Statistika For Life: 20 new messages in 10 topics

sci.stat.math
http://groups.google.com/group/sci.stat.math?hl=en

sci.stat.math@googlegroups.com

Today's topics:

==============================================================================
TOPIC: Order Statistics of Independent Normal Distribution.
http://groups.google.com/group/sci.stat.math/browse_thread/thread/36b5b17b3e01ddc4?hl=en
==============================================================================

== 1 of 2 ==
Date: Fri, Nov 16 2007 2:41 am
From: Wudong Liu

Dear all:
Now in a project of mine, I need to obtain the mean and std of extreme
order statistics of independent normal distribution(not necessary
standard). I know this should not be a hard job. Can anyone please
give me a reference on this, where I can find some already derived
equations.

Thank you.
Warren

== 2 of 2 ==
Date: Fri, Nov 16 2007 5:10 am
From: "David Jones"

Wudong Liu wrote:
> Dear all:
> Now in a project of mine, I need to obtain the mean and std of extreme
> order statistics of independent normal distribution(not necessary
> standard). I know this should not be a hard job. Can anyone please
> give me a reference on this, where I can find some already derived
> equations.
>
> Thank you.
> Warren

You could try ...

Order Statistics by HA David and HN Nagaraja (3rd Edition, 2003, Wiley)

David Jones

==============================================================================
TOPIC: wrong R-Squared value??
http://groups.google.com/group/sci.stat.math/browse_thread/thread/259e11ac412a3219?hl=en
==============================================================================

== 1 of 5 ==
Date: Fri, Nov 16 2007 5:03 am
From: Paige Miller

On Nov 15, 12:54 pm, m00es <m0...@yahoo.com> wrote:
> On Nov 15, 10:53 am, jantunes <jasantu...@gmail.com> wrote:
>
>
>
> > > I believe that when you take a validation data set,
> > > you can indeed
> > > have such wild predictions that SSR > SST, or SSE >
> > > SST. This
> > > indicates that there is a problem with the way the
> > > model fits to your
> > > validation data.
>
> > > I don't think R-squared is the proper way to compare
> > > the validation
> > > fit to the training fit. I would compare the MSE from
> > > the validation
> > > data set to the MSE of the training data set -- if
> > > they are close,
> > > that's good, if they are widely different, that's
> > > bad.
>
> > I've done some searching on MSE and it appears that MSE is good to compare different statistics models (lowest MSE = best model), but not in giving an abslotute value like R-squared.
> > I'm not familiar with these but I've seen them in the literature: Chi-squared, F-test, p-value. Isn't there any (abslolute) statistic measure I can produce that validates y' (prediction) against the real and full data?
>
> Why not just correlate the predicted values with the observed values
> and square that?
>
> So, you start with one set of data and find the least squares
> regression line:
>
> Y_hat = b0 + b1 X
>
> Note that the squared correlation between the observed Y values and
> the predicted values from this model (i.e., the Y_hat values) is equal
> to R^2.
>
> Now take a new set of data. Predict Y_hat using the least squares
> regression line found in the first dataset. Calculate the squared
> correlation between the (new) Y values and the predicted Y_hat values.
> This will be between 0 and 1 and indicates how much of the variance in
> the Y values (in the new dataset) can be accounted for based on
> knowing X and using the regression equation found using the first
> dataset.
>
> m00es

You could have a high R^2 between predicted Y and the actual values
and still have a terrible fit in the new set of data. Correlation in
this case does not imply a good fit.

--
Paige Miller
paige\dot\miller \at\ kodak\dot\com

== 2 of 5 ==
Date: Fri, Nov 16 2007 6:03 am
From: jantunes

> > This is what I do:
> > 1) get 200 data points (x is a time series; y is
> > CPU usage)
> > 2) do linear regression based on those 200 points,
> > resulting in some y'=a + bx
> > 3) get R-squared (R^2=0.96) for the y'
>
> At this point -- Are you doing anything to get rid of
> "spurious" correlations based on simple trends, etc.?
No. I'm sorry but I don't even know what that is.

> OLS regression may give useful results, in some
> sense, but it won't give legitimate tests, and values
> such as R-squared might be approximately useless,
> even when they are as big as 0.96, if the whole thing
> represents a simple trend.
What do you mean by a simple trend?

> > Then, I want to validate that trendline/prediction
> > by comparing it with more real data:
> > 4) get more data points, past the 200 points
> > (eg 10000)
>
> Wow! I though only astronomers used 50 times the
> baseline for projections. What *is* this problem,
> anyway?
I'm trying to predict the resource usage for a given computer task (x = number of times the taks is repeated). So, I get a different y and y' (prediction) for a different type of resource (CPU, memory, etc).

