Confidence Intervals and Hypothesis Tests for Means

The Central Limit Theorem (CLT)

The Central Limit Theorem is a foundational concept in statistics, describing how the sampling distribution of the sample mean approaches a Normal distribution as the sample size increases, regardless of the population's original distribution.

• Definition: The mean of a random sample has a sampling distribution whose shape can be approximated by a Normal model. The larger the sample, the better the approximation will be.

• Implication: Even if the population distribution is not Normal, the distribution of sample means will become Normal as sample size grows.

• Application: This allows statisticians to use Normal-based inference for means, even with non-Normal populations, provided the sample size is sufficiently large.

• Example: Simulating averages of dice rolls demonstrates the transition from uniform to bell-shaped distributions as sample size increases.

Sampling Distribution of the Mean

The sampling distribution of the mean describes how sample means vary from sample to sample. It is modeled by a Normal distribution with a specific mean and standard deviation.

• Mean: The mean of the sampling distribution is equal to the population mean, μ.

• Standard Deviation: The standard deviation of the sampling distribution is , where σ is the population standard deviation and n is the sample size.

• Notation:

• Key Point: The larger the sample size, the smaller the spread of the sampling distribution.

• Example: Comparing the probability of a single extreme value versus the mean of a large sample being extreme.

Standard Error

When the population standard deviation is unknown, we estimate the standard deviation of the sampling distribution using the sample standard deviation. This estimate is called the standard error (SE).

• Formula for sample mean:

• Formula for sample proportion:

• Purpose: SE quantifies the uncertainty in estimating the population parameter from a sample.

Student's t-Distribution

When the population standard deviation is unknown and estimated from the sample, the sampling distribution of the mean follows a Student's t-distribution, which accounts for additional uncertainty.

• Definition: The t-distribution is bell-shaped, unimodal, and symmetric, but has fatter tails than the Normal distribution, especially for small sample sizes.

• Degrees of Freedom (df): The shape of the t-distribution depends on the degrees of freedom, usually n - 1.

• Formula:

• Standard Error:

• Application: Used for confidence intervals and hypothesis tests for means when σ is unknown.

Confidence Intervals for Means

A confidence interval estimates the range in which the true population mean is likely to fall, based on sample data.

• One-Sample t-Interval Formula:

• Standard Error:

• Critical Value: depends on the confidence level and degrees of freedom.

• Interpretation: "We are 95% confident that the true mean lies within the interval."

Assumptions and Conditions for Inference

Statistical inference for means requires several assumptions and conditions to be met:

• Independence Assumption: Data should be independent, often ensured by random sampling.

• Randomization Condition: Data must arise from a random sample or randomized experiment.

• 10% Condition: Sample size should be less than 10% of the population.

• Normal Population Assumption: Data should be nearly Normal (unimodal and symmetric). For small samples, this is critical; for larger samples, t-methods are robust unless data are extremely skewed.

One-Sample t-Test for the Mean

The one-sample t-test is used to test hypotheses about the population mean when the population standard deviation is unknown.

• Null Hypothesis:

• Test Statistic:

• Standard Error:

• P-value: Calculated using the t-distribution with n - 1 degrees of freedom.

• Conclusion: Based on the P-value, decide whether to reject or fail to reject the null hypothesis.

Sample Size Determination

Determining the appropriate sample size is crucial for achieving a desired margin of error in confidence intervals.

• Formula:

• Considerations: Use a "good guess" for s if unknown, or conduct a pilot study.

• Critical Value: If n is unknown, use the z* value from the Normal model as an approximation.

• Application: Ensures the sample size is large enough to achieve the desired precision.

Cautions and Best Practices

When interpreting confidence intervals and performing hypothesis tests, keep the following in mind:

• Interpretation: Confidence intervals are about the mean, not individual observations.

• Uncertainty: The interval varies randomly; your uncertainty is about the interval, not the true mean.

• Data Quality: Check for independence, bias, outliers, skewness, and multimodality.

• Appropriate Methods: Use Normal models for proportions and Student's t methods for means.

Summary of Key Formulas

• Standard Error for Mean:

• Confidence Interval for Mean:

• One-Sample t-Test Statistic:

• Sample Size Formula: