Reuters Editors » Blog Archive » Rethinking rights, accreditation, and journalism itself in the age of Twitter | Blogs | - http://blogs.reuters.com/reuters...
"But the point, I hope, is clear. The old means of control don’t work. The old categories don’t work. The old ways of thinking won’t work. We all need to come to terms with that."
- Mr. Gunn
via Bookmarklet
Statistics as a worldview. When you think this way, you say different kinds of things about the world, what you know, and generally how you see things.
- Mr. Gunn
via Bookmarklet
Good list of video resources, including Scivee, JoVE, etc. probably should include Precedings, as well.
- Mr. Gunn
via Bookmarklet
If I have data with three dimensions (2 sample locations, 2 treatment, and 2 sources) and I need to make it easy to compare the two treatments to one another in the context of paired sample locations and sources, what's the best way to do it. Oh, yeah, the data spans 6 logs.
I currently have 12(!) bar graphs to separate out the high, low, and middle of the dynamic ranges, with a set containing treatments within one location and a set comparing treatments withing another location, so 3x3x2 graphs. There's gotta be a better way.
- Mr. Gunn
looking at your data... first (stupid) observation: it wouldn't it be easier to handle in a table with four columns Treatment,Property-Name,Place,Result ?
- Pierre
... with those four columns you could upload your data in a SQL engine a make aggregates (group by,sum,mean...)
- Pierre
Thanks, Pierre. I guess I asked a vague question, maybe because I'm not really sure what I want. I want to display the quantititive differences between the treatment groups for each property, and it's hard to display the differences in a compact manner with the values spanning such a large range. I've tried taking the log of the data, but that makes it harder to read and not nearly as clear.
- Mr. Gunn
linear model/anova with terms for the categories you are looking at? Or PCA across the matrix, zero out component(s) specifying location, home in on treatment-informative axes (tracey-widom stats are useful here). LM is certainly simpler: upload as table into R then go: lm(prop1 ~ location + source + treatment, data=myTable). Look at the qqnorm() for the residuals, which should lie on...
more...
- Chris Cotsapas
If you then want to compare properties apples-to-apples, you can convert them into Z scores (ie standardize) as foreach (property P) foreach(sample i) (P_i - mean(P))/sd(P)
- Chris Cotsapas
Chris, I thought about PCA, but I thought it might be a bit overkill, since I already know the main important dimensions. I'm a bit limited on how I can do transformations of the data, too, since they all have their own characteristic units and the numbers will be interpreted in the context of the known normal ranges.
- Mr. Gunn
Lm should still work. Each prop is handled differently so units aren't a problem.
- Chris Cotsapas
via Nambu
Props to @JATetro for pointing out that I just needed to take the relative differences, which collapses everything into the same range, making it graphable on the same chart.
- Mr. Gunn
I was going to suggest taking logs to achieve the same end, but relative diffs is better. Again (http://friendfeed.com/the-lif...), kudos all round: this is a great example of community in action.
- Bill Hooker
Yes, I was thrilled to have so many good suggestions from skilled people. Bill - I tried the log thing, but it makes the comparisons less visually apparent. Taking %diff messes up the units, so I'll have to put that in as table or something, but the good thing about it is cuts the number of data points in half.
- Mr. Gunn
@chris I think the R function scale(matrix) does a similar approach of standising data using root mean square instead of standard deviation. You can use it on a whole data matrix rather than looping each variable.
- Michael Barton
I agree with Chris to recommend to standardising the data if you doing any modelling, as this can prevent over-variation of individual parameters biasing model estimation.
- Michael Barton
I want you to all hold me to this: When I get done with what I'm doing now, I'm never making another graph or chart in Excel. Way too much of my life spent messing around with stupid shit like font sizes & scales.
Nice. Never keen on apps that require my Twitter password though, especially through a non-SSL connection. If logged in to Twitter via a browser, there's a cookie named _twitter_sess that the app could use instead.
- Neil Saunders
I prefer having the citations appear in FF - am always wary of things which will increase the number of my tweets :)
- Allyson Lister
Alternative: send your CiteULike to FriendFeed as custom RSS, then to Twitter from there.
- Neil Saunders
The cool thing about this is that you can tweet anyone's references, not just stuff from your own library. The password thing is kinda lame, though, I agree.
- Mr. Gunn
"What should matter, ultimately, is the citation rate and importance of individual or articles or authors, not journals."
- Mr. Gunn
via Bookmarklet
Good blog post. Totally agree with the quote you highlighted. I think some publishers are in for a rude awakening in the coming years when they realize that just their overall ISI isn't important anymore. Getting a hold of paper/author level metrics could completely change the game.
- Brian Krueger - LabSpaces
I liked the meeting categories. Not so sure about the differences between media and mainstream twittering/blogging people - I find it hard to see any distinction there.
- Nils Reinton
You mean, other than the financial incentive?
- Mr. Gunn
Yes ! That said, I suspect there are bloggers making money from their blogging out there. The lines are fuzzy - blogs are also "media".
- Nils Reinton
Does anyone believe that pay-per-download is a good idea? It didn't work that well for data access be itCable, dialup, or mobile, so why would it work here?
- Mr. Gunn
via Bookmarklet
For those who haven't seen it, a collection of bookmarklets useful for stopping annoying behaviors on a page, such as redirects. Prompted by LinkedIn's regrettable decision to put hijack frame around all its links.
- Mr. Gunn
via Bookmarklet
Bitesize Bio - Small Worlds is a new initiative organised by Alan Cann at the University of Leicester (and of the excellent Microbiology Bytes) that aims to encourage scientists to use the immense power of web 2.0 in their professional lives. - http://bitesizebio.com/2008...
I love this part: Nick says: "One group who could particularly benefit are early stage research scientists who lack an adequate mentor/peer support structure around them, for example those in small research groups, who could use web 2.0 applications to build a network of fellow researchers whose experience they can draw upon to help with their professional development.Such a network can also provide valuable moral support at an often difficult period career period!"
- Steve Koch
Could you access the small worlds site? It was password protected when I tried.
- Steve Koch
For those piping their twitter stream in here, perhaps using this to filter your stream would make sense? I'm available to help if you need it.
- Mr. Gunn
via Bookmarklet