Path: news.mathworks.com!not-for-mail
From: "Ilco Petrov" <ili191@mail.ru>
Newsgroups: comp.soft-sys.matlab
Subject: Re: Log CDF and PDF
Date: Mon, 20 May 2013 12:48:08 +0000 (UTC)
Organization: Russian University fo OIl And Gas
Lines: 71
Message-ID: <knd628$7kl$1@newscl01ah.mathworks.com>
References: <kncpu3$4bc$1@newscl01ah.mathworks.com> <14d25051-36d7-4458-93c8-3f3b844dc1b4@googlegroups.com>
Reply-To: "Ilco Petrov" <ili191@mail.ru>
NNTP-Posting-Host: www-03-blr.mathworks.com
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
X-Trace: newscl01ah.mathworks.com 1369054088 7829 172.30.248.48 (20 May 2013 12:48:08 GMT)
X-Complaints-To: news@mathworks.com
NNTP-Posting-Date: Mon, 20 May 2013 12:48:08 +0000 (UTC)
X-Newsreader: MATLAB Central Newsreader 4319607
Xref: news.mathworks.com comp.soft-sys.matlab:795818

TideMan <mulgor@gmail.com> wrote in message <14d25051-36d7-4458-93c8-3f3b844dc1b4@googlegroups.com>...
> On Monday, May 20, 2013 9:21:07 PM UTC+12, Ilco Petrov wrote:
> > Dear friends,
> > 
> > %I  have defined some log regression with follolwing  CDF:
> > 
> > p=[0.001,0.01:0.01:1];
> > 
> > b1=0.01;
> > 
> > b2=0.5;
> > 
> > m=2;
> > 
> > bci2100=p./(1+(((log(p)/log(b1)+log(p)/log(b2)))./m).^m);
> > 
> > plot(p,bci2100)
> > 
> > % 0<p,bci, b1-2<=1
> > 
> > 
> > 
> > How can I define  in Matlab:
> > 
> > - PDF for bci with a.m.  dicrete'p' sequence;
> > 
> > - CDF and PDF for bci as continiuos function;
> > 
> > - generate random numbers  for 'p' (say sets of  50, 100, 200 for 'p') in (0:1)
> > 
> > - generate a detailed descriptive statistics report    real or random 'bci'(similar to Excel  and including mean, median, mode, stnandard deviation, sigma, standard mistakes, t-ststistics, hypothesis evaluation,) ; also relative and live reliblility
> > 
> > - Compare 'bci' to a normal distribution and model 'bci' parmeters (b,m) to influence Mu and sigma (location and scale parameters) so than bci to  be comparable to a normal distribution.
> > 
> > 
> > 
> > Please send comments to my email. 
> > 
> > Best regards
> > 
> > Ilian Petrov
> 
> It's a homework assignment, isn't it?
> What have you done towards solving the problem?
> Show us your code and where you're having trouble, then someone might help.
> Or would you prefer us to just give you the code?
> Then you could claim our work as your own.
> The English word for people who do that is: CHEAT.


Dear Sir (Mr TiedMan),
Thanks for being very quick, kind and polite in your own way!
I have all thinks in in Excel, where I did not have any problem! My publication is already published in a top oil and gas magazine!  
Sorry, I am new to Matlab, as I started to copy  my project to another package since it will   be a long project and  it is better to recheck resullts. And to see if Matlab is better as product and service support. So far the second is not obvious at all, but I guess you are not a typical case, rather an... 
It is not at all student homewok as I am a phd from Bulgaria (EU) based here in Moscow, where there are not much publications for Matlab, in Bulgaria also.
My colleages here in Moscow are very kind and the Matlab community  is very supportive and cooperative. But they work on technical aspects, while my project is in economics and there is no expertise in logistics distributions. The point is that my aproach to the log regression is specific and does not fit with typical ways of expression and formula. 
The questions I asked are routine - I am not asking you a code for a modelq Or some top secret data or individual algorithm.
If you have some publications and similar scrip, please simple advise - do not insult me!
I looked in your Distribution fitting tool, but there I can not load my formula, just data - I do not need that.
I already sent you my code for the bci, which is actually not 'vanila' log regression, but have some elements of neuron network even at this level.

If you do not have experience in log regressions, better do not be that agressive - you are talking to real persons and clients. The questions I asked are routine - I am not asking you a code for a model - just simple thinksabout simple technical instruments. And Matlab is not a unique progarm. You are not unique, also.
As far as I understand your job is to help people, not to insult them hiding behind the virtulal curtain and thinking you are untuchable. Giving technical  saaistance is not giving godness
My self, I am a lawyer, also.
So, kindly  I ask you to the  the following:
-  to make an official excuse to me personally to me and all readers for your impertinent expression, as this blog is public, but not yours and you are not at home. You are paid, I assume, to help custummers, not to insult them.
- to pass my questions to somebody who is more  polite and cooperative and our corespondence   to your boss for opinion and comment. 
Only an excuse will stop me develop a legal case in due time.

Expecting immediate excuse from you and/or your boss.
Ilian Petrov