Please forgive me if I am posting this in the wrong forum. Here is the context of my question:
- I am conducting a drug trial, of sorts.
- I have 7-8 potential candidates for the treatment.
- Between each drug administration, there has to be a 'wash-out' period of around 2-3 days, so the cycle for testing one drug is 5 days (per person).
My problem is this - for 8 different candidates that will take 40days! To reduce the total time the experiment might take, I have had an idea, but I'm not sure if it will be experimentally sound - maybe someone could give some advice:
I'm thinking I randomly assign each person, 4 of the 8 drugs. This will reduce the time. For example, say I have 18 people, and there are 8 drugs ABCDEFGH:
I could randomly assign each person in the following way: ADEG AFCB BCFH GCDA HDCE HBEG DEFG AEHF ECGD BHDF BAEF HEAD EACH CFGB FBDH CAGB FABG DCGH, which means that each drug is being tested by 9 people.
Each drug has a 5-day cycle, so each experiment will last 20 days (whilst each person is tested independently, but at the same time). If I am testing the effect of each drug on 4 different parameters (say, w,x,y,z) how can I record the data succinctly in a table.
Just to be more clear, I shall give a quick example. Say I have person 1, who has been assigned ABCD - I record w,x,y,z for each of A, B, C, and D. I record these parameters for all the other randomly assigned strings - how could I record this?
EDIT 1
Here is what I have so far, in terms of how I originally planned to represent the data.
But as you can see, it will be a very long experiment - can it be made more succinct?
EDIT 2 -
Come on guys! Any help is really appreciated - any advice please?
