both? Each approach has its own strengths, and
statisticians use both in practice.
Why do professionals use b
I marked this posting as Off Topic because it doesn’t specifically
apply to R and Statistics, but is rather a general question about
statistics and the teaching of statistics. If this is annoying to you,
I apologize.
As I wrap up my work in my beginning statistics course, I’d like to ask
a philoso
A relevant thread from a few years ago where this was discussed:
https://www.stat.math.ethz.ch/pipermail/r-help/2023-August/477904.html
I generally use:
export OPENBLAS_NUM_THREADS=1
export MKL_NUM_THREADS=1
since in my experience the biggest performance gains come from switching to
OpenBLAS /
> smallepsilon via R-help
> on Sun, 04 May 2025 18:11:57 + writes:
> Peter, The eigenvalues are not identical(), but are
> all.equal(). When n is 20, the crossproduct is
> (numerically) a diagonal matrix with +-1 on the
> diagonal. When n is 50, this is not the c
10 matches
Mail list logo
