6A playoff brackets

[randymc]

No! That is not correct, and you know this. The result does not change the expected result, you have to have large samplings...way more the 46 times.

 

"There is no universal constant at which the sample size is generally considered large enough to justify use of the plug-in test. Typical rules of thumb range from 20 to 50 samples." (http://en.wikipedia.org/wiki/Z-test)

Edited November 1, 2010 by randymc

[onefortheteam]

One more question before I call it a night, where, in your opinion, is the best football (at the highest classification) in the state of TN played year in and year out?

I honestly, do not know. It could be anywhere in the state. Opinions vary, mine changes game to game about teams, districts. Does yours not?

 

I don't get to see the East or Middle play, I don't even get to see all the West teams play. Logically, a reasonable person would want to see all the teams, to be able to make a informed statement. I think a reasonable statement would be, "I haven't seen enough teams across the state to know. I've only seen some of the West."

[onefortheteam]

"There is no universal constant at which the sample size is generally considered large enough to justify use of the plug-in test. Typical rules of thumb range from 20 to 50 samples." (http://en.wikipedia.org/wiki/Z-test)

So if I flip a coin 46 times...it is done. Nope, haven't convinced me on that. nice try with the wiki, though.

[randymc]

I honestly, do not know. It could be anywhere in the state. Opinions vary, mine changes game to game about teams, districts. Does yours not?

 

I don't get to see the East or Middle play, I don't even get to see all the West teams play. Logically, a reasonable person would want to see all the teams, to be able to make a informed statement. I think a reasonable statement would be, "I haven't seen enough teams across the state to know. I've only seen some of the West."

Fair enough, I on the other hand have, and have talked to people across the entire state who have seen lots of games. You obviously have watched enough basketball games across the state to logically reach your opinion that the best basketball in the state is played in Memphis?

 

Goodnight!

[onefortheteam]

"There is no universal constant at which the sample size is generally considered large enough to justify use of the plug-in test. Typical rules of thumb range from 20 to 50 samples." (http://en.wikipedia.org/wiki/Z-test)

Do you read anything? Are you a politian? This is the 1st line on the page you linked too.

"A Z-test is any statistical test for which the distribution of the test statistic under the null hypothesis can be approximated by a normal distribution. Due to the central limit theorem, many test statistics are approximately normally distributed for large samples. Therefore, many statistical tests can be performed as approximate Z-tests if the sample size is not too small."

 

What is wrong with you? Come on man.

[randymc]

So if I flip a coin 46 times...it is done. Nope, haven't convinced me on that. nice try with the wiki, though.

Wow, I thought I was going to bed. Pick the statistics book of your choice then.

 

If you flip a coin 46 times and got 33 heads, we could calculate the probability of getting these results, it would be a very small probability inferring one of two things. The coin is fair and you are observing a very unusual outcome, or the coin is not fair, it's up to you to decide which. I believe the probability of 33 heads in 46 tosses is somewhere around .1%, 1 out of 1000 pretty small, agreed?

[onefortheteam]

Fair enough, I on the other hand have, and have talked to people across the entire state who have seen lots of games. You obviously have watched enough basketball games across the state to logically reach your opinion that the best basketball in the state is played in Memphis?

 

Goodnight!

Nope, I never said that....and you know it. Track record...please...

[randymc]

Do you read anything? Are you a politian? This is the 1st line on the page you linked too.

"A Z-test is any statistical test for which the distribution of the test statistic under the null hypothesis can be approximated by a normal distribution. Due to the central limit theorem, many test statistics are approximately normally distributed for large samples. Therefore, many statistical tests can be performed as approximate Z-tests if the sample size is not too small."

 

What is wrong with you? Come on man.

keep reading please! it goes on to give the rule of thumb I stated for sample sizes. It gives a basic rule of thumb on how to determine the appropriate sample size. I'll continue to quote a little more, since you just like reading the 1st 3 sentences.

 

"There is no universal constant at which the sample size is generally considered large enough to justify use of the plug-in test. Typical rules of thumb range from 20 to 50 samples. For larger sample sizes, the t-test procedure gives almost identical p-values as the Z-test procedure."

 

You don't get it do you?

[onefortheteam]

Wow, I thought I was going to bed. Pick the statistics book of your choice then.

 

If you flip a coin 46 times and got 33 heads, we could calculate the probability of getting these results, it would be a very small probability inferring one of two things. The coin is fair and you are observing a very unusual outcome, or the coin is not fair, it's up to you to decide which. I believe the probability of 33 heads in 46 tosses is somewhere around .1%, 1 out of 1000 pretty small, agreed?

Yes, 46 times is a small sampling. Also, it is not unheard of to get extreme results, due to small samplings.

[randymc]

Nope, I never said that....and you know it. Track record...please...

But you HAVE watched enough basketball to have the opinion that Memphis plays the best basketball in the state, otherwise you would have posted the same answer you posted about football? You earlier stated "Memphis would be my opinion" when asked where the best basketball in the state was played year in and year out, but your post above says you haven't watched enough football across the state to know where the best football was played year in and year out. Why can't we infer that you have seen enough basketball across the state to have that opinion?

[randymc]

Yes, 46 times is a small sampling. Also, it is not unheard of to get extreme results, due to small samplings.

So you are telling me that the 1/1000 chance we would see 33 heads is reasonable? come on, usually 5% or less is considered statistically significant.

[onefortheteam]

keep reading please! it goes on to give the rule of thumb I stated for sample sizes. It gives a basic rule of thumb on how to determine the appropriate sample size. I'll continue to quote a little more, since you just like reading the 1st 3 sentences.

 

"There is no universal constant at which the sample size is generally considered large enough to justify use of the plug-in test. Typical rules of thumb range from 20 to 50 samples. For larger sample sizes, the t-test procedure gives almost identical p-values as the Z-test procedure."

 

You don't get it do you?

I do, but I don't think you do. From under conditions: Nuisance parameters should be known, or estimated with high accuracy (an example of a nuisance parameter would be the standard deviation in a one-sample location test). Z-tests focus on a single parameter, and treat all other unknown parameters as being fixed at their true values. In practice, due to Slutsky's theorem, "plugging in" consistent estimates of nuisance parameters can be justified. However if the sample size is not large enough for these estimates to be reasonably accurate, the Z-test may not perform well.

The test statistic should follow a normal distribution. Generally, one appeals to the central limit theorem to justify assuming that a test statistic varies normally. There is a great deal of statistical research on the question of when a test statistic varies approximately normally. If the variation of the test statistic is strongly non-normal, a Z-test should not be used.