Question

Reformulate your hypothesis test from your week 5 discussion to incorporate a 2-sample hypothesis test, as specified in Chapter 10. What would be your data? What is your null hypothesis? What is your alternate hypothesis? What would be your Type 1 and Type 2 errors relative to your decision? Suppose you have a p-value of 0.01, what does this mean relative to your problem and decision? Suppose your p-value is 0.20, what does this mean relative to your problem and decision? If you reformulated your design for 3 or more samples, what would be the implications of interaction? When would you use the Tukey HSD or the Tukey-Kramer test, and WHY?

Answer 1

Answer:

The followinmg discussionn is expected to be regarding statristical test

the following are the steps for carrying out any statistical test

Null hypotheisis: If the claimed value of the mean and actual mean doesnot vary significantly

Alternate hypothesis;   If the claimed value of the mean and actual mean vary significantly

Type 1 error: The incorrect rejection of a true null hypothesis (a "false positive").

Type 2 error: The incorrectly retaining a false null hypothesis (a "false negative").

If the P-value is greater than 0.05, Null hypothsis is not rejected. So it implies that there is no significance different between caomparing data or comparing claimedm results with actual estimation.

Hence, P = 0.01 implies, Null hypothsis is rejected

P= 0.20 indicates Null hypothsis is not rejected

If we include 3 or more samples then design of random experimentatuion has to be done...like ANOVA analysis which compare various samples.

We use Tukey - Kramer test (T test ) for the samples population which follows bell curve which may be inclined towards right side or left side, but only if population is less than 30

Tukey's test compares the means of every treatment to the means of every other treatment. It also applicable simultaneously to the set of all pairwise comparisons and and identifies if any difference between two means is present and also if the difference calculated is greater than the expected standard error.

~ s/sqrt(n)