Introductory Statistics: Probability Distributions t-Distribution When to Use Degrees of Freedom Heavier Tails than Normal

What Is This?

The t-distribution is a probability distribution used to estimate population parameters when the sample size is small and the population standard deviation is unknown. It appears in exams to test your understanding of statistical inference and hypothesis testing, particularly when dealing with small sample sizes.

Why It Matters

The t-distribution is commonly tested in statistics exams, particularly in introductory and intermediate-level courses. It frequently appears in questions worth 10-15% of the total marks. This topic tests your ability to apply statistical methods to real-world data, especially when sample sizes are limited.

Core Concepts

1. When to Use the t-Distribution: Use it for hypothesis testing and constructing confidence intervals when the sample size is small (typically n < 30) and the population standard deviation is unknown.
2. Degrees of Freedom (df): This is a key concept in the t-distribution, calculated as df = n - 1, where n is the sample size. It affects the shape of the distribution.
3. Heavier Tails than Normal: The t-distribution has heavier tails compared to the normal distribution, meaning it has more probability in the tails and less in the center.
4. Shape Changes with df: As the degrees of freedom increase, the t-distribution approaches the normal distribution.
5. Two-Tailed vs. One-Tailed Tests: Understand the difference between these tests and when to use each.

Prerequisites

1. Understanding of Normal Distribution: You need to know the basics of the normal distribution to understand how the t-distribution differs.
2. Basic Statistical Concepts: Knowledge of mean, standard deviation, and sample size is essential.
3. Hypothesis Testing: Familiarity with null and alternative hypotheses, p-values, and significance levels.

The Rule-Book (How It Works)

• Primary Rule: Use the t-distribution for small sample sizes (n < 30) when the population standard deviation is unknown.
• Degrees of Freedom: Calculated as df = n - 1.
• Heavier Tails: The t-distribution has more area in the tails compared to the normal distribution.
• Visual Pattern: Imagine the t-distribution as a normal distribution with fatter tails that get thinner as df increases.

Exam / Job / Audit Weighting

• Frequency: Common
• Difficulty Rating: Intermediate
• Question Type: Multiple choice, short answer, problem-solving

Difficulty Level

Intermediate

Must-Know Rules, Formulas, Standards, or Principles

1. t-Score Formula: ( t = \frac{\bar{x} - \mu}{s / \sqrt{n}} ), where (\bar{x}) is the sample mean, (\mu) is the population mean, (s) is the sample standard deviation, and (n) is the sample size.
2. Degrees of Freedom: df = n - 1
3. Confidence Interval: ( \bar{x} \pm t \left( \frac{s}{\sqrt{n}} \right) )

Worked Examples (Step-by-Step)

Easy

Question: A sample of 10 observations has a mean of 50 and a standard deviation of 10. Construct a 95% confidence interval for the population mean.
Step-by-Step: 1. Calculate the degrees of freedom: df = 10 - 1 = 9 2. Find the t-value for 95% confidence and 9 df (from t-tables or calculator): t ≈ 2.262 3. Calculate the margin of error: ( 2.262 \left( \frac{10}{\sqrt{10}} \right) \approx 7.12 ) 4. Construct the confidence interval: ( 50 \pm 7.12 ) Answer: (42.88, 57.12)

Medium

Question: A researcher wants to test if the mean score of a test is different from 70. A sample of 15 students has a mean score of 72 with a standard deviation of 8. Use a 0.05 significance level.
Step-by-Step: 1. State the hypotheses: ( H_0: \mu = 70 ), ( H_1: \mu \neq 70 ) 2. Calculate the t-score: ( t = \frac{72 - 70}{8 / \sqrt{15}} \approx 1.96 ) 3. Calculate the degrees of freedom: df = 15 - 1 = 14 4. Find the critical t-value for 0.05 significance and 14 df (from t-tables or calculator): t ≈ 2.145 5. Compare the t-score to the critical value: 1.96 < 2.145 Answer: Fail to reject the null hypothesis.

Hard

Question: A company claims that the average life of their light bulbs is 1000 hours. A consumer group tests 20 bulbs and finds an average life of 980 hours with a standard deviation of 120 hours. Test the company's claim at a 0.01 significance level.
Step-by-Step: 1. State the hypotheses: ( H_0: \mu = 1000 ), ( H_1: \mu < 1000 ) 2. Calculate the t-score: ( t = \frac{980 - 1000}{120 / \sqrt{20}} \approx -1.44 ) 3. Calculate the degrees of freedom: df = 20 - 1 = 19 4. Find the critical t-value for 0.01 significance and 19 df (from t-tables or calculator): t ≈ -2.539 5. Compare the t-score to the critical value: -1.44 > -2.539 Answer: Fail to reject the null hypothesis.

