Inferential statistics

Inferential statistics
The need to use the sample statistic to draw conclusions about the population characteristic is one

of the fundamental applications of statistical inference in business and economics.

On many occasions we do not have enough information to calculate an exact value of population

parameters () and therefore make the best estimate of this value from the corresponding sample

statistics ().

A single sample statistic () is calculated from the sample to provide a best estimate of the true value

of the corresponding population parameter ().

Inferential statistics

1) Mean:

2) Variance:

3) Standard Deviation:
 Confidence Intervals
a point estimate does not provide information about ‘how close is the estimate’ to the

population parameter unless accompanied by a statement of possible sampling errors

involved based on the sampling distribution of the statistic.

There are many applications where it is preferable to determine an interval within which we

would expect to find the value of the parameter.

An interval estimate for a population is called a confidence interval.

However, the confidence interval is constructed so that we have high confidence that it does

contain the unknown parameter.

Interval estimation of population mean
we want an interval such that X lies in this interval with probability 0.95.
𝑷 ( 𝒎𝒊𝒏< 𝑿<𝒎𝒂𝒙 ) =𝟎 . 𝟗𝟓 .
suppose we want an interval which is symmetric about zero i.e. between and .
0.95

So is where

0.025+0.95

−𝑑 𝑑
0.975

0.025 0.05/2=0.025
𝑑
5
 Confidence Intervals
Interval estimation of population mean

𝑿± 𝑬
𝝈
𝑬 =𝒁 𝒄 ∗
√𝒏

critical value of standard normal variable that

represents confidence level

𝑿−𝑬 𝑿 𝑿+𝑬
 Confidence Intervals
Interval estimation of population mean

(
𝑿 ± 𝒁𝒄 ∗
𝛔
√𝒏 )
(
𝑿 − 𝒁𝒄 ∗
𝛔
√𝒏 ) (
<𝝁< 𝑿 + 𝒁 𝒄 ∗
𝛔
√𝒏 )
 Confidence Intervals
Interval estimation of population mean
The value of Z at different significance levels

Confidence Level,

90% 0.10 0.05 1.645

95% 0.05 0.025 1.960
99% 0.01 0.005 2.576
 Confidence Intervals
Interval estimation of population mean
Example 1:
The average zinc concentration recovered from a sample of measurements in 36 different
locations in a river is found to be 2.6 gram/mm. Assume that the population standard
deviation is 0.3 gram/mm.
Find a 95% C.I. for the mean zinc concentration in the river.
𝜶
𝝈 =𝟎 .𝟑 𝒏=𝟑𝟔 𝒙 =𝟐 . 𝟔 𝜶 =𝟎 . 𝟎𝟓 =𝟎 .𝟎𝟐𝟓 𝒁 (𝟎 .𝟎𝟐𝟓 )=𝟏 . 𝟗𝟔
𝟐
𝝈 𝝈
𝒙
¯−𝒛 𝜶 < 𝝁< 𝒙
¯ +𝒛 𝜶
( 𝟐 ) √𝒏 ( 𝟐 ) √𝒏
𝟎.𝟑 𝟎.𝟑
𝟐.𝟔−𝟏.𝟗𝟔 <𝝁<𝟐.𝟔+𝟏.𝟗𝟔
√𝟑𝟔 √ 𝟑𝟔
𝟐.𝟓𝟎<𝝁<𝟐.𝟕𝟎
 Confidence Intervals
Interval estimation of population mean
Example 2:
Test (SAT) mathematics scores of a random sample of 500 high school seniors in Texas are collected,
and the sample mean and sample standard deviation are found to be 501 and 112, respectively. Find
99% C.I. for the mean SAT mathematics score for seniors in Texas.
𝜶
𝝈 =𝟏𝟏𝟐 𝒏=𝟓𝟎𝟎 𝒙 = 𝟓𝟎𝟏 𝜶 =𝟎 .𝟎𝟏 = 𝟎 .𝟎𝟎𝟓 𝒁 (𝟎 .𝟎𝟎𝟓 )=𝟐 . 𝟓𝟕𝟔
𝟐

𝝈 𝝈
𝒙
¯ −𝒛 < 𝝁 < 𝒙
¯ + 𝒛
( 𝟐)
𝜶
√ 𝒏 ( 𝟐 ) √𝒏
𝜶

𝟏𝟏𝟐 𝟏𝟏𝟐
𝟓𝟎𝟏−𝟐.𝟓𝟕𝟓 <𝝁<𝟓𝟎𝟏+𝟐.𝟓𝟕𝟓
√ 𝟓𝟎𝟎 √ 𝟓𝟎𝟎
𝟒𝟖𝟖.𝟏<𝝁<𝟓𝟏𝟑.𝟗
 Confidence Intervals
Interval estimation of population mean

Example 3:

A manager has found that historically the scores on tests given to applicants for
entry level positions follow a normal distribution with a standard deviation of
32.4 points. A random sample of nine test scores from the current group of
applicants had a mean score of 187.9 points. Find 90% confidence interval for
the mean score of the current group of applicants.
 Confidence Intervals
Interval estimation of population mean

Example 3:
The Solution :

