Re: Inverse of NORMSDIST function - Algorithms Discussion Boards

sumit70343-Jul-08 18:10

3-Jul-08 18:10

How to find Inverse of NORMSDIST function

ie NORMSINV

It Returns the inverse of the standard normal cumulative distribution. The distribution has a mean of zero and a standard deviation of one.

Syntax

double NORMSINV(double probability)

Probability is a probability corresponding to the normal distribution.

Re: Inverse of NORMSDIST function

Dan3-Jul-08 18:12

Dan

3-Jul-08 18:12

1 / NORMSDIST

Re: Inverse of NORMSDIST function

sumit70343-Jul-08 18:38

sumit7034

3-Jul-08 18:38

thanks 4 reply
But I m not getting exact answer when i match my answer from ms excel

Re: Inverse of NORMSDIST function

⁷³Zeppelin3-Jul-08 21:34

⁷³Zeppelin

3-Jul-08 21:34

No, that's not what is meant by "inverse". It's the inverse distribution function he's looking for.

I'm the ocean. I'm a giant undertow.

Re: Inverse of NORMSDIST function

cp98763-Jul-08 18:43

cp9876

3-Jul-08 18:43

You should check out http://www.google.com.au/codesearch[^] first when you have a well known function that you want, I had a quick check and there seems to be implementations there.

Peter
"Until the invention of the computer, the machine gun was the device that enabled humans to make the most mistakes in the smallest amount of time."

Re: Inverse of NORMSDIST function

sumit70343-Jul-08 19:40

sumit7034

3-Jul-08 19:40

I Didn't see any implementations there. If u have seen any then plz provide some link.

Re: Inverse of NORMSDIST function

cp98763-Jul-08 19:51

cp9876

3-Jul-08 19:51

There are multiple implementations there - it is really in your interest to learn how to search for them. I bet you simply typed in "NORMSINV" and just got lots of references to uses of the function, gave up and came back here. You have to be a little creative and try to make the search engine find function definitions. I went to the same page and with my next search came up with several implementations.

Peter
"Until the invention of the computer, the machine gun was the device that enabled humans to make the most mistakes in the smallest amount of time."

Re: Inverse of NORMSDIST function

⁷³Zeppelin3-Jul-08 21:43

⁷³Zeppelin

3-Jul-08 21:43

The inverse CDF of the normal distribution doesn't have an analytical form. You can find an approximation here[^].

The other place to look is in the online version of Numerical Recipes[^]. They have an algorithm for the inverse normal CDF.

You can also use the following taken from here[^].

What is a good approximation to the inverse of the 
cumulative normal distribution function? Mathematically we can 
write this as: Find X such that Q(X) = p for any 0 < p < 1. 
(Note: this computes an upper tail probability.) Again, it is 
not possible to write this as a closed form expression, so we 
resort to approximations. Because of the symmetry of the normal distribution, 
we need only consider 0 < p < 0.5. If you 
have p > 0.5, then apply the algorithm below to q = 1-p, 
and then negate the value for X obtained. (This approximation 
is also from Abramowitz and Stegun.) 

t = sqrt[ ln(1/p^2) ] 


           c_0 + c_1*t + c_2*t^2 
X = t - ------------------------------ 
         1 + d_1*t + d_2*t^2 + d_3*t^3 


c_0 = 2.515517 
c_1 = 0.802853 
c_2 = 0.010328 
d_1 = 1.432788 
d_2 = 0.189269 
d_3 = 0.001308 

See Abramowitz and Stegun; Press, et al.

You should Google a little harder instead of always asking here. These algorithms were worked out a long time ago and have been available for a long time.

I'm the ocean. I'm a giant undertow.

Re: Inverse of NORMSDIST function

Paul Conrad23-Jul-08 12:18

Paul Conrad

23-Jul-08 12:18

73Zeppelin wrote:
You should Google a little harder instead of always asking here

I think it is more of a case of sheer laziness. He's asking about the FDIST function now, and I pointed him to Wolfram's Mathworld.

"The clue train passed his station without stopping." - John Simmons / outlaw programmer

"Real programmers just throw a bunch of 1s and 0s at the computer to see what sticks" - Pete O'Hanlon

NORMSDIST function

sumit70342-Jul-08 22:28

sumit7034

2-Jul-08 22:28

How to find NORMSDIST function of ms excel.It Returns the standard normal cumulative distribution function. The distribution has a mean of 0 (zero) and a standard deviation of one. Use this function in place of a table of standard normal curve areas.

