Sampling Distributions (CLT)
Struggle with the Central Limit Theorem? Draw 10,000 samples from highly skewed or bimodal parent populations and watch the perfect normal bell curve emerge.
WHAT IS A SAMPLING DISTRIBUTION?
A sampling distribution is the distribution of a statistic (like or ) across all possible samples of a fixed size from a population. It is the bridge between probability and statistical inference. While a population distribution describes individuals, a sampling distribution describes how a sample statistic varies from sample to sample. This variation is known as **sampling variability**.
THE CENTRAL LIMIT THEOREM (CLT)
The CLT is the most important theorem in statistics. it states that for a large enough sample size (usually ), the sampling distribution of the sample mean will be approximately normal, regardless of the shape of the population distribution. This allows us to use normal probability calculations even when the underlying population is skewed or non-normal.
HOW TO USE THIS VISUALIZATION
1. **Choose Population**: Select a population shape (Normal, Uniform, Skewed, or Custom). 2. **Set Sample Size ()**: Change from 2 to 100. Watch how the sampling distribution becomes narrower and more normal as increases. 3. **Animate Sampling**: Click "Sample" to see individual data points being drawn and their mean added to the sampling distribution. 4. **Compare Statistics**: Toggle between the distribution of means () and the distribution of proportions ().
AP EXAM CONNECTION
Unit 5 is the foundation for the rest of the course. You must master the three conditions for sampling distributions: Randomness (to avoid bias), 10% Rule (to ensure independence when sampling without replacement), and Normal/Large Sample condition (to justify using the normal model). The CLT only applies to the *shape* of the distribution, not the center or spread.
CORE FORMULAS
AP EXAM CONNECTION
Unit: Unit 5: Sampling Distributions (Topic 5.2-5.7)
Learning Objective: UNC-4.B
COMMON MISCONCEPTIONS
- Thinking the CLT says the *population* becomes normal as increases.
- Confusing the standard deviation of the population (sigma) with the standard deviation of the statistic (sigma_{ar{x}}).
- Forgetting to check the or conditions before using normal calculations.
KEY TAKEAWAYS
- Sampling distributions describe the behavior of statistics, not individuals.
- The Central Limit Theorem ensures normality for large .
- Increasing sample size decreases sampling variability.
- Bias is a property of the center; variability is a property of the spread.
PRACTICE QUESTIONS
Q1 (QUANTITATIVE): A population is highly right-skewed with and . If we take samples of size , describe the shape, center, and spread of the sampling distribution of .
Show Answer & Explanation
Answer: Shape: Approx. Normal; Center: 50; Spread: 1.58
Explanation: By CLT, since , the shape is approx. normal. The mean is . The standard deviation is .
Q2 (CONCEPTUAL): What happens to the standard deviation of the sampling distribution if the sample size is quadrupled?
Show Answer & Explanation
Answer: The standard deviation is cut in half.
Explanation: Because the formula includes in the denominator, . Dividing by 2 is the same as multiplying by 1/2.
