Professional Documents
Culture Documents
Quantitative Methods in Management
Quantitative Methods in Management
MANAGEMENT
Course content
Chapter Page content
number
1 11-32 Introduction, variables, levels of measurement, types of statistics
12 430-446 Simple linear regression, estimating bo and b1, measures of variations, SST, SSR and
SSE, coefficient of determination, coefficient of correlation.
Chapter 7
Chapter 7 : 234-257
Sampling and Sampling
Distributions
Learning Objectives
In this chapter, you learn:
• To distinguish between different
sampling methods
• The concept of the sampling distribution
• To compute probabilities related to the
sample mean and the sample proportion
• The importance of the Central Limit
Theorem
Unit 3: Sampling Theory
Introduction to Sampling
• Sample
– Subset of the population
– Sampling
Finite Population:
If the population consists of a finite number of
individuals, then it is called a Finite Population.
Infinite Population:
In a statistical survey aimed at
determining average per capita
income of the people in a city, all
earning individuals in the city form
the population.
Why Sample?
• Selecting a sample is less time-
consuming than selecting every item in
the population (census).
Probability
Samples
Simple
Random Systemati Stratifie Cluste
c d r
Probability Sample:
Simple Random Sample
• Every individual or item from the frame
has an equal chance of being selected
Populati
on
Divided
into 4
strata
Probability Sample
Cluster Sample
• Population is divided into several “clusters,” each
representative of the population
• A simple random sample of clusters is selected
• All items in the selected clusters can be used, or items can
be chosen from a cluster using another probability
sampling technique
• A common application of cluster sampling involves election
exit polls, where certain election districts are selected and
sampled.
Populati
on
divided Randomly
selected
into 16 clusters for
clusters. sample
Multi Stage Sampling
• Sampling carried out in stages
• Material regarded as being made up
of a number of I stage sampling
units, each of which is made up of a
number of II Stage units and so on
• Example – sample of 5000
households in Karnataka
– I Stage – State – divided into District
– II Stage – Districts – divided into villages
– III Stage – Villages – divided into
households
Judgement Sampling
• Choice of a sample depends
exclusively on the judgement of
the investigator
• Quality of the sample depends
exclusively on the judgement of
the person selecting the sample
Convenience Sampling
• Elements are included in the
sample without pre specified or
known probability of being
selected – convenience of
researcher
• A convenient chink or slice of
the population is taken
• Example
– From telephone directories
– Professor conducting research
may use student volunteers
Quota Sampling
• Quotas are set based on a
given criteria, but within the
quotas, the sample is
judgmental
• Example
– If out of 100 people to be
interviewed, 60 are to be
housewives, 25 farmers, 15
children less than 15 years
Biased Sampling
• Picking a sample by choosing
people who would have very
strong feelings on the issue
Snowball Sampling
• Survey subjects are selected
based on referral from other
survey respondents
Probability Sample:
Comparing Sampling Methods
• Sampling Error
– As sample results are based on
partial or incomplete analysis of the
population features, any statistical
inference based on the sample may
not always be correct
• Non sampling error
– Incorrect enumeration of population
– Non random selection of samples
– Use of faulty questionnaire
– Wrong editing, coding or analysis
Types of Survey Errors
• Coverage error or selection bias
– Exists if some groups are excluded from the frame
and have no chance of being selected
• Sampling error
– Variation from sample to sample will always exist
• Measurement error
– Due to weaknesses in question design, respondent
error, and interviewer’s effects on the respondent
(“Hawthorne effect”)
Types of Survey Errors
(continu
ed)
Excluded
• Coverage error from frame
Follow up
• Non response error on
nonrespon
ses
Random
• Sampling error differences from
sample to
sample
• Measurement error Bad or leading
question
SAMPLING DISTRIBUTION
N = population size n sample size
N= (1,2,3,4,5) n= 3 NCn ways = 10
Mean Medi SD Prop . .
an
1 1,2,3 6/3
2 1,2,4 7/3
3 1,2,5 8/3
4 2,3,4 9/3
5 2,3,5 10/3
6 3,4,5
7 1,3,4
8 1,3,5
9 1,4,5
10 2,4,5
Sampling Distributions
• A sampling distribution is a distribution of all of the possible
values of a sample statistic for a given size sample selected
from a population.