> > 5) get R-squared for the y' (this time against the
> > new data)
>
> Use the squared deviations from the predicted values,
> predicting from the original 200 points. It is hard
> to find much fault with the RMS error.
> Isn't this exercise supposed to be validation of the
> original equation? - then you have to use the
> original equation.
y' is the original equation, the data (y) used in R-squared calculation is not (only the first 200 points are the same).

> Which R-squared? You show, yourself, you can't
> figure out what to use to make a "proper"
> R-squared, or else, how to make decent sense of
> R-squared.
Then what should I use? I need a statistically recognized measure of the prediction (y') against the data it is supposed to predict (not the data used for creating y').

Thanks!

== 3 of 5 ==
Date: Fri, Nov 16 2007 6:13 am
From: jantunes

> > > I believe that when you take a validation data
> > > set, you can indeed have such wild predictions
> > > that SSR > SST, or SSE > SST. This indicates
> > > that there is a problem with the way the model
> > > fits to your validation data.
> > >
> > > I don't think R-squared is the proper way to
> > > compare the validation fit to the training fit.
> > > I would compare the MSE from the validation
> > > data set to the MSE of the training data set --
> > > if they are close, that's good, if they are
> > > widely different, that's bad.
> >
> > I've done some searching on MSE and it appears that
> > MSE is good to compare different statistics models
> > (lowest MSE = best model), but not in giving an
> > abslotute value like R-squared.
>
> Modelling techniques such as Partial Least Squares
> typically uses a measure of residual error to
> compare models from a training set to a validation
> set. I see no reason why a similar measure can't
> be used in an Ordinary Least Squares model as well.

Can you give me some pointer for that measure (how can I calculate it or the name)?

> > I'm not familiar with these but I've seen them in
> > the literature: Chi-squared, F-test, p-value. Isn't
> > there any (abslolute) statistic measure I can produce
> > that validates y' (prediction) against the real and
> > full data?
>
> I suppose you could do an F-test of MSE(training
> set)/MSE(validation set). I'm not sure if this violates
> any of the standard assumptions ... I'll have to think
> about that.

I'm not sure if this test is usefull for what I want to prove.

Thanks!

== 4 of 5 ==
Date: Fri, Nov 16 2007 6:21 am
From: jantunes

> > > > I believe that when you take a validation data
> > > > set, you can indeed have such wild predictions
> > > > that SSR > SST, or SSE > SST. This indicates
> > > > that there is a problem with the way the model
> > > > fits to your validation data.
> > > >
> > > > I don't think R-squared is the proper way to
> > > > compare the validation fit to the training fit.
> > > > I would compare the MSE from the validation
> > > > data set to the MSE of the training data set --
> > > > if they are close, that's good, if they are
> > > > widely different, that's bad.
> > >
> > > I've done some searching on MSE and it appears
> > > that MSE is good to compare different statistics
> > > models (lowest MSE = best model), but not in
> > > giving an abslotute value like R-squared.

> > >
> > > I'm not familiar with these but I've seen them
> > > in the literature: Chi-squared, F-test, p-value.
> > > Isn't there any (abslolute) statistic measure I
> > > can produce that validates y' (prediction)
> > > against the real and full data?
> >
> > Why not just correlate the predicted values with
> > the observed values and square that?
> >
> > So, you start with one set of data and find the
> > least squares regression line:
> >
> > Y_hat = b0 + b1 X
> >
> > Note that the squared correlation between the
> > observed Y values and the predicted values from
> > this model (i.e., the Y_hat values) is equal
> > to R^2.
> >
> > Now take a new set of data. Predict Y_hat using
> > the least squares regression line found in the
> > first dataset. Calculate the squared correlation
> > between the (new) Y values and the predicted Y_hat
> > values. This will be between 0 and 1 and indicates
> > how much of the variance in the Y values (in the
> > new dataset) can be accounted for based on knowing
> > X and using the regression equation found using the
> > first dataset.
> >
> > m00es
>
> You could have a high R^2 between predicted Y and the
> actual values and still have a terrible fit in the new
> set of data. Correlation in this case does not imply a
> good fit.

Exactly. I tried that before. Both prediction and real data were very correlated (high R) but fitted terribly.

Thanks!

== 5 of 5 ==
Date: Fri, Nov 16 2007 6:44 am
From: jantunes

> > I've done some searching on MSE and it appears that
> > MSE is good to compare different statistics models
> > (lowest MSE = best model), but not in giving an
> > abslotute value like R-squared.
>
> You've got it backwards. R-square is relative, not
> absolute. It depends on the size of the errors,
> relative to the overall variability.
> MSE is an absolute measure of the size of the errors,
> although you should be looking at sqrt(MSE), the
> root-mean-square error, because it's in the right
> units.

I was referring to the fact that MSE is meaningful when compared to other MSEs (thus relative). But yes, you're right.

> Similarly, if you insist on using a relative
> measure, you should look at sqrt(1 - R^2),
> the rms error relative to the overall SD.

Yes, a relative measure is what I need because I only have one prediction. I need a value of the "fitness" of the prediction (without needing to compare it against other predictions).
But I cannot rely on R^2 since I get different (and strange) values depending on the equation (eg R^2 = SSR/SST; R^2 = 1 - (SSE/SST)). So, I don't think I can use sqrt(1 - R^2), though statistics is not anywhere near my field of expertise.

Thanks!

==============================================================================
TOPIC: Help - Correlation of measurable and ordinal data plssss
http://groups.google.com/group/sci.stat.math/browse_thread/thread/aa9fda68325d8e7d?hl=en
==============================================================================

== 1 of 1 ==
Date: Fri, Nov 16 2007 7:25 am
From: "geetha.shree@gmail.com"

Hi
I am need to design an experiment for my research work, which involves
ranking of a product finish(plastic panels).

Each of the Panels has 6 measurable variables associated (say
thickness, shininess, color, gloss, etc., which can be MEASURED by an
instrument) In a group of 100 panels I have selected only 18 panels
which have low, medium and high value of each Variable, but all other
variable have average value of their own [i.e., low,medium, high value
of A1 and Average values of A2,A3,A4,A5,A6(100 panels)]
---------------------------------------------------------
Ex:
Panel No. A1 A2 A3 A4 A5 A6

Panel 1: 2 avgA2 avgA3 avgA4 avgA5 avgA6
Panel 2: 14 avgA2 avgA3 avgA4 avgA5 avgA6
Panel 3: 27 avgA2 avgA3 avgA4 avgA5 avgA6
Panel 4: avgA1 5 avgA3 avgA4 avgA5 avgA6
Panel 5: avgA1 17 avgA3 avgA4 avgA5 avgA6
Panel 6: avgA1 36 avgA3 avgA4 avgA5 avgA6
.
.
.
Panel 18:avgA1 avgA2 avgA3 avgA4 avgA5 35
----------------------------------------------------

The above 18 panels are evaluated i.e, just RANKED by people based on
what they like (Ranking based on the overall Finish ONLY, so they are
not aware of the SIX variables)

The people who are ranking the plastic panel are focusing on the
Product FINISH only. They Rank from 1 to 18 ( 1 = BEST and 18 =
WORST )
Person Panel 1 Panel 2 Panel 3 ...... Panel 18
1. 4 14 7 1
2. 13 10 3 5
3. 9 7 15 11
4.
5.
.
.
.
99.
100.

My aim is to determine which among the six variable is more
influential/ related to RANK and develop a STANDARD for this
instrument.

My problem is how can I do statistical analysis to develop an STANDARD
if I have a RANK DATA and a MEASURABLE DATA ...

The Rank data does not follow a normal distribution even after
transformation.

Of the 6 variables only 3 variables are normally distributed and the
rest 3 are not Normally distributed.

Is it necessary to have each of the data ( rank, A1, A2, A3, A4, A5 ,
A6) to be normally distributed to do regression analysis.

Can you please suggest me some solution for how approach this very
Tricky problem.

==============================================================================
TOPIC: Anova with continuous variable
http://groups.google.com/group/sci.stat.math/browse_thread/thread/d44fa29a8fefa03a?hl=en
==============================================================================

== 1 of 3 ==
Date: Fri, Nov 16 2007 7:46 am
From: junkjem@gmail.com

Hello,
Lets take for example the following experiment (which is similar to
mine but with some other variable...)
Someone has to taste a meal is estimate how spicy it is.
It is always the same meal, but the quantity of salt and pepper
varies.
In some conditions there is no pepper, in other there is the same
amount of pepper and salt.
The quantity of salt (and pepper) varied between condition, let's say
3, 5, 7, 9, and 11 mg.
So to summarize here are the value of the independent variables:

Cond Salt Pepper
1 3 0
2 5 0
3 7 0
4 9 0
5 3 3
6 5 5
7 7 7
8 9 9
I have 6 estimations per conditions.
I have done an anova with two factors: 1] quantity of salt, 2]
presence of pepper.
Of course both factor are significant. The purpose of the experiment
is to test if the interaction is significant. We want to know if the
increase in the spice estimate with the introduction of pepper is
constant over the quantity of salt.

