Thursday, November 8, 2007

Cost vs. ANCOVA

My supervisor just asked me an interesting question on email. In RT research, it's quite common to "control" for baseline response time by either subtracting it from experimental condition RTs or run an ANCOVA using baseline RT as covariate. She wants to know if these two control methods are the same.

Here's my response:
Mathematically, they are not the same. Imagine a distribution of response time, subtracting control RT from experimental RT is like shifting the distribution down by a constant. But of course, this substraction is done at a mean level for each individual, so individual differences would be included in the costs (e.g., someone is exceptionally interfered by the flankers, regardless of whether it is congruent or incongruent, would incur a much larger cost than someone who is not interfered by the mere appearance of flankers). The end result is a much lower mean and more variability.

On the other hand, running an ANCOVA using control RT as covariate is like generating a new distribution, which would give you a different mean (central tendency measure) and a different standard error (variability). In this case, however, the variability would be smaller. This is because each individual's performance in each condition is considered as a distribution. ANCOVA partials out the common variability between control trials and each of the congruent and incongruent trials. The end result, in this case, is a mean that is analogous to the raw mean, but a tighter variability. Sometimes changes in ANCOVA is very small (if the control is not very correlated with the experimental conditions).

Any thoughts?

Friday, November 2, 2007

More stress...

After sending in the application for a fellowship next year, now I am facing this daunting task of writing my dissertation... I've officially started yesterday and am currently in the expected progress. Now the stress has just mutated to another species...

The major problem I have with stress is that it leads me to confusion and I end up with no idea where to start my work. I try to overcome the overwhelming effect of stress by sitting in front of the computer and just work. Honestly, it works! Once I get into the working mode, I feel more comfortable and seem to be able to see some light at the end of the tunnel.

My supervisor wants me to hand in part of my dissertation in about 2 weeks (about 60-70 pages). Then I'll go to a conference at Long Beach, CA (presentation prepared, thank God). The following deadline is in early Dec, when she wants to see my whole package (that would be about 150-160 pages). On top of that, I also have to finish teaching a course with 30 some students... It's a small class and I have no TA... wonderful... It's also a brand new course that I am building from scratch... Guess I'll get through it.

James has been wonderful, can't find a better person to support me. :) He even listens to me babbling on my theories! What's there to complain?

Back to writing....

Tuesday, August 28, 2007


Stress is interesting... It strikes you when you are least aware and prepared. It lands on your skull while you are thinking and slowly immerses into your brain...

For those who work close to me, they know I am working on a few applications. That's when the stress shapes up. Reaching the end of my student life, I feel ambivalent about it. Am I ready for a job? Or should I say, will I get a job? The uncertainty in graduate education is a nuisance, but it is part of the game. So, I just have to suck it up and deal with it.

My stress-released strategy is to sleep, eat and think (Yes, I can totally indulge myself in my own mental state without awakening). Time to continue my mental exercise...

Sunday, July 15, 2007

I'm back

Yes, I haven't been keeping up with my promise. And I've been slacking in writing.... the blog. But I haven't been lazy in writing my other papers. For an update, I've accumulated a few more publications on my CV. For two of the most recent ones, they were actually accepted on the same day!! YAY!!

Things are fine, overwhelming but fine. I feel like I am constantly in this journey of learning. There isn't a day that I feel that I have learned enough. My feeling is always, "Oh my God, there's still soooo much I don't know." My hunch tells me that this feeling will be with me for the rest of my life.

Married life is excellent! James and I will have our anniversary next Wednesday. This year also marks our 11th anniversay since we met. All I can say is that our relationship grows stronger and stronger. :)

Alright, time to go back to work, later...

Tuesday, December 5, 2006

NDS Lite!

I've got it! Finally! After resisting my temptation for a long time, I finally get NDS lite. Can't wait to play -- now I just have to wait for the Wii...

Saturday, December 2, 2006

Dye Tag Attack!

So, I didn't keep my word and post a blog last week... Well, I was attacked by a dye tag... Why? Er.... ok, James and I went shopping on a weekend and he needed a white shirt. So, we bought a white shirt. When we were paying for the shirt, we looked around and didn't pay much attention to the lady who was processing our payment. She was talking to her colleague in a language we didn't understand... Anyway, we left the store and went home.

Guess what? The lady didn't take off the dye tag! I was surprised that I could actually walked out of the store without hearing a beep! So, James and I planned to go back and ask the lady to take the tag off. You know, there's no way you can loosen a dye tag unless you have the security check thingy at the counter. Due to my curiosity, I decided to examine the dye tag a little and tried a few experiments on it.

For those who know me, you would also know that I am quite strong... So, this is not good when you are dealing with a dye tag situation -- I broke the tag and ink spilt out -- onto my fingers, hands and a few drops landed on my desk. ha ha ha. Now I really look like a thief! Then my cousin got me the alcohol and exfoliating scrub and help me to get the ink off. My aunts were all laughing and they told me not to walk into that store in the near future... James found out and couldn't believe I did that. Oh well.... it took 3 days to have the ink came off.

This is totally an example of an uncontrolled experiment gone bad... :(

Monday, November 20, 2006

Lazy GG...

I am quite lazy in maintaining a blog, mostly because I spend most of my time in front of the computer working and simply looking at the monitor makes me tired. :P OK, I promise I'll at least update the blog once a week! Another reason for the "blog procrastination" is that I don't know what to share... I am basically a boring person, work consumes most of my time....

Hmm, one thing I can share with you this week is that I gave my first formal lecture that is NON-STATISTICS (Miffy, this is rare for the SAS ASSASSIN) last Thursday. It was on cognitive development and gender differences in a third year cognition class. So, it went ok, I was a bit nervous but fortunately I am a guest lecturer so I can say whatever I want :> If I need to rate my own performance, I would give myself a 65% because there is still lots of room to improve. There will be another lecture this Friday. This time, it is on non-parametric statistics, I'll try my best :) (Note: got another on next week... I'm going to be a professional guest lecturer by the end of this month. Funny thing is -- all three lectures are in different subjects!)

Well, writing this post didn't take me more than 10 mins... perhaps I could be a bit more prolific :) Stay tuned...