Math Forum / Mathematics / Statistics / March 2010

I am using a weighted least squares routine (York et al., 2004, Am. J. Phys. 72, 367-375) and working on the assumption of uncorrelated errors. I want to consider the possibility of correlated errors, but I am not too sure what this exactly means, and how to calculate this.
My ...

My Logistic regression equation is:
logit(y) = b0 + b1*X + b2*Group + b3*X*Group
X = a continous variable
Group = a dichotomous variable coded 0/1 (Reference is 0)

    If I have two continuous random variables x and z related as
                       z = x + exp(-x)
   what is and how can I find p(z,x) i.e. joint density of z and x??
Regards,

This is related to extreme value thrm.
Theoretically, for a given dist, we can check in which extreme value dist its domain of attraction belongs.
However, in reality or practically, we dont know what is the dist of that data set. Therefore, i would like to know how to estimate ...

I am a clinical psychologist with a strong math background (undergrad
degrees in electrical engineering and physics). I'd like to develop a
"deeper" understanding of quantitative methods used in my field, but it
seems hard to find "middle ground" sources.  On the one hand, many ...

I am sure there is a simple command for this but for whatever reason
it is eluding me. I have two identification numbers that I want to
merge into one to create a unique identifier for each case. Neither
number is very long three to for digits max. Does anyone know what

Hi experts!
I have a process I am trying to evaluate. The process measures 12
different categorical variables. The possible outcomes are "low",
"medium" and "high" for some of the variables and "black" "grey" and

I have high frequency stock price data that I need to analyze. My objective is to not assume any seasonal component and just identify a trend. Here is where I run into problems with R. There are two main functions that I know of to analyze this time series: decompose() and stl(). ...

International Financial Management 9e Madura Instructors solution
manual and test bank now for all students at affordable prices.
Contact me at alltestbanks11[at]gmail.com to buy it today.

I've been asking 100 patients by phone for the names of their
prescribed drugs; additionaly, the patients' drugs were controlled
during home visits. Two thirds of the prescibed drugs were named by
the patients and found during home visits, some were named but not

In attempt to create a bell curve in excel I am trying to understand a
few concepts. So far research has lead to two resources. First, How to
create a bell curve in Microsoft Excel is here: http://support.microsoft.com/kb/213930/nl.
The explanation posted there is mechanical. As ...

I've got a pile of statistics books on my desk. I try reading them, but the
answer to my question is not obvious. I know where to look but ....
It's simple: I want to fit data for a single sample to a minimum
number of comparison samples.

i have read the following:
ln(1+ax+by)=ax+by after making a small approximation (without specifying what the approximation is).
can someone explain to me what approximation was made?
I am attaching the initial equation

Let's say we have the following --- A1 and A2 refer to two sets of
ranks from some group A; B1 and B2 refer to two sets of ranks from
some group B, and these ranks are compared against another set of
ranks, C. Furthermore,

Any input will be appreciated.  I have county level data, numerator,
denominator and its quotient.  This information can be aggregated up
to a state or national value.  One could argue that states with the
most counties could bias the national results.  I am interested in