I have done the anova using Matlab (function anovan). I have to option
to set the quantity of the salt to a continuous variable. It seems
intuitive to me to use this option. But the problem is that I don't
know exactly of the algorithm used in that case.
I understand the algorithm of a typical ANOVA, but I can't find any
information on how to treat a continuous variable.
Thank you for your help.
Jem

== 2 of 3 ==
Date: Fri, Nov 16 2007 9:02 am
From: Paige Miller

On Nov 16, 10:46 am, junk...@gmail.com wrote:
> Hello,
> Lets take for example the following experiment (which is similar to
> mine but with some other variable...)
> Someone has to taste a meal is estimate how spicy it is.
> It is always the same meal, but the quantity of salt and pepper
> varies.
> In some conditions there is no pepper, in other there is the same
> amount of pepper and salt.
> The quantity of salt (and pepper) varied between condition, let's say
> 3, 5, 7, 9, and 11 mg.
> So to summarize here are the value of the independent variables:
>
> Cond Salt Pepper
> 1 3 0
> 2 5 0
> 3 7 0
> 4 9 0
> 5 3 3
> 6 5 5
> 7 7 7
> 8 9 9
> I have 6 estimations per conditions.
> I have done an anova with two factors: 1] quantity of salt, 2]
> presence of pepper.
> Of course both factor are significant. The purpose of the experiment
> is to test if the interaction is significant. We want to know if the
> increase in the spice estimate with the introduction of pepper is
> constant over the quantity of salt.
>
> I have done the anova using Matlab (function anovan). I have to option
> to set the quantity of the salt to a continuous variable. It seems
> intuitive to me to use this option. But the problem is that I don't
> know exactly of the algorithm used in that case.
> I understand the algorithm of a typical ANOVA, but I can't find any
> information on how to treat a continuous variable.
> Thank you for your help.
> Jem

ANOVA with a continuous predictor is usually called Ordinary Least
Squares Regression, or just regression for short.

--
Paige Miller
paige\dot\miller \at\ kodak\dot\com

== 3 of 3 ==
Date: Fri, Nov 16 2007 9:03 am
From: Paige Miller

Oh, if your goal is to estimate an interaction, the design you used
probably isn't much help. You might want to look at factorial
experiments.

--
Paige Miller
paige\dot\miller \at\ kodak\dot\com

==============================================================================
TOPIC: Conditional Probability.
http://groups.google.com/group/sci.stat.math/browse_thread/thread/e22ead0b091bc3bf?hl=en
==============================================================================

== 1 of 1 ==
Date: Fri, Nov 16 2007 9:38 am
From: hrubin@odds.stat.purdue.edu (Herman Rubin)

In article <fhg68g$2cud$1@pyrite.mv.net>,
C. G. Montgomery <cgm@physics.utoledo.edu> wrote:
> probability@farfara.org wrote:

>> What do you think of this?

>> http://www.farfara.org/

> I think none of the symbols are visible in Firefox, nor other reasonable
>browsers.

Some of the symbols are hard to make out in Internet
Explorer, but they would probably be just as hard in
print using the same fonts. Other than that, I had
no problem in reading them.

--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Department of Statistics, Purdue University
hrubin@stat.purdue.edu Phone: (765)494-6054 FAX: (765)494-0558

==============================================================================
TOPIC: YOU THINK I AM A SUCKER , John ( R ) Smith?
http://groups.google.com/group/sci.stat.math/browse_thread/thread/9038fc3be1e9cc3c?hl=en
==============================================================================

== 1 of 4 ==
Date: Fri, Nov 16 2007 10:14 am
From: John Smith

Luisa,

Your response does not answer my question. To reiterate,

I wrote: Either the parameter is INSIDE or OUTSIDE. The probability that the parameter is inside is either 100% or 0%. Same for the probability that the parameter is outside. ***
Your wrote: Is the proof that you don't understand, NOTHING AT ALL; how Monte Carlo method is able to derive Critical Values.

My response: are the critical values statistics or parameters???? Do you even know the difference?

John

== 2 of 4 ==
Date: Fri, Nov 16 2007 12:18 pm
From: "Luis A. Afonso"

1) Because you, John Smith, are seemly GAY you call me Luisa a lot of times hopping that I return Jeannie, Jeannie, Joan, but I merely take it by a way you chose to try to seduce me.
I do not consume that kind of goods: at home you surely will find a "piece" at yours fully satisfaction. US are full of this Population.
2) If you was not so ignorant you certainly had noted that the Table1 of Lilliefors paper refers to CRITICAL VALUES of the
_____Sample Statistics D, called also a Kolmogorov-Smirnov Distance. NOT LESS, NOT LEAST.
3) About your commitment to invite H. W. Lilliefors to post a comment in this matter? Do you forgot or the phone call you say you do is PLAIN FORGERY?
______

Luis Amaral Afonso

== 3 of 4 ==
Date: Fri, Nov 16 2007 1:02 pm
From: John Smith

Luiser,

I am happy you finally mentioned
"RITICAL VALUES of the
_____Sample Statistics D, called also a Kolmogorov-Smirnov Distance. NOT LESS, NOT LEAST."

Now answer my question, "are the critical values statistics or parameters????"

I did call Lilliefors. He said you are an idiot.

John

== 4 of 4 ==
Date: Fri, Nov 16 2007 2:08 pm
From: "Luis A. Afonso"

A never answered torturing question!
Who is so cruel not to go in aid!
Are Statistics or Parameters?
My heart is unable to reach a decision,
My suffering's not to be said.
Oh true inextricable confusion
How much expected hard work ahead.

****
Luis Amaral Afonso

Johner Smither wrote:

*** Luiser,

I am happy you finally mentioned
"RITICAL VALUES of the
_____Sample Statistics D, called also a Kolmogorov-Smirnov Distance. NOT LESS, NOT LEAST."
Now answer my question, "are the critical values statistics or parameters????"
I did call Lilliefors. He said you are an idiot.
********************

==============================================================================
TOPIC: Call For Papers: WORLDCOMP'08, 25 Int'l. Joint Conferences in Comp. Sci.
, Comp. Eng., and Applied Computing, July 2008, USA
http://groups.google.com/group/sci.stat.math/browse_thread/thread/f290ec5992be490c?hl=en
==============================================================================

== 1 of 1 ==
Date: Fri, Nov 16 2007 10:28 am
From: "A. M. G. Solo"

Dear Colleagues:

I would appreciate if you would share the following announcement with
those who might be interested.

Best regards,

A. M. G. Solo
Publicity Chair, WORLDCOMP'08
Principal/R&D Engineer, Maverick Technologies America Inc.
----------------------------------------------------------

Call For Papers
and
Call For Session Proposals

The 2008 World Congress in Computer Science,
Computer Engineering, and Applied Computing
WORLDCOMP'08
(composed of 25 Joint Conferences)
July 14-17, 2008, Las Vegas, USA

You are invited to submit a paper and/or a proposal to organize
a session/workshop. All accepted papers will be published in the
respective conference proceedings. The Academic Co-sponsors of
WORLDCOMP'08 will soon be finalized which will include research
laboratories affiliated with major institutions (Academic Co-sponsors
of WORLDCOMP'07 included: major research laboratories at
Massachusetts Institute of Technology, Harvard University, The
University of Texas at Austin, Purdue University, Indiana University,
Georgia Institute of Technology, Columbia University, Russian Academy
of Sciences, and others. Corporate sponsors included: Google, Inc.;
Intel Corporation; and Salford Systems).

The 2008 World Congress in Computer Science, Computer Engineering,
and Applied Computing (WORLDCOMP'08) is composed of the following
25 conferences (all will be held simultaneously, same location
and dates: July 14-17, 2008, USA):

o The 2008 International Conference on Parallel and Distributed
Processing Techniques and Applications (PDPTA'08)

o The 2008 International Conference on Grid Computing and
Applications (GCA'08)

o The 2008 International Conference on Computer Design (CDES'08)

o The 2008 International Conference on Scientific Computing (CSC'08)

o The 2008 International Conference on Artificial Intelligence
(ICAI'08)

o The 2008 International Conference on Genetic and Evolutionary
Methods (GEM'08)

o The 2008 International Conference on Machine Learning; Models,
Technologies and Applications (MLMTA'08)

o The 2008 International Conference on Information Theory and
Statistical Learning (ITSL'08)

o The 2008 International Conference on Bioinformatics and
Computational Biology (BIOCOMP'08)

o The 2008 International Conference on Software Engineering Research
and Practice (SERP'08)

o The 2008 International Conference on Wireless Networks (ICWN'08)

o The 2008 International Conference on Image Processing, Computer
Vision, and Pattern Recognition (IPCV'08)

o The 2008 International Conference on Modeling, Simulation and
Visualization Methods (MSV'08)

o The 2008 International Conference on Computer Graphics and Virtual
Reality (CGVR'08)

o The 2008 International Conference on Internet Computing (ICOMP'08)

o The 2008 International Conference on Semantic Web and Web Services
(SWWS'08)

o The 2008 International Conference on Security and Management
(SAM'08)

o The 2008 International Conference on Data Mining (DMIN'08)

o The 2008 International Conference on Information and Knowledge
Engineering (IKE'08)

o The 2008 International Conference on e-Learning, e-Business,
Enterprise Information Systems, and e-Government (EEE'08)

o The 2008 International Conference on Embedded Systems and
Applications (ESA'08)

o The 2008 International Conference on Frontiers in Education:
Computer
Science and Computer Engineering (FECS'08)

o The 2008 International Conference on Foundations of Computer
Science (FCS'08)

o The 2008 International Conference on Engineering of Reconfigurable
Systems and Algorithms (ERSA'08)

o The 2008 International Conference on Communications in Computing
(CIC'8)

(a link to each conference's URL can be found at
http://www.world-academy-of-science.org - the web site is currently
under construction; servers are being replaced - the link
shown above would take you to the 2007 offering of WORLDCOMP; later,
the same link would take you to the the 2008 WORLDCOMP.)

