As Puneet Lahoty asked in Khan Academy (and I have the same doubt): How do we decide what method to use to estimate the Standard Error. Method 1) Perform correction. So standard error = sqrt(p hat * (1- p hat) / (n-1) ) Method 2) Do not perform correction. Standard error = sqrt(p hat * (1- p hat) / n ) There is a third way, that was used in previous videos: sqrt((n * p * (1 - p)) / n - 1)
I've the same question. In one of the other examples, he computes std.deviation of the population(standard Error) using this formula---> (std.deviation of a random sample)/(sqrt(n)) where std.deviation of random sample is actually computed using Bernoulli method by taking the square root of variance(i.e. S^2 = (p(1-p)^(2) + p(0-p)^(2))/(n-1) ) of this random sample.
If sample size was n < 30 ---- would you opt for a t statistic instead of a z statistic? If we do not know to population standard deviation, as stated in the video, aren't we supposed to use a t statistic ?
How do we figure out the third decimal place of the critical value. It’s multiple choice so you don’t need to know how to do this in order to get the question right, but it’s a huge weakness to not be able to do this, so I feel very uncomfortable carrying on without this knowledge In this particular example if you were to average the numbers on…. Wow I think I figured it out. You add them then divide by 2. That was so easy
As Puneet Lahoty asked in Khan Academy (and I have the same doubt):
How do we decide what method to use to estimate the Standard Error.
Method 1) Perform correction. So standard error = sqrt(p hat * (1- p hat) / (n-1) )
Method 2) Do not perform correction. Standard error = sqrt(p hat * (1- p hat) / n )
There is a third way, that was used in previous videos: sqrt((n * p * (1 - p)) / n - 1)
I've the same question. In one of the other examples, he computes std.deviation of the population(standard Error) using this formula--->
(std.deviation of a random sample)/(sqrt(n))
where std.deviation of random sample is actually computed using Bernoulli method by taking the square root of variance(i.e. S^2 = (p(1-p)^(2) + p(0-p)^(2))/(n-1) ) of this random sample.
If sample size was n < 30 ---- would you opt for a t statistic instead of a z statistic? If we do not know to population standard deviation, as stated in the video, aren't we supposed to use a t statistic ?
How do we figure out the third decimal place of the critical value. It’s multiple choice so you don’t need to know how to do this in order to get the question right, but it’s a huge weakness to not be able to do this, so I feel very uncomfortable carrying on without this knowledge
In this particular example if you were to average the numbers on…. Wow I think I figured it out. You add them then divide by 2. That was so easy
How to assume normal distriution if there are only males and females?
..
1st