Hypothesis Testing Essentials

Hypothesis testing is a statistical procedure that uses sample evidence to determine if a stated hypothesis about a population is reasonable or should be rejected.

Core Principles

  • Null Hypothesis (H0): A statement about a population parameter assumed to be true, always containing an equality.
  • Alternative Hypothesis (Ha): A claim that contradicts the null hypothesis, indicating what we suspect might be true.
  • Type I Error: Rejecting a true null hypothesis (false positive).
  • Type II Error: Failing to reject a false null hypothesis (false negative).
  • Significance Level (α): The maximum allowable probability of a Type I error, typically set at 10% or less.
  • P-value: The probability of observing sample data as extreme as, or more extreme than, the observed data, assuming the null hypothesis is true.

Action Steps

  • 1. State the Null (H0) and Alternative (Ha) hypotheses.
  • 2. Define the test procedure and the significance level (α).
  • 3. Calculate the Test Statistic (TS) and the P-value.
  • 4. Compare the P-value to α: Reject H0 if P-value < α; otherwise, do not reject H0.
  • 5. Interpret the decision in the context of the problem.

Formulas

  • One-sample z-test statistic: $$z = \frac{\bar{x} - \mu_0}{\sigma/\sqrt{n}}$$
  • One-sample t-test statistic: $$t = \frac{\bar{x} - \mu_0}{s/\sqrt{n}}$$
  • Two-sample t-test statistic: $$t = \frac{(\bar{x}_1 - \bar{x}_2) - (\mu_1 - \mu_2)}{\sqrt{\frac{s_1^2}{n_1} + \frac{s_2^2}{n_2}}}$$
  • Paired t-test statistic: $$t = \frac{k_d}{\bar{s}_d/\sqrt{n}}$$
  • One-sample z-test statistic (prop): $$z = \frac{\hat{p} - p_0}{\sqrt{\frac{p_0(1-p_0)}{n}}}$$
  • Two-sample z-test statistic (prop): $$z = \frac{(\hat{p}_1 - \hat{p}_2) - (p_1 - p_2)}{\sqrt{\hat{p}(1-\hat{p})(\frac{1}{n_1} + \frac{1}{n_2})}}$$
  • P-value for Ha: μ > μ0: $$P = P(Z > z_{stat})$$ (right-tail)
  • P-value for Ha: μ < μ0: $$P = P(Z < z_{stat})$$ (left-tail)
  • P-value for Ha: μ ≠ μ0: $$P = 2 \times \text{one-tailed P-value}$$

Key Terms

  • Hypothesis: An assumption or statement about a population parameter.
  • Parameter: A population mean or proportion.
  • Null Hypothesis (H0): A statement about the population that will be assumed to be true.
  • Alternative Hypothesis (Ha): A claim about the population that is contradictory to H0.
  • Type I Error: Rejecting a true null hypothesis (false positive).
  • Type II Error: Failing to reject a false null hypothesis (false negative).
  • Significance Level (α): The maximum allowable probability of a Type I error.
  • P-value: The probability that an outcome of the data will happen purely by chance when the null hypothesis is true.
  • Test Statistic: A standardized value calculated from sample data used to determine whether to reject H0.
  • One-tailed Test: A test that checks for deviation in only one direction (greater than or less than).
  • Two-tailed Test: A test that checks for deviation in both directions (greater or less than).

Pro Tips

  • The null hypothesis (H0) must always contain equality (=, ≤, or ≥).
  • The alternative hypothesis (Ha) always contradicts the null hypothesis.
  • A small p-value (typically ≤ 0.05) indicates strong evidence against H0, leading to its rejection.
  • The Power of the Test (1-β) represents the probability of correctly rejecting a false null hypothesis.

Pitfalls to Avoid

  • Failing to identify the parameter before analysis leads to incorrect hypothesis formulation.
  • Confusing Type I and Type II errors results in misinterpreting test outcomes.
  • Using a large p-value (> 0.05) to reject H0 leads to incorrect conclusions.

Myth vs Reality

  • Hypothesis testing aims to prove the null hypothesis is true.: Hypothesis testing aims to determine if there is enough evidence to reject the null hypothesis; it does not prove it true.
  • A Type I error is more serious than a Type II error.: The relative seriousness of Type I and Type II errors depends on the specific context of the problem.

Real World Examples

  • Testing if college students take less than five years to graduate.: H0: μ ≥ 5, Ha: μ < 5 (left-tailed test).
  • Testing if 29% of high school seniors get drunk each month.: H0: p = 0.29, Ha: p ≠ 0.29 (two-tailed test).
  • A supplement company claims its Vitamin D pills raise blood D levels above the national average of 20 ng/mL.: This is a right-tailed test to see if the mean is greater than 20 ng/mL.

Statistics

  • Maximum allowable probability of a Type I error (α): Set at most 10%
  • Typical threshold for small p-value: ≤ 0.05

Quiz

  • What is the primary purpose of hypothesis testing?: To determine if sample evidence supports rejecting a population hypothesis.
  • Which of the following statements correctly defines a Type I error?: Rejecting a true null hypothesis.
  • If a p-value is 0.03 and the significance level (α) is 0.05, what is the decision regarding the null hypothesis?: Reject H0.

Related cheat sheets

  • Milestones in the Development of Philosophy
  • Year 9 Maths Revision Cheat Sheet
  • Philosophy's Four Eras: From Greece to Russell
  • Sequences, Series, and Parametric Calculus Cheat Sheet
  • Polar Coordinates: Area & Arc Length Essentials
  • Theory of Computation Essentials

More like this

  • More cheat sheets by @magythesmartcookie
  • Science & Academic cheat sheets
  • Explore all cheat sheets

ClipSheet — AI Cheat Sheet Generator

ClipSheet transforms YouTube videos, PDFs, and text into structured cheat sheets and study notes using AI. Built for students, professionals, and content creators who need to learn faster.

Features

  • AI-powered extraction of key concepts, formulas, and action steps
  • Automatic quiz and flashcard generation for active recall
  • PDF export and public sharing via unique URLs
  • Support for YouTube videos, PDFs, and raw text input

Browse by Category

  • All Cheat Sheets
  • Science & Academic
  • Technology
  • Health & Fitness
  • Coding
  • Business
  • Education
  • Productivity
  • Finance
  • Lifestyle

Legal

  • Privacy Policy
  • Terms of Service
  • Imprint
  • Verträge hier kündigen