Log in

No account? Create an account
infohigh [entries|archive|friends|userinfo]

[ website | My Website ]
[ userinfo | livejournal userinfo ]
[ archive | journal archive ]

sigh [Dec. 19th, 2007|01:49 am]
[spot |ottawa-home]
[muzak |The Reason feat. Sara Quin - We're So Beyond This]

I'm supposed to have gotten off this thing, but whatever. A quick note.

I am quite amused that Kylie Minogue was in the Street Fighter movie. lol :)

I really gotta see that movie sometime. And Mortal Kombat II, for that matter.
Link10 comments|Leave a comment

eternally unconvinced [Nov. 26th, 2007|04:39 pm]
[muzak |Le Tigre - TKO]

I have come to the conclusion that I absolutely despise facebook, as a company, and am permanently quitting. In as soon as a week, I suppose. I also despise LiveJournal and am quitting that too. The reason for the delay is so that I can get a blog and such nicely rolling on my own domain/host.

I also highly recommend the use of an RSS reader to keep track of websites. I have been using Vienna for Mac, though I'm sure you can find your own for whatever systems you use. RSS readers allow you to escape blog-vendor-lockin as we experience here with LJ (the "I can't keep track of my non-lj-friends" thing).

Anyway, I'm looking for intelligent writeups about the theory of randomness. If you have any recommendations please please let me know! However, I am not interested in colloquial bastardizations of the term (ex. "that was so random lol"), and the relevant Wikipedia pages have been subject to disturbing amounts of both vandalism and misunderstanding. Sigh.

See, I'm working on my own set of lectures on Statistics. As probability theory is very relevant to statistical theory (I'm not sure the latter explicitly relies on the former.... but does it? That question is seriously haunting me!), I would like to begin at least with a mention of probability. But probability is subject to a number of different interpretations; at least two, anyway (are there more? I need to find out!). And I believe this distinction is in some way related to the various understandings or definitions of randomness. Of which there appear to be many; although I'm having difficulty finding descriptions of them.

I would like to even go so far as to define probability theory as the study of randomness, but this is perhaps unconventional. Furthermore, Kolmogorov's axiomatic basis for probability theory does not require any mention of randomness; so some mathematicians may protest. *shrug*

Despite all my worry about these problems, I'm really trying to make Lecture 1 jump right into statistics, without worrying too much about probability theory. I wonder how much this is feasible, however, or if it will run me into horrible problems the moment I introduce a random variable. Eeks.
Link32 comments|Leave a comment

perl [Oct. 11th, 2007|02:18 am]
[muzak |Ali Tabatabaee & Matty Lewis - His World]

ugh, I'm trying to fix some bad old perl scripts. I wrote them, but they make no sense to me. Some wonderful "features":
  • a line of code is commented with the ominous: # MISERABLE HACK

  • the variable $crazytime. I don't know what it does :(

  • some syntax in this code breaks vim's syntax highlighting. sigh...

This should be a fun night.

It doesn't help that I'm now hopelessly obsessed with Sonic.
Link5 comments|Leave a comment

horse and i [Sep. 17th, 2007|04:24 am]
[muzak |Stars - Your Ex-Lover is Dead]

omg! a post! but really.... a rant about independence.

Lately I've been frustrated by attempting to rewrite the regression coefficients of a linear model in terms of the correlation coefficients between my explanatory variables. I was hoping, rather, to find some resource somewhere with the formulae I require. Everything I've found, au contraire, in textbooks, lecture notes, the intarwebs, etc., has fallen terribly short. For now I'll concentrate on one little problem that confused me greatly for a few days of otherwise-blissful vacation.

In the statement of multiple linear regression, there are three different uses of the word independence:
  1. Linear regression literature will speak of the independent variables, usually denoted X_ij for all j, which are also called the explanatory variables, the regressors, the predictors. Regression likes to call them "independent" variables simply to contrast them with the "dependent" variable, y_i, also called the response variable, the regressand, etc.

