On Oct 8, 2011, at 16:04 , francy wrote:
Hi,
I am having trouble understanding how to approach a simulation:
I have a sample of n=250 from a population of N=2,000 individuals, and I
would like to use either permutation test or bootstrap to test whether this
particular sample is
On Oct 9, 2011, at 12:00 , francesca casalino wrote:
Thank you very much to both Ken and Peter for the very helpful explanations.
Just to understand this better (sorry for repeating but I am also new in
statistics…so please correct me where I am wrong):
Ken' method:
Random sampling of
Thank you very much to both Ken and Peter for the very helpful
explanations.
Just to understand this better (sorry for repeating but I am also new in
statisticsÂ…so please correct me where I am wrong):
Ken' method:
Random sampling of the mean, and then using these means to construct a
I may be speaking out of turn here, but I would prefer not to see R-help
turn into a tutorial site for basic statistics.Such sites already exist
(e.g. http://stats.stackexchange.com/).
I realize that there is occasionally reason to venture down this path a way
within legitimate R contexts, but
I'll concur with Peter Dalgaard that
* a permutation test is the right thing to do - your problem is equivalent
to a two-sample test,
* don't bootstrap, and
* don't bother with t-statistics
but I'll elaborate a bit on on why, including
* two approaches to the whole problem - and how your
Dear Peter and Tim,
Thank you very much for taking the time to explain this to me! It is much
more clear now.
And sorry for using the space here maybe inappropriately, I really hope this
is OK and gets posted, I think it is really important that non-statisticians
like myself get a good idea of
Hi,
I am having trouble understanding how to approach a simulation:
I have a sample of n=250 from a population of N=2,000 individuals, and I
would like to use either permutation test or bootstrap to test whether this
particular sample is significantly different from the values of any other
Hi Francy,
A bootstrap test would likely be sufficient for this problem, but a
one-sample t-test isn't advisable or necessary in my opinion. If you use a
t-test multiple times you are making assumptions about the distribution of
your data; more importantly, your probability of Type 1 error will
8 matches
Mail list logo
