I don't know what field you are in but in mathematical subjects many people submit drafts of working papers online to sites such as arXiv.org. More recently Nature have started their Precedings services which offers a similar service for the life sciences. This can be a good way of protecting your ideas because it will make others less likely to copy your work once it is visibly in the public domain under your name.

Sorry I have not followed your other posts, what do you want to do a PhD in?

What do you like doing that makes you go "I really love life!" maybe something that you used to do a lot but perhaps not so much anymore? Maybe revisit old hobbies or activities :)

Exercise and eating well is good too. Fed the body, feed the mind.

The 2x2 was what I was originally thinking but the poster said they were interested in the conditional probability of the response given that the user has a need which means you are looking at just one column (or row) of the 2x2 contingency table. An odds ratio only applies if you are comparing the two groups.

I maybe misinterpreting your requirements but a maximum likelihood estimate of the Pr( Service meets need GIVEN Service User has a need ) is simply the empirical ratio of the number of people with a need who are satisfied by the service to the number of people with a need.

it doesn't sound like you actually need logistic regression.

So you are interested in the following probability ...

Pr( Service meets need GIVEN Service User has a need )

Sorry, just read your problem more clearly and have a question ...

if the SU has no specific need, how do you define the response?

You've just got a 2 x 2 contingency table right?

If so, I don't see why you can't use a Chi-Squared or Fisher's exact test?

This is a good time to start making your move. Although the deadlines for things are probably a few months away, you need to plan. Work out what you want to do, identify people you want to work with and places where you want to work.

If he is a well established name it is more prestigious for him to be last author anyway. First authorship is more important for junior people like us (students and postdocs) because it tells people what we can do when we apply for later jobs. However, as a PI, you want to be last author on lots of papers to show research councils that you can lead and manage research projects and direct those under you.

There are slightly different rules for electronic theses. There seems to be a UK move to get doctoral theses published in online repositories and there are copyright issues for this medium. Consult your library services if this affects you.

Publishers are worried about mass reproduction so if you are only submitting a paper thesis they won't care. It is the electronic editions that they are more concerned about.

The best person to ask is whoever is supervising you.

Yes, I'm at Oxford.

Ah, you will be working on HIFU then? Julia Schanbel moved to Oxford last year. I'm surprised that there are no funding options open to you in Oxford.

If the City guy has industrial experience then that sounds fine. It is a topic where I would imagine industrial experience counts for a lot.

Up to you what you want to do I guess.