General Chair and Coordinator:

H. R. Arabnia, PhD
Professor, Computer Science
Editor-in-Chief, The Journal of Supercomputing (Springer)
The University of Georgia
Department of Computer Science
415 Graduate Studies Research Center
Athens, Georgia 30602-7404, USA

Tel: (706) 542-3480
Fax: (706) 542-2966
E-mail: hra@cs.uga.edu

Purpose / History:

This set of joint conferences is the largest annual gathering of
researchers in computer science, computer engineering and applied
computing. Many of the 25 joint conferences in WORLDCOMP are the
premier conferences for presentation of advances in their
respective
fields. We anticipate to have 2,600 or more attendees from over 80
countries participating in the 2008 joint conferences.

The motivation is to assemble a spectrum of affiliated research
conferences into a coordinated research meeting held in a common
place at a common time. The main goal is to provide a forum for
exchange of ideas in a number of research areas that interact. The
model used to form these annual conferences facilitates
communication
among researchers from all over the world in different fields of
computer science, computer engineering and applied computing. Both
inward research (core areas of computer science and engineering)
and
outward research (multi-disciplinary, inter-disciplinary, and
applications) will be covered during the conferences.

WORLCOMP'08 will be composed of research presentations, keynote
lectures, invited presentations, tutorials, panel discussions, and
poster presentations. In recent past, keynote and/or tutorial
speakers
included: Prof. Michael J. Flynn (Stanford U.); Prof. John H.
Holland
(U. of Michigan, Ann Arbor); Prof. H. J. Siegel (Colorado State
U.);
Prof. Barry Vercoe (MIT); Prof. Ruzena Bajcsy (U. of California,
Berkeley); Prof. A. K. Dunker (Indiana U. and Purdue U.); Prof. Jun
Liu
(Harvard U.); Dr. Jim Gettys (developer of X Window, ...); Dr.
Chris
Rowen (President and CEO, Tensilica, Inc.); and many other
distinguished
speakers.

Proposal for Organizing Sessions/Workshops:

Each session will have at least 6 paper presentations from
different authors (12 papers in the case of workshops). The
session chairs will be responsible for all aspects of their
sessions; including, soliciting papers, reviewing, selecting, ...
The names of session chairs will appear as Associate Editors in
the conference proceedings and on the cover of the books.

Proposals to organize sessions should include the following
information: name and address (+ email) of proposer, title of
session, a 100-word description of the topic of the session,
the name of the conference the session is submitted for
consideration, and a short description on how the session will
be advertised (in most cases, session proposers solicit papers
from colleagues and researchers whose work is known to the
session proposer). email your proposal to H. R. Arabnia (address
is given above). We would like to receive the proposals by
December 10, 2007.

Submission of Papers:

Prospective authors are invited to submit their draft paper
(about 5 to 8 pages - single space, font size of 10 to 12) to
H. R. Arabnia by Feb. 25, 2008. email submissions in MS document
or PDF formats are preferable (Fax or postal submissions are also
fine.) All reasonable typesetting formats are acceptable (later,
the authors of accepted papers will be asked to follow a particular
typesetting format to prepare their papers for publication.)

The length of the Camera-Ready papers (if accepted) will be limited
to 7 (IEEE style) pages. Papers must not have been previously
published or currently submitted for publication elsewhere. The
first page of the draft paper should include: title of the paper,
name, affiliation, postal address, email address, and telephone
number for each author. The first page should also identify the
name of the Contact Author and a maximum of 5 topical keywords that
would best represent the content of the paper. Finally, the name
of the conference that the paper is being submitted to must be
stated on the first page.

Papers will be evaluated for originality, significance, clarity,
impact, and soundness. Each paper will be refereed by two experts
in the field who are independent of the conference program
committee.
The referees' evaluations will then be reviewed by two members of
the program committee who will recommend a decision to the chair of
the track that the paper has been submitted to. The chair will
make
the final decision. Lastly, the Camera-Ready papers will be
reviewed
by one member of the program committee.

