Null Hypothesis Significance Testing

• Inferential Statistics


  A set of statistical procedures to test hypotheses (i.e., make inferences) about a population
• Null Hypothesis Significance Testing (NHST)


  The process by which researchers determine if their data support or fail to support their hypothesis
• NHST


  1. State hypotheses

  2. Set the criterion for burden of proof (alpha level)

  3. Collect data and calculate statistics

  4. Make a decision about the null hypothesis according to the criterion from Step 2

  
• Null Hypothesis (Ho)


  States that there is no change, no difference, no relationship
• Alternative Hypothesis (H1)


  States that there is a change, a difference, or a relationship
• Alpha level (α)


  The probability value criterion that is used to distinguish very unlikely sample means from likely sample means
• Test statistic


  Any statistic with a known distribution from which we can calculate a p-value (e.g., z, t, F)
• 1. value


  The probability of obtaining a test statistic that is that large or larger if the null hypothesis is true
• The equation for a z-test is: z = (x_i - μ) / σ
• Type I error


  Occur when we reject the null hypothesis when it is in fact true
• Type II error


  Occur when we fail to reject the null hypothesis when the null hypothesis is really false
• To reduce Type I errors, lower the alpha level so that the cut-off is more stringent
• To reduce Type II errors, lower measurement error, collect data more precisely, increase the size or detectability of thing you are trying to measure, collect a large sample