μ
X i
P(x)
N .3
18 20 22 24 .2
21
4 .1
σ
(X μ)i
2
2.236
18
A
20
B
22
C
24
D
x
N
Uniform Distribution
Developing a
Sampling Distribution
(continu
Now consider all possible samples of size n=2ed)
16
1st 2nd Observation
Obs Sample
18 20 22 24
Means
1st 2nd Observation
18 18,1 18,2 18,2 18,2 Obs 18 20 22 24
8 0 2 4
18 18 19 20 21
20 20,1 20,2 20,2 20,2
8 0 2 4 20 19 20 21 22
22 22,1 22,2 22,2 22,2
16 possible
8 0 2 4 22 20 21 22 23
samples
24 24,1 24,2 24,2
(sampling with 24,2 24 21 22 23 24
8 replacement)
0 2 4
Developing a
Sampling Distribution
(continu
ed)
Sampling Distribution of All Sample Means
16 Sample Sample
Means
1st 2nd Observation Means
Obs 18 20 22 24 _ Distribution
P(X
18 18 19 20 21 ).
3
20 19 20 21 22 .
2
22 20 21 22 23 .
1
24 21 22 23 24 0 _
18 19 20 21 22
23 24 X
(no longer
Developing a
Sampling Distribution
(continu
ed)
Summary Measures of this Sampling Distribution:
μX
X 18 19 19 24
i
21
N 16
σX
( X i μ X
) 2
μ 21 σ 2.236 μX 21 σX 1.58
_
P(X) P(X)
.3 .3
.2 .2
.1 .1
0 18 20 22
0 _
X 18 19 20 21 22 23 24
24 X
A B C D
Sampling Distribution…
• The function used – Mean or SD – is
the Sample Statistic
• The SD of the distribution of the
sample statistic is the Standard
Error of the Statistic
• The expected value is regarded as the
true value and any deviation is
regarded as error of estimation due
to sampling effects
Sample Mean Sampling Distribution:
Standard Error of the Mean
• Different samples of the same size from the same
population will yield different sample means
• A measure of the variability in the mean from sample to
sample is given by the Standard Error of the Mean:
(This assumes that sampling is with replacement or
sampling is without replacement from an infinite population)
σ
σX
n
• Note that the standard error of the mean decreases as the
sample size increases
Sample Mean Sampling Distribution:
If the Population is Normal
• If a population is normally distributed
with mean μ and standard deviation σ,
the sampling distribution of X is also
normally distributed with
μX μ σ
and σX
n
Z-value for Sampling Distribution
of the Mean
Normal
μx μ Population
Distribution
• μ x
x Normal Sampling
(i.e. is Distribution
unbiased ) (has the same
mean)
μx
x
Sampling Distribution Properties
As n increases, Larger
σx decreases sample
size
Smaller
sample
size
μ x
Sample Mean Sampling Distribution:
If the Population is not Normal
σ
μx μ σx
and
n
Central Limit Theorem
the
As the n↑
sampling
sample
distributio
size
n
gets
becomes
large
almost
enough
normal
…
regardless
of shape
of
population x
Sample Mean Sampling Distribution:
If the Population is not Normal
Sampling Population
distribution Distribution
properties:
Central Tendency
μx μ
μ x
Variation Sampling Distribution
σ (becomes normal as n increases)
σx Larger
n Smaller
sample
sample
size
size
μx x
How Large is Large Enough?
N-n
___ _______
n N-1
Problem 4
• In a sample of 25 observations
from a normal distribution with
mean 98.6 and SD 17.2, what is
p(92 < x < 102)
• n = 25 = 17.2 = 98.6
• / n = 3.44
• P(92< x <102)
= p(-1.92 < z < 0.99)
= .4726 + .3389
= .8115
Problem 5
• The auditor of a credit card
company knows that on an
average, the daily balance of
any given customer is 112
and the SD 56. From 50
randomly selected accounts
what is the probability that
the sample average daily
balance is
• < 100 ( .0643)
• Between 100 and 130 ( .9241)
Problem 6
• From a population of 125
items, with mean of 105 and
SD 17, 64 items are chosen,
what is the standard error of
the mean?
N = 125 n = 64
= 105 = 17
SE = 1.4896
Population Proportions
π = the proportion of the population having
some characteristic
• Sample proportion ( p ) provides an estimate
of π:
• Approximated by a
Sampling
P( p )
normal distribution if: Distribution
s
.