Members of Program and Organizing Committees:

The Program Committee includes members of chapters of World Academy
of Science (chapters: supercomputing; scientific computing; AI;
imaging science; databases; simulation; software engineering;
embedded systems; internet and web technologies; communications;
computer security; and bioinformatics.) The Program Committee for
individual conferences is currently being formed. Those interested
in joining the Program Committee should email H. R. Arabnia
(hra@cs.uga.edu) the following information: Name, affiliation
and position, complete mailing address, email address, tel/fax
numbers, a short biography together with research interests and
the name of the conference offering to help with.

Location of Conferences:

The conferences will be held in the Monte Carlo hotel, Las Vegas,
Nevada, USA (with any overflows at other near-by hotels). This is
a mega hotel with excellent conference facilities and over 3,000
rooms. It is minutes from the airport with 24-hour shuttle
service to and from the airport. This hotel has many recreational
attractions, including: waterfalls, spa, pools, sunning decks, Easy
River, wave pool, lighted tennis courts, health spa, nightly shows,
a number of restaurants, ... The negotiated room rate for
conference attendees is very reasonable. The hotel is within
walking distance from most other attractions (recreational
destinations, Golf courses, ...)

Important Dates:

Dec. 10, 2007: Proposals for organizing/chairing sessions/
workshops
Feb. 25, 2008: Submission of papers (about 5 to 8 pages)
March 25, 2008: Notification of acceptance
April 25, 2008: Camera-Ready papers and Registration due
July 14-17, 2008: The 2008 World Congress in Computer Science,
Computer Engineering, and Applied Computing
(WORLDCOMP'08 - 25 joint conferences)

Topical Scope for each Conference:

To receive the complete list of topics for each of the
25 conferences, send an email to hra@cs.uga.edu or
wait for the conferences' url's to be constructed.

Future Announcements: If you do not wish to receive future
announcements
about this event, please send an email to hra@cs.uga.edu.

==============================================================================
TOPIC: Interesting (but difficult) question - calculating 'implied'
probabilities of a wager
http://groups.google.com/group/sci.stat.math/browse_thread/thread/245aac10e44fcef8?hl=en
==============================================================================

== 1 of 1 ==
Date: Fri, Nov 16 2007 3:03 pm
From: "Pavel314"

"Anonymous" <no.reply@here.com> wrote in message
news:EZqdnXCpq9-olaDanZ2dnUVZ8sHinZ2d@bt.com...
>
>
> Pavel314 wrote:
>
>> "Pavel314" <Pavel314@NOSPAM.comcast.net> wrote in message
>> news:SoCdnbzFjODOpaHanZ2dnUVZ_sOrnZ2d@comcast.com...
>>
>>>"Anonymous" <no.reply@here.com> wrote in message
>>>news:Ou6dnXpmPox49KTanZ2dnUVZ8s-qnZ2d@bt.com...
>>>
>>>>Here is a hypotheical scenario.
>>>>
>>>>A friend and I decide to visit the local county fair. There is a
>>>>competition to see who can throw a heavy ball the highest. I bet my
>>>>friend that I can throw the heavy metal ball more than X metres high.
>>>>
>>>>He in turn, says "I'll pay you a dollar for every Y centimeters that you
>>>>can throw the ball above X meters - BUT to make it worth my while, you
>>>>have to PAY ME Z dollars for me to take on the bet".
>>>>
>>>>From the above, my friend has calculated (implicitly from the wager he
>>>>has made), the probability of me being able to throw the ball above X
>>>>metres. How may I calculate the probaility, so I can work out the
>>>>(implied) odds of my success?
>>>>
>>>>What methodology/logic/technique may I use to calculate the probability
>>>>of me throwing the ball above X metres (based on the wager given above)?
>
> Hi Paul, thanks for your feedback. Incidentally, I agree with you - I am
> thinking along the same lines - it may not be possible to calculate the
> oddds, without knowing the distribution of the height of the throws. I'll
> do some more thinking ...

After another lunch hour spent considering the situation, here's what
I've come up with. I still don't have an answer but maybe this will help.

Assume your throw distance to be normally distributed, not an unnatural
assumption.

YOUR BET

You estimate that your average throw, trying to make the longest throw
you can, will be 100 * X + E centimeters, where X meters is the minimum
distance you have to throw to win the bet. You also estimate that the
limit point, X meters, is two standard deviations below your mean throw;
this gives you only a 2.5% chance of losing the bet. So the standard
deviation of your throw is E / 2.

FRIEND'S BET

Assume that our friend has seen you throw in the past and makes the
same estimates that you have on mean and standard deviation. Wanting the
same risk that you put on your bet, he sets the parameters of his bet so
that he doesn't have to pay you unless your throw goes more than two
standard deviations above the estimated mean, 100 * X + 2 * E.

