Estimation of Parameters 2

t- Distribution
This is a probability distribution which is utilized in

estimating parameters of a certain population in case of
the sample size is small and/or the population variance
or standard deviation is unknown. It was formulated by
an Irish brewing employee William S. Gosset in 1908.
He published his finding using the pseudonym Student
t, hence, t-distribution is sometimes called Student's t-
distribution.
t- Distribution
Properties of t- Distribution
1. It is bell-shaped curve symmetrical about the mean
and is unimodal.
2. The mean of the distribution is equal to 0 and is
located at the center of the distribution.
3. The curve is asymptotic to the x-axis.
4. The variance of the distribution is always greater than
1. This makes it flatter and wider at the middle.
5. The variance of the distribution is equal to
𝑑𝑓 / (𝑑𝑓 − 2), where df is the degree of freedom.
t- Distribution
If sample sizes are small, sometimes the population
standard deviation or variance is unknown, rely on the t-
distribution whose value can be known using:
(𝒙−𝝁)
𝒕= 𝒔
𝒏
where:
𝑥 – sample mean 𝜇 – population mean
s – standard deviation n – sample size
t- Distribution Table
Identifying t- value
To denote the t-value, it is conveniently written as
𝑡 𝛼 ,𝑑𝑓 . So, if you are asked on the t-value denoted by
𝑡 0.05 ,8 means the t-value corresponding to 𝛼 = 0.05 and
df = 8.
Identifying Percentiles Using t- Distribution Table
Percentile is one of the measurements in statistics
which tells the value below in which an observations’
percentage in a set of observations falls.
Illustrative Example 1:
n = 14 Percentile = 95th 𝑡(𝛼,𝑑𝑓) =
Solution:
To find the value of 95th percentile, identify first the
degrees of freedom.
Solution:
To solve for 95th percentile, we need to understand first
its implication which is to get the t-value that is less than
the probability 0.95 and the right tail probability that is
0.05.
df = 11 Percentile = 90th 𝑡(𝛼,𝑑𝑓) =
The graph of a distribution with df = 15 is shown below.
The shaded area on the right is 0.05, find the value of
t1 ?
The graph of a distribution with df = 15 is shown below.
The shaded area on the right is 0.05, find the value of
t1 ?
Length of Confidence Interval
Estimation – process of determining parameter values
Estimate – a value or a range of values that approximate
a parameter. It is based on sample statistics computed
from sample data.
Interval Estimate – also called confidence interval, is a
range of values that is used to estimate a parameter. In
using interval estimate, confidence level are used.
Commonly used confidence level are (90%, 95%, 99%)
Confidence Level – refers to the probability that the
confidence interval contains the true population
parameter. Its value is
Confidence Level = ( 1 - α )100%
where α = probability that the confidence interval does
not contain the true population parameter
Critical Value– the value that indicated the point beyond
which lies the rejection region. This region does not
contain the true population parameter.
Interval Estimate of Population Mean with Known
Variance
𝜎 𝜎 𝜎
𝑥 ± 𝑍𝛼 𝑜𝑟 𝑥 − 𝑍𝛼 < 𝜇 < 𝑥 + 𝑍𝛼
2 𝑛 2 𝑛 2 𝑛
𝑥 – sample mean
𝜎 – population standard deviation
n – sample size
𝜎
𝑍𝛼 2 – margin of error that refers to the maximum
𝑛
allowable difference between the sample and true value
Common Confidence Levels with their
Corresponding Reliability Factor
( 1 - α ) 100% 𝒁𝜶
𝟐
Confidence Level
99% 2.575
95% 1.96
90% 1.645
Identify and compute the length of confidence interval
Confidence level = 95% σ = 9 n = 20 𝑥 = 56
Confidence level = 95% σ = 9 n = 20 𝑥 = 56
𝜎 𝜎
𝑥 − 𝑍𝛼 < 𝜇 < 𝑥 + 𝑍𝛼
2 𝑛 2 𝑛
9 9
56 – 𝑍0.05 2 < 𝜇 < 56 + 𝑍0.05 2
20 20
9 9
56 – 1.96 < 𝜇 < 56 + 1.96
20 20
56 – 3.94< 𝜇 <56 + 3.94
52.06< 𝜇 < 59.94 or (52.06,59.94)
The mean score of a random sample of 49 Grade 11
students who took the first periodic test of Statistics
and Probability is calculated to be 78. The population
variance is known to be 0.16. Find the 95% confidence
interval for the mean of the entire Grade 11 students.
Confidence level = 95% σ = 0.4 n = 49 𝑥 = 78
𝜎 𝜎
𝑥 − 𝑍𝛼 < 𝜇 < 𝑥 + 𝑍𝛼
2 𝑛 2 𝑛
0.4 0.4
78 – 𝑍0.05 2 < 𝜇 < 78 + 𝑍0.05 2
49 49
0.4 0.4
78 – 1.96 < 𝜇 < 78 + 1.96
49 49
78 – 0.112< 𝜇 <78 + 0.112
77.888< 𝜇 < 78.112 or (77.89,78.11)
Interval Estimate of Population Mean with Unknown
Variance
𝑠 𝑠
𝑥− 𝑡 𝛼
,𝑛−1
<𝜇<𝑥+ 𝑡 𝛼
,𝑛−1
2 𝑛 2 𝑛
𝑥 – sample mean
𝑠 – population standard deviation
n – sample size
𝑠
𝑡 𝛼,𝑛−1 – margin of error that refers to the maximum
2 𝑛
allowable difference between the sample and true value
Confidence level = 95% s=3 n = 25 𝑥 = 30
Solution:
𝑠 𝑠
𝑥− 𝑡 𝛼
,𝑛−1
,𝑛−1
2 𝑛 2 𝑛
3 3
30 − 𝑡 0.05 < 𝜇 < 30 + 𝑡 0.05
,25−1 25 ,25−1 25
2 2
3 3
30 − 𝑡 0.025,24 < 𝜇 < 30 + 𝑡 0.025,24
25 25
Confidence level = 95% s = 3 n = 25 𝑥 = 30
Solution:
3 3
30 − 2.064 < 𝜇 < 30 + 2.064
25 25
30 − 1.24 < 𝜇 < 30 + 1.24
28.76 < 𝜇 < 31.24
The following are randomly selected scores in Filipino
test of twelve Grade 10 students:
75 65 76 80 85 77
81 83 80 70 71 69
Find a 99% confidence interval for the mean score of all

