Education and science ©1994-2003 Kevin Boone
Home     Section index     K-Zone home
Workshop on experimental design

Site search

Articles
- So you want to be a university lecturer? Read this first!

What is statistics actually for?

More...

The K-Zone
K-Zone computing

K-Zone law

K-Zone education and science

K-Zone motorcycles

K-Zone DIY

K-Zone railways

K-Zone martial arts

About the author

K-Zone home page

 
What question?
contents
A hypothesis
Experimental design: what is the hypothsis?

What hypothesis for the Boggett and Scarper experiment?

What hypotheses might the experimenters have asserted and tested in the evaluation of their new system?

Remember that asserting a hypothesis implies that you know some way to test whether it is true or not

In practice you are going to unable to prove that your hypothesis is true, since however many times you repeated the experiment and found it to be true, there is still the possibility that the next time it would be found to be false. However, only one observation is necessary to disprove a hypothesis. The normal experimental technique is to assert a null hypothesis, complementary to your hypothesis, and the observations which will lead to it being assumed disproved. If the null hypothesis is disproved, this implies that your primary hypothesis (or some alternative hypothesis) can be assumed true, at least for the present.

This may seem odd, but it is a perfectly standard procedure in the experimental sciences.