GITAM DEEMED TO BE UNIVERSITY

GITAM SCHOOL OF BUSINESS

BENGALURU 2024-2026
MASTER OF BUSINESS ADMINISTRATION BY

GANESH N (2024203915)
MADHU N ANGADI (2024203869)
PADMINI REDDY R (2024203912)
SHREENIVASAREDDI (2024203938)

Quantitative Techniques

Submitted to:
Dr Manindra Rajak

GITAM
(Deemed to be university)
1. One-Sample t-Test

Assumption: Population standard deviation unknown, sample size generally small (n < 30).

Q1: A startup claims its app reduces anxiety levels to a score of 35 on a standard anxiety scale.
A psychologist tests this on 12 users and finds a mean of 37.2 with a sample standard deviation
of 4.8. At a 5% significance level, can the psychologist reject the startup's claim?

Ans: To determine whether the psychologist can reject the startup’s claim, we perform a one-
sample t-test. Here’s how to approach it:

Step 1: Define the Hypotheses

• Null hypothesis (H₀): μ = 35 (The app reduces anxiety to a score of 35)

• Alternative hypothesis (H₁): μ ≠ 35 (The app does not reduce anxiety to 35)

This is a two-tailed test.

Step 2: Gather the Sample Data

• Sample size (n) = 12

• Sample mean (x̄) = 37.2
• Sample standard deviation (s) = 4.8
• Population mean under H₀ (μ₀) = 35
• Significance level (α) = 0.05

Step 3: Calculate the Test Statistic

Step 4: Determine the Critical t-Value

Degrees of freedom (df) = n - 1 = 11

From the t-distribution table, for a two-tailed test at α = 0.05 and df = 11:

Critical t ≈ ±2.201

Step 5: Compare t-Statistic with Critical Value

• Calculated t = 1.588
• Critical t = ± 2.201

Since 1.588 < 2.201, we fail to reject the null hypothesis.

The graph shows the t-distribution with 11 degrees of freedom:

• The red shaded areas are the rejection regions for a 5% significance level.
• The green dashed line represents the test statistic (t = 1.588).
• The black dashed lines mark the critical values (±2.201).

Since the green line lies within the non-shaded area, we do not reject the null hypothesis.

Conclusion

At the 5% significance level, there is not enough evidence to reject the startup's claim.
The psychologist cannot conclude that the app does not reduce anxiety to a score of 35.

2. One-Sample z-Test

Assumption: Population standard deviation is known.

Q1: A pharmaceutical company states that their drug lowers blood pressure by 10 mmHg on
average. A hospital tests it on 50 patients and finds a mean reduction of 9.2 mmHg. The
population standard deviation is known to be 2.8 mmHg. Test the company's claim at 5% level.

Ans: To test the pharmaceutical company’s claim using a one-sample z-test, we follow these
steps:

Step 1: Set Hypotheses

• Null hypothesis H0: μ=10 (The drug reduces BP by 10 mmHg)

• Alternative hypothesis H1: μ ≠ 10 (The reduction is not 10 mmHg)

This is a two-tailed test.

Step 2: Calculate the Test Statistic

Step 3: Determine Critical z-Values

At α = 0.05 for a two-tailed test:

Critical z-values: ± 1.96

Step 4: Make a Decision

• Since z = −2.0 < −1.96z, the test statistic falls in the rejection region.
• Therefore, we reject the null hypothesis.

the test statistic falls in the rejection region, we reject the null hypothesis. This means the
sample provides enough evidence to doubt the company's claim that the drug lowers blood
pressure by exactly 10 mmHg.

Conclusion:

At the 5% significance level, there is sufficient evidence to reject the company's claim. The
drug does not appear to reduce blood pressure by exactly 10 mmHg on average.

3. Two-Sample (Independent Samples) t-Test and z-Test

Use t-test when σ unknown, z-test when σ known.
Q1: Two trainers claim different effects on weight loss. 20 clients under Trainer A lost an
average of 5.2 kg (SD = 1.1), and 22 clients under Trainer B lost an average of 4.6 kg (SD =
0.9). Test at 5% whether Trainer A is more effective.
Ans: To determine whether Trainer A is more effective than Trainer B at inducing weight
loss, we'll conduct a two-sample t-test (since population standard deviations are unknown
and we're given sample standard deviations). Here's how we proceed:

Step 1: State the Hypotheses

• μ₁ = mean weight loss under Trainer A

• μ₂ = mean weight loss under Trainer B

We want to test whether Trainer A is more effective, so we use a one-tailed test:

• H₀ (null): μ₁ ≤ μ₂ (Trainer A is not more effective)

• H₁ (alternative): μ₁ > μ₂ (Trainer A is more effective)

