Wednesday, January 25, 2012

Liberals "Surge" in Polls Within the Margin of Error

"Liberals continue to gain steam" shouts the headline from the Globe and Mail.

"But the poll, as emphasized by La Presse, showed the Liberal Party climbing to 19 per cent of decided voter support, up significantly from the meagre 14.2 per cent share of votes it received in the province last May" declares The Hill Times.

"The Liberals, on the other hand, have gained nine points in Quebec since that same June poll, and sit at 19 per cent. Support for the Bloc Québécois is stagnating at only 22 per cent" states Maclean's confidently.

In the poll quoted by the Hill Times and Maclean's they conveniently ignore the fact that according to the poll, the Conservatives are now sitting at 25% in Quebec (compared to their 16.5% result in the 2011 election).  A far greater increase than the Liberals who only increased from 14.2% (2011 election) to 19%.   Neither publication even mentioned the Conservatives' numbers, I had to go to the original article in La Presse to get that.  So I'm suspicious that these articles are biased already.

In the poll quoted by the Globe and Mail, the Liberals have gained 3% so they now sit at 22%.  The Conservatives hover around 37% and the NDP around 28%.   Can we say that the increase in Liberal support is significant?  For the case where a party or person has increased their support by 20% in a single week, I think no one will argue that the increase is not significant. Conversely,  if a party or person only increased in support by 1%, I think very few people would argue that the increase is significant.  But where do we draw the line and how? 

The poll says it has an accuracy of plus or minus 3%, 19 times out of 20.  So an increase in 3% is pushing that limit, right? But what if the last poll slightly underestimated the actual Liberal support by 1.5% and this poll slightly overestimates the actual Liberal support by 1.5%? In which case the actual difference would be almost zero but the reported difference would still be 3%.

In scientific terms, if we are trying to determine if a change is significant there are a number of tools and methods available and some are far more thorough than others.  I'd like to show a very simple way.

1. Take the difference between the two values in question. In our case, the difference in the Liberal support was +3%.

2. Assuming that the errors are independent and Gaussian, add the standard errors of the two polls in quadrature (add the squares and take the square root of the total). In our case the square root of 9 + 9 is about 4.2

We would then say that the difference in Liberal support is 3% plus or minus 4%, 19 times out of 20.

So is it possible that the Liberal "surge" could simply be the result of random errors in the poll? Absolutely.  

Is it more likely that the Liberals are increasing in support than they are decreasing? Of course.  

Would I feel confident stating that they are and drawing a number of conclusions about the direction of the party? No.

Wednesday, January 18, 2012

Ignorance is not Strength

So I ended up reading an article entitled "some people shouldn't talk about science".  While I found the article interesting at first, I was utterly repulsed by the idea that we should arbitrarily limit scientific discussion.  Even someone who is uninformed can contribute meaningfully to a scientific discussion, I thought.

And then I read this article. And, filled with righteous indignation I began to question whether or not some people really shouldn't talk about science.

While warning that "it only has to leak" once to cause an irreversible calamity, the author then points to a leak that occurred at the Point Lepreau Nuclear Generating Station where 6 L of heavy water were spilled on the floor. Evacuation of the 'facility' occurred.  And more ominously, the author warns us, some of that dangerous radioactive stuff may have escaped into the atmosphere.  This comes on the heels of an incident where barrels of diluted hydrazine were accidentally dumped into the ocean.

I'm not completely familiar with the incidents, but a couple things I want to note.

Firstly, as you probably know the Point Lepreau Nuclear Generating Station has been shut down for refurbishment for a few years now and they are on the verge of starting it back up so they are refilling the primary heat transport system with heavy water.  Without heavy water, a CANDU reactor cannot sustain nuclear reactions.  Heavy water that has been inside the primary heat transport system of an active nuclear reactor will have increased amounts of tritium and potentially radioactive iodine and other radioactive elements from failed fuel elements.  Heavy water that has never been inside a core still will contained some tritium.  But the water in your fridge also contains tritium, because tritium is produced naturally through the interaction with cosmic rays (although less than heavy water).  I'm not sure if the heavy water that spilled had ever been inside a core or not, but since the discussion is only about tritium I'm guessing not likely. So, if 6 L of heavy water spilled inside a building and some small trace amounts of tritium escaped will anyone, anywhere be harmed by it? Absolutely not. Which is why the CNSC stated unequivocally that [1]

"The spill did not result in any risk to the public, the environment or the workers."

So why evacuate the 'facility' you may ask? Well, chances are they didn't evacuate the whole 'facility'. They probably evacuated staff from a portion of the facility, specifically the reactor building [1].  And probably it was just a precaution.

Finally, hydrazine is a non-nuclear danger at power plants in general, not just nuclear power plants. Thermal power plants such as natural gas or coal fired power plants both use hydrazine. So even if nuclear power plants never existed and instead Point Lepreau was a giant natural gas fired power plant, it would still be possible to have hydrazine accidentally dumped into the ocean.

I could go on about how no a single death can be attributed to Three Mile Island accident.  How Windscale's "deadly release" only caused an additional 30 cancer deaths, but over 100 people were killed in a Russian dam accident in a single day.  How the public hysteria about a shipment of steam generators from Bruce Power is an example of junk science winning over reason.  But you get the idea.

The article over-hypes the dangers of nuclear power plants and to someone who is uninformed of the topic, will badly mislead them.  However, I'm not worried and I don't believe that the author shouldn't be allowed to voice his opinion on nuclear power plants.

Whenever someone or some group exaggerates the truth to make a political point or makes a statement that is uninformed it will inevitably backfire on them. Because when the truth is ultimