NMIMS Centre for Distance and Online Education

Quantitative Methods - I
Internal Assignment Applicable for Jun 2025

Answer 1-
Introduction –

Statistical analysis is a fundamental tool in business and engineering decision-making,

providing a systematic approach to understanding data and making informed
judgments. One of the most critical aspects of statistical inference is analyzing sample
means, particularly in quality control, production management, and product reliability
assessments. In practical applications, businesses and engineers often rely on sample
data to estimate population parameters since collecting data from an entire population is
often impractical or impossible.

A key principle that facilitates statistical inference is the Central Limit Theorem (CLT).
This theorem states that for a sufficiently large sample size, the distribution of the
sample mean will approximate a normal distribution, regardless of the population’s
original distribution. This property enables analysts to calculate probabilities, construct
confidence intervals, and assess how increasing the sample size affects statistical
precision. Understanding the implications of the CLT is crucial for quality control in
manufacturing, financial risk assessments, and other fields where estimating population
characteristics accurately is essential.

In this study, we analyze a dataset of battery lifespans to answer the following key
questions:

 What is the probability that the sample mean lifespan falls below a
specified threshold?
 How can we construct a confidence interval for the sample mean, and what
does it indicate about the population mean?
  What is the impact of increasing the sample size on statistical measures
such as standard error and probability estimates?

By addressing these questions, we gain valuable insights into the behavior of sample
statistics, which help businesses and engineers ensure quality, optimize processes, and
reduce uncertainty in decision-making. Through statistical modeling, organizations can
predict performance, anticipate potential failures, and make data-driven improvements
that enhance efficiency and reliability.

1. Probability That the Sample Mean is Less Than 1150 Hours

The probability of obtaining a sample mean below a specific threshold can be

determined using the Central Limit Theorem (CLT), which states that the sampling
distribution of the sample mean is approximately normal if the sample size is sufficiently
large.

Step 1: Calculate the Standard Error (SE)

The standard error measures the variability of the sample mean and is given by the
formula:

Where:
SE=σ/n

 = Population standard deviation = 200 hours

 = Sample size = 50

SE=20050≈28.28 hours

Step 2: Calculate the Z-Score

The Z-score indicates how many standard errors the sample mean of 1150 is away from
the population mean of 1200:
Z=Sample Mean−Population Mean/SE
Z=1150−1200/28.28≈−1.77

Step 3: Find the Probability

P(Xˉ<1150)≈0.0384 or 3.84%

Using the standard normal distribution table, the cumulative probability for is
approximately 0.0384.

Thus, the probability that the sample mean is less than 1150 hours is:

2. 95% Confidence Interval for the Sample Mean

A confidence interval provides a range in which the true population mean is likely to lie
with a specified confidence level (95% in this case).

Step 1: Identify the Critical Z-Value For a 95% confidence level, the critical Z-value is:

Z
critical=1.96

Step 2: Calculate the Margin of Error (ME) The margin of error is calculated as:

ME=Z
critical ×SE
ME=1.96×28.28≈55.45

Step 3: Determine the Confidence Interval The confidence interval is given by:

CI= {Sample Mean} \pm ME

CI=1200±55.45= 1200 \pm 55.45
CI=[1144.55,1255.45]
Thus, the 95% confidence interval for the sample mean lifespan is approximately
[1144.55 hours, 1255.45 hours].

3. Effect of Increasing Sample Size to 100

An increase in sample size reduces the standard error, leading to more precise
estimates.

Impact on Standard Error

For : SE=σ/n=200/100=20 hours

Comparing with the original, we see that increasing the sample size reduces variability
in the sample mean.

Impact on Probability Calculation: Using the reduced standard error (SE=20SE = 20):

1. Recalculate the Z-score for Xˉ<1150\{X} < 1150:

Z=1150−120020=−2.50Z = \{1150 - 1200}/ {20} = -2.50

2. Find the cumulative probability for Z=−2.50Z = -2.50 (from the Z-table):

P(Xˉ<1150)≈0.0062 or 0.62%

The probability decreases significantly, reflecting the increased precision of the sample
mean with a larger sample size.

Effect on Confidence Interval: With the reduced standard error, the margin of error
also decreases:

ME=1.96×20=39.2ME = 1.96 \times 20 = 39.2

The 95% confidence interval for n=100n = 100 becomes:

CI=1200±39.2=[1160.8,1239.2]
From the Z-table, the cumulative probability for is approximately 0.0062 or 0.62%.

Thus,the probability of the sample mean being below 1150 hours decreases
significantly, showing greater precision.

Effect on Confidence Interval

With, the margin of error is:

The new 95% confidence interval is:

The narrower confidence interval reflects increased precision in estimating the

population mean.

Conclusion

Key findings from this analysis include:

1. The probability that the sample mean lifespan is less than 1150 hours is
approximately 3.84%.
2. The 95% confidence interval for the sample mean lifespan is approximately
[1144.55 hours, 1255.45 hours].
3. Increasing the sample size to 100 reduces the standard error, leading to a
lower probability (0.62%) of obtaining a sample mean below 1150 hours and
a narrower confidence interval [1160.8, 1239.2].

These results demonstrate the importance of larger sample sizes in statistical analyses,
improving estimate reliability and decision-making accuracy.

These findings underscore the importance of sample size in statistical analyses.