Step 2: Gather the Data

• Sample 1 (Trainer A):

o n₁ = 20
o x̄₁ = 5.2 kg
o s₁ = 1.1 kg
• Sample 2 (Trainer B):
o n₂ = 22
o x̄₂ = 4.6 kg
o s₂ = 0.9 kg

Step 3: Calculate the Test Statistic

We use the two-sample t-test formula (assuming unequal variances – Welch’s t-test):

Step 4: Degrees of Freedom

Using Welch–Satterthwaite equation:

So, df ≈ 37.
Step 5: Find the Critical Value and Make a Decision

At α = 0.05 for a one-tailed test with df = 37, the critical t-value ≈ 1.687.

Since our calculated t = 1.923 > 1.687, we reject the null hypothesis.

There is statistically significant evidence at the 5% level to conclude that Trainer A leads
to greater weight loss than Trainer B.

Conclusion

There is significant evidence at the 5% level to conclude that Trainer A is more effective
than Trainer B in promoting weight loss.

4. Two-Sample Paired t-Test

Used when same subjects are measured twice.

Q1: Ten employees are tested before and after a time management workshop. Their
productivity scores before and after are recorded. The mean of the differences is 4.1 units, with
SD = 2.5. Test whether the workshop had an effect.

Ans: To test whether the time management workshop had an effect on productivity, we can
perform a paired t-test (also known as a dependent t-test). This compares the means of two
related groups — in this case, the same employees before and after the workshop.

Step 1: State Hypotheses

• Null Hypothesis H0: μd = 0 (no effect)

• Alternative Hypothesis Ha: μd ≠ 0 (there is an effect)
Step 2: Calculate the test statistic

The formula for the t-statistic in a paired t-test is:

Where:

• dˉ = 4.1
• μ0 = 0
• sd = 2.5
• n = 10

Step 3: Find the critical value or p-value

Degrees of freedom (df) = n−1 = 9

For a two-tailed test at α=0.05, the critical t-value from the t-table is approximately ± 2.262.

Step 4: Compare and conclude

Since the computed t=5.19 > 2.262, we reject the null hypothesis.

Here's the graph of the t-distribution for your test:

• The red dashed lines mark the critical values (± 2.262).

• The green line shows the calculated t-statistic (5.19).
• The shaded red regions represent the rejection areas of the null hypothesis.
Since the green line lies within the rejection region, we reject the null hypothesis —
confirming that the workshop had a statistically significant effect.

Conclusion:

There is statistically significant evidence at the 5% level that the workshop had an effect on
productivity.

N5. One-Sample Chi-Square Test (Goodness-of-Fit)

Tests whether observed frequencies fit a known distribution.

Q1: A die is rolled 120 times. The observed frequencies for faces 1–6 are: 15, 22, 18, 20, 25, 20. Test
whether the die is fair.

Ans: To test whether the die is fair using a One-Sample Chi-Square Test (Goodness-of-
Fit), we need to compare the observed frequencies to the expected frequencies if the die were
fair.

Steps to perform the test:

1. State the hypotheses:

o Null hypothesis (H0): The die is fair, so each face has an equal chance of
appearing.
o Alternative hypothesis (Ha): The die is not fair, meaning the observed
frequencies do not fit the expected distribution.

2. Calculate the expected frequency for each face:

If the die is fair, the expected frequency for each face is the same, and it can be
calculated as:

So, the expected frequency for each face is 20.

3. Chi-Square Test Statistic:

The test statistic is calculated as:
 Where:

o Oi = observed frequency for the i-th face

o Ei = expected frequency for the i-th face

For each face:

o O1 = 15, O2 = 22, O3 = 18, O4 = 20, O5 = 25, O6 = 20

o E1 = E2 = E3 = E4 = E5 = E6 = 20

4. Degrees of freedom:
The degrees of freedom (df) for this test is:

df=number of categories−1=6−1=5

5. Significance Level:
Let’s assume the significance level α=0.05

6. Find the critical value:

We can look up the critical value for χ2 with 5 degrees of freedom at α=0.05. The
critical value is χ2 0.05,5.

Now, let's calculate the Chi-Square statistic.

The calculated Chi-Square test statistic is 2.9, and the critical value for 5 degrees of freedom
at α=0.05 is 11.07.

Decision:

• If the test statistic is greater than the critical value, we reject the null hypothesis.
• If the test statistic is less than or equal to the critical value, we fail to reject the null
hypothesis.

Since 2.9 is less than 11.07, we fail to reject the null hypothesis. This means there is no
significant evidence to suggest that the die is unfair. Based on the observed data, we conclude
that the die appears to be fair.