[Snaggles]

Originally Posted by DeathsSilkyMist [You must be logged in to view images. Log in or Register.]

The problem with this line of thinking is you are clearly biased against me. It is probably due to people repeating strawmen and lies, which influences how you read my posts. The fact that you think I am "never wrong" simply proves you don't read what I post, and you are making assumptions about me. I have admitted to being wrong plenty of times on these forums, and you can look back into the post history to check.

If you were actually concerned about giving posters advise, you would be talking to the people who clearly troll others in an attempt to shut down the conversation. That is a much stronger indication of arrogance and pride. The fact that I am willing to go out and provide evidence for my claims shows that I am not arrogant enough to assume I am correct, simply because I say so. I back up what I say.

It is quite telling that people only have advise for me, and none of the other posters who are clearly acting worse. If you were being consistent, you wouldn't stop at giving me advise. You would tell Troxx to stop bloating threads with silly gifs when he is being arrogant and assuming he cannot be wrong. You would tell Gloomlord that posting hundreds of off-topic posts simply to "criticize" someone is not productive, and simply bloats the thread.

I'm not scrubbing your 4500+ posts for historical tidbits. I cant recall you posting once with any humility, running one stupid test without an ounce of "I could be wrong here but..." baked in. Nobody here has poisoned my views against you, an ounce of levity in a DSM post would be refreshing though. Hell, it's a video game. You arent trying to convince people against eating Tide pods.

I don't care if people troll. You can either try to shut them down or just offer a counter-point. If people cant tell the difference between a reasoned effort to help and trolling this millennium won't be nice to them. Assuming they dont try to lick a wall outlet before that.

Seriously though, if my posts, tests, and general logic drive the community at large insane they will tell me. I'd probably adjust my approach a bit if that was the case or at least tease back with a bit of humor. I do believe what I post but understand if people don't agree. They didnt sign up for a class and I'm not getting paid to teach.

Originally Posted by bcbrown [You must be logged in to view images. Log in or Register.]

By no means am I a professional statistician, but I have worked with plenty. High quality statistical testing requires, at a minimum:

An explicit mental model of the world, with all assumptions stated clearly. You need to be able to articulate your understanding of the world before you can know whether your results indicate an improvement of that understanding.

An explicit hypothesis. You need to know what you are looking for in your experiment. Ad-hoc exploratory data gathering can be useful in trying to formulate a hypthothesis, but that exploratory data will not be useful in determining whether a hypothesis is confirmed or rejected.

An experiment design. You need to know ahead of time what data you wish to gather, how to gather it, and when to stop the experiment. An example of a flawed experiment would be trying to show that a certain gear combo causes a certain DPS increase, and then stopping your parse as soon as you show that DPS increase.

Sanity-checking the resulting data to confirm your assumptions have been met. If not, then your understanding of the world is flawed and your data unusable. You need to first run a different experiment to find and fix the flaws in your assumptions.

Run a well-defined, repeatable analysis. You need to know ahead of time what metrics you wish to calculate. You should also do some sort of calculation of statistical confidence, whether frequentist or Bayesian.

Scientific integrity. You need to publish your results whether or not they support your hypothesis. If the results violate some of your assumptions, you cannot rely on the results of any data analysis.

Thank you for this. I never thought something so interesting would be found on page 42 of a SK stat thread [You must be logged in to view images. Log in or Register.]




In summary, though, pick the race you want. Level the race you want. Pick the stats you want and be ok with probably regretting something about your class/race/stats at one point. Get good at your class and weed through the BS. Don't afk for DKP's and play the hell out of the game so it inspires people to want to roll the same class. Download Gameparse and check it occasionally to draw some conclusions so you can cut through bias and feelings. Oh and always bring plat to tip for ports...port beggers are losers.