𝝈 𝝈
𝒙
¯ −𝒛 < 𝝁< 𝒙
¯ + 𝒛
( 𝜶𝟐 ) √𝒏 ( 𝜶𝟐 ) √𝒏

𝟑𝟐. 𝟒 𝟑𝟐. 𝟒
𝟏𝟖𝟕. 𝟗− ( 𝟏 .𝟔𝟒𝟓 ) <𝝁<𝟏𝟖𝟕.𝟗+(𝟏 .𝟔𝟒𝟓)
√𝟗 √𝟗
𝑪.𝑰.=[𝟏𝟕𝟎.𝟏𝟑𝟒,𝟐𝟎𝟓.𝟔𝟔𝟔]
 Confidence Intervals
Interval estimation of population mean

Example 4:
It is known that the standard deviation in the volumes of (591 milliliter) bottles
of natural spring water bottled by a company is 5 milliliters. One hundred
bottles are randomly sampled and measured.
a) Find the 90% confidence interval estimate for the population mean
volume.
b) Calculate the 99% confidence interval for the population mean volume.
 Confidence Intervals
Interval estimation of population mean

Example 4:
The Solution : 𝝈 =𝟓𝒏 =𝟏𝟎𝟎 𝒙 =𝟓𝟗𝟏
𝜶
𝜶 =𝟎 . 𝟏 =𝟎 . 𝟎𝟓 𝒁 ( 𝟎 . 𝟎𝟓 )=𝟏 . 𝟔𝟒𝟓
𝟐

𝝈 𝝈
𝒙
¯ −𝒛 < 𝝁< 𝒙
¯ + 𝒛
( 𝟐)
𝜶
√ 𝒏 ( 𝟐 ) √𝒏
𝜶

𝟓 𝟓
𝟓𝟗𝟏− ( 𝟏 . 𝟔𝟒𝟓 ) <𝝁<𝟓𝟗𝟏+(𝟏 . 𝟔𝟒𝟓)
√ 𝟏𝟎𝟎 √ 𝟏𝟎𝟎
𝑪.𝑰.=[𝟓𝟗𝟎.𝟏𝟕𝟕𝟓,𝟓𝟗𝟏.𝟖𝟐𝟐𝟓]
 Confidence Intervals
Interval estimation of population mean

Example 4:
The Solution : 𝝈 =𝟓𝒏 =𝟏𝟎𝟎 𝒙 =𝟓𝟏𝟗
𝜶
𝜶 =𝟎 . 𝟎𝟏 =𝟎 . 𝟎𝟎𝟓 𝒁 (𝟎 .𝟎𝟎𝟓 )=𝟐 . 𝟓𝟕𝟓
𝟐

𝝈 𝝈
𝒙
¯ −𝒛 < 𝝁< 𝒙
¯ + 𝒛
( 𝟐)
𝜶
√ 𝒏 ( 𝟐 ) √𝒏
𝜶

𝟓 𝟓
𝟓𝟗𝟏− ( 𝟐 . 𝟓𝟕𝟓 ) <𝝁<𝟓𝟗𝟏+(𝟐 . 𝟓𝟕𝟓)
√ 𝟏𝟎𝟎 √ 𝟏𝟎𝟎
𝑪.𝑰.=[𝟓𝟖𝟗.𝟕𝟏𝟐𝟓,𝟓𝟗𝟐.𝟐𝟖𝟕𝟓]
 Confidence Intervals
Interval estimation for Population Proportion

You know that normal distribution as an approximation of the sampling distribution of sample

proportion , The confidence interval estimate for a population proportion at confidence

coefficient is given by

𝐑± 𝒁𝒄∗ ( √
𝑹(𝟏 − 𝑹)
𝒏 )
 Confidence Intervals
Interval estimation for Population Proportion
Example 5:
Suppose we want to estimate the proportion of families in a town, which have two or more children. A
random sample of 144 families shows that 48 families have two or more children. Setup a 95 per cent
confidence interval estimate of the population proportion of families having two or more children.
The Solution : 𝑥 48 1
The sample proportion is: 𝑅= = = 𝑛= 144 , R=
1
, 𝒁 𝜶 =± 1.96
𝑛 144 3 3 2

( √ ( ) )
1 1
1−
( √
R ± 𝑍𝑐∗
𝑅 (1 − 𝑅 )
𝑛
1
)
= ± 1.96 ∗
3
3
144
3

0.256 ≤ 𝑅 ≤ 0.410
 Confidence Intervals
Example 6:
In a survey of school students, a sample of 300 students found that 105 of them
obtained an excellent estimate, creating a confidence interval of 95% for the
percentage of excellent students.
R=105/300=0.35 𝑛=300 , Z 0 . 025 =1 . 96

( √
R ± 𝑍𝑐∗
𝑅 (1 − 𝑅 )
𝑛 )
=0 .35 ± 1.96 ∗ ( √
0 .35 (1− 0.35 )
300 )
0 . 35 − ( 1 . 96 ∗ 0 . 028 ) <𝑅 <0 . 35+(1 . 96 ∗ 0 . 028)

0 . 295<𝑅 <0 . 405

Good luck