Class 12
Week 7: Biostatistics Overview
1. Introduction to Inferential Statistics
Purpose: Inferential statistics is used to draw conclusions about a population based on sample data.
Key Concepts:
Population: Complete set being studied.
Sample: Subset of the population used for analysis.
Parameter: A descriptive measure of a population (e.g., population mean, population standard deviation).
Statistic: A descriptive measure of a sample (e.g., sample mean, sample standard deviation).
2. Sampling Distributions
Definition: The sampling distribution is the distribution of a statistic (e.g., mean) over all possible samples of a given size from a population.
Random Samples:
Obtain a simple random sample of size n.
Calculate the sample mean.
Repeat until all possible simple random samples of size n are obtained.
Characteristics:
Each sample has its own mean.
Collectively, these sample means form the sampling distribution of the sample mean.
3. Central Limit Theorem (CLT)
Importance: As sample size increases, the sampling distribution of the mean approaches a normal distribution, regardless of the population’s distribution shape.
Conditions for Normality:
If the population distribution is normal, the sampling distribution of the mean will also be normal for any sample size N.
If the population is not normal, a sample size of about 30 (N=30) is generally sufficient for the sampling distribution to appear normal.
With highly skewed populations or distributions with extreme outliers, larger samples may be necessary (N=500 or more) to achieve normality in the sampling distribution.
4. Standard Error
Definition: Standard error (SE) measures the dispersion of sample means around the population mean.
Formula for SE of the Mean:
SE = σ / √n, where σ is the population standard deviation and n is the sample size.
Relationship to Population Standard Deviation: The standard error is typically smaller than the population standard deviation due to reduced variability with summary measures compared to individual measurements.
5. Examples of Sampling Distributions
If the population distribution is significantly non-normal, the distribution of the means will still tend to be normal with an increase in sample size.
Examine distributions of various population shapes and their corresponding sampling distributions:
Normal population distribution yields a normal sampling distribution.
Non-normal populations (skewed, bimodal, etc.) show normality in the sampling distribution as sample size increases.
6. Application Example: Latency Times to AIDS
Given: Mean latency time = 5.24 years, std deviation = 10.15 years.
Compute probability that a randomly sampled individual has latency time ≥ 8 years using N distribution.
For a sample of size 50, compute the probability that the mean latency time is ≥ 8 years using the standard error formula:
SE = σ / √n = 10.15 / √50 = 1.44.