I think there is a thread like this somewhere in the archives but I can't find it...

Anyway. I thought I would get chapter one done in 6 weeks... It took me about 4 months. Then this chapter, number two, I thought I would get done in 6 weeks (it was half written already from an earlier 'mistake') and I am two months in and still so much to do.

How long does it take you guys to write your chapters? Am I horrendously slow? I know I am too pendantic for a first draft but almost need to be so I am in 'the zone' with it.

Advice on speeding up anyone?! It is possible - or even recommended -to 'speed up'?

Any advice gratefully received...

Grrr the title was meant to be 'how *long* to write a chapter'. how annoying I can't change it!

i know what you mean. i was only meant to spend a couple of days maybe a week maximum researching about cluster analysis, i ended up taking much longer, in the end, i told myself, i *ONLY* have one day to finish the research, reading and making notes. and you know what, i got it done, in the day, because i knew i only had that one day left to get it done.

i know in the begining getting the first draft does take a long time.
so dont feel bad about you spending time working on your chapter, because you're working on your thesis, and that is great! .

i find giving myself time constraints helps. otherwise if i dont have a "time limit" i can just keep going on forever!

tell yourself you *ONLY* have X amount of time on chapter X, and if you don't get it completed by then, then it's *tough luck!* you have to move onto the next chapter.

that way psychologically you will concentrate on the *essential components*.

check out this article, it might give you some insight. http://www.slackermanager.com/2008/03/my-egg-timers-set-to-30-minutes.html

Hey Lara

Thanks for your help! I do have deadlines, lots of them but I also have an 'inner child' that will make me spend time on it until I get right to the wire and have to move on! This is my first piece of work with my won deadline - no MRes deadlines or monitoring meetings/first year transfer... I am learning but am also wondering how long is average so I know what to expect of myself...

confusing stuff this PhD!!

thanks again

Lara, I don't want to sound stupid, but what is cluster analysis and how are you using it? I put a post up recently asking for help with content or frequency analysis but got no replies. I'm wondering whether cluster analysis might be relevant.

4 mths is not too bad if this includes all the research, but if it's just writing-up pre-existing notes/findings etc, then it's too long.

It's important not to be a perfectionist, but rather get things down on paper. I procrastinate too often about getting things 'just right', and then end-up having to extend the deadline and often rushing work.

the four months was including all the background reading, focused reading, analysis and writing... Am social science so is all discourse analysis, reading reports and applying political theory as well as writing... maybe not so bad then? Same for this chapter. I sort of analyse and write at the same time...

Hmmm I haven't really completed any of my chapters to final polished version so it's difficult for me to figure out how long i take on a chapter.

sometimes a chapter involves alot of literature reading and tying everything up, or another chapter consists of alot of result analysis which sucks up a lot of time.

i think you're working just fine. and i wish i had your problem! my problem is more of a motivation to keep working at my thesis for hours on end.

so that's really great you willing to invest so much time on your thesis

basically it takes as long as it takes, and you're already putting deadlines on yourself, so i wouldnt worry at all. you're progressing well!

pamw, you don't sound stupid at all! that's a good question! :)

in a nutshell:
"Clustering can be considered the most important unsupervised learning problem; so, as every other problem of this kind, it deals with finding a structure in a collection of unlabeled data.
A loose definition of clustering could be “the process of organizing objects into groups whose members are similar in some way”.
A cluster is therefore a collection of objects which are “similar” between them and are “dissimilar” to the objects belonging to other clusters."


cont....

..."What is cluster analysis?

Cluster analysis is an exploratory data analysis tool for solving classification problems. Its object is to sort cases (people, things, events, etc) into groups, or clusters, so that the degree of association is strong between members of the same cluster and weak between members of different clusters. Each cluster thus describes, in terms of the data collected, the class to which its members belong; and this description may be abstracted through use from the particular to the general class or type...."

"
Cluster analysis is thus a tool of discovery. It may reveal associations and structure in data which, though not previously evident, nevertheless are sensible and useful once found. The results of cluster analysis may contribute to the definition of a formal classification scheme, such as a taxonomy for related animals, insects or plants; or suggest statistical models with which to describe populations; or indicate rules for assigning new cases to classes for identification and diagnostic purposes; or provide measures of definition, size and change in what previously were only broad concepts; or find exemplars to represent classes."

So you googled it as well!! Can you recommend any literature that might be useful as I think this is the sort of analysis I need. I'm classifying types of medieval clothing into different groups over time.

i am personally using cluster analysis, to see if different parts of a tumour from an individual patient, have the same "genetic" profile.
if the different "regions" have the same gene loss or not.

if all the regions have the same genetic profile, than i will expect all the regions to "cluster" together,

or if they are different, i can see "which" regions are more "closely" related, because they will be put in the "same" cluster.

sorry does that make sense?

check out these websites for further clarification:

http://www.statsoft.com/textbook/stcluan.html

http://www.psychstat.missouristate.edu/multibook/mlt04.htm

yah i spent about 2 weeks googling cluster analysis to death! i didnt have any access to books, but there is alot of good articles on the internet explaining it all.
and yap the stuff i just copied pasted for you, i just copied from my word doc. notes, which are originally from google articles

there is a book on cluster analysis called "Cluster analysis"

http://www.amazon.com/Cluster-Analysis-Brian-S-Everitt/dp/0340761199

but i found the articles on the internet just as informative. and the book abit too complicated for me.
i had a statician who helped me to sort out my data and how to use R for cluster analysis (R being the free online statistical package)