Common Exam Traps & Mistakes

1. Mistake: Using the normal distribution instead of the t-distribution for small samples.
2. Wrong Answer: Using z-scores for small samples.
3. Correct Approach: Always use t-scores for n < 30.
4. Mistake: Incorrectly calculating degrees of freedom.
5. Wrong Answer: df = n
6. Correct Approach: df = n - 1
7. Mistake: Not recognizing the need for a one-tailed test.
8. Wrong Answer: Using a two-tailed test when the hypothesis is directional.
9. Correct Approach: Identify the type of test based on the hypothesis.
10. Mistake: Misinterpreting the t-value from tables.
11. Wrong Answer: Using the wrong critical value.
12. Correct Approach: Ensure you match the df and significance level correctly.

Shortcut Strategies & Exam Hacks

• Memory Aid: Remember "t for small, z for large" to quickly decide between t and z distributions.
• Elimination Strategy: If a question involves small samples and unknown population standard deviation, eliminate options involving z-scores.
• Pattern Recognition: Look for keywords like "small sample," "unknown population standard deviation," and "degrees of freedom" to trigger t-distribution use.

Question-Type Taxonomy

1. Multiple Choice: Common in introductory stats exams.
2. Example: What is the degrees of freedom for a sample size of 12?
3. Favored By: GRE, GMAT
4. Short Answer: Requires calculations and brief explanations.
5. Example: Calculate the t-score for a sample mean of 50, sample standard deviation of 10, and sample size of 15.
6. Favored By: University stats courses
7. Problem-Solving: Involves hypothesis testing and confidence intervals.
8. Example: Test if the population mean is different from 100 with a sample mean of 105, sample standard deviation of 15, and sample size of 20.
9. Favored By: Advanced stats courses, job interviews

Practice Set (MCQs)

Question 1

Question: What is the degrees of freedom for a sample size of 15? Options: A. 14 B. 15 C. 16 D. 13 Correct Answer: A. 14 Explanation: df = n - 1 = 15 - 1 = 14 Why the Distractors Are Tempting: B and C are common mistakes in calculating df.

Question 2

Question: Which distribution should you use for a sample size of 25 with an unknown population standard deviation? Options: A. Normal distribution B. t-distribution C. Chi-square distribution D. Binomial distribution Correct Answer: B. t-distribution Explanation: Use the t-distribution for small samples with unknown population standard deviation.
Why the Distractors Are Tempting: A is tempting if you forget the sample size rule.

Question 3

Question: What is the t-score for a sample mean of 50, population mean of 45, sample standard deviation of 10, and sample size of 10? Options: A. 1.58 B. 2.00 C. 2.50 D. 3.00 Correct Answer: A. 1.58 Explanation: ( t = \frac{50 - 45}{10 / \sqrt{10}} \approx 1.58 ) Why the Distractors Are Tempting: B, C, and D are plausible t-scores but incorrect calculations.

Question 4

Question: For a 95% confidence interval with 14 degrees of freedom, what is the critical t-value? Options: A. 1.761 B. 2.145 C. 2.624 D. 3.143 Correct Answer: B. 2.145 Explanation: From t-tables, the critical t-value for 95% confidence and 14 df is approximately 2.145.
Why the Distractors Are Tempting: A, C, and D are critical values for different df or confidence levels.

Question 5

Question: A researcher wants to test if the mean weight of a product is different from 100 grams. A sample of 12 products has a mean weight of 105 grams with a standard deviation of 15 grams. What is the t-score? Options: A. 1.33 B. 1.50 C. 1.75 D. 2.00 Correct Answer: A. 1.33 Explanation: ( t = \frac{105 - 100}{15 / \sqrt{12}} \approx 1.33 ) Why the Distractors Are Tempting: B, C, and D are plausible but incorrect t-scores.

30-Second Cheat Sheet

• Use t-distribution for small samples (n < 30) and unknown population standard deviation.
• Degrees of freedom: df = n - 1
• t-distribution has heavier tails than the normal distribution.
• t-score formula: ( t = \frac{\bar{x} - \mu}{s / \sqrt{n}} )
• Confidence interval: ( \bar{x} \pm t \left( \frac{s}{\sqrt{n}} \right) )
• As df increases, t-distribution approaches normal distribution.

Learning Path

1. Beginner Foundation: Review normal distribution and basic statistical concepts.
2. Core Rules: Understand when to use the t-distribution and how to calculate degrees of freedom.
3. Practice: Solve problems involving t-scores, confidence intervals, and hypothesis testing.
4. Timed Drills: Practice under exam conditions to improve speed and accuracy.
5. Mock Tests: Take full-length practice exams to solidify your understanding.

Related Topics

1. Normal Distribution: Understanding the normal distribution is crucial for comparing it with the t-distribution.
2. Hypothesis Testing: Knowing how to set up and test hypotheses is essential for applying the t-distribution.
3. Confidence Intervals: Constructing confidence intervals using the t-distribution is a common exam topic.