ผลต่างระหว่างรุ่นของ "Probstat/notes/chi-squared distribution"

จาก Theory Wiki
ไปยังการนำทาง ไปยังการค้นหา
 
(ไม่แสดง 3 รุ่นระหว่างกลางโดยผู้ใช้คนเดียวกัน)
แถว 2: แถว 2:
  
 
== Definition ==
 
== Definition ==
 
+
{{กล่องฟ้า|
Let <math>Z_1,Z_2,\ldots,Z_n</math> be independent unit normal random variables.  A random variable
+
'''Definition:''' Let <math>Z_1,Z_2,\ldots,Z_n</math> be independent unit normal random variables.  A random variable
  
 
<center>
 
<center>
แถว 9: แถว 9:
 
</center>
 
</center>
  
is called a ''chi-squared'' random variable with <math>n</math> degree of freedom.  We also write
+
is called a ''chi-squared'' random variable with <math>n</math> degrees of freedom.  We also write
  
 
<center>
 
<center>
 
<math>X\sim \chi_n^2.</math>
 
<math>X\sim \chi_n^2.</math>
 
</center>
 
</center>
 +
}}
  
 
Wikipedia has a [http://en.wikipedia.org/wiki/Chi-squared_distribution nice article on chi-squared distribution] which also includes plots of its pdf and cdf.
 
Wikipedia has a [http://en.wikipedia.org/wiki/Chi-squared_distribution nice article on chi-squared distribution] which also includes plots of its pdf and cdf.
แถว 23: แถว 24:
 
=== Expectations and variances ===
 
=== Expectations and variances ===
  
If <math>X</math> is chi-squared with <math>n</math> degree of freedom, we have that its expectation
+
If <math>X</math> is chi-squared with <math>n</math> degrees of freedom, we have that its expectation
  
 
<center>
 
<center>
แถว 50: แถว 51:
 
</center>
 
</center>
  
Note that the only differences between this term and the previous one is the use of sample mean <math>\bar{X}</math> instead of the population mean.  It can be proved (not here) that in fact, for normal population, <math>S^2</math> (with some scaling) is actually a chi-squared random variable with <math>n-1</math> degree of freedom.  That is,
+
Note that the only differences between this term and the previous one is the use of sample mean <math>\bar{X}</math> instead of the population mean.  It can be proved (not here) that in fact, for normal population, <math>S^2</math> (with some scaling) is actually a chi-squared random variable with <math>n-1</math> degrees of freedom (instead of <math>n</math> as in the term computed from <math>\mu</math>).  That is,
  
 
<center>
 
<center>

รุ่นแก้ไขปัจจุบันเมื่อ 20:23, 5 ธันวาคม 2557

This is part of probstat.

Definition

Definition: Let be independent unit normal random variables. A random variable

is called a chi-squared random variable with degrees of freedom. We also write

Wikipedia has a nice article on chi-squared distribution which also includes plots of its pdf and cdf.

Properties

Here we states important properties of the chi-squared distribution without proofs.

Expectations and variances

If is chi-squared with degrees of freedom, we have that its expectation

and its variance

Sample variances

The chi-squared distribution is very important when we want to reason about the sample variances (See notes). Under that settings, we sample from a normal population whose mean is and variance is .

We first note that if and is known, a term similar to the one we used to compute the same variance is chi-squared. Recall that is unit normal. Therefore,

However, usually, is unknown and we are left to the sample variance, defined as

.

Note that the only differences between this term and the previous one is the use of sample mean instead of the population mean. It can be proved (not here) that in fact, for normal population, (with some scaling) is actually a chi-squared random variable with degrees of freedom (instead of as in the term computed from ). That is,

More over, for normal population, and are independent. This is very surprising because both quantities are calculated from the same sample.

These two facts are important in the development of the procedure for calculating confidence intervals in case where is unknown. (See notes.)

Two important facts about sample means and sample variances:

1.

2. and are independent.

Links