about.me Follow me on Facebook Follow me on Goodreads Follow me on Twitter

Me on Twitter

…generated with the code from Mike Croucher on github and some post-processing of the png with graphicsmagick and pngcrush.

Update 25.11.2015

And after debugging the source – too much was deleted from the tweets (everything after an URL, everything after the first mention of another twitter user) – the whole thing looks like this:

Read: Counterfactuals and Causal Inference

Counterfactuals and Causal Inference is a very practical book that discusses the different approaches to identify causal effects (in non-experimental and experimental data) at a very abstract level. Depending on the reader this may be a good or not so good thing. I had to expend substantial effort to work through the text and I fear that even though I understand directed acyclical graphs I have not developed any intuition in their application that would help me in my applied modelling. Often, the text remains at a too abstract level.

What the text is missing is an even more practical guide with more concrete applied problems and their solutions. Yet, the text is good. It’s not a handbook for a quick how to do it. It’s not a textbook for undergraduates. It’s a critical survey of the state of the art of statistical approaches for the identification of causal effects. It’s a valuable reminder that the regression approach is no magic bullet.

That being said, the text raises the important question of identification and alerted me that some effects that we estimate and report may not be the effects that we would like them to be. I guess I will have to be even more careful when I interpret regressions in the future.

Addendum: I have read the first edition that I had for already some years sitting on my to-read shelf. I just discovered that there is a 2nd, revised edition available.

Read: Foundations and Fundamental Concepts of Mathematics

While Eves’ Foundations and Fundamental Concepts of Mathematics is certainly a bit outdated by now – it is 1997 reprint of a textbook originally published in 1990 – it was still fun and interesting to read.

The books offers a nice historical overview of fundamental concepts of mathematics (hence the title) that includes not just the historical background but a solid introduction of each concept itself. Of course, solid means here that the introduction just provides as much depth as is needed to understand what it is all about. As such the different chapters may whet one’s appetite for more on the respective topic. Just when it gets interesting the text stops. It has to. Otherwise, Eves would not be able to cover as much as he does.

Sometimes maybe, the little detail that is given can also already seem a bit too much. Getting to a theorem 48 in just one chapter shows that Eves is certainly not just skipping over details when he feels the reader may benefit from a rigorous presentation of the material.

Read: David Falkayn: Star Trader

Reading Anderson’s Technic Civilization Sage makes you feel like a historian who tries to piece together the story of a society long gone by looking at a few personal accounts, by following the exploits, the fates and fortunes, of a few exceptional individuals. There are no records of ordinary persons.

You may get romantic notions of adventures, reckless and successful quests. And yet, Anderson manages to also show the dark(er) side, to hint at the fate of those left behind. That is quite an accomplishment. I still believe that not writing a unified tome (with multiple time lines, going back and forth), not putting everything in one book but having a collection of short stories and novellas is cause for how much better this work seems compared to other, more recent space operas.

The self-contained small(er) pieces are fun to read. You a read a story and you can put down the book feeling (entertained and) satisfied and rewarded. Reading never becomes chore, you do not have to read on so that something …anything happens! Instead a lot is happening in just a few pages. Of course, the frequent re-introductions of the protagonists are repetitive but some new facets are added to the characters every time and so you do not mind.

A final observation, though. While the physics (as far as you can expect from a science fiction novel) and economics seems sound (ok, this is not a textbook) I am not so sure about the armchair sociobiology that Anderson is feeding his readers. On the other hand, given that the short stories and novellas were written in the 60s and early 70s he was certainly was at the forefront of the idea that and how biological factors (like being a herbivore, carnivore, omnivore) determine individual social behavior and society. E. O. Wilson’s Sociobiology was only published in the mid-70s.

Read: Statistics Done Wrong

Reinhart’s Statistics Done Wrong is a refreshingly entertaining exposition of typical and embarrassingly widespread problems with the statistical analysis in (published) research.

It is not a textbook. It is non-technical. There are no formulas and only very few numbers. Nevertheless, it teaches the art of statistics. It may even instill the wish in the (un)initiated reader to pick up a statistics textbook and finally learn the stuff. As such it may be a good gift for a first year PhD researcher. Knowing about statistical power and related concepts before any data is collected can dramatically improve any research design and thus the final research (article).

There is nothing new in Statistics Done Wrong. All problems and all the examples chosen to illustrate them are already well known or were at least discussed in the usual blogs on applied statistics and data analysis. It is obvious that Reinhart follows, e. g., Andrew Gelman’s blog. Of course, he does. Everyone interested in the use and abuse, in good and bad practice of statistics follows (or should follow) Andrew’s blog. Nevertheless, Reinhart adds additional value. His writing is clear and accessible.

I have only one quibble: Reinhart states in the preface that he is not advocating any of the recent trends in and attempts to improve the practice of statistics: may this be the complete abandoning of p-values, the use of “new statistics” based on confidence intervals, or a switch to Bayesian methods. Actually, he is advocating rather strongly for the use of the “new statistics”. He advocates the use of effect size estimates and confidence intervals over vanilla p-values. This is absolutely fine. Yet, he should stand openly to this position and not deny it.