Statistical Distributions Notes
Sampling Distribution
Definition: Probability distribution of a statistic from repeated random samples.
Key Concepts:
Population: Entire set of observations.
Sample: Subset of the population.
Statistic: Summary characteristic of a sample (e.g., sample mean).
Sampling Distribution: Distribution of a statistic over multiple samples.
Sampling Distribution of the Sample Mean (X)
Sample Mean: Average of a sample, represented as X.
Mean of Sampling Distribution: E(X) = Population Mean (µ).
Standard Error of Mean: SE(X) = σ/√n.
Central Limit Theorem (CLT)
Sampling distribution of sample mean approaches normal distribution as n increases (n ≥ 30).
Mean = Population Mean (µ). Standard deviation (SE) = σ/√n.
Importance of Sampling Distribution
Inferential Statistics: Estimates population parameters from sample statistics.
Hypothesis Testing: Determines the probability of sample means under null hypothesis.
Confidence Intervals: Provides range for population parameters.
Types of Sampling Distributions
Sampling Distribution of the Sample Mean (X).
Sampling Distribution of the Sample Proportion (p̂).
Sampling Distribution of the Sample Variance (s²).
Standard Normal Distribution
Definition: Special case of normal distribution (mean = 0, SD = 1).
PDF: f(x) = (1/√(2π)) e^(-x²/2).
Properties:
Symmetry around mean.
68-95-99.7 Rule for standard deviations.
Application: Calculating Z-scores, confidence intervals, hypothesis testing.
Chi-Square Distribution
Definition: Distribution of sum of squares of standard normal variables.
PDF: f(x, ν) = (x^(ν/2 - 1) e^(-x/2)) / (2^(ν/2) Γ(ν/2)).
Properties: Non-negative, Mean = ν, Variance = 2ν.
Application: Goodness-of-fit tests, independence tests.
t-Distribution
Definition: Used when sample size is small and population SD is unknown.
PDF: f(t, ν) = [Gamma((ν + 1)/2)] / (√(νπ) Gamma(ν/2))(1 + t²/ν)^(-(ν + 1)/2).
Properties: Symmetric, approaches normal distribution as ν increases.
Application: Hypothesis testing, confidence intervals for means.
F-Distribution
Definition: Ratio of two independent chi-square variables.
PDF: Non-negative, positively skewed.
Properties: Mean = ν2 / (ν2 - 2) (ν2 > 2).
Application: Comparing variances in ANOVA, model comparisons.
Symbols in Statistics
µ (Mu): Population mean
x̄ (X-bar): Sample mean
σ (Sigma): Population standard deviation
s: Sample standard deviation
n: Sample size
E(X): Expected value of statistic
SE(X): Standard error of mean
p̂ (P-hat): Sample proportion
ν (Nu): Degrees of freedom
Γ (Gamma): Gamma function
Z: Z-score
χ² (Chi-square): Chi-square statistic
F: F-statistic
These symbols are fundamental in understanding and working with statistical concepts.