Nayland College - Mathematics
Randomly allocate to two groups
Treatment group vs non treatment group
Collect data from two groups eg exercise vs non exercise, what age did babies walk?
Compare medians. Observed difference of 'blah'
What if there is no effect? Assume random
Randomly pair up group and measurement, compare medians of two groups, plot dot plot of differences between medians of two groups
|Open Inzite randomised tests|
|Import data (check set up correctly)|
|Go to Analyse tab|
|Set median (or mean)|
|Data is a comparison of recorded medians for the two groups|
Randomised distribution shows the distribution of the differences between the two groups if allocation is by chance alone
eg prob of 0.028 is unlikely
Focus on the plan
How are we going to randomise groups
How are we going to have random placebos
This will be the major issue.
How will we be able to ensure the only difference between the two groups is the treatment?
Do students have to design their own experiment? This will be hard
How do we get students to do this?
Conclusion The chance that the difference that we found that would occurr randomly is 0.028 which is unlikely.
We can rule out that chance is acting alone