Businesses and engineers must carefully determine the appropriate sample size based
on the required precision and reliability. A small sample may lead to misleading
conclusions due to high variability, whereas a larger sample provides greater accuracy
but may require more resources. Striking the right balance is essential for efficient and
effective decision-making.

Ultimately, understanding the behavior of sample means allows organizations to

improve quality control, optimize production, and enhance reliability predictions.
Whether evaluating battery lifespans, financial performance, or operational efficiency,
statistical methods play a crucial role in ensuring data-driven, informed decision-making.
By leveraging these techniques, businesses and engineers can minimize risk, enhance
product quality, and make strategic improvements based on sound statistical reasoning.

Answer 2.a-
Introduction –

Probability is a vital concept in statistics, allowing us to analyze the likelihood of specific

outcomes in a random experiment. Here, we examine a scenario involving a custom
deck of 16 cards, which consists of 10 red and 6 black cards. The problem involves
drawing two cards without replacement and calculating two probabilities: (1) the
probability that both cards are black, and (2) the probability that at least one of the two
cards is red. The analysis will demonstrate how fundamental probability principles, such
as combinations and complementary events, are applied to solve real-life problems.

Solution-

1. Probability that Both Cards Drawn are Black

Step 1: Understand the Problem To find the probability of drawing two black cards, we
consider that no replacement occurs after drawing the first card. The outcome depends
on two successful draws, both being black.

Step 2: Total Possible Outcomes The total number of ways to draw two cards from a
deck of 16 cards is calculated using combinations:
Total Outcomes= (162)=16×152=120

Step 3: Favorable Outcomes- The number of ways to draw two black cards out of the
6 black cards:

Favorable Outcomes= (62)= 6×52=15

Step 4: Probability Calculation The probability is the ratio of favorable outcomes to

total outcomes:

P(Both Black)=Favorable Outcomes

Total Outcomes=15120=0.125

Thus, the probability that both cards drawn are black is 12.5%.

2. Probability that At Least One Card is Red

Step 1: Complementary Event Instead of directly calculating this probability, we use

the complement rule. The complementary event is that none of the two cards is red,
meaning both cards are black. The probability of at least one red card is:

P(At Least One Red)=1−P(Both Black)P(\text{At Least One Red}) = 1 - P

Step 2: Substituting Values From the previous calculation, P(Both Black)=0.125P:

P (At Least One Red)=1−0.125=0.875

Thus, the probability that at least one card drawn is red is 87.5%.

Conclusion

Using probability principles, we determined the following results:

1. The probability that both cards drawn are black is 12.5%.

2. The probability that at least one of the two cards is red is 87.5%.
This analysis demonstrates how combinations and complementary rules simplify
complex problems. These methods are essential tools for decision-making in a wide
range of fields, from gaming to business risk assessments. By leveraging these
techniques, we gain valuable insights into random outcomes and improve our predictive
capabilities.

Answer 2.b-
Introduction –

Quality control is a critical aspect of manufacturing processes, ensuring that products

meet specified standards and customer requirements. In this case, a milling machine
produces rods with an average length of 15.00 cm and a standard deviation of 0.3 cm
due to the machine's settings and age. The customer's acceptance criteria specify that
rod lengths must fall within the range of 14.80 cm to 15.20 cm. To determine the
acceptance percentage, we use statistical principles, specifically the normal
distribution, to calculate the proportion of rods that meet these specifications.

Solution-

Step 1: Understand the Problem

The rod lengths are normally distributed with:

 Mean (μ\mu): 15.00 cm

 Standard Deviation (σ\sigma): 0.3 cm

The specified acceptable range is:

 Lower Limit: 14.80 cm

 Upper Limit: 15.20 cm
We need to calculate the probability that a randomly selected rod falls within this range.
This probability corresponds to the area under the normal curve between the two
limits.

Step 2: Calculate Z-Scores

The Z-score indicates how many standard deviations a value is away from the mean.
The formula is:

Z=Value−μ/σ

For 14.80 cm:

Z
lower=14.80−15.000.3=−0.200.3=−0.67

For 15.20 cm:

Z
upper=15.20−15.000.3=0.200.3=0.

Step 3: Find Cumulative Probabilities

Using the Z-table or a normal distribution calculator:

 For Z=−0.67Z = -0.67, the cumulative probability is approximately 0.2514.

 For Z=0.67Z = 0.67, the cumulative probability is approximately 0.7486.

Step 4: Calculate Acceptance Percentage

The probability that a rod falls within the acceptable range is the difference between the
cumulative probabilities:

P(14.80≤X≤15.20)=P(Z_ upper)−P(Z _lower)

P(14.80≤X≤15.20)=0.7486−0.2514=0.4972
The acceptance percentage is:

Acceptance Percentage=0.4972×100=49.72%

Conclusion

Given the milling machine's settings and standard deviation of 0.3 cm, 49.72% of the
rods produced will meet the customer's specifications for length (within 14.80 cm to
15.20 cm). This relatively low acceptance rate highlights the impact of variability in the
manufacturing process, influenced by factors such as the machine's age. To improve
the acceptance percentage, measures such as recalibrating the machine or reducing
the standard deviation through process optimization could be implemented. These
adjustments would enhance product quality and ensure better alignment with customer
requirements, boosting satisfaction and operational efficiency.