[Joherba]

Some students threw three fair dice, each numbered from 1 to 6.
They recorded how many times the numbers on the dice were the same.

Name
1) Number of throws
2) All different
3) to the same
4) All the same

Masood 1) 40 2) 26 3) 12 4) 2

Saleh 1)140 2) 81 3) 56 4) 3

Walid 1) 20 2) 10 3) 10 4) 0

Ali 1)100 2) 54 3) 42 4) 4

Which student's data are most likely to give the best estimate of the probability of getting each result?

Please explain your answer.

[sarnian]

Well Joherba

That was the question. Perfectly copied.
As to my reply to your question :
What is the connection between best estimate and sample size?
And what have you done so far with the question yourself?
Any processing done of the 4 x 4 results?
What is unclear? Where did you get stuck?
Or do you expect us to do your homework?

[Joherba]

Please help me out! I do not make heads or tails with this!!

[Perito]

Which has a better probability of accurately representing the possible data set?

1. Throwing a set of dice once?
2. Throwing a set of dice twice?
3. Throwing a set of dice a thousand times?

The more times you throw the dice, the more "samples" you have, and thus you can model the possible results better. In this case, the students aren't measuring all possibilities, they're just measuring the probability that all dice are the same, or all dice are different, or that two are the same.

There are various statistical tests to show the possible error in the measurement. I'm not sure what tests you're currently studying. If you are studying one, that is probably what the teacher expects you to use to validate your choice.

In statistics, there is a (sort of mythical) quantity, the true answer. Since you don't know the true answer, you're trying to find the best estimate of the true answer by experimentation. If you could throw the dice an infinite number of times, you would get a perfect estimate of the true answer.

[Joherba]

Thans for this, I appreciate your help!

[sarnian]

Joherba

I already gave you a similar answer (like Perito's) in my previous response :

What is the connection between best estimate and sample size?

The lack of any information other than the question gave me the impression that you wanted us to do your homework. But that is not the intention of this board. It is only a HELP board. We provide hints into what direction you have to think. It is you who has to do the homework.