Review

Standard Normal Distribution Z

Conversion of Normal Distribution to Standard

P{Z < -a} = P{Z > a} and P{−a < Z < a} = 2P{Z < a} − 1

Percentile of Normal Random Variables P{Z > zα} = α

zα is the intercept on X- Axis and is negative when α is more than 0.5
zα is the 100(1 − α) percentile of the standard normal distribution
1
 Review

Conversion of Normal Distribution to Standard

[RV] – E[RV]
Z=
SD[RV]

2
Continuity Correction

3
Continuity Correction

4
Continuity Correction

5
Continuity Correction

6
 Continuity Correction
Now for a binomial distribution
 Sampling Statistics
𝜶 = Significance Level
100(1- 𝜶) = Confidence Interval (95%)

±𝒁𝜶/𝟐 𝝈
𝒁𝜶 (=𝟎.𝟎𝟓)/𝟐
𝒁𝜶 (=𝟎.𝟎𝟎𝟑)/𝟐
𝒁𝜶 (=𝟎.𝟏𝟔)/𝟐

8
 Sampling Statistics
Income Number
Population Size =1000,  =   = 100 < 200 1
250 24
190
325 45
190
375 90
425 150
150 150
475 190
525 190
90
90 575 150
625 90
45 45 675 45
750 24
24 24 >800 1
1 1
200 300 400 450 500 550 600 650 700 800
350

Distribution of approximate number of members in each range

Population Size =1000,  =   = 100
𝑺𝒂𝒎𝒑𝒍𝒆 𝑴𝒆𝒂𝒏 ± 𝒁𝜶/𝟐 𝝈
190

190

150 150

90
90

45 45

24 24
1 1
200 300 400 450 500 550 600 650 700 800
350

Distribution of approximate number of members in each range

 Population Size =1000,  =   = 100

190

190

150 150

90
90

45 45

24 24
1 1
200 300 400 450 500 550 600 650 700 800
350

Distribution of approximate number of members in each range

 Sampling Statistics

471.7 500 528.3

480 500 520

Random Variable
Sample Size vs Sample Numbers
Sampling Distribution
Expected Value of Sampling Distribution
Standard deviation of Sampling Distribution 12
 Sampling Statistics
Considering a population whose values are equally likely to be
either 1 or 2. That is, if X is the value of a member of the population,
then
 Sampling Statistics

Calculate the expected value and variance of this population

 Sampling Statistics
Take a sample size of 2 from this population and obtain the probability distribution of
the sample mean (X1 + X2)/2, and calculate its expected value and variance

Since the pair of values X1, X2 can assume any of four possible pairs of values, the
sample space will be
Sampling Statistics
 Sampling Statistics

Obtain the probability distribution of the sum

SUM: Probability = 2:1/4 3:1/2 4:1/4

E[SUM] = 3,

Variance [SUM] = 1/2

 Sampling Statistics
Obtain the probability distribution of the sample mean if sample size is 3 and
calculate its expected value and variance

For Sample Size 3

Obtain the probability distribution of the sum if sample size is 3

SUM: Probability = 3:1/8 4:3/8 5:3/8 6:1/8

E[SUM] = 4.5, Variance [SUM] = 3/4

 Sampling Statistics
Obtain the probability distribution of the sample mean if sample size is 4 and
calculate its expected value and variance

For Sample Size 4

Obtain the probability distribution of the sum and calculate its expected
value and variance if sample size is 4

E[SUM] = 6.0, Variance [SUM] = 1

 Sampling Statistics

Population Mean = ? Variance = ?

Sample Size E[Mean] Variance

2 ? ?
3 ? ?
4 ? ?

Sample Size E[Sum] Variance

2 ? ?
3 ? ?
4 ? ?
 Sampling Statistics

Population Mean = 1.5 Variance = 1/4

Sample Size E[Mean] Variance

2 1.5 1/8
3 1.5 1/12
4 1.5 1/16

Sample Size E[Sum] Variance

2 3.0 1/2
3 4.5 3/4
4 6.0 1
 Sampling Statistics
Sample
Size X Probability E(Mean) Variance
Mean
2 1 1/4
2 3 1.5 1/2 1.5 1/8
4 2 1/4
3 1 1/8
4 1.33 3/8
3 1.5 1/12
5 1.7 3/8
6 2 1/8
4 1 1/16
5 1.25 4/16
4 6 1.5 6/16 1.5 1/16
7 1.75 4/16
8 2 1/16
 Sampling Statistics
𝜇 = 𝑋ത ± 𝑍𝛼/2 𝜎/ 𝑛

±2σ/√n

PROBABILITY OF PICKING UP EXTREME SAMPLE DECREASES

AS SAMPLE SIZE INCREASES
As Sample Size Increases, Variance Decreases (sample spread decreases)
and hence picking up Samples closer to Mean increases
 Sampling Statistics
Ability to learn about the underlying population distribution by
observing the sample data
If X1, . . . , Xn are independent random variables having a common probability distribution,
we say they constitute a sample from that distribution.

Let X1, . . . , Xn be a sample of values from the population with mean μ and variance σ2

Then the sample mean is defined by

Since the value of the sample mean X is determined by the values of the random variables in
the sample, it follows that X is also a random variable. Its expectation can be shown to be

That is, the expected value of the sample mean X is equal to the population mean μ.

