Archive for October, 2011

h1

Strategy and Design

October 18, 2011

As I had mentioned in my previous post, I had been on a Smarter Cities Challenge engagement in September, looking at combating the problem of vacant properties in Syracuse.  Besides spending time with a statistician, I also spent time with technology strategists.  This inspired me to read a Harvard doctoral dissertation by Charles Jason Woodward, Architectural Strategy and Design Evolution in Complex Engineered Systems.  He began his career at IBM before going to Harvard.  The beginning of the abstract is as follows.

Engineers have traditionally been trained to solve design problems without regard to the potentially competing interests of other designers. But just as technology strategists are increasingly drawn into the technical minutiae of product development decisions, engineers are increasingly exposed to the competitive forces that shape their requirements and the resources at their disposal. I propose that architectural strategy—the application of strategic thinking to system design problems—should therefore be integrated with the theory and practice of engineering design.

I found several parts of it to be rather interesting, and so I thought I’d share a thought or two from it with you.  First a working definition of strategic interdependence:

…artifacts are composed of many interacting parts, typically designed by teams of people spread across many organizations.  In turn, they function as parts of larger systems, such as the Internet and the global transportation network, whose designs evolve without centralized coordination or control.  Although design decisions are dispersed in such systems, the interests of the designers are often intertwined.  When one designer’s decisions affect the outcomes of another’s design process and vice versa, their designs are strategically interdependent.  Strategic designers act with an awareness of their influence on other designers, which often arises from technological interdependence among the artifacts being designed. 

The main theoretical construct introduced by Woodward is a generalization of a design structure matrix (DSM) (which finds all kinds of uses) and is called a design structure network (DSN).  It is rather expressive and is used to develop the theoretical construct of a system design game (SDG), where dynamics come into play.  As he says:

If architectural strategy were a game, then a design structure network would be an image of the playing field at a snapshot in time.  While a still picture may display evidence
of motion, one can neither predict the players’ trajectories nor explain their history without knowing something about the forces that propel them.  In the context of strategic system design, these forces arise from interactions among agents (such as designers, consumers, regulators, and financiers) that are mediated by artifacts and institutions.  

I know you have had some recent interest in dynamics of systems, so I wonder if this idea would be of interest.  In any case, Woodward goes on to perform Monte Carlo experiments to play out large SDGs and develops insight into system design with architectural constraints.  Let me not give away the punchlines.

In my earliest research work, I used Monte Carlo simulations to derive results, but have not used that methodology since.  Perhaps it is time to return to it: I just need a good problem.  Any suggestions?  Simulating a (smarter) city?   

Advertisements
h1

The Drug called Google Scholar

October 17, 2011

I was just reading a little bit about dose-response functions in medicine and how they may have different shapes.  Somehow I had assumed that most treatments would have monotonic effects, but in fact they may not.  Consequently, there is often a need to perform statistical tests to see whether there is a monotonic trend. 

Continuing on with my scientometrics meme (this is getting worse than the birds, eh?), I went ahead and collected data for all years from 2004 to 2011 (the 2011 set does not yet contain all theses).  I had previously demonstrated that there were indeed more references in 2010 than in 2004, but was that a coincidence, or is there an actual monotonic trend?  If you plot out the mean and median, it does seem like there might be a noisy upward trend, but a formal test would be nice.  Of course, I am thinking of “technological progress” as the dose and the number of references as the response.


Looking around the internet for the appropriate statistical test for monotonicity, I found that this area of order-restricted inference is actually not at all well-settled.   This is particularly the case for unbalanced designs and non-parametric settings, as here.  Often this is due to computational difficulties. 

Notwithstanding, I decided to follow the regression-style method of Tukey et al. that “combines all the allowed principles of witchcraft.”  As Tukey et al. argue, using a unified regression is better than pairwise KS-tests or their equivalents, as one might have considered trying. 

In contrast to their setting  where doses have actual measures, e.g. in milligrams, in my setting it is very unclear what the “dose of technological progress” is.  Hence, rather than considering arithmetic, ordinal, and arithmetic-logarithmic candidate dose scalings and using the one with minimal p-value, I restricted myself to only ordinal scaling. As Capizzi et al. say, “the use of regression on a single scaling may generate controversy and doubt about one’s motives, especially in a regulatory environment,” but oh well.

Note that unlike traditional uses of regression for parameter estimation, here the goal is detection: to detect whether or not there is a monotonic trend.

So we have a sequence of ordinal doses, sample sizes, and mean responses as follows.

2004 2005 2006 2007 2008 2009 2010 2010
Ordinal Dose 0 1 2 3 4 5 6 7
Sample Size 62 68 109 95 108 100 92 47
Mean Response 98.87 104.01 98.11 102.21 101.57 107.23 111.83 108.15

With this data, I went ahead and used SPSS to perform linear regression, getting a positive slope of 1.75 and a p-value for the hypothesis test against the null hypothesis of slope 0 of 0.09.  Hence, there is evidence in favor of a positive trend (at the 90% confidence level).  If one were using matlab, then the functions regstats and linhyptest would be useful.

Although I had learned a little statistics when doing some connectomics work in the past (e.g. not to make this mistake), I am certainly learning much more these days.  For example, when I was doing a Smarter Cities Challenge project for three weeks last month, I spent a good chunk of time with a statistician, who was big on what the data shows and picked up some tricks and tips. 

Incidentally, you might have some interest in these two new neuroscience papers, from Allerton and NIPS, though maybe you have already found them by browsing, searching, or being alerted.