ThimphuTech was the first technology blog in Bhutan. We started writing it in 2009, just as broadband and mobile internet started to take off. (Although internet in Bhutan was launched in 1999, it was either super-slow or super-expensive, and was only used by a selected few).

In the blog, we wrote about technology and food, but also about plenty of other stuff. The blog became popular and influential in Bhutan. A companion bi-weekly column -- Ask Boaz -- was published for many years in the Kuensel, Bhutan's national newspaper. (The complete Kuensel columns are available as an ebook, Blogging with Dragons).

We stopped updating the blog when we left Bhutan in 2014, but the information within the posts can still prove useful, and thus we decided to keep it online.

We thank all our readers.
Tashi Delek,
Boaz & Galit.

Monday, March 19, 2012

Software for Statistical Analysis

A recent tweet by Sonam Tshering mentioned a tender for a single IBM SPSS software license by MoLHR.
It seems that SPSS is the statistical software of choice in Bhutan not only at MoLHR. Sonam raised a good question: why not use the free open-source software R?

An ema-inspired ad by SAS
From my experience as a user and as a teacher of statistics and data analysis courses for statisticians and non-statisticians (business students, engineers, and more), my sense is that R is not a good choice for non-statistician users unless they are computer science graduates. R is a programming-based software that requires knowledge of the R programming language. It does have a basic graphic interface (GUI), but that is far inferior to almost all commercial software packages. Commercial software tends to have pull-down menus that do not require programming skills. Whether the user has sufficient expertise in performing the right analyses and interpreting them correctly is another question...

So the question I would ask is whether IBM's SPSS is the right tool compared to other menu-based software. One bonus point is that everyone is using it here, and that is indeed a big advantage in terms of knowledge, file sharing, etc. An interesting possibility is the free SPSS alternative called PSPP -- worthwhile checking whether that can work as a fee-free replacement (I've never used it).

In terms of commercial, paid statistical software, the market is highly competitive. Another major player is SAS (had they only known to post their ema-ad in Bhutan!). SAS has a range of different tools, from programming-based packages to drag-and-drop and menu-driven tools. However, they are usually quite expensive aside from the JMP product. Econometricians love Stata (expensive but powerful for research). Another, reasonably-priced software is Minitab, which is popular with Six Sigma and quality assurance users.

A final note: statistical analysis can be tricky, especially when done by "running software" blindly. My best advice is to invest most of your time visualizing your data. For that, good visualization software is crucial, and unfortunately statistical software tend to have very weak visualization capabilities. Once you get an understanding of your data by visualizing it, statistical analysis will help determine whether what you see in the charts is random or an actual effect.