0% found this document useful (0 votes)
19 views33 pages

IME692Slides 03

The document discusses advanced statistical methods for business analytics, focusing on hypothesis testing in various scenarios such as product warranties, weight consistency in food products, traffic flow analysis, and internet service speed claims. It provides examples of hypothesis testing for means and variances, including specific cases and statistical rules for rejecting null hypotheses. The content is aimed at equipping readers with the necessary statistical tools to validate claims and make informed decisions in business contexts.

Uploaded by

bhowte
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
19 views33 pages

IME692Slides 03

The document discusses advanced statistical methods for business analytics, focusing on hypothesis testing in various scenarios such as product warranties, weight consistency in food products, traffic flow analysis, and internet service speed claims. It provides examples of hypothesis testing for means and variances, including specific cases and statistical rules for rejecting null hypotheses. The content is aimed at equipping readers with the necessary statistical tools to validate claims and make informed decisions in business contexts.

Uploaded by

bhowte
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd

IME692: ADVANCED

STATISTICAL METHODS FOR


BUSINESS ANALYTICS (Part 03)

Raghu Nandan Sengupta


Department of Management Sciences (DoMS)
Indian Institute of Technology Kanpur, INDIA

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 1


Methods for Business Analytics
(Part # 03)
Statistical Inference:
Hypothesis Testing (# 01)
A manufacturer of a particular type of electrical
motor has come up with a better hp rating motor
then its existing competitors and wants to market
that. As is the norm for any manufacturing product,
a certain warranty life is to be specified by the
manufacturer and the company under our
consideration specifies a warranty life of 1 year
instead of 8 months given for such rating products.
Now you as an engineer are quite skeptical on
hearing that the warranty time is 1 years and want
to test the validity of this statement which the
manufacturer is making.
IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 2
Methods for Business Analytics
(Part # 03)
Statistical Inference:
Hypothesis Testing (# 02)
The food and beverage company which manufactures jelly and jams
sells them in bottles of 100 gms, 250 gms and ½ kg sizes and you are
the marketing general manager of that firm. In order to meet the
growing market demand for these products your company has
installed a new high productive automatic jelly/jam filling machine, but
there has been complains afterwards that on an average the weight of
the 100 gms bottles for the jams are never exactly the same as they
have been found to be either more or less than 100 gms. So in order
to answer this complain and monitor the productivity of the new
machine the company has entrusted you the responsibility to solve
the problem and hence you would like to test whether the weights on
an average for the bottles coming out are about 100 gms (with some
errors) or is there a significant difference in the weights of the bottles,
which may be a major concern for the company and hence may
necessitate the implementation of some corrective action in order to
first identify and then rectify the problem.

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 3


Methods for Business Analytics
(Part # 03)
Statistical Inference:
Hypothesis Testing (# 03)
The traffic flow at the main market road in
the city of Amritsar is highest in the each
day in the morning from 1000 to 1200
hours, and you as the commissioner of
police of Amritsar, want to see whether it is
really needed to have the road closed to
motor cars and commercial vehicles for that
part of the day in order avoid any accidents,
which has been reported at a rate of 3 per
week with a certain distribution.
IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 4
Methods for Business Analytics
(Part # 03)
Statistical Inference:
Hypothesis Testing (# 04)
In the city of Guwahati a new internet
service provider (ISP) has just opened its
service and is providing high speed internet
services and claims the speed of its
services are 500 Mbps. You are the resident
of that city are interested to get a new
internet connection but would like to verify
this fact and then take a decision whether to
take the connection from this new ISP or
continue with the old ISP.
IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 5
Methods for Business Analytics
(Part # 03)
Statistical Inference:
Hypothesis Testing

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 6


Methods for Business Analytics
(Part # 03)
Statistical Inference:
Hypothesis Testing

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 7


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the mean)
H0:  = 0 vs HA:  = A (A < 0), 2
known

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 8


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the mean)
H0:  = 0 vs HA:  = A (A > 0), 2 known

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 9


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the mean)
H0:  = 0 vs HA:  = A (A  0), 2 known

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 10


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the mean)
H0:  = 0 vs HA:  = A (A < 0), 2 unknown

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 11


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the mean)
H0:  = 0 vs HA:  = A (A > 0), 2 unknown

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 12


Methods for Business Analytics
(Part # 03)
Example # 052
H0:  = 0 vs HA:  = A (A > 0), 2 unknown
A manufacturer of bars of steel claims that the
average breaking strength of his product is
more than 52. The breaking strength of each
bar in a sample of 15 is: 51.3, 52.1, 50.3, 50.2,
51.9, 50.0, 52.5, 50.7, 49.3, 49.3, 48.3, 48.1,
48.2, 47.8 and 47.5. Given this information we
are to examine if the manufacturers claim is
supported by these data. Consider =5% or
loc=(1-  )=95%

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 13


Methods for Business Analytics
(Part # 03)
Example # 052 (contd…)
H0:  = 0=52 vs HA:  = A (A > 0=52), 2 unknown

We reject H0 if is true

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 14


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the mean)
H0:  = 0 vs HA:  = A (A  0), 2 unknown

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 15


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
H0:  = 0 vs HA:  = A (A < 0),  known

So the rule is reject H0 if


s*2n<(202n,1-)/n

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 16


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
H0:  = 0 vs HA:  = A (A > 0),  known

So the rule is reject H0 if


s*2n>(202n,)/n

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 17


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
H0:  = 0 vs HA:  = A (A  0),  known

So the rule is reject H0 if


s*2n<(202n,1-/2)/n
OR

s*2n>(202n,/2)/n

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 18


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
H0:  = 0 vs HA:  = A (A < 0),  unknown

So the rule is reject H0 if


S2n<{202n-1,1-}/(n-1)

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 19


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
H0:  = 0 vs HA:  = A (A > 0),  unknown

So the rule is reject H0 if


S2n>{202n-1, }/(n-1)

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 20


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
H0:  = 0 vs HA:  = A (A  0),  unknown

So the rule is reject H0 if


s2n<{202n-1,1-/2}/(n-1)
OR

s2n>{202n-1,/2}/(n-1)

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 21


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the mean)
 Difference of 1 and 2, provided 1 and
2 are known
 Difference of 1 and 2, provided 1 and
2 are unknown, but equal
 Difference of 1 and 2, provided 1 and
2 are unknown, but unequal

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 22


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
Ratio of (21 /22) provided 1 and 2, are
known
H0:  = 0 vs HA:  = A (A < 0)
So the rule is reject H0 if
(s*2m/s*2n)<Fm,n,1-

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 23


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
Ratio of (21 /22) provided 1 and 2, are
known
H0:  = 0 vs HA:  = A (A > 0)
So the rule is reject H0 if
(s*2m/s*2n)>Fm,n,

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 24


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
Ratio of (21 /22) provided 1 and 2, are
known
H0:  = 0 vs HA:  = A (A  0)
So the rule is reject H0 if
(s*2m/s*2n)<Fm,n, 1-/2
Or
(s*2m/s*2n)>Fm,n,/2

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 25


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
Ratio of (21 /22) provided 1 and 2, are
unknown
H0:  = 0 vs HA:  = A (A < 0)
So the rule is reject H0 if
(s2m/s2n)<F(m-1),(n-1),1-

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 26


Methods for Business Analytics
(Part # 03)
Example # 053
Two experimenters, Shruti Mittal and Parva Goyal,
take repeated measurements of the length of a
copper wire. On the basis of the data obtained by
them, which are given below, test whether Shruti's
measurement is more accurate (think what accuracy
means here) than Parva's. Consider =0.05.
Shruti’s measurement (in mm): 12.47, 12.44, 11.90,
12.13, 12.77, 11.86, 11.96, 12.25, 12.78, 12.29
Parva;s measurement (in mm): 12.06, 12.34, 12.23,
12.46, 12.46, 12.39, 11.98, 12.22

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 27


Methods for Business Analytics
(Part # 03)
Example # 053 (contd…)
Given the data let us denote X and Y as the random
variables which denote the distribution of measurement
made by Shruti and Parva, such that X~N(μ X,σ2X) and
Y~N(μY,σ2Y).
From the data we have
• nX=n_X=10
• Xmean,n_X=12.2850
• sX=0.333042, i.e., s2X=0.110917
• nY=n_Y=8
• Ymean,n_Y_=12.2675, i.e., s2Y=0.031964
• sY=0.178786
• F9,7,1-0.05=(1/F7,9,0.05)=(1/3.29)=0.3040
IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 28
Methods for Business Analytics
(Part # 03)
Example # 053 (contd…)
H0:  = 0 vs HA:  = A (A < 0)
So the rule is reject H0 if
(s2m/s2n)<F(m-1),(n-1),1-
• (s2X/s2Y)=(0.110917/0.031964)=3.470019
• F9,7,1-0.05=(1/F7,9,0.05)=(1/3.29)=0.3040
• Now as s2X/s2Y= 3.470019≤ F9,7,1-0.05=0.3040, is
NOT true, hence we cannot reject the null
hypothesis, which means that there is significantly
no difference in Shrutis measurements/readings
with respect to Parva s measurements/readings.
IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 29
Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
Ratio of (21 /22) provided 1 and 2, are
unknown
H0:  = 0 vs HA:  = A (A > 0)
So the rule is reject H0 if
(s2m/s2n)>F(m-1),(n-1), 

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 30


Methods for Business Analytics
(Part # 03)
Statistical Inference: Hypothesis
Testing (for the variance)
Ratio of (21 /22) provided 1 and 2, are
unknown
H0:  = 0 vs HA:  = A (A  0)
So the rule is reject H0 if
(s2m/s2n)>F(m-1),(n-1), 1-/2
Or
(s2m/s2n)>F(m-1),(n-1), /2

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 31


Methods for Business Analytics
(Part # 03)
To check for normality of data
We need to check for the normality of X is and Y
1) List the observation number in the column # 1,call it i.
2) List the data in column # 2.
3) Sort the data from the smallest to the largest and place in
column # 3.
4) For each ith of the n observations, calculate the
corresponding tail area of the standard normal distribution
(Z) as follows, A = (i – 0.375)/(n + 0.25). Put the values in
column # 4.
5) Use NORMSINV(A) function in MS-EXCEL to produce a
column of normal scores. Put these values in column # 5.
6) Make a copy of the sorted data (be sure to use paste
special and paste only the values) in column # 6.
7) Make a scatter plot of the data in columns # 5 and # 6.
IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 32
Methods for Business Analytics
(Part # 03)
To check for normality of data
Checking normality of data

450
400
350
300
250
Data

200
150
100
50
0
-2.5 -1.6 -1.2 -1.0 -0.8 -0.6 -0.5 -0.3 -0.2 -0.1 0.1 0.2 0.3 0.5 0.6 0.8 1.0 1.2 1.6 3.0
Normal Score

IME602: Advanced Statistical R.N.Sengupta,DoMS.,IIT Kanpur,INDIA 33


Methods for Business Analytics
(Part # 03)

You might also like