–nπ 5 3
.
2
.
1
and
0 0 .2 .4 .6 p
n(1π) 5 8 1
π(1π)
where
μ p π σp
and n
(where π = population
proportion)
Z-Value for Proportions
Standardize p to a Z value with the formula:
p p
Z
σp (1)
n
Example
Standardized
Sampling Normal
Distribution Distribution
0.42
51
Standar
dize
0. 0.4 0 1.
40 5
p 44
Z
Standard Error of Proportion
• Infinite Population
pq/n
• Finite Population
______
N-n
_______ pq/n
N-1
Problem 7
• The President of a company
believes that 30% of the firm’s
orders come from first time
customers. A simple random
sample of 100 orders is used
to estimate the proportion of
first time users
• What is the standard error of
proportion (.0458)
Problem 7…
• What is the probability that
the sample proportion will be
• Between .20 & .40
= p(.20<p<.40)
= p[(.2-.3/.0458) <z<(.4-.3/.0458)]
= p(-2.18<z<+2.18)
.4854 * 2 =.9708
• Between .25 & .35
= p(-1.09 < z < +1.09)
= .3621 * 2 = .7242
Chapter Summary
• Introduced sampling distributions
• Described the sampling distribution of the
mean
– For normal populations
– Using the Central Limit Theorem
• Described the sampling distribution of a
proportion
• Calculated probabilities using sampling
distributions
Business Statistics:
A First Course
5th Edition
Chapter 8
Descriptive Inference
SampleE SampleA
_ sa
XE n XA
se
In reality, the sample mean is just one of many possible
sample means drawn from the population, and is rarely
equal to µ.
Estimation
Point Estimation
In
In point
point estimation
estimation wewe use
use the
the data
data from
from the
the sample
sample
to
to compute
compute aa value
value ofof aa sample
sample statistic
statistic that
that serves
serves
as
as an
an estimate
estimate of
of aa population
population parameter.
parameter.
We
We refer to x as
refer to as the
the point
point estimator
estimator of
of the
the population
population
mean ..
mean
ss is
is the
the point
point estimator
estimator of
of the
the population
population standard
standard
deviation ..
deviation
p is
is the
the point
point estimator
estimator of
of the
the population
population proportion
proportion pp
Terms, Statistics & Parameters
Introduction…
• Use of sample statistic to
estimate population parameter
Lower Upper
Confidence Confidence
Point Estimate Limit
Limit
Width of
confidence interval
Point Estimates
Mean μ X
Proportion π p
Estimator
• The sample mean, is the most
common estimator of the
population mean
• The sample variance, is the most
common estimator of the
population variance
• The sample standard deviation, s,
is the most common estimator of
the population standard deviation
• The sample proportion, is the most
common estimator of the
population proportion
Types
• Point Estimate – Single number
used to estimate
single-valued estimate.
A single element chosen from a
sampling distribution.
Conveys little information about the
actual value of the population
parameter, about the accuracy of the
estimate
Types
• Interval Estimate – Range of
values
An interval or range of values
believed to include the unknown
population parameter.
Associated with the interval is a
measure of the confidence we have
that the interval does indeed contain
the parameter of interest.
Properties of a good estimator
• Property of unbiasedness
– Expected value of the estimator is equal to the
parameter being estimated.
• Property of efficiency
– Smallest variance
• Property of sufficiency
– Use as much information as possible from the
sample
• Property of consistency
– Sample size increases, estimate tends to be
parameter value
Point Estimate
• The sample mean is the best
estimator of the population
mean
• The sample SD is the best
estimator of the population SD
• Sample proportion is the best
estimator of the population
proportion
Problem 1
From the following data find the
point estimates of the
population mean and the
population SD
5 8 10 7 10 14
Problem 2
A survey question for a sample of
150 individuals yielded 75 YES
responses, 55 NO responses
and 20 NO OPINIONS
What is the point estimate of the
proportion in the population
who respond
(i) Yes (ii) No (iii) No Opinion
Problem 3
A bank wants to determine the
number of tellers during lunch
rush on Fridays. Data on the
number of people who entered the
bank between 11 am and 1 pm on
Friday over the last 3 months is:
242 275 289 306
342 385 279 245
269 305 394 328
Find point estimates of mean & SD of
population from which the sample
was drawn
Problem 4
In a sample of 400 textile workers, 184
expressed extreme dissatisfaction
regarding a prospective plan to modify
working conditions. Because this
dissatisfaction was strong enough to
allow management to interpret plan
reaction as being highly positive, they
were curious about the proportion of
total workers harboring this sentiment.
