For smaller samples where the population standard deviation is unknown, the t-distribution is commonly used.

🔹 13. Z-Distribution vs T-Distribution

This is a common Data Science interview topic.

Z-Distribution

Often used when:

• Population standard deviation is known

• Or under appropriate large-sample conditions

T-Distribution

Often used when:

• Population standard deviation is unknown

• Sample standard deviation is used instead

• Especially with smaller samples

The t-distribution has heavier tails than the standard normal distribution.

As the sample size increases, the t-distribution becomes increasingly similar to the normal distribution.

🔹 14. Confidence Interval for a Population Proportion

Confidence intervals can also estimate population proportions.

Suppose: 600 out of 1,000 customers prefer Product A.

Then: Sample Proportion = 600 / 1,000 = 0.60

So: Sample Proportion = 60%

We can construct a confidence interval around this 60% estimate to quantify uncertainty about the true population proportion.

This is commonly used for: Customer surveys, Conversion rates, Election polling, A/B testing, Marketing analytics, Healthcare studies

🔹 15. Confidence Intervals in A/B Testing

Suppose we compare two versions of a website.

Version A: Conversion Rate = 8.2%

Version B: Conversion Rate = 9.1%

The observed difference is: 9.1% − 8.2% = 0.9 percentage points

But is this difference actually meaningful?

We can calculate a confidence interval for the difference.

Suppose the confidence interval for B − A is [0.2%, 1.6%]

The entire interval is positive.

This provides evidence that Version B may genuinely have a higher conversion rate than Version A.

This is one reason confidence intervals are extremely useful in experimentation and product analytics.

🔹 16. Confidence Intervals and Hypothesis Testing

Confidence intervals and hypothesis testing are closely related.

Suppose we're testing: H₀: Population Mean = 100 and we calculate a 95% Confidence Interval =[104,112]

The value 100 is outside the interval.

For a corresponding two-sided test at the 5% significance level, this would generally lead us to reject H₀.

Now suppose the confidence interval is[98,108]

The value 100 is inside the interval.

We would generally fail to reject H₀.

This connection is particularly useful when interpreting statistical tests.

🔹 17. What Determines the Width of a Confidence Interval?

Three important factors determine the width.

1️⃣ Confidence Level

Higher confidence → Wider interval

2️⃣ Variability

Higher variability → Wider interval

3️⃣ Sample Size

Larger sample size → Narrower interval

In simple terms:

More variability = Less precision

More data = More precision

More confidence = Wider range

🔹 18. Common Mistakes

• ❌ Mistake 1: "95% probability that the parameter is inside the interval" - This is not the technically correct frequentist interpretation.

• ❌ Mistake 2: Thinking a higher confidence level gives a narrower interval - It's the opposite.

• ❌ Mistake 3: Confusing standard deviation with standard error

• ❌ Mistake 4: Assuming a wider interval is more precise - A wider interval represents greater uncertainty.

• ❌ Mistake 5: Ignoring sample size

🔹 **19.