teek - if you transform the data, then make sure you do it for all the data within the same test i.e. don't compare x (transformed) and y (untransformed). But you don't have to do it across separate tests, unless you then go on to talk about/plot values e.g. Mr Man 1 scored 3 and Mr Man 8 scored .0001 (because you transformed Mr Man 8's data).

Anyhoo, if you have SPSS 18 with the bootstrapping module you can click the 'bootstrap' option on the t-test, which can correct for non-normal data which means you don't have to use mann-whitney

omg its 12.30 - WHAT!? Where did the morning go!???

Right, I need to have lunch, get a massive caffeine hit and get back to it!

goal 2 done.

Goal 3: write up sample and sample representativeness in method section

goal 1 done, must get on with goal 2

maybe you need the sample sizes more equal in order to get a bigger effect size (just completely guessing here!)

I'm feeling pretty tired, after a 9-5 day of solid teaching - not even lunch! Yesterday and parents here before that. But hubs is up in London so I have 2 days to get some proper work done without having to break to pick him up from the station at 6.

So today's goal

Goal 1: make coffee and drink
Goal 2: right up about which control variables I used in my method section

I think that's right, although you've found a significant different it only accounts for 0.9% of the total variance, so its a very small effect.

see page 4 onwards of this: http://www.statisticshell.com/effectsizes.pdf

How many participants do you have in each group?

Good luck DanB - its all good experience anyways

I wish I could find even ONE job to apply to :-(

study 3a is about me designing a questionnaire - so basically a long method. and then study 3b is applying that questionnaire I guess, with the same sample that it is tested in, but in study 3a, just talking about the structure of the questionnaire and 3b talking about actual hypotheses linked to the other questionnaires e.g. "construct x on Sneaks' questionnaire will moderate the ABC contstruct on mr man's questionnaire"

The reason I'm not sure whether to include it is because a) the questionnaire is based on a template analysis, which I changed AFTER designing the questionnaire, so now doesn't relate well to questionnaire :-( b) factor structure is awful c) prelim analysis shows questionnaire doesn't really work i.e. hypotheses are all rejected :-( But at the mo, sup thinks its 'worthwhile' but I'm not so sure.

Well you've prompted me to think about mine a bit more!

I think I'm going with

study 3a intro, method, results, discussion. Study 3b intro, method (similar as same participants, but more detailed), results, discussion. Study 3 overall discussion.

Truth be told, I want to ditch 3a completely!

I'm so exhausted today! my parents were here yesterday, and left at 5am this morning. Obviously I was busy yesterday with them and then was up at 3am, waved them off at 5am, with just enough time for them to spend 30 mins 'having a go' about "you must really get this PhD done, the sooner the better blah blah" - they have NO idea a) what a PhD is b) what mine is in c) that I spend 12 hour days doing the PhD - I mean do they think I just sit around, I am "getting this PhD done" :-s :-s :-s :-s :-s :-s :-s and then told me off for not eating 5 a day, and then told me I'd never get a job :-s so feeling tired and peed off.

Due to drive up to london tonight, so spending today packing for spending the week up in london and getting over last few days!

I'm in a similar situations (well I'm nowhere near finishing and have nowhere near as much as you but...) I have a huge questionnaire study, where I designed my own questionnaire and then chucked it in with a load of other questionnaires in a big study. So I have to explain the questionnaire development AND talk about the other questionnaires, and all in all there will be about 20 hypotheses! And I can't really separate them and pretend they were different studies because they use the same participants.

Anyhoo.

I *think* I'm going to do study 3a and study 3b, so they are separated to ease the reading for the examiners, so its not one HUGE method section AND intro AND discussion etc. For me I'm having Study 3a = my questionnaire, development etc. Study 3b = other questionnaires, AND testing hypotheses that are based on my questionnaire.

Not sure if this is relevant at all! But I would go with whatever is easier to read for the examiner.

I always used to think that 'which' is for people i.e. those participants which...

and 'that' is for things e.g. trees that fall on peoples heads.....


But then I'm not so sure any more, after a few wiggly lines in word 2007 :-( I just go for whatever sounds right :$

======= Date Modified 23 Aug 2010 15:26:25 =======
There are a few threads on this, from way back when - but you should be able to search them.

I think the overall advice has been...

- get a really good broker who understands what your stipend is
- go to banks that are more understanding of stipends - I *think* nat west has been given as an example of one of these but the older threads will have a list of them I'm sure
- get a guarantor - that's how me and hubs got ours. Although the guarantor has to be someone who could afford to pay your mortgage AND theirs, should you default on payment
- have a MASSIVE deposit.

No I haven't, although I was going to use it for my PhD. My sup has paid for me to go on a course later in the year, but its not to do with my PhD.