Hypothesis testing

The field of statistics provides a framework to formally test a hypothesis using probability. This page introduces the fundamental ideas behind hypothesis testing. Subsequent pages describe an array of quantitative methods used to evaluate different types of hypotheses and data.

 
 
Enjoy the videos and music you love, upload original content, and share it all with friends, family, and the world on YouTube.
 

Hypothesis Testing

How do we use statistical samples to not only estimate a parameter from a population but also draw some conclusions about the population?

P-values are central to statistics. In this video we will discuss what p-values mean, how to use p-values to draw conclusions and what factors might affect t...
 

P-values

What is a P-value? What does it mean and how can we use P-values to draw conclusions? This video will also cover the different types of statistical errors (Type I and Type II errors), why we typically reject the null hypothesis when P < 0.05, and whether and when we should use an adjusted significance level.

Why do we calculate P-values as probabilities of getting values as extreme OR MORE EXTREME than our observed sample?
 

P-values, why do we consider values equal to OR MORE EXTREME than our observed value?

When we calculate a P-value from a sample we measure the probability of getting an estimate that is as extreme OR MORE EXTREME than what we observed when the null hypothesis is true. This video tries to explain why we consider more extreme values in this calculation.

Additional Resources

Sampling and Statistical Power - StatsTree handout

Whitlock & Schluter - The Analysis of Biological Data

Chapter 6: pages 151-169 [Sapling]

 
 

Hypothesis testing: Basics

Intro: Intuition behind hypothesis testing, and explanations of null and alternative hypotheses, test statistics, and type I and type II errors.

Hypothesis testing: All you need to know

Intermediate: Worked examples for some tougher hypothesis tests.

 

P values

Intro: The most basic explanation of p values.

Review Questions

 

  1. Data on tooth decay is collected from a sample of Americans. Which of the following could be a null hypothesis?

    (a) Consumption of soda has no effect on dental health.

    (b) People who drink soda as kids have a higher incidence of dental issues.

  2. A spectrometer is used to measure the wing-feather colors of northern flickers in California, Wyoming, and Colorado. Which of the following could be an alternative hypothesis?

    (a) Feather color is the same among all three populations.

    (b) The northern flicker populations have different colored wing-feathers.

  3. Which of the following is a type I error, and which is a type II error?

    (a) rejecting a true null hypothesis

    (b) failing to reject a false null hypothesis

The Next Steps

Confused?

Let’s move down the tree and review these concepts.

Ready to Move Forward?

Let’s move up the tree to the next topic.