Normal Distribution Function

Source: Internet
Author: User

1) use MATLAB to draw a probability density function image with a normal distribution.
X = [-.];
Y = normpdf (x, 0, 1); % normal distribution function.
Figure;
Axes1 = axes ('pos', [0.1 0.1 0.85 0.85]);
Plot (x, y );
Set (axes1, 'ylim', [-0.01 0.43], 'xlim', [-3 3]);
Figure 1:

2) Verify that the point of the probability density function in the interval (-∞, ∞) is 1.
Here, the mu = 3 and Sigma = 5 parameters are used (Note: all these two parameters are used below ).
Y = 'exp (-1/2 * (X-3)/5) ^ 2)/(SQRT (2 * PI) * 5 )';
S = int (Y,-INF, INF) % int integral function (INF stands for infinity ).
Output: S = 1

3) the maximum value is obtained when x = Mu is verified.
Idea: Solve the point where the first derivative of the function is zero.

* First Derivative
Y = 'exp (-1/2 * (X-3)/5) ^ 2)/(SQRT (2 * PI) * 5 )';
D = diff (y); % differential function.
SD = simplify (d)
Output result: SD =-1/250 * (X-3) * exp (-1/50 * (X-3) ^ 2) * 2 ^ (1/2)/PI ^ (1/2)

* Determine the resolution position through the image
X = [0: 0.];
SD =-1/250.*(X-3 ). * exp (-1/50.*(X-3 ). ^ 2 ). * 2. ^ (1/2 ). /PI. ^ (1/2 );
Axes1 = axes ('pos', [0.1 0.1 0.85 0.85]);
Plot (x, SD );
Set (axes1, 'ylim', [-0.01 0.01], 'xlim', [0 40]);
Figure 2:

We can see that there is a solution near 3.

* Define and solve Functions
Function Y = f (x)
Y =-1/250.*(X-3 ). * exp (-1/50.*(X-3 ). ^ 2 ). * 2. ^ (1/2 ). /PI. ^ (1/2 );

R = fzero ('F', 3)
Output: r = 3

From the figure above, we can see that x> 20 is almost a straight line. If 20 is used:
R = fzero ('F', 20)
Output: r = 3

This means that it is infinitely close to 0.

* The value of this parameter is the maximum value.
The first derivative of the probability density function is 0 and the result is 3, which is exactly Mu, and then the function of x = 1, x = 4 and x = 3.Value comparison.
> Normpdf (1, 3, 5)
Ans = 0.0737

> Normpdf (4, 3, 5)
Ans = 0.0782

> Normpdf (3,3, 5)
Ans = 0.0798

Obviously, the function values on both sides of X = 3 are smaller than those on X = 3, indicating that this point is the maximum point. Graph Based on the Normal Distribution FunctionWe can see that this point is the maximum value.

4) Verify that X = Mu +-sigma (8 or-2) has an inflection point.
Idea: Calculate the point where the second derivative is zero.

* First obtain Second-Order Differentiation
Y = 'exp (-1/2 * (X-3)/5) ^ 2)/(SQRT (2 * PI) * 5 )';
D = diff (Y, 2); % differential function.
SD = simplify (d)
Output: SD = 1/6250 * exp (-1/50 * (X-3) ^ 2) * 2 ^ (1/2) * (-16 + x ^ 2-6 * X) /PI ^ (1/2)

* Determine the resolution position through the image
X = [-20:0. 00];
SD = 1. /6250. * exp (-1/50.*(X-3 ). ^ 2 ). * 2. ^ (1/2 ). * (-16 + X. ^ 2-6. * X)/PI. ^ (1/2 );
Axes1 = axes ('pos', [0.1 0.1 0.85 0.85]);
Plot (x, SD );
Set (axes1, 'ylim', [-0.005 0.005], 'xlim', [-20]);
Figure 3:
It can be seen that the curves between (-) and () have an intersection with Y = 0, so there are two solutions.

* Define and solve Functions
Function Y = f (x)
Y = 1. /6250. * exp (-1/50.*(X-3 ). ^ 2 ). * 2. ^ (1/2 ). * (-16 + X. ^ 2-6. * X)/PI. ^ (1/2 );

R = fzero ('F',-5)
R =-2

> R = fzero ('F', 5)
R = 8.0000.

Two inflection points x = 8 and x =-2 are obtained, namely, Mu +-sigma.

5) solve the verification curve with the X axis as the gradient line:
A vertical gradient Line X = A is the gradient line of Y = f (x) <=> Lim f (x) = ∞ or Lim f (x) = ∞
X-> A + 0 x-> a-0
Among them, a is found in the intermittent point -- ∞ type second type of intermittent point B horizontal gradient nearline
X → + ∞ (-∞), Y = B is the gradient line of Y = f (x) <=> Lim f (x) = B (or Lim f (x) = B)
X-> + ∞ X->-∞

Calculate the limit value B when the first order is reciprocal to X tends to infinity. If yes, there is a horizontal gradient line y = B.
* Define the function first:
Function Y = f (x)
Syms X; % defines symbol variables.
Y = exp (-1/2 * (X-3)/5) ^ 2)/(SQRT (2 * PI) * 5 );

* Returns the limit of the first derivative when x tends to infinity.
Limit (F, INF)
Ans = 0

6) Verify the three Sigma rule
Train of Thought: Solve the points of the probability density function in the [mu-3 * Sigma, Mu + 3 * Sigma] interval.
Y = 'exp (-1/2 * (X-3)/5) ^ 2)/(SQRT (2 * PI) * 5 )';
Double (INT (Y,-12, 18 ))
Ans = 0.9973

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.