# About...

7.8.2015## ... me

I'm interested in and blogging here about a lot of things surrounding Statistics, Mathematics, Society, Research Methodology and Computing. For example:

- R programming
- Functional programming
- Text mining
- Qualitative Comparative Analysis
- History, Philosophy and Sociology of Knowledge, Science and Statistics
- Open Source and Open Science

I work at WZB Berlin Social Science center as "assistant for data infrastructure and data analysis" in the Manifesto Project. The Manifesto Project provides data for quantitative content analyses of parties’ election programs from more than 50 countries covering all free, democratic elections since 1945. I'm mostly doing data carpentry and R programming. More specifically, I maintain the Manifesto Corpus and the project's R package manifestoR providing access and processing routines for the corpus and our data.

On the formal academic side, I hold a B.Sc. in cognitive science from the Univeristy of Osnabrück, and one in mathematics from Berlin Institute of Technology. I've also studied half of the mathematics Master's program at Humboldt University Berlin and I'm seriously consider the other half.

## ... this page

This page is a somewhat non-linear table of contents for more web content I'm involved in producing. See ...

- ... the blog
- ... and software ...
- ... my gitlab
- ... or find me on twitter ...
- ... or github.

## ... the name

"Points of Interest" reflects for me several important aspects:

1) This is a **personal** page. The only characteristic all of its (linked) content
shares is that I find it relevant or interesting. Very obviously what this is changing over time.

2) "Point" is another word for **datum** -- the singular of "data", i.e. the
particular, countable atoms data are made of. I believe it's a relevant aspect of data --
and one that is too often forgotten -- that it consists of
singular entities, points, small particular elements that are dynamic,
and have to be aggregated together to make up "data".

3) A point is something **geometric**. Geometry is a mighty mathematical tool
that I think provides deep insights about probability, statistics and data.
The two classical interpretations of mathematical probabilities, "degrees of
belief" vs. "long-run frequencies", have become two camps in a fight about
which we forget how clear and intuitive statistical tools and the concept
of probability can be interpreted in a the metaphor of geometry, metric
and shape. I think the language this story should be told in is that of
functional analysis, based on its fundamental concepts of spaces, reshapings
of them (operators), information reduction (projection) and angles (scalar products).
Statistical learning theory
comes pretty close to that, to drop the last buzz word for this paragraph.

4) "Points of interests"" is actually a technical term in **geo** computing -- it's
a place with a specific function or aspect of interest to the user of the geo information.
This association has a double aspect to me: I like metaphors of maps and landscapes
very generally, and it's the only thing in this explanation of the page name which
can be related to a rather important technology playing a role in a lot of stuff
I'm writing and thinking about: information processing, computing and software.