MrMarc

3158 Reputation

18 Badges

16 years, 199 days

MaplePrimes Activity


These are replies submitted by MrMarc

sorry acer but it is not.  I do however sincerely appreciate your input :-)
I plotted your myPDF and myCDF and they appear to me to have the wrong shape.
They dont have the characteristic spike at -10 which an aggregated probability from -infinity to -Stop
will give you :-)

@alec thanx for your help and input  (Impressed that you managed to crack my identity ha ha )

 

 

sorry acer but it is not.  I do however sincerely appreciate your input :-)
I plotted your myPDF and myCDF and they appear to me to have the wrong shape.
They dont have the characteristic spike at -10 which an aggregated probability from -infinity to -Stop
will give you :-)

@alec thanx for your help and input  (Impressed that you managed to crack my identity ha ha )

 

 

 I think we are talking about different things here. The probability distribution I am talking with an N(0,20) with an stop

at -10 has a 0.308 probability of getting -10 because we sum all probabilities from -infinity to  -10.

The probability distribution we get with your Maple code has a  0.018 probability of getting -10 because it

simply cuts the distribution at -10. This is not what I want to achive but it might be the goal of someone ells ?!

 I think we are talking about different things here. The probability distribution I am talking with an N(0,20) with an stop

at -10 has a 0.308 probability of getting -10 because we sum all probabilities from -infinity to  -10.

The probability distribution we get with your Maple code has a  0.018 probability of getting -10 because it

simply cuts the distribution at -10. This is not what I want to achive but it might be the goal of someone ells ?!

 

The problem however as I see it is that C is no longer a Correlation Matrix after your transformation.

You have element that has a value of 3.55 etc . Wount this be a problem ?! 

 

The problem however as I see it is that C is no longer a Correlation Matrix after your transformation.

You have element that has a value of 3.55 etc . Wount this be a problem ?! 

I would like to be able to copy 2D input from Maple and simply past it to "new comment" window without having to worry

about formating. The equations/text should appear as in Maple. Now I have to first past it in a txt document and

rearange all the equation so it fits the original formating and then copy and past it into the "new comment" window..

 

Another thing I noticed is that when you copy  2D input from Maple and past it into a txt document all  :   becomes ;

for some reason. Also the structure (spacing, tabs etc) of the code completely disappears.

 

Another thing I would like to have is a button to upload images directly as the FileManager button.

Now I have to first upload the image to my files and then copy the link ( or more exactly copy haft the link because it does

not work if you copy the complete link as sugested for some reason ) and past it into the Isert / Edit Image is

a bit of a hassle :-)

 

No I cant get it to work man sorry :-)  Could you please post some code illustrating this.

The most important thing is that the mathcontainer is updated contineously and while the mathcontainer is

updated the user should be able to use Maple for other activities. The basic code could be for example something like:

 

SetProperty(MathContainer0, value, L1, refresh = true):
Do(%MathContainer0 = print(st)) ;

 

Another thing I dont understand is why is all the output printed when you call:   thread_done := true

In my opinion the output should be printed with 1 second intervals and not printed all at once

after you call  thread_done := true

 

No I cant get it to work man sorry :-)  Could you please post some code illustrating this.

The most important thing is that the mathcontainer is updated contineously and while the mathcontainer is

updated the user should be able to use Maple for other activities. The basic code could be for example something like:

 

SetProperty(MathContainer0, value, L1, refresh = true):
Do(%MathContainer0 = print(st)) ;

 

Another thing I dont understand is why is all the output printed when you call:   thread_done := true

In my opinion the output should be printed with 1 second intervals and not printed all at once

after you call  thread_done := true

ha, ha these comments were funny. Alec master of the universe (maybe maple universe)

Sound like something in a starwars movie :-)

Yes I agree with the original poster . I also find the assignment A:=45 a bit annoying.

In my opinion Maple should display A:=45 not just 45. Another thing that is a bit annoying is the inability to type 

"Variable X" = X:=A : Error, illegal use of an object as a name

which means that it can be difficult to keep track of which variable is which unless you

define the variable in two steps X:=A ;  "Variable X" = X which takes up a lot of space if you have many variables :-)

I started the survey but I found it to be to detailed and to long which meant that I did not have the energy to complete it :-)

 

I think I figured it out. Just for the sake of the argument and if someone else is searching for "copula" I will provide my solution.

The Gaussian Copula (Bivariate Distribution is Normal) plus some Meta-Gaussian Distributions (Marginal Distributions can be

different for example StudentT, Gumbel etc)  can be ploted as follows:

 

restart:

with(Statistics):   with(plots):

rho := 0: mu[x] := 0: mu[y] := 0: sigma[x] := 1: sigma[y] := 1:

N(x, y) = exp(-((x-mu[x])^2/sigma[x]^2-2*rho*(x-mu[x])*(y-mu[y])/(sigma[x]*sigma[y])+(y-mu[y])^2/sigma[y]^2)/(2*(1-rho^2)))/(2*Pi*sigma[x]*sigma[y]*sqrt(1-rho^2)) :

F := proc (x, y) options operator, arrow; (1/2)*exp(-(1/2)*x^2-(1/2)*y^2)/Pi end proc :

C := proc (u, v) options operator, arrow; F(Quantile(Normal(0, 1), u), Quantile(Normal(0, 1), v)) end proc :

 

We can now plot the copula function which maps the probabilities u and v as follows

 

plot3d(C(u, v), u = 0 .. 1, v = 0 .. 1, axes = box, title = ["Gaussian Copula Function", font = [times, bold, 18]], color = blue, labels = ["u", "v", "C"], font = [times, roman, 14]) ;




 







We can find the Joint Probability Density Function (PDF)  and plot the Bivariate Normal Distribution as follows

 

C(PDF(RandomVariable(Normal(0, 1)), x), PDF(RandomVariable(Normal(0, 1)), y));

plot3d(C(u, v), u = 0 .. 1, v = 0 .. 1, axes = box, title = ["Gaussian Copula Function", font = [times, bold, 18]], color = blue, labels = ["u", "v", "C"], font = [times, roman, 14]) ;
 

 

 

 

We can find the Joint Probability Density Function (PDF)  and plot the Bivariate Gumbel Distribution as follows

 

C(PDF(RandomVariable(Gumbel(0, 1)), x), PDF(RandomVariable(Gumbel(0, 1)), y)) ;

plot3d(C(PDF(RandomVariable(Gumbel(0, 1)), x), PDF(RandomVariable(Gumbel(0, 1)), y)), x = -5 .. 8, y = -5 .. 8, axes = box, title = ["Bivariate Gumbel", font = [times, bold, 18]], style = patchcontour, color = "PowderBlue", contours = 20, labels = ["x", "y", "P(x,y)"], font = [times, roman, 14]) ;

 

 

Note that the above road map with a Gaussian Copula as starting point can be used to find many purmutations of the above.

Many exotic joint distributions with different margins.... :-)

I like it !  :-)  

I like the fact that you can add comments.

The only think that I am missing is an easy way for the author to be able to update a worksheet that he has shared..

Ohh...I just discovered that it is possible :-)   "Edit this Application"   that is great !

Thanx Axel for sharing your work :-)

First 30 31 32 33 Page 32 of 33