Birla Institute of Technology & Science, Pilani
Work-Integrated Learning Programs Division
First Semester –2024-25
End-Semester Test
EC-3 Makeup
Course No. : MBAZC417/ PDBAZC417/ PDFTZC417
Course Title : QUANTITATIVE METHODS
Nature of Exam : Open Book
Weightage : 40% No. of Pages =4
No. of Questions = 4
Duration : 2.0 Hours
Date of Exam :
Note:
1. Please follow all the Instructions to Candidates given on the cover page of the answer book.
2. All parts of a question should be answered consecutively. Each answer should start from a fresh
page.
3. Assumptions made if any, should be stated clearly at the beginning of your answer.
4. Please be brief and legible in your answers.
Q1a. Parenting workshop was taken with 10 parent couples as the audience., and the feedback
was taken from each participant and the following were the rating obtained on a scale of 10.
Couple Rating by man Rating by woman
1 9 8
2 7 6
3 5 4
4 5 07
5 6 7
6 8 8
Examine whether men are more satisfied with the workshop at 2% significance level (4 marks)
Answer -1a:
To examine whether men are more satisfied with the workshop than women at the 2% significance
level (or a 98% confidence level), we'll use a paired t-test.
Null hypothesis H0: There is no difference in satisfaction levels between men and women.
Alternative hypothesis H1: Men are more satisfied than women.
Page 1 of 12
Calculate the difference in ratings for each couple as below:
Couple Rating by Men Rating by Women Difference
1 9 8 1
2 7 6 1
3 5 4 1
4 5 7 -2
5 6 7 -1
6 8 8 0
Mean of the differences as (1+1+1-2-1+0)/6 = 0
Standard deviation of differences as sqrt {(1+1+1+2+2+0)/6−1}=sqrt (8/5) =1.26
Calculate the t-statistic:
t= d‾/{sd/sqrt(n)} = 0 / {1.26/6} =0
Compare the t-statistic to the critical value from the t-distribution table at n-1 degrees of freedom and
2% significance level.
For a one-tailed test at the 2% significance level and 5 degrees of freedom, the critical value is
approximately 2.571 (from t-distribution tables).
Since our calculated t-statistic (0) is less than the critical value (2.571), we fail to reject the null
hypothesis.
Based on the data, we do not have sufficient evidence to conclude that men are more satisfied with
the workshop than women at the 2% significance level.
Q1b. A manufacturing company has three factories (F1, F2, and F3) that supply products to
four warehouses (W1, W2, W3, and W4). The supply capacity of each factory and the demand
at each warehouse are shown below, along with the shipping cost per unit from each factory to
each warehouse. Factory F1 has a supply capacity of 70 units. Factory F2 has a supply capacity
of 50 units. Factory F3 has a supply capacity of 30 units. Warehouse W1 requires 30 units.
Warehouse W2 requires 40 units. Warehouse W3 requires 20 units. Warehouse W4 requires
60 units. The following are the shipping costs per unit in dollars. Determine the optimal
shipping schedule that minimizes the total transportation cost while meeting the demand at
each warehouse and not exceeding the supply from each factory. (4 marks)
Answer – 1b:
Let xij be the number of units transferred from ith factory to jth warehouse
Page 2 of 12
Objective is to minimise the cost = 4x11 + 6x12 +8x13 + 7x14 + 5x21 + 4x22 + 7x23 + 6x24
+ 8x31 + 5 x32 +6x33 + 4 x34
s.t. constraints
x11 + x12 + 13 + x14 =70 (Supply constraint of Factory F1)
x21 + x22 + x23 + x24 = 50 (Supply constraint of Factory F2)
x31 + x32 + x33 + x34 = 30 (Supply constraint of Factory F3)
x11 + x21 + x31 = 30 (Demand constraint of Warehouse W1)
x12 + x22 + x32 =40 (Demand constraint of Warehouse W2)
x13 + x23 + x33 =20 (Demand constraint of Warehouse W3)
x14 + x24 + x34 =60 (Demand constraint of Warehouse W4)
All xij >= 0
Q1c. A researcher wants to estimate the proportion of adults in a city who support a new public
health policy. She wants the estimate to be within a margin of error of ±3% per month with a
confidence level of 95%. From previous studies, the researcher believes the proportion
supporting the policy is around 0.5. However, to be conservative, she decides to use p=0.5.