  2. A fundamental assumption of most linear regression analysis is that each sampled data point is statistically independent of the others. That is, the random error terms (epsilon_i) are statistically independent of each other. This says nothing of the explanatory variables (but does help to describe the response variable y_i).

  3. In multiple linear regression (where we have multiple explanatory variables, that is, X_ij for a range of j), the "independent" explanatory variables must be linearly independent of each other. If this is not true then there is the problem of "multicollinearity", and the regression coefficients are not uniquely specified.

In particular, one can quite well perform a linear regression when some explanatory variables are statistically correlated. But not if they are perfectly correlated (a correlation coefficient of +/- 1), as that would mean they are linearly dependent, and we violate rule 3.

What boggles my mind, is that after gouging through dozens of references, I have not found any resource that mentions these multiple inconsistent uses of the same word in the same setting! At least Wikipedia actually states that it means linear independence for rule 3, on its regression analysis page. But some texts may as well have written: "The independent variables may be non-independent so long as they are independent", although that might have answered my question if I knew how to interpret it.

And in case you were worried, there are of course ways to continue an analysis if the assumptions of 2 and/or 3 are not met. Although, these methods may be undesirable. Mwaha.
LinkLeave a comment

rollerblades = luv [Jun. 27th, 2007|02:48 am]
[spot |home]
[muzak |Teddybears feat. Neneh Cherry - Yours to Keep]

I finally have some rollerblades! I'm soo happy and excited about them. I'm pretty bad at skating still but I'm not as terrible as I thought I'd be. My new K2's are much better than the old pair I used to have, so I'm still getting used to trusting them to go over bumps smoothly etc. Anyway, it's much faster to get to campus now :)

Stuff is busy. I want to code webapps. I've been very appreciative of the videos at the YUI Theatre, and watching them instead of doing my work. Work is going okay.... but I should be trying to find a real job. I love my current hobo-jobs though.

I love summer. The weather makes me soooo happy. And rollerblading :D

Mr. Tenty pointed me to the Ontario electoral reform referendum magic thingy happening that I hadn't heard about. Propaganda site here. You'll get to vote yay-or-nay for the proposed system in October's provincial ballot. I'm probably going to be against, but it will take me a while to figure out enough of the system to have an opinion either way. I'll probably post a rant about it here sometime.

If you do go to that site, though, be sure to check out Billy Ballot! (warning: flash)

Also after a discussion with Mr. Tenty, I really want to use Fuse to hack in transparent opt-in file versioning into my filesystems... sigh, how come versioning wasn't taken up by the mainstream filesystems many years ago?

*shrug* And now, I must try and finish my Perl hacks for Psych people.. because I told myself that was due today. And I have a meeting in the morning where I'd like to present some performance metrics on my NMF LSA IR system.... but they don't work yet. eeks!
Link29 comments|Leave a comment

nevermind [Jun. 4th, 2007|10:33 pm]
[spot |home]
[mewd |cookie-dough]
[muzak |The Fray - How to Save a Life]

I broke it.

cherry cherry [May. 24th, 2007|12:46 am]
[spot |home {kinderhaus}]
[mewd |shleepy]
[muzak |Electric Skychurch - Endless Horizon [I Love Bob Mix]]

make: Warning: File `destiny' has modification time 43 s in the future

So much has happened, so this is mostly a catchup-post. For my own sake, really, I guess.

I'm moved into the "kinderhaus" which is happy. Prof. Ali had enough funding magically to hire me back for the summer, so I'm once again (and for the last freakin' time!) doing a Stats RA for him. Hopefully this means I can get some closure with at least some of our projects so I can kiss it all behind me and move on with my life. I'm also working part-time for the Psych dept. which is going really well too; fixing bad perl scripts and writing bad c++ code :) So life is busy but actually productive, so I'm feeling a lot less like a hobo. I've gotten mostly into a schedule, that involves sleep and work and exercise and even *gasp* cooking (sorta). I feel like I'm finally (sllowwllyy) becoming who I want. I guess. :S

Visited Ottawa the weekend before last, got to visit Nikki which always makes for insightful convo and tea. And went bowling with Katie and Robin and Momma-T-Lisa which was random and crazyfun. What was said at the table, stays at the table! I can't wait to go back, which will happen for Canada Day at the latest. Road trip anyone? ;)

I'm with Dee now which is groovacious. She got me into Heroes, but I was disappointed by the finale (no hardcore boss fight! waah)

Now that I'm getting paid more I'm gonna pick up a new pair of rollerblades! YaaY! It will be just like in Hackers ftlolz.

