search this site.

220113P - INFERENTIAL STATISTICS FOR CONTINUOUS DATA

Copyright 1995-2023 © by Prof Omar Hasan Kasule - Admin
Category:
Print Friendly and PDFPrint Friendly

Presented at the Research Methodology Winter Camp of AlMaarefa University on January 13, 2022 at 10.00am by Omar Hasan Kasule MB ChB (MUK), MPH (Harvard), DrPH (Harvard) Professor of Epidemiology and Bioethics

 

PARAMETRIC ANALYSIS OF CONTINUOUS DATA:

  • Parametric analysis is used for normally distributed data.
  • Inference on continuous data is based on the comparison of sample means.
  • Three test statistics are commonly used: z, t- and F-statistics. F is also called ANOVA.
  • The z-statistic is used for large samples. The t and F are used for small or moderate samples.
  • The z-statistic and the t-statistic are used to compare 2 samples.
  • The F statistic is used to compare 3 or more samples.

 

STEPS OF PARAMETRIC ANALYSIS:

  • State the null and alternative hypotheses in terms of means.
  • Check that the samples are normally distributed and that sample variances are equal.
  • Use technology to compute the test statistic and derive the p-value.

 

NON-PARAMETRIC ALTERNATIVES:

  • Non-parametric tests are used for data that is not normally distributed (graph not symmetrical).
  • The signed-rank test and the rank sum tests are equivalent to the 2 sample t test.
  • The Kruskall-Wallis test is equivalent to the one-way ANOVA test.