All a larger sample size is going to do is narrow down the range of the confidence interval. The range is adequate enough for what I set out to accomplish. Yes the rolls are random but how random? Are the odds actually 1:14 for any outcome or are they skewed to give more 1's or more 1's and less 14's? I understand the frustration, most folks don't comprehend statistical probability.
Wow, that gave me a good chuckle, people keep pointing out how you are wrong, I mean look through the thread and yet you come out with "most folks don't comprehend statistical probability", it's genuinely rare to come across such delusion. I'm out.
I have facts, logic, science and math on my side, what's in your corner? Insults? Where did anyone point out that I am wrong?
I remember the first lesson in the class; they let us calculate our chances of winning the lottery.
I would say that's the problem. If you want to convince people of something then you would need to do a better job to achieve that.
Again, you need present an experiment with a bigger sample pool.
You are right, but only (4) coin flips is not adequate. My data set is 257 on a random outcome of 14 possibilities. That means I used 18 times the possible outcomes. So an equivalent sample for a coin flip would be 36 or lets say 40 for round numbers. I just flipped a coin 40 times and got heads 24 and tails 16. To apply the same logic I did for the siege rolls, the mean is 60% heads. Is 60% indicative of the actual odds of an even sided coin? Let's check the confidence interval. The standard deviation is 7.84% and we need 1.96 standard dev's to be within the 95% confidence range. That means the 60% mean +/- 15.37%. Since we know the true probability is 50% exactly, and our confidence interval falls within this range, the data set is valid and the coin is fair. If I got a data set showing the coins confidence interval that did not include the 50% value, then we could question the validity of the coin being fair. I hope this makes sense. I think folks are getting very hot under the collar so I'm going to drop this now. It's almost like discussing politics or religion, gesh.
However, the standard deviation on flipping 24 heads out of 40 is sqrt(24)/40 = 12.25%, yes?
I hope not to come across as a know it all but it's probably too late for that for some people. The difference between the method I used and yours has to do with a sample data set versus a finite data set. When I say standard deviation, I should have more correctly called it the sample standard deviation. The point is we do not know what the actual standard deviation is but we can estimate for purposes of forming the confidence interval. We estimate it based on the sample variance.I am not how under the collar! I love a good math discussion.
If you are doing this right, you will have recorded your results on all of the possible results of the die roll. I suggest adding your results to my and Lilje's results and then looking at the total. You are essentially saying that there are 14 possible outcomes and you have a 5% chance of one of those outcomes being a statistical anomaly. That's not concerning at all! If you look at my plot on the previous page, the roll for #9 is over 2.5 standard deviations away from the expected. But in the broader context, that's not concerning.
My apologies, I didn't realize what a sensitive subject this is. I would love to compile more data and if/when I get it, I will analyze it as well. If the data shows that my current conclusions are not valid, I have no issue with falling on my sword and retracting my statements. However, the data set as it stands currently is leading me to believe that the odds to roll a "1" are almost double what they theoretically should be.
I'm confused how I acted like it was sensitive? I'm just trying to tell you when you put that kind of click bait it makes it hard to take you seriously. And you can't just say that you are right without sufficient. This isn't true until proven otherwise, you have to prove it before anyone wil believe you. Everyone except you is providing massive amounts of data and evidence. Now, if you were to do the same as them, I wouldn't immediately dismiss you as someone who has zero idea what they are talking about. Hell, a dev even told us the actual formula(correct me if I'm wrong here anyone)!
I don't mean you in particular as being sensitive, I was meaning the community as a whole. I did not expect to get the level of feedback this has generated, that's all. Am I missing something? Where is this massive amount of data? I've seen a couple of people share some data sets but nothing "massive" and certainly nothing that contradicts any thing I have proposed to this point.
They are giving massive reasons and proof for this being most likely just s flux and have provided much more days then you have
Honestly, I hope I am wrong but I need to convince myself of that via data. Would you mind telling me how you came about your data set? Iron man? What Country? What CB? I'd like to eliminate as many variables as possible.
I have data that says otherwise. Just because you say so, doesn't make it so. Call me incredulous given the recent history of world leaders, bankers and various people in a position of authority throughout the world to not be honest. The only bias that I see that is confirmed is that rolling a "1" is more probable than a 1:14 chance and rolling a "14" is less than a 1:14 chance.