What is the minimum sample size required for the researcher to achieve her desired level of
precision? (2 marks)
Answer -1c:
Page 3 of 12
Q2a. A company manufactures three products: P1, P2, and P3. Each product requires a different
amount of three resources: Raw Material, Labor, and Machine Time. The company aims to
maximize its profit while ensuring it does not exceed the available resources and meets
minimum production requirements for each product. The profit per unit of each product is as
follows: $20 for Product P1, 25$ for Product P2 and 30$ for Product P3. The number of units
of Product P1 produced should be atleast half the number of units of Product P2 produced, and
not more than thrice the number of units produced for product P3. If the resource requirements
per unit of each product are given in the table below, write the mathematical formulation of the
LPP to find out the optimal product mix for maximum profit. (5 marks)
Answer:
Page 4 of 12
Let the number of products produced for P1, P2 and P3 be x1, x2 and x3.
Objective is to maximise Profit = 20x1 + 25x2 + 30x3
s.t.
3x1 + 4x2 + 5x3 <= Available units of raw material
2x1 + 3x2 + 4x3 <= Available hours of labor
1x1 + 2x2 + 3x3 <= Available hours of machine time
x1, x2, x3 >= 0
Q2b. Explain the difference between the following in not more than 30 words each: (5 marks)
a) 1-tailed test and 2-tailed test
Answer:
Differences between one-tailed test and two-tailed test
1. Directionality:
o One-tailed tests focus on one direction (either greater than or less than).
o Two-tailed tests consider both directions (different from).
2. Significance Level:
o For a one-tailed test with a significance level of α (alpha), the critical region is
in one tail of the distribution.
o For a two-tailed test with the same α (alpha), the critical region is split between
both tails, so each tail has α/2.
3. Critical Values:
o One-tailed tests have one critical value.
o Two-tailed tests have two critical values (one for each tail).
b) type-1 error and type-2 error
Answer:
Type I Error (False Positive): Type I error occurs when you reject the null hypothesis when it is
actually true. This means you think you found a significant effect when there is none. The
probability of making a Type I error is denoted by α, which is the significance level commonly
taken 5%).
Type II Error (False Negative): Type II error occurs when you fail to reject the null hypothesis
when it is actually false. This means you think there is no significant effect when there actually is
one. The probability of making a Type II error is denoted by β. The power of the test, which is 1-
β, represents the probability of correctly rejecting a false null hypothesis.
Page 5 of 12
c) Inferential statistics and descriptive statistics
Answer:
Descriptive Statistics: To summarize and describe the main features of a data set in a
quantitative manner. It uses measures like mean, median, mode, range, variance, standard
deviation, and graphical representations such as histograms, pie charts, and bar graphs.
Example: If you have test scores of 30 students, descriptive statistics would involve calculating
the average score, the highest and lowest scores, and possibly creating a graph to show the
distribution of scores.
Inferential Statistics: To make inferences about a population based on a sample of data. It
involves generalizing from a sample to a population. It uses methods like hypothesis testing,
confidence intervals, regression analysis, and ANOVA. Example: If you have test scores of 30
students and you want to make predictions about the performance of all students in the school,
inferential statistics would involve using the sample data to make such generalizations.
d) Assignment model and transportation model
Answer:
The Assignment Model and the Transportation Model are both linear programming techniques
used for optimization problems, but they serve different purposes and have distinct
characteristics. Here's a summary of their differences:
Assignment Model: The Assignment Model is used to assign a set of tasks to a set of agents
(e.g., workers, machines) in the most efficient way, usually minimizing the total cost or time.
It involves a one-to-one assignment between tasks and agents.
Transportation Model: The Transportation Model is used to determine the most cost-efficient
way to transport goods from multiple sources (e.g., factories) to multiple destinations (e.g.,
warehouses). It involves many-to-many relationships between sources and destinations. The
supply and demand constraints must be satisfied, meaning the total supply from all sources
must meet the total demand at all destinations.
e) ANOVA and Chi-Square test
Answer:
ANOVA (Analysis of Variance) and the Chi-Square test are both statistical tests used to
analyze data, but they serve different purposes and are applied in different scenarios. Here's a
detailed comparison:
Page 6 of 12
ANOVA (Analysis of Variance): ANOVA is used to compare the means of three or more
groups to determine if there are statistically significant differences between them. Here the data
is continuous and have the following assumptions:
o Independence of observations.
o Normality of the distribution of the residuals.
o Homogeneity of variances (equal variances among groups).
Chi-Square Test: The Chi-Square test is used to determine if there is a significant association
between two categorical variables or to test the goodness of fit of an observed distribution to
an expected distribution. Here the data is Categorical data and have the following assumptions:
o Independence of observations.
o Expected frequency of at least 5 in each cell for a reliable result.
