Chapter 9
Chapter 9: Sampling Distributions
9.1 Introduction to Sampling Distributions
Definition: A sampling distribution is created through the process of sampling.
Methodology: Utilizes rules of probability, expected value, and variance to derive the sampling distribution.
9.2 Types of Sampling Distributions
Sampling Distribution of the Mean
Involves repeated sampling and measuring the mean of samples.
Sampling Distribution of a Proportion
Focuses on the ratio of successes to the total sample size.
Sampling Distribution of the Difference Between Two Means
Considers the differences in means from two independent samples.
9.3 Sampling Distribution of the Mean
Example: Rolling a fair die infinitely results in a random variable (X) defined as the number of spots on any throw.
Probability Distribution for X: P(1) = 1/6, P(2) = 1/6, ..., P(6) = 1/6
Mean (μ) and Variance (σ²) can be calculated.
9.4 Sampling Distribution of Two Dice
Sampling distribution is derived from all possible combinations of two dice rolls.
Sample Size (n = 2): 36 possible outcomes; 11 unique means (e.g., x̄ = 3.5 occurs frequently).
9.5 Construction of Sampling Distributions
The sampling distribution of the sample mean is classified and organized based on the outcomes of the sample.
Standard Error: The standard deviation of the sampling distribution, calculated as σ/√n.
9.6 Central Limit Theorem (CLT)
Definition: The mean of a random sample approaches a normal distribution as sample size increases.
Critical Points:
If the population is normal, the sample mean is normal regardless of sample size.
If the population is not normal, a sample size of n ≥ 30 is generally adequate for normal approximation.
9.7 Sampling Distribution of the Sample Mean
The relationship between the sample mean and the population parameters.
Formula: Z = (X̄ - μ) / (σ/√n)
9.8 Finite Population Correction
When dealing with finite populations, a correction factor is applied to the standard error.
If N (population size) is at least 20 times larger than n (sample size), the correction can often be ignored.
9.9 Application of Sampling Distributions
Example 9.1(a): Sparkling water bottles mean amount with realized values.
µ = 2.2L, σ = 0.3L; Probability that X > 2 is computed.
Example 9.1(b): Mean of four bottles. Assessed for probabilities exceeding 2.0L.
9.10 Probability and Inference
Example 9.2: Analysis of political support over a sample size of 300 regarding voter representation.
Probability that more than 50% would vote for a candidate based on current support levels.
Uses p-hat to determine probabilities and validate claims.
9.11 Difference of Two Means
Derived from two independent normal populations.
Conditions for normality and calculation of mean and standard deviation when comparing sample means.
9.12 Statistical Inference
Knowledge of the parameter includes probability statements about sample statistics.
Transition from assessing the population parameters to sampling from the population for better statistical inferencing.
Next Steps: Use the established sampling distribution to infer about the population parameters.