MathsMate: Resources for Research Proposal IV
The challenges you might face with the statistical aspects of this course include
- understanding the general structure of statistical inference (aka "null hypothesis testing"),
- choosing an appropriate testing procedure(s) for your experimental design and then
- estimating the sample size(s) required by that testing procedure to make the experiment worthwhile (aka "power analysis").
The following sites provide insights into these challenges, or at least serve as good "jumping off" points to other, more specifc, resources.
Use the menu bar at the end of the page to return or to contact the Maths Learning Service.
"Statistics at square one"
- A classic introductory statistical text for Medicine and the Health Sciences. 
Which analysis? - There are
a multitude of statistical tests available (often more than one option for the
same experimental design!), so choosing an appropriate one can be difficult. The
links listed on this page might help.
Guides to good statistical practice - Although designed for Agricultural Science,
these guides are useful for other areas. In particular the section "guides about
analysis".
The British Medical Journal published a series of articles titled "how to read a paper" which discuss the statistical aspects of published research:
How to read a paper: Statistics for the non-statistician. I: Different types of data need different statistical tests - a checklist of questions to help you appraise the statistical validity of a paper.
How
to read a paper: Statistics for the non-statistician. II: "Significant"
relations and their pitfalls - continuation of the checklist above.
How
to read a paper: Papers that go beyond numbers - to "study things in their
natural setting, attempting to make sense of, or interpret, phenomena in terms
of the meanings people bring to them".
Simplified sample size calculations
- A guide to sample size calculation formulae for some common tests used in clinical
research.
Online sample size "calculators"
- For some of the more basic statistical tests you can calculate the estimated
sample size required online. This page contains a decent selection of what's out
there.