Time lag diagrams

During Persuasive 2012 (great conference by the way) I was experimenting with some ways of looking at time series data. I have been very appealed by a bunch of visualizing options coming from people working on Chaos and nonlinear systems. One very simple approach is to plot a time series by plotting the state of the system at t on the x-axis and t-1 on the y-axis. More advance methods exits (see, e.g. http://en.wikipedia.org/wiki/Phase_space), but I thought this simple one was appealing for a lot of social science time series data.

However, after running the below simulations I am kind of unsure. The plots show time lagged presentations of the following functions (from left to right in each panel:

f(x) = 0.5
f(x) = 1.5x / 20   (the 20 added for rescaling)
f(x) = sin(x)

All “time series” are computed in the range [-10, 10]. The first three panels (rows) however show different “sampling” frequencies from the respective functions that generate the time series (1, .1, .01). A striking observation here for me is the fact that with high sampling frequency a sinoid and a straight line are very hard to distinguish using the time-lag plots. Their use thus depends on the sampling frequency however this latter is hard to determine when the functional form is unknown.

Now, the first 3 panels (rows) represent simulations without any noise, so they still seem relatively useful in distinghuising the different functional forms. The lower three panels are again for different sampling frequencies, but this time with noise ( ~Unif(-1,1), added to the process afterwards, no random walk.)

The fourth row basically shows that with low sampling frequency and some noise on top of the actual signal, the time-lag diagram will not at all allow one to distinguish between the different functional form of the time-series.

The simulations were informative for me since recently I have been looking at some data coming from an experiment reported in Science a while ago (“A wandering mind is an unhappy mind” by Killingsworth and Gilbert).

Now, I was doing these same time-lag plots of people’s happiness. Below is a plot showing the plots for a number of randomly selected participants. Which functional form do you think we are looking at?

Waiting for flight

KLM did not feel like it today..

Anyway, now on my way back from Finland where today is Vappu, a big party ;) luckily yesterday I got some of the festivities.

Petri and I just finished a bunch of writing on papers etc. the trip went well.



TEDx Talk

Even though this blog is largely inactive – I might change it around some time soon – I wanted to share the following video with you:

And a small picture so it shows up on the front page:

Oops. Forgot about my blog


Its been a while since I kind off forgot about this blog after coming back from the US. I will be looking for some better solution than me creating a quiet and boring blog…

Anyway, I have been traveling – conferences, holidays etc. etc. Also, I have been working on PersuasionAPI (www.persuasionapi.com) together with Arjan Haring. And, I have been writing up my thesis.

And, I have been skateboarding and trying to support Waalhalla!



Work and Golf

Hey hey

After a long silence a quick update:

A bunch of stuff happened in my work. First, Dean Eckles and I got featured in Wired magazine: http://www.wired.com/magazine/2011/04/st_essay_persuasion_profiling. Second an article I wrote last year got featured on the ACM website: http://cacm.acm.org/blogs/blog-cacm/107125-stats-were-doing-it-wrong/fulltext

So, now I am getting a lot of responses to both. People are using my work both in Industry and Academia, and it is great to see the interest. Dean Eckles and I just submitted a new paper on this work, and I am working with Steven Duplinsky on a more applied study. It going well!

Also, Arjan Haring and I started PersuasionAPI (after already doing some of this myself via Apistat) to be able to use some of the work on e-commerce websites and other online outlets. This is going to be cool because it provides industrial scale testing of my academic work, and a chance to improve conversion of websites.

Next week I will be at CHI 2011 – Vancouver, Canada.

Next to work I am obviously still trying to enjoy CA, so here are some pictures of yesterdays round of golf :)

Long time


Since I have been working quite a bit I have not been uploading much. However, all is well! I have been working on a great paper and some cool analysis with Dean Eckles, and found some great results in another study which I will write up together with Steven. Also, I met Jerry and his girlfriend Krista who are really cool and are going to teach me how to play golf :)

Anyway, life is good around here. Only a few more weeks to go (including one in Canada) and I will be back in the Netherlands again….

A few pictures just to keep everyone informed:

1. I stepped on my glasses. Apparently they do not take that very well….

2. Thats Jerry and Krista in Santa cruz (By the way, the make cool pictures)

3. My own try to do a cool picture…

4. Boats, harbor (no clue where this is really…)

5. Foothills behind Stanford. Cool place to walk around.

See you all soon!


Hey hey,

After a week of lots of work, I finished a STW grant proposal, started my thesis, started a complicated analysis, and finished a JCMC paper, today was pay-back time. The waves were pretty big at Cowell’s so I had a really great longboarding session. I should really get out there every weekend. It is so much fun!

Some pics:

Lazy wednesday

Today no skateboarding for me… and since I was thinking about a bunch of choas stuff I read about a few year ago I decided to give it a go using [R]..

So here are my nice chaos plots:

This one is one of chaotic growth – just a simple t+1 = r*(1-t)*t where r is set to over 3.89.

This second one is the Lorenz attractor… A cool dynamic system.

If you want the [R] code, let me know