Quest For Data

Questions lead.  Answers follow. 

I first heard this expression more than two decades ago at a statistics conference held in Kansas.  A then popular statistics guru was the presenter. I don’t remember much else about the presentation, but that expression was a valuable insight for me at that time and I have kept it.  Which questions we ask and seek answers to drive our lives forward.

Collectively, those questions steer our culture into the future.  The answers we accept help us find the optimum path to get where asking those questions lead us.

I think we form the best answers to our questions when we seek out and consider relevant data.  As a statistician, I am very familiar with how difficult it can be to identify and collect the relevant data.  Figuring out what data will tell me, or rather my clients, what they seek to learn and then collecting a representative sample of that data can be an elusive goal.  That’s why I decided to name my blog ‘Quest for Data’.

The purpose of my blog is discuss what I consider interesting questions of our times and seek the relevant data to form opinions and ideas about the problems that provoked those questions.

I’m going to write about what I consider interesting questions and the data that is needed to answer those questions.  What is publicly available and what can it tell us about the answers to these questions?

When I can obtain data, I’ll publish it along with where it comes from. Then I’ll add the results of any analysis I do with the data.

I have decided to start with a question regarding the accuracy of voting machines results in U.S. elections.  This is a suspicion I have harbored since the 2004 election when I examined the Ohio data from the Bush/Kerry contest.  A statistical analyses of various U.S. elections over the past decade show troublesome patterns in the residuals; patterns that indicate a relationship between the size of the polling group and the percent of votes for the republican candidate.  Why this pattern causes me concern is the subject of my post “Cause for Suspicion”.

However, the next step with that project will take some time as I must apparently file a lawsuit to get access to the data. In the meantime, I’ll be writing about other issues, profound and trivial, that I think about and have sought data on.  I actually have a few quirky personal projects that I’ve done but not published.  For the most part, they aren’t worthy of publication in a peer-reviewed journal. They are just examples of my own personal quest for data and the difficulties I have encountered in collecting it.