Global Energy Use: Decoupling or Convergence Accepted to be Published in Energy Economics

My paper with Zsuzsanna Csereklyei on trends in global energy use and whether they can be better explained by decoupling or convergence in energy intensity or some mixture has been accepted to be published in Energy Economics. I wrote a blogpost about the paper in December last year when we first completed the paper.

This was not a bad review experience though Zsuzsanna who is in a short-term post-doc position would have liked it to be faster! We first sent the paper to World Development who desk-rejected it. Then we sent it to Energy Economics. The first review took seven months due to one of the referees dropping out due to family health problems and then the journal needed to get another referee. We turned around the paper in 12 days and then got a conditional acceptance a month later. We turned that around in one day and got the final acceptance a day later. This paper applies the method developed in Anjum et al. (2014) to energy and also adds treatment of spatial autocorrelation. The whole process of writing and publishing this paper took place while Anjum et al. has been in review...

Update 5 October

The journal also got the final version of the paper with page numbers onto the web incredibly quickly following us returning the final proofs.

Having Small Government Should Never Be a Reason for Making It Bigger

It seems that the Grattan Institute argues in its submission to the National Reform Summit that because Australia's government is relatively small by the standards of other developed countries we can or should increase its size. This argument makes no sense to me, though it seems to be often made. Perhaps other countries spend inefficiently or perhaps Australians are not interested in spending on some of the things that those countries spend on. We should look first at the outcomes we have as a country and, if there are poor outcomes that Australians would like improved, we then need to ask whether government can make a difference. Only then does it make sense to ask whether spending or taxes should be higher. I don't think this is really a political statement, as I leave open the final choice on whether to increase the size of government or not. But it makes no sense to talk about increasing the size of government simply to be nearer OECD means.

As for whether we should change the taxation arrangements for superannuation the simplest, fairest, and possibly relatively efficient  approach is to use the same approach as US 401k and 403b funds and tax payouts at normal income tax rates but not tax contributions or earnings in the accumulation stage. It's simple to show that under reasonable assumptions that this approach generates higher retirement incomes than the current Australian approach. It also has the huge advantage of reducing bureaucracy. Self managed superannuation funds are costly to run in Australia because of the need for accounting and auditing to make sure that they are paying the correct taxes. In the US, an IRA is just like another brokerage account except for the rules on contributions and withdrawals, which can be managed by the broker.

The Extent and Consequences of P-Hacking in Science

Interesting paper from my biology colleagues at ANU on the effects of "p-hacking" - searching for more significant results by looking at various statistical models or samples and picking the more significant ones to report - on reported science. They conclude that when there is a strong real effect it can be detected despite p-hacking by looking at the "p-curve". The p-curve is the distribution of p-values across all the studies collected in a meta-analysis. If the curve is skewed right - there is a peak at very high significance levels (numbers a lot smaller than 5%) then there is a real effect. However, p-hacking can inflate the estimated size of the effect if we use a simple average of effect sizes in the literature. The main novelty of their paper I think is that they collected a large number of p-values from various fields of science using text-mining to test these ideas in the empirical literature.

In meta-analysis in economics, a popular approach is to test the effect of degrees of freedom or precision (inverse of the standard error) on the values of the reported test statistics using regression analysis. This effect is called the power-trace. The idea is that if there is a true effect, then, due to increasing statistical power, reported test statistics will be more significant the higher the degrees of freedom in the underlying study.* Some of these methods can also be used to estimate the true effect size adjusted for publication bias.

In our meta-analysis of energy-GDP Granger causality tests we also present graphs of the distribution of the test-statistics. These seemed to be roughly normal with a mean of about 1, which means there is excess significance in this literature but that the mean test statistic is not statistically significant (the solid histogram in the background is the standard normal distribution):

To help interpret these graphs, note that a normal test statistic (-probit(p)) of zero means that the original Granger causality test p-value was 0.5. A test statistic of 1.65 implies that the original p-value was 0.05 and a test statistic of -1.65 implies that the p-value was 0.95. The econometric analysis in the paper showed that there was no statistically significant relationship between these test statistics and degrees of freedom, also suggesting that there was no genuine effect. We showed in the paper that there did seem to be a robust effect from GDP to energy when underlying studies controlled for energy prices.

We didn't report the actual p-values though, and so I am curious what the p-curves look like. First I made a couple of histograms with bins for each 1% increment of p-values:

Uh-oh! The mode is for 0-1%! According to Head et al.'s methodology that means there is a true effect in each direction of causality. When I broke down the range from p=0 to p=0.1 into 100 bins, again the mode was for the smallest value. So, what does it mean when the overwhelming majority of studies find results that are less significant than the 1% or 0.1% level and yet the mode is for 0-1% or 0-0.1%? And when these results are for not particularly large sample sizes? Either the p-curve or the meta-regression/power trace method is wrong here. One hypothesis is that non-stationarity in macro-economic time series and the over-fitting problem discussed in our paper result in many spuriously significant test statistics in relatively small samples that wouldn't arise with more classically behaved data.

* Though this method can detect a "genuine effect" there is no guarantee that this is a "causal effect". If no studies control for the relevant variables or effects to identify a causal effect then the meta-analyst won't be able to detect a causal effect either. Similarly, if the meta-analyst doesn't control for all the relevant variables included in the underlying studies they may also fail to identify a causal effect when some papers do identify one. All the meta-analyst can find is a robust partial correlation in the underlying studies if one exists.

Donglan Zha

Donglan Zha is visiting Crawford School for the next year. She is an associate professor at Nanjing University of Aeronautics & Astronautics and works on energy economics including research on substitution possibilities and the rebound effect. Her office is in Constable's Cottage across the road from the main Crawford Building. Her ANU e-mail address is donglan.zha@anu.edu.au. Please welcome Donglan to the Crawford School, I'm sure she will be happy to meet with you.

International Energy and Poverty: The emerging contours

New book that will be released this month: International Energy and Poverty: The emerging contours. I am the authors of the introductory chapter on energy and growth. There will be a book launch at University of Denver on 11 September at 9:30am as part of the "Access to Energy for All" event. Contact Lakshman Guruswamy for details if you want to attend.