In this study the null hypothesis would be that there is no differencee between the two drugs on average. One group would have been taking drug A and then the second group would get drug B. Nothing wrong with that setup. Might not be the way the FDA wants final trials but it would be fine for an internal study. More embarassment for the professor. What subjects do you claim to teach. does that school require its professors to have advanced degrees?
Wrong. This is an assumption just as the assumptions "A is more effective than B" and "A is less effective than B." There is no reason to make "A is equally effective as B" a special assumption. None of them is a null hypothesis. You have no idea what a null hypothesis is. If you like, you can use this as an assignment and try to figure out what the null hypothesis is in this case. Give it a try and I'll help.
Null Hypothesis The null hypothesis, H0, represents a theory that has been put forward, either because it is believed to be true or because it is to be used as a basis for argument, but has not been proved. For example, in a clinical trial of a new drug, the null hypothesis might be that the new drug is no better, on average, than the current drug. We would write H0: there is no difference between the two drugs on average. We give special consideration to the null hypothesis. This is due to the fact that the null hypothesis relates to the statement being tested, whereas the alternative hypothesis relates to the statement to be accepted if / when the null is rejected. The final conclusion once the test has been carried out is always given in terms of the null hypothesis. We either "Reject H0 in favour of H1" or "Do not reject H0"; we never conclude "Reject H1", or even "Accept H1". If we conclude "Do not reject H0", this does not necessarily mean that the null hypothesis is true, it only suggests that there is not sufficient evidence against H0 in favour of H1. Rejecting the null hypothesis then, suggests that the alternative hypothesis may be true. http://www.stats.gla.ac.uk/steps/glossary/hypothesis_testing.html again you are a professor of which subjects?
This use of the null hypothesis is based on prior knowledge that drug B is already more effective than placebo, so that if A is more effective than B, then A is automatically more effective than placebo. Normally, null hypothesis would be the default hypothesis that rejects all a priori assumptions. In the case of a clinical trial, the standard null hypothesis would be "drug A has no effect on disease" rather than "drug A is not more effective than drug B." The former is much more meaningful because, even if drug A is more effective than drug B, if drug B has a negative effect compared to placebo, then the comparison between A and B is not useful. In the case you cited, if B is already known to be more effective than placebo then substituting the alternative hypothesis "A is not more effective than B" in place of the null hypothesis "A has no effect on the disease" is logically consistent. However, even if you are allowed to do this under certain conditions, you should not confuse the meaning of the null hypothesis (no a priori assumptions) and the alternative hypothesis (desired assumptions). OTOH, if there is no prior knowledge that one of the drugs is more effective than placebo, then their null hypothesis would be incorrect.
I will desist from embarassing you on this subject unless you attempt another cheap shot. Just remember you could not have been more wrong.
I admit that I was confused by what I consider to be proper definition of null hypothesis and what is generally accepted way of setting up and testing null hypothesis. My definition is more stricter than the usual definition but I often forget that. What you cited certainly reflects this difference. People take the opposite of any hypothesis as their null hypothesis and proceed to test it. IMHO, this is very dangerous and can lead to totally nonsensical conclusions. Jacob Cohen describes it as a ritual conducted to convince ourselves that we have the evidence needed to confirm our theories. A more stricter definition of null hypothesis, OTOH, would avoid a lot of the pitfalls. My view is, that you cannot take the opposite of any hypothesis and "create" your own null hypothesis. Here is a very pertinent quote from wiki: Coming back to the problem of the generals and the battles. The simplest null hypothesis (which would satisfy both mine and generally accepted definition) is that the generals have no effect on the battles. The statistical test is whether the number of generals that win consecutive battles fall within or outside the random distribution. It turns out, 3% for 5 consecutive wins is exactly within the random distribution. It does not disprove the alternative hypothesis that generals matter, but it certain fails to repute the null hypothesis, thus giving strong suspiscion that generals don't really matter. The connection to the ID theory is obvious.
regarding the generals -- your conclusion violates statistical protocals and defies common sense. Even if we were to set up the study the way you did: (which would be a bit looney) your null hypothesis is that the generals have no effect on battles -- then you might say the null hypothesis is not rejected but you can not say that it is true. Per my earlier stats website. If we conclude "Do not reject H0", this does not necessarily mean that the null hypothesis is true, it only suggests that there is not sufficient evidence against H0 in favour of H1. Rejecting the null hypothesis then, suggests that the alternative hypothesis may be true.
This describes the origin of this universe. Bodies are "evidence" that the Son of God is separated and separable. Each is testing his "right" to bear "arms". This eventually leads to some generals who can win five battles in a row. Jesus
I had repeated many times that I would not know whether it is true or not. But the point is that without the rejection of the null hypothesis, you cannot claim that the opposite is true. BTW, the null hypothesis is supposed to be "a bit looney" because you expect it to be proven false. The suprise is if you cannot.