sssCHAPTER 5. Introduction To Estimation 23

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 5

31/03/2023

CHAPTER 5
ESTIMATION

Dr. Lam Son


sonlam@ftu.edu.vn
033.6969.909

1
31/03/2023

2
31/03/2023

Example. The height of young people in a locality


is a normally distributed random variable with a  u  u  
standard deviation of 10cm. Randomly selecting P X −  2    X +  2  =1−
30 young men from that region, their average  n n 
height is 170. From the result of the experiment, we have: x = 170;n = 30
a. Estimate the average height of young people
there with 95% confidence. and u /2 = 1.96
b. b. Find the probability that the average height of
the youth there does not exceed 172cm. We have a confidence interval for population mean:

 1.96.10 1.96.10 
Let X be the height of young people in a locality 170 − ; 170 + 
 30 30 
 X N (  ;102 )
= (166.42; 173.58 )
 u  u  
P X −  2    X +  2  =1−
 n n 

a. b. Find the probability that the average height of Case 2: σ 2is unknown
the youth there is not more than 172cm.
 S S 
 u .  P  X − t(n2−1)    X + t(n2−1)  = 1− 
P X +   =1−  n n
 n 
From the result of the experiment, we have: x = 170;n = 30  S 
P    X + t(n −1)  = 1−
u . n 30
 n
 = 2  u = = = 1.1
n  10
  = 0.3643  t (n −1)S 
 1 −  = 1 − 0.3643 = 0.8657 (confidence)
P X −     = 1−
 n 

 (n −1) S S 
Example.  X − t 2 ; X − t(n2−1) 
To estimate the average height of male students in university  n n
A, the height of 25 randomly selected male students was
measured and the following results were obtained:
x = 170,16 s 2 = 5,223 s = 2,285
Height 166 168 170 172 175  = 1 −  = 1 − 0,95 = 0,05
number of people 2 5 10 6 2
Estimate the average height of a male student with 95% t(n2−1) = t0( ,24025) = 2,064
confidence.
Confidence interval for the average height of a
male student with 95% confidence is:
 2,285 2,285 
170,16 − 2,064 ; 170,16 + 2,064. 
 25 25 
= ( 169,216; 171,103)

3
31/03/2023

Estimating 2 :
Example.
The size of a machine part is a normally distributed
random variable. Taking a sample of 30 machine parts, we
 (n − 1)S 2 (n − 1)S 2  calculate sample mean 0.47 and sample variance 0.032.
P  2(n −1)   
2
 =1− With 95% confidence, estimate the size dispersion of the
  2 12(−n −21)  entire machine part.
  (n − 1)S 2
P  2(n −1)   2 
(n − 1)S 2 
 =1−
  2 12(−n −21) 

 2 (n − 1)S 2  From the result of the experiment, we have: s 2 = 0.032;n = 30
P    =1−
12(−n −1)   0.025 = 45.72;  0.975 = 16.05
2(29) 2(29)

 We have a confidence interval for population mean:

 (n − 1)S  2  (30 − 1)0.0322 (30 − 1)0.0322 


P  2(n −1)   2  = 1 −   
;
 45.72 16.05 
   =(0,000649; 0,001851)

 u 2 p (1 − p ) u 2 p (1 − p ) 
Pp − pp+  = 1−
 n n 
 

 u p (1 − p ) 

P pp+  = 1− ( 2)
 n 
 
 u p (1 − p ) 
Pp −   p  = 1− ( 3)
 n 
 

Example.
To evaluate the percentage of moldy materials in the
warehouse. They randomly selected 300 bags from that
warehouse and found that 45 bags were moldy. If the
percentage of mold materials in stock is 15%, with an error of
5%, what is the reliability?
 u 2 f (1 − f ) 
P p −f   = 1−
 n 
 
45
f = = 15%, n = 300,  = 0,05
300
 n
u 2 = = 2,43
f (1 − f )
 = 0,015   = 98,5%

4
31/03/2023

You might also like