Syntax

NORMSDIST(z)

Z is the value for which you want the distribution.

Thanks

I know,

CPallini2-Jul-08 22:51

CPallini

2-Jul-08 22:51

drinking beer is a wonderful experience.
Big Grin | :-D

If the Lord God Almighty had consulted me before embarking upon the Creation, I would have recommended something simpler.
-- Alfonso the Wise, 13th Century King of Castile.

This is going on my arrogant assumptions. You may have a superb reason why I'm completely wrong.
-- Iain Clarke

[My articles]

Re: I know,

sumit70342-Jul-08 23:50

sumit7034

2-Jul-08 23:50

What do u Mean?

Re: I know,

CPallini2-Jul-08 23:54

CPallini

2-Jul-08 23:54

Don't you agree on beer drinking statement?
Big Grin | :-D

Re: I know,

sumit70343-Jul-08 0:04

sumit7034

3-Jul-08 0:04

No
If u know the answer plz tell me..

Re: I know,

CPallini3-Jul-08 0:11

CPallini

3-Jul-08 0:11

How can I answer if there is NO question?
Smile | :)

Re: I know,

sumit70343-Jul-08 0:28

sumit7034

3-Jul-08 0:28

i want to make function to calculate Normsdist like this:---

Public Function calculateNormsdist(ByVal z As Single) As Single

and it will give the answer
can u implement it??

Re: I know,

cp98763-Jul-08 0:52

cp9876

3-Jul-08 0:52

sumit7034 wrote:
can u implement it??

yes

Peter
"Until the invention of the computer, the machine gun was the device that enabled humans to make the most mistakes in the smallest amount of time."

Re: I know,

CPallini3-Jul-08 0:56

CPallini

3-Jul-08 0:56

sumit7034 wrote:
can u implement it??

cp9876 wrote:
yes

I was pretty sure about.
Big Grin | :-D

Re: I know,

sumit70343-Jul-08 1:36

sumit7034

3-Jul-08 1:36

plz implement it Laugh | :laugh:

Re: I know,

Paul Conrad3-Jul-08 18:32

Paul Conrad

3-Jul-08 18:32

sumit7034 wrote:
plz implement it

Why him? Can't you?

"The clue train passed his station without stopping." - John Simmons / outlaw programmer

"Real programmers just throw a bunch of 1s and 0s at the computer to see what sticks" - Pete O'Hanlon

Re: I know,

CPallini3-Jul-08 0:53

CPallini

3-Jul-08 0:53

sumit7034 wrote:
i want to make function

sumit7034 wrote:
can u implement it?

The two statements above are in contraddiction (unless sumit7034 and cpallini are the same person Roll eyes | :rolleyes:

).

BTW Now your question is clear, but is too broad and a bit lazy: what have you done so far? What are your troubles about?
I mean, numerically computing the cumulative of the normal distribution isn't such a daunting task, I suppose.
Smile | :)

Re: NORMSDIST function

⁷³Zeppelin3-Jul-08 2:11

⁷³Zeppelin

3-Jul-08 2:11

Implementation 1:

// returns the cumulative normal distribution function (CNDF)
// for a standard normal: N(0,1)
double CNDF(double x)
{
	int neg = (x < 0);
	if ( neg ) 
		x *= -1;

	double k(1/(1+0.2316419*x));
	double y=((((1.330274429*k-1.821255978)*k+1.781477937)*k-0.356563782)*k+0.319381530)*k;
	y = 1.0 - 0.398942280401*exp(-0.5*x*x)*y;
	
	return (1-neg)*y + neg*(1-y);
}

Implementation 2

// another implementation of the CNDF
// for a standard normal: N(0,1)
double CumNorm(double x)
{
	// protect against overflow
	if (x > 6.0)
		return 1.0;
	if (x < -6.0)
		return 0.0;

	double b1 = 0.31938153;
	double b2 = -0.356563782;
	double b3 = 1.781477937;
	double b4 = -1.821255978;
	double b5 = 1.330274429;
	double p = 0.2316419;
	double c2 = 0.3989423;

	double a = fabs(x);
	double t = 1.0 / (1.0 + a * p);
	double b = c2*exp((-x)*(x/2.0));
	double n = ((((b5*t+b4)*t+b3)*t+b2)*t+b1)*t;
	n = 1.0-b*n;
	
	if ( x < 0.0 )
		n = 1.0 - n;
	
	return n;
}