Math Forum / Mathematics / Statistics / October 2008

Q: Two possible outcomes to a test is PASS or FAIL. Is the probability of a pass 0.5 ? if not, explain why not ?
My approach:
We cannot take the above problem purely on the number of results and as similar to the toss of a coin. Clearly, the factor of the candidates actual ...

Minimum difference between the successive values of a N(0, sigma):n sample
With one exception (sigma=10) indicated by *) I put sigma=1. The table below concerns the 95% and 99% quantiles of the indicated statistics. 400000 samples were used for each n.
_____________95%____99%____

How would this study be analyzed:
It's a single-blinded RCT to evaluate the effect of a special diet on
7 parameters, vs two other diets, the DASH diet and the USDA Food
Pyramid diet. The sample is 75 patients with risk factors for coronary

In my work, Im trying to estimate approximate completion times for
tasks. I have my predicted times (from my model) and to I also have
the actual completion times. What is the best way to prove that my
prediction times are very close to the actual times?

if X has a geometric Distribution. How can you show that
P(X > k+j | X>k) P(X>j)
the only hints : k and j are nonnegative and X is memoryless.
Not sure

I have some results from clinical data, each result is scored from 0
to 1, where 0 is bad and 1 is perfect.
I would like to see if there is any correlation with patients'
patologies, so I have a little list of pathologies that the patient

I have been playing with the classic LDA problem consisting of two
normal distributions, and the goal is studying the classification
error rate in terms of number of samples N and dimensionality of the
space D. The normals share the same isotropic covariance (zero off

x=1,2,3,4,5,6,............n-2,n-1,n
for example
at x=1 sine wave is Maximum
at x=2 sine wave is Maximum

i got data from a research (animal feeding) which has 3 factors
(vitamin E, % inclusion of dry corn, and solubles).
levels of vitamin E - 2 (with and without)
Levels of % inclusion of dry corn - 3 (0%, 10% and 20%)

given the random variables Y_i,...,Y_n a contrast
between them is a linear combination
sum_{i=1 to n} (a_i)*(Y_i), with the property that
sum_{i=1 to n} (a_i)=0. Two contrasts  

I'm having a tough time tracking down an example of what I thought
would be a common issue.  I am interested in using a hierarchical
Poisson model to estimate the rate of disease (symptom) appearance
both spatially and temporally.

Given a random sample how close together are the values? Or, alternatively, what are, because too close or too far, the odd pairs of values?
The question is answered by the following way: Simply to find out the percentiles of distances.
a) order the sample,
b) find out the ...

I have the following problem:
there are two samples (30 data each one), which don't follow a normal
distribution,
I want a test to affirm with an \alpha=0.01 that the to samples follow

I am working on a supervised learning classification problem that bins
out to C_i classes,
i.e. if we think of a histogram, then each of the classes constitutes
a bin.

For a time series of 216 monthly returns, the correlation of returns
to past SUMS of returns over the last n1:n2 periods are
ACF_SUM(01:12)    0.134
ACF_SUM(13:24)    -0.025