Math Forum / Mathematics / Statistics / July 2009

Sample A consists of firms with good quality management
SampleB consists of firms with bad quality management
the sizes of the sample are different. IS it possible to test whether the Net income of sample A is different than the net income of sample B. Can I compute the p value for ...

I want to compare two distributions and guess if they are different
(p-
value). The only information I have is the Mean, the QQ-intervals
(25-75 percentiles) and the Standard Deviation. What would be the best

The problem: If 100 novices are asked to aim at a target, they will
hit all around the target. But as per the statistics their average
would be all around the target (some above, some below, left or
right). But as per the Normal Distribution they would be hitting more

       I hope this is appropriate for this group.  I do get around to
analytical problems eventually.  First, a little background...
       I'm a book seller, and want to write a program to automatically
reprice my books based on other copies already available.  In the past,

Has anyone heard of Single Cell Bore Analysis? The client wants to do
a analysis on the impact of multiple services received by individual
consumers and they specifically asked about this "single cell bore
analysis", which I have never heard of. Thank you in advance for your

(Note: cross-posted in sci.math)
Friends,
First, I want to assure you that this isn't a homework problem (I only
wish it were). While this is definitely work-related, I've made it

*******************************************************************
*******************************************************************
                           ENTER HERE:
          >>> http://your-guide-online.com/about/chipper-manual <<<

When we take the "mathematic" mean of n iid rvs Xi, when n approximate infinity, the CLT shows that no matter what the distribution of Xi is, the distribution is approximate to the normal distribution with mean u and variance sigam/sqrt(n).
I am curies that what if we use other ...

This post is continuing the post from the last week,
http://groups.google.com/group/sci.stat.consult/browse_thread/thread/d69c5e39a28
e3d96/ecc77f8333d46fc9?lnk=gst&q=probability+at+work#ecc77f8333d46fc9
Rich said,
"Thus, if you observe 30%  with *100* ratings, the 95% CI

I'm certain that racial profiling is an informal application of
statistics, but I am uncertain of the kind of statistics.

How do I compare 262,143 pairs of means to see which pair demonstrates the greatest disparity? Let's assume the distribution of the data is not normal. I realize that if the greatest disparity is found in one pair, but another pair has a disparity less by just 0.1, it hardly ...

I want to generate random deals of a standard deck of 52 cards. I
believe there are ~8E67 possible deals.
If I am using a pseudo random number generator (PRNG) that has a
period of only 17E6 (such as the one in Visual Basic), I will only get

I have an empirical cummulative distribution function (ECDF) I want to
"best-fit" to an extreme value distribution (EVD). One source I came
across suggested that rather than trying to estimate the params of the
EVD from the moments of the ECDF, instead use the params computed from

I have an empirical cummulative distribution function (ECDF) I want to
"best-fit" to an extreme value distribution (EVD). One source I came
across suggested that rather than trying to estimate the params of the
EVD from the moments of the ECDF, instead use the params computed from

The title of the post may seem strange, but the problem is simple.
Consider a three-treatmant experiment in which for n replicates counts
are observed. However, my aim is not to compare counts (mean count is
what interests me) for all replicates, but only for those where