grade 10 students, assuming that the students' score is
approximately normally distributed.
STUDENT x x-𝒙 ( x - 𝒙 )2
1 75 75 - 76 = -1 1
2 65 65 - 76 = -11 121
3 76 76 - 76 = 0 0
4 80 80 - 76 = 4 16
5 85 85 - 76 = 9 81
6 77 77 - 76 = 1 1
7 81 81 - 76 = 5 25
8 83 83- 76 = 7 49
9 80 80 - 76 = 4 16
10 70 70 - 76 = -6 36
11 71 71 - 76 = -5 25
12 69 69 - 76 = -7 49
Σx = 912 Σ( x - 𝒙 )2 = 420
STUDENT x x-𝒙 ( x - 𝒙 )2
1 75 75 - 76 = -1 1
2 65 65 - 76 = -11 121
3 76 76 - 76 = 0 0
4 80 80 - 76 = 4 16
5 85 85 - 76 = 9 81
6 77 77 - 76 = 1 1
7 81 81 - 76 = 5 25
8 83 83- 76 = 7 49
9 80 80 - 76 = 4 16
10 70 70 - 76 = -6 36
11 71 71 - 76 = -5 25
12 69 69 - 76 = -7 49
Σx = 912 Σ( x - 𝒙 )2 = 420
Confidence level = 99% s = 6.18 n = 12 𝑥 = 76
𝑠 𝑠
𝑥− 𝑡 𝛼
,𝑛−1
,𝑛−1
2 𝑛 2 𝑛
6.18 6.18
76 − 𝑡 0.01 < 𝜇 < 76 + 𝑡 0.01
,12−1 12 ,12−1 12
2 2
6.18 6.18
76 − 𝑡 0.005,11 < 𝜇 < 76 + 𝑡 0.005,11 𝑥
12 12
Confidence level = 99% s = 6.18 n = 12 𝑥 = 76
6.18 6.18
76 − 3.106 < 𝜇 < 76 + 3.106
12 12
76 − 5.54 < 𝜇 < 76 + 5.54
70.46 < 𝜇 < 81.54
Appropriate Sample Size Using Length of the Interval
In estimating, the sample size needs to be
considered in order to make it more valid and reliable.
Especially on research, the number of participants must
be considered. The number of members or element of a
population must be taken into consideration aside from
being manageable. With this, the researcher/s will be
able to make a feasible conclusion about the parameter
of a certain population being studied.
Appropriate Sample Size Using Length of the Interval
The following formula can be used to determine the
appropriate sample size.
𝑧∝ 𝜎 2
2
𝑛=
𝐸
𝑧∝ − critical value based on the desired confidence level
2
𝐸 − desired margin of error
𝜎 − population standard deviation
Find the minimum sample size required to estimate an
unknown population mean using the following given
data.
Confidence level = 95%
Margin of error = 75
Standard deviation = 250
Confidence level = 95% E = 75 σ= 250
𝑧∝ 𝜎 2
2
𝑛=
𝐸
2
𝑧0.05 (250)
2
𝑛=
75
2
1.96(250)
𝑛=
75
𝑛 = 42.68 ≈ 43
A bookstore confirms that the durability of their textbooks
follows a normal distribution with a standard deviation of
5 years. How many textbooks must be selected as
samples if you wanted to estimate with 99% confidence
that the sample mean is within 2 years of the true
population mean?
Given: Standard deviation = 5 Confidence Level = 99%
Margin of Error = 2
𝑧∝ 𝜎 2
2
𝑛=
𝐸
2
𝑧0.01 (5)
2
𝑛=
2
2
2.575(5)
𝑛=
2
𝑛 = 41.44 ≈ 42

Estimation of Parameters 2

Uploaded by

Copyright:

Available Formats

Estimation of Parameters 2

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Estimation of Parameters 2

Uploaded by

Copyright:

Available Formats

t- Distribution

This is a probability distribution which is utilized in

Find a 99% confidence interval for the mean score of all

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.