I might have broken my finger today by smashing it into a fat pipe I was trying to jump and grab onto. It's all swollen and purple :D

These days I'm listening to Hole, Kate Bush, Crystal Method, and a bunch of random indie my dad gave me. If that makes any sense at all. But kousu pushed me in love with Secret Mommy - Kool Aid River.

WCF is on my mind a lot. Everything is sooo... political, which seems a tragedy. I thought things were getting a lot better, but today I realized again how so many ppl in our group are still fairly in the dark about what's been going on and don't know what to make of anything. Meeting tomorrow... hopefully it helps stuff get better. Hopefully people don't give up :S hope hope hope...

Nevertheless, this coming weekend is the WCF camping retreat. Man that's gonna be awesome, just to disappear for a while. If I can go at all. I'm pretty sure I'll go.

Meh! Random post. I shuppose that's it, for now.
make: warning:  Clock skew detected.  Your build may be incomplete.
Link8 comments|Leave a comment

hobo time was now; then; a river of bass [Apr. 9th, 2007|01:50 am]
[spot |ottawa-home]
[muzak |Underworld - Juanita / Kiteless / To Dream of Love]

Life is absolutely nuts. Wonderful weekend, with understanding (and encouraging) family, relaxing, a vacation I kinda needed to help me feel a little less of a failure. But first, for you FFVII fans: Feffiroff!! Thank you, Alex :)

My mom bought me a black macbook. It is <3 <3 computer <3. Love in a box. My best friend. My life. I require it for absolutely everything. And it's purply-blue now :) Thanks, mom. And yes, my life has become pretty pathetic.... lulz.

Researchy-work this term has been..... reeally draining. And hard. And I've spent most of it confused, poring over busted matlab code. And my prof's been disappointed because I haven't got as much done as I should be able to. Half of the problem is that I haven't been able to concentrate very much, and I can't figure out why. So that's been very hobo. And there's so much other work I need to do too, but I don't have the time. Or rather, I can't get enough done with my time lately. sigh.

I'm trying to get fixed. Awesome friends are awesomely helpful for that I find. And at least I have macbook now :)

I'm actually kinda excited to be moving (from the "comfy++ apartments" with alfedenzo to the "Kinderhaus" with g4c9z; although he probably doesn't know it yet!). That will happen later this month, although it's not tooootally confirmed (but I think math_foo has confirmed). I dunno why, maybe just the change of scene will help. Moving excites me; sleeping in a different spot. We'll see.

Easter turkey is splendiferous. While incidentally downtown I popped by kousu's place but he wasn't home but his housemate let me in to use the bathroom which was super-nice :)

I have applied for M.CM! We'll see how that goes!! Here's hoping :) I almost didn't apply but then Ali talked me into it. And Prabhakar gave me a reference which is super-awesome-nice. I hope I hope I hope it works. But I'm not counting on it. But just getting references makes me feel like much less of a hobo.

Driving back to uw tomorrow. Hopefully noone else remembers the past week, or two. I'm trying not to. I'm looking forward to some refreshing de-hobo-ification.

WCF stuff is freaking nuts. But I think progress is actually being made. It feels kinda nice, after struggling for so long...... I just hope it works. There's still so much I want to get done on that end... and I'll feel pretty crummy if it all results in nil.

This was a terrible blog post. But it'll have to do for now. Happy Easter, all who care.
Link31 comments|Leave a comment

[ viewing | most recent entries ]
[ go | earlier ]