In addition, it can be shown that the variance of the sample mean is

 Sampling Statistics
We can conclude that sample mean is also centred on the population mean μ, but its
spread becomes more and more reduced as the sample size increases.
Sampling Distribution

±σ/√n
σ/√n σ/√n

X μ X
±2σ/√n
±3σ/√n
 Central Limit Theorem
One of the most important results in probability theory, known as the central limit
theorem, which states that the sum (and thus also the average) of a large number of
independent random variables is approximately normally distributed.

Provided that all the random variables tend to be of roughly the same magnitude so that
none of them tends to dominate the value of the sum, it can be shown that the sum of a large
number of independent random variables will have an approximately normal distribution
 Distribution of the Sample Mean
Let X1, . . . , Xn be a sample of values from the population with mean μ and variance σ2

Then the sample mean is defined by

it follows from the central limit theorem that also will be approximately normal
when the sample size n is large. Since has expectation μ and standard deviation
σ/√n, the standardized variable

has an approximately standard normal distribution

Distribution of the Sample Mean
 Suppose that exactly 46 percent of the population favours a particular candidate.
If a random sample of size 200 is chosen, what is the probability that at least 100 favour
this candidate?
If X is the number who favour the candidate, then X is a binomial random variable with
parameters n = 200 and p = 0.46. The desired probability is P{X ≥ 100}.

Therefore, to compute P{X ≥ 100}, we should use the normal approximation on the
equivalent probability P{X ≥ 99.5}. Considering the standardized variable
Distribution of the Sample Mean
Distribution of the Sample Mean
 Distribution of the Sample Mean

Thus, we see that increasing the sample size from 36 to 64 increases the probability that the
sample mean will be within 4 of the population mean from 0.913 to 0.978
 Interval Estimator
When we estimate a parameter by a point estimator, we do not expect the
resulting estimator to exactly equal the parameter, but we expect that it will be
“close” to it. To be more specific, we sometimes try to find an interval about the
point estimator in which we can be highly confident that the parameter lies. Such
an interval is called an interval estimator.

Definition An interval estimator of a population parameter is an interval that is

predicted to contain the parameter. The confidence we ascribe to the interval is the
probability that it will contain the parameter.

𝜇 = 𝑋ത ± 𝑍𝛼/2 𝜎/ 𝑛
 Interval Estimator
Interval Estimator of the Mean of a normal population with known population variance
 Interval Estimator

Now, since z0.025 = 1.96, it follows that 95 percent of the time the
absolute value of Z is less than or equal to 1.96
 Interval Estimator

𝜇 = 𝑋ത ± 𝑍𝛼/2 𝜎/ 𝑛
Interval Estimator
Interval Estimator
 The value of the sample mean is

Since σ = 3, it follows that a 95 percent confidence interval estimate of μ

is given by

19.3 ± 1.96 (3/√10) = 19.3 ± 1.86

That is, we can assert with 95 percent confidence that the actual intensity
of the signal lies between 17.44 and 21.16
For any value of α between 0 and 1, the probability that a standard normal
lies in the interval between −zα/2 and zα/2 is equal to 1 − α
For n = 10, X = 19.3, and σ = 3, calculate 90 and 99 percent confidence interval
estimate of μ

Note that the larger the confidence coefficient 100(1 − α), the larger the
length of this interval.
For instance, suppose we want to determine an interval of length at most b
that, with 95 percent certainty, contains the population mean. How large a
sample is needed?

To answer this, note that since z0.025 = 1.96, a 95 percent confidence interval
for μ based on a sample of size n is
If the population standard deviation is σ = 2 and we want a 95 percent
confidence interval estimate of the mean μ that is of size less than or equal to
b = 0.1, how large a sample is needed?

This indicates that for a population with standard deviation is σ = 2, we need

a sample size of 6147 to be 95 percent confident that the mean lies within a

value of actual mean ± 0.05.

In the case where σ is known and sampling is from a
normal distribution, the confidence limits on μ are
Sampling Statistics
 Sampling Proportions
How Large a Sample Is Needed?
The central limit theorem leaves open the question of how large the sample size n needs to be
for the normal approximation to be valid, and indeed the answer depends on the population
distribution of the sample data. For instance, if the underlying population distribution is
normal, then the sample mean will also be normal, no matter what the sample size is. A
general rule of thumb is that you can be confident of the normal approximation
whenever the sample size n is at least 30. That is, practically speaking, no matter how non
normal the underlying population distribution is, the sample mean of a sample size of at least
30 will be approximately normal. In most cases the normal approximation is valid for much
smaller sample sizes. Indeed, usually a sample size of 5 will suffice for the approximation to
be valid.
 Point Estimator of a Population Proportion
Suppose that we are trying to estimate the proportion of a large population that is in favour of
a given proposition.

Let p denote the unknown proportion.

To estimate p, a random sample should be chosen, and then p should be estimated by the
proportion of the sample that is in favour. Calling the estimator ,

we can express it by

where X is the number of members of the sample who are in favour of the proposition and n is
the size of the sample.
 Point Estimator of a Population Proportion

Since

For instance, suppose a random sample of size 900 is chosen.

Then no matter what proportion of the population is actually in favour of the

proposition,
it follows that the standard error of the estimator of this proportion is less than or
equal to
1/(2√900) = 1/60.