Tuesday, May 26, 2015

Forecasting

I found quite amusing to discover several papers about forecast performance and the ability to estimate future events.

It has repeatedly said that forecasting shouldn’t be an economist job. Future is unforeseeable for
everyone and none of the economist tools can help there.  Regardless of what is said, many of us
can’t stay away from forecasting. Two recent papers have been analysing the forecasting power of different people.

http://www.apa.org/pubs/journals/releases/xap-0000040.pdf

http://www.cis.upenn.edu/~ungar/papers/forecast_AAAI_MAGG.pdf

Aparently being open-minded, a knowledge on probabilistics, interacting with others and discuss your forecasts with other analysts increases significatively your chances of being right.

Saturday, May 16, 2015

Stata in Google Scholar

In the academic world the use  of analytical/statistical tools is essential to do research. The data analysis and empirical research has grown exponentially in academic publications as PCs became universally affordable, -- there is an interesting graph showing the growth of empirical research in the economic literature (vs theoretical) that unfortunately I couldn’t find.


The most widely used of those statistical tools is R, as the graph below shows. However, Stata is surprisingly matching R. Strangely enough Stata is not that ubiquitous outside the academic world.




Source: http://www.r-bloggers.com/statas-academic-growth-nearly-as-fast-as-rs/

Wednesday, April 15, 2015

Statistics done wrong

Statistics Done Wrong (a website and a book) is a very useful guide to the most common statistical errors explained in a simple and strightforward way.

"Statistics Done Wrong is a guide to the most popular statistical errors and slip-ups committed by scientists every day, in the lab and in peer-reviewed journals. Many of the errors are prevalent in vast swaths of the published literature, casting doubt on the findings of thousands of papers. Statistics Done Wrong assumes no prior knowledge of statistics, so you can read it before your first statistics course or after thirty years of scientific practice."

http://www.statisticsdonewrong.com/index.html


Sunday, March 15, 2015

Support for free markets by country

The Pew research Center carried out a Global attitude and trends survey in October 2014 which shows some interesting results. One result that brought my attention is the differences in support for free market economic systems.



As you can see South Korea is the country that agrees most with the statement "Most people are better off in a free market economy,...".

Greece, Japan and Spain are on the opposite site. Economic Stagnation or crisis seems to correlate well with this. But, arguably, is Northern Europe, US and UK the most economically free countries. So, it seems that the non-economically free countries tend to blame something they don't have for their problems.

Tuesday, February 24, 2015

A new Data Scientist position

The White House has appointed its first chief data scientist (CDS) for data policy.

 "CDS will be to responsibly source, process, and leverage data in a timely fashion to enable transparency, provide security, and foster innovation for the benefit of the American public, in order to maximize the nation’s return on its investment in data."

This new post will be filled by D J Patil.

Thursday, January 15, 2015

Older leaders by countries


A month ago the Telegraph published an article about how the old pensioner is ruining the young generations’ future and hopes in the UK. It was a bit harsh but the whole point was that youngsters are a minority without political or economical power and therefore brought to their knees by the politically active and rich older generations.

If that is the case, that should have a negative impact on future (present) economic growth. First, it’s known that older generations are more conservative and risk-averse: they’ve got much to lose (assets, savings) and nothing to win (low and decreasing productivity). Secondly, with a more conservative society, regulation would grow, new technologies banned (Uber, Airbnb?) and anti-inflation policies applied. With a scenario like this, younger generations’ expectations would be pretty grim. Creativity and innovation would be harder and as a consequence investment scarce. GDP growth is to good extent a consequence of expectation. Japan could be an example of this.

Research has found a direct relationship between GDP and population age. Smlan Roy, has calculated that the shrinking working-age population dragged down Japan’s GDP growth by an average of just over 0.6 percentage points a year between 2000 and 2013, and that over the next four years that will increase to 1 percentage point a year. Germany’s shrinking workforce could reduce GDP growth by almost half a point. In America, under the same assumptions, the retirement of the baby-boomers would be expected to reduce the economy’s potential growth rate by 0.7 percentage points.

The effects of population age on GDP is probably more complicated than that. Experience is key:
“A clutch of recent studies suggests that older workers are disproportionately more productive—as you would expect if they are disproportionately better educated. Laura Romeu Gordo of the German Centre of Gerontology and Vegard Skirbekk, of the International Institute for Applied Systems Analysis in Austria, have shown that in Germany older workers who stayed in the labour force have tended to move into jobs which demanded more cognitive skill. Perhaps because of such effects, the earnings of those over 50 have risen relative to younger workers.”

It is well known that there is an inverted U relationship between age and salary being 50 when the maximum is reached, ie where experience is not enough to compensate for the loss of creativity.

In any case, seems clear to me that on the extreme a society full of 70 years old pensioners could hardly grow. But even more important, a society were power is biased toward older people wouldn’t be fair.


I generated the following graph that shows the average age of the CEOs of the largests companies and Government members per country. 


The second graph shows the difference between the average leader (CEOs and Gov. members) and the average citizen.


In all cases the leaders are older than the average citizen. Spain is the most extreme case, they are about 25 years older.

Wednesday, December 17, 2014

Data languages and salaries

Last month O’Reilly published their annual DataScientist Salary and Tools Survey. It brought a lot of attention and was the most read article for several weeks at R-bloggers. This is the second year of this report which is an anonymous survey to expose the tools successful data analysts and engineers use, and how those tool choices might relate to their salary. 800 respondents who work in and around the data space, and from a variety of industries across 53 countries and 41 U.S. states.

They found that tools from, what they describe as cluster 3 (Python, R, Matlab,…), increase the average data scientist salary by $1,900 per tool. On the contrary tools in Cluster 1 (SPSS, SQL, Excel, SAS…) bring down salaries by $1,100 per tool. Specifically the report states “The median salary of respondents who use tools from Cluster 1 but not a single tool from the other four clusters is $82k, well below the overall median [which is $98,000]”.

The data was collected from Strata conference attendees which is made of a broad spectrum of data analysts. So, I thought, why don’t we use another source and focus on economics? I checked what Linkedin says about salaries in the economiscs sector about data softwares in the USA and these are the results:

*salaries are in US dollars, the number of jobs are according to LinkedIn USA in December 2014.


Seems that the maximum salary is reached by the combination R+SQL or R alone. But the largest number of opportunities are for those who know SQL, around 750.

This results match those reached by O'Reilly. R seems to be growing and salaries grow accordingly.