He will pay you one dollar for each Y centimeters you throw past 100 *
X. He will have already collected Z dollars for taking the bet, so to
break even if you throw to two standard deviations beyond the mean we
need:

Z = (2 * E) / Y

Solving for E,

E = (Z * Y) / 2

This puts your mean throw as

( 100 * X ) + ((Z * Y) / 2)

and the standard deviation of your throw as

(Z * Y) / 4

So at least we have the distribution of your throw in terms of your friend's
bet parameters.

I'm sure there's a way to calculate payback by the probability of each Y
segment but I don't have that yet.

Paul

==============================================================================
TOPIC: MI5 Persecution: BA984 LHR->TXL 13/6/98 (1082)
http://groups.google.com/group/sci.stat.math/browse_thread/thread/d9cf6020e726a8e1?hl=en
==============================================================================

== 1 of 1 ==
Date: Fri, Nov 16 2007 6:51 pm
From: MI5Victim@mi5.gov.uk

BA984 LHR->TXL 13/June/1998

Certainty level: 100%

In June 1998 I travelled on the above British Airways flight to Berlin
with my mother, to visit her family. There were two women in seats 30D/E,
about 4/5 rows behind us. It was quite obvious from the torrent of abuse
during these flight that these women had been instructed to harass me
and attempt to obtain a reaction.

I did manage to record much of the flight, but unfortunately much of the
recording is unclear because of high background noise on the aircraft.
The following three excerpts from the recording are the best I can do.

The segment at position 11:34 minutes on my recording contains a fairly
quiet word "paranoid", followed immediately by a much louder
"yeah, he's paranoid, yeah". During the flight the abuse was not sexual,
as it so often is elsewhere, but attacking my mental health.

One of the women in seats 30D/E said "paranoid" very clearly towards the
end of the flight, but unfortunately I had run out of minidisc space and
stopped recording by then. There is absolutely no doubt in my mind that
these women were directed to harass me. This harassment happens without
fail on British Airways flights; I've been on something like three or
four BA flights in the last 5 years and it's happened each time.
Presumably this is because of international law which says incidents on
aircraft during flight are actionable in the airline's country of
origin - so my persecutors want a reaction from me, and they want to see
me "done" in the UK where they can influence the justice system.

These incidents never happen on foreign-domiciled carriers.

1082

--
Posted via NewsDemon.com - Premium Uncensored Newsgroup Service
------->>>>>>http://www.NewsDemon.com<<<<<<------
Unlimited Access, Anonymous Accounts, Uncensored Broadband Access

==============================================================================
TOPIC: MI5 Persecution: BHS Croydon 18/12/98 (3257)
http://groups.google.com/group/sci.stat.math/browse_thread/thread/a3d90586dd5ff00e?hl=en
==============================================================================

== 1 of 1 ==
Date: Fri, Nov 16 2007 8:10 pm
From: MI5Victim@mi5.gov.uk

Evil old bat in BHS 18/12/98

Certainty level: 40%

Not quite sure how sure I am about this one. I went down to Croydon (Surrey)
with my mother to buy her a beret. After doing the shopping, we went to
the BHS store restaurant to lunch on fish and chips.

You can guess the rest. Auditory hallucinations my shrink calls them,
faithfully recorded on Sony minidisc. Some old cow going on about
"see that chap, the one over there, something's wrong with him".

It is quite tiring being attacked by random idiots in the street, or as
in this case, by some random, evil old bat in a restaurant. Fortunately
it is only a sporadic occurrence. My enemies seem of late reluctant to
waste resources in my direction. Should I take this as an insult? Am I not
worth the millions of taxpayers money which has been wasted on me? Are the
obsessives of MI5 themselves the "nutters" and "really mad" which they
accuse me of being? Interestingly this suggestion as to the psychological
profiles of Security Service personnel has been made by others... it does
lead one to wonder, doesn't it?

3257

--
Posted via NewsDemon.com - Premium Uncensored Newsgroup Service
------->>>>>>http://www.NewsDemon.com<<<<<<------
Unlimited Access, Anonymous Accounts, Uncensored Broadband Access

==============================================================================

You received this message because you are subscribed to the Google Groups "sci.stat.math"
group.

To post to this group, visit http://groups.google.com/group/sci.stat.math?hl=en

To unsubscribe from this group, send email to sci.stat.math-unsubscribe@googlegroups.com

To change the way you get mail from this group, visit:
http://groups.google.com/group/sci.stat.math/subscribe?hl=en

To report abuse, send email explaining the problem to abuse@googlegroups.com

==============================================================================
Google Groups: http://groups.google.com?hl=en

Statistika For Life

Sabtu, 17 November 2007

20 new messages in 10 topics - digest

Tidak ada komentar:

Arsip Blog

Mengenai Saya