Give a point estimate of this proportion
Confidence Intervals
Random I am 95%
confident
Sample
that μ is
Populati Mean between
on μ,
(mean, X= 40 & 60.
50
is
unknown
)
Sam
ple
General Formula
• The general formula for all
confidence intervals is:
Population Population
Mean Proportion
σ Known σ Unknown
Confidence Interval for μ
(σ Known)
• Assumptions
– Population standard deviation σ is known
– Population is normally distributed
– If population is not normal, use large sample
σ
X Zα/2
n
where is the point estimate
ZXα/2 is the normal distribution critical value for a probability of /2 in
each tail is the standard error
σ/ n
Finding the Critical Value, Zα/2
Zα/2 1.96
• Consider a 95% confidence interval:
1α 0.95soα 0.05
α α
0.025 0.025
2 2
Population Population
Mean Proportion
σ Known σ Unknown
Do You Ever Truly Know σ?
• Probably not!
d.f. = n - 1
Degrees of Freedom (df)
Idea: Number of observations that are free to vary after
sample mean has been calculated
Let X1 = 7
If the mean of these
Let X2 = 8 three values is 8.0,
What is X3? then X3 must be 9
(i.e., X3 is not free to
vary)
Here, n = 3, so degrees of freedom = n – 1 = 3 – 1 = 2
(2 values can be any numbers, but the third is not free to vary for
a given mean)
Student’s t Distribution
Note: t Z as n increases
Standard
Normal
(t with df = ∞)
t (df = 13)
t-distributions are bell-
shaped and symmetric,
but have ‘fatter’ tails than t (df = 5)
the normal
0 t
Student’s t Table
Upper Tail Area
Let: n = 3
df .25 .10 .05 df = n - 1 = 2
= 0.10
/2 = 0.05
1 1.000 3.078 6.314
46.698 ≤ μ ≤ 53.302
Problem
• From a population with SD 1.65, a
sample of 32 items resulted in
34.8 as an estimate of the
mean. Find the SE of the mean.
Compute an interval estimate
that should include the
population mean 99.7% of the
time
= .292
Interval Estimates 34.8 ± .867
33.93 - 35.67
Problem
Estimate the mean life of
windshield wiper blades
under typical driving
conditions for CL of 95%
SD 6 months
Sample size = 100
Mean = 21 months
11587.5 - 12012.5
Problem
Nielsen Media Research reports
that household mean TV
viewing time during 8 pm to 11
pm is 7.75 hrs per week.
Assuming a sample size of 180
households and a sample SD
of 3.45 hrs, what is the 95%
Confidence Interval estimate of
the mean TV viewing time per
week during the 8pm to 11 pm
time period? (7.25 to 8.25)
Problem
Average tyre pressure in a
sample of 62 tyres was 24ppsi
and SD 2.1 ppsi.
Population Population
Mean Proportion
σ Known σ Unknown
Confidence Intervals for the
Population Proportion, π
(1)
σp
n
• We will estimate this with sample
data:
p(1 p)
n
Confidence Interval Endpoints
p(1 p)
p Zα/2
n
• where
– Zα/2 is the standard normal value for the level of confidence desired
– p is the sample proportion
– n is the sample size
• Note: must have np > 5 and n(1-p) > 5
Example
Determining
Sample Size
For the
Mean Sampling
error (margin
of error)
σ σ
X Zα / 2 e Zα / 2
n n
Determining Sample Size
Determining
Sample Size
For the
Mean
σ 2
Zα / 2 σ2
e Zα / 2 Now
n
solve for 2
n n to get e
Determining Sample Size
• To determine the required sample size for
the mean, you must know:
2 2 2 2
Z σ (1.645) (45)
n 2 2
219.19
e 5
For the
Proporti
on
Solution:
For 95% confidence, use Zα/2 = 1.96
e = 0.03
p = 0.12, so use this to estimate π