Quick Recap: Hypothesis Testing

Hypothesis Testing

• Hypothesis Testing is the use of statistics to determine the probability that a given hypothesis is true. Usually, the process can be completed by utilizing a simple test.
• Statistical inference can be with two variables (bivariate), or more than two variables (multivariate)

Bivariate Hypothesis Test

• A bivariate hypothesis test is a statistical inference with two variables.
• All bivariate tests follow the same initial steps:
  1. Identify the null and alternative hypotheses
     • The null hypothesis represents a situation where there is no relationship between our two variables; the null hypothesis will be rejected if our alternative hypothesis is correct, but it will not be rejected if our hypothesis is incorrect.
     • The alternative hypothesis is our own hypothesis which we are trying to prove
  2. Choose a significance level (how certain do we want our conclusion to be)
  3. Choose the appropriate hypothesis test: (See the Selecting the Appropriate Hypothesis Test page for more info!)
     • Difference of means (t-test)
     • Difference of proportions (z-test)
     • Bivariate regression
     • Correlation coefficient
     • Chi-square test
  4. Calculate test statistic and P-value
     • Use the formula associated with the chosen hypothesis test to calculate these
  5. Interpret the P-value
     • Reject the null hypothesis when the p-value is less than the significance level
     • Fail to reject the null hypothesis when the p-value is greater than the significance level

Limitations of Bivariate Hypothesis testing

• Shows relationship, but not necessarily a cause
  • Does not account for confounding variables
• Requires random sample
• Statistical significance is not equal to substantive importance

Dig Deeper

• Introduction to hypothesis testing, Chapter 8Links to an external site.