Q3a. A quality control manager at a factory wants to compare the consistency (variability) of
production times between two machines, Machine A and Machine B. The manager suspects
that one machine may have higher variability in production time than the other and decides to
test if there is a significant difference in the variances of the production times. To test this, he
takes a sample of production times (in minutes) from each machine. Sample from Machine A
had size of 10 with a sample variance =4.5, while that from machine B had size of 12 with a
sample variance =2.8. Assuming that production times are normally distributed for both
machines, perform an F-test to determine if there is a significant difference between the
variances of production times at a significance level of α=0.05. (3 marks)
Answer-3a:
Page 7 of 12
Q3b. A study was conducted to determine if there is a relationship between customer
satisfaction and the type of product they purchased. The data collected from 300 customers is
summarized in the following contingency table. Using a 0.05 significance level, test whether
there is a significant association between customer satisfaction and the type of product
purchased. (5 marks)
Answer-3b:
To determine if there is a significant association between customer satisfaction and the type of
product purchased, we'll perform a chi-square test of independence.
Null hypothesis H0: The customer satisfaction is independent of the type of product purchased,
Alternative hypothesis H1: They are associated.
The expected frequency for each cell is calculated using the formula:
Eij= (Row total × Column total) / Grand total
Let's calculate these for each cell:
• For Satisfied & Product A:
E11=120×90/300 = 36
• For Satisfied & Product B:
E12=120×120/300 = 48
• For Satisfied & Product C:
E13=120×90/300 = 36
• For Neutral & Product A:
E21=100×90/300 = 30
• For Neutral & Product B:
E22=100×120/300 = 40
• For Neutral & Product C:
Page 8 of 12
E23=100×90/300 = 30
• For Dissatisfied & Product A:
E31=80×90/300 = 24
• For Dissatisfied & Product B:
E32=80×120/300 = 32
• For Dissatisfied & Product C:
E33=80×90/300 = 24
The formula to compute the chi-square statistic is:
χ2=∑(Oij−Eij)^2/Eij
where Oij are the observed frequencies and Eij are the expected frequencies.
Calculations:
χ2=(30−36)^2/36+(40−48)^2/48+(50−36)^2/36+(20−30)^2/30+(50−40)^2/40+(30−30)^2/30
+(40−24)^2/24+(30−32)^2/32+(10−24)^2/24 = 32.57
After calculating each term, sum them up to get the chi-square value.
Degrees of freedom for a contingency table is df = (r−1)×(c−1) = (3-1) * (3-1) = 4
Use a chi-square distribution table to find the critical value for α=0.05 at df = 4. The critical
value is approximately 9.488.
Since, χ2 (Cal) 32.57 > 9.488, we reject the null hypothesis.
Q3c. In a certain city, 2% of the population has a specific disease. A medical test is available
that detects the disease. However, the test is not perfect. If a person has the disease, the test
will correctly detect it with a probability of 95%. If a person does not have the disease, the test
will incorrectly indicate they have it 3% of the time. Suppose a randomly selected person from
the city tests positive. What is the probability that they actually have the disease? (2 marks)
Answer-3c:
Page 9 of 12
Q4a. A random sample of 50 students at a university is taken to estimate the average time students
spend studying per week. The sample mean is found to be 18 hours, with a sample standard deviation
of 3.5 hours. Calculate the 95% confidence interval for the true mean time students spend studying
per week. Interpret the confidence interval. (2 Marks)
Answer – 4a:
Q4b. A health researcher is studying the average cholesterol level of adults in a certain city.
From a random sample of 80 adults, the mean cholesterol level is found to be 200 mg/dL with
a standard deviation of 15 mg/dL. The researcher reports a confidence interval for the mean
cholesterol level as 196 mg/dL to 204 mg/dL. Find the significance level α for this confidence
Page 10 of 12
interval, using appropriate tables. Interpret what this significance level means in the context of
this study. (3+1 = 4 marks)
Answer-4b:
Q4c. In a regression model, the total sum of squared variations in the target variable is 20000. The sum
of squared variations due to residuals are 8000. The degrees of freedom for the residuals are 8. Total
number of observations is 25. Answer the following questions:
a) What will be the value of R-square? (2 marks)
b) What will be the standard error of the regression model? (2 marks)
Answer-4c:
a) First, the formula for R-square is:
R2 = (1−SSres)/SStotal
where:
• SSres is the sum of squared residuals (or errors).
• SStotal is the total sum of squared variations in the target variable.
Given:
• SStotal=20000
• SSres=8000
Now, plug these values into the formula:
R2 = (1−8000)/20000 = 0.6
Page 11 of 12
So, the value of R^2 is 0.6.
b) The standard error of the regression model can be calculated using the following
formula:
SEregression=sqrt(SSres/dfres)
Where:
SEregression is the standard error of the regression.
SSresSS is the sum of squared residuals (8000 in this case).
dfres is the degrees of freedom for the residuals (8 in this case).
Now, let's calculate it:
SEregression=sqrt (8000/8) =sqrt (1000) =31.62
So, the standard error of the regression model is 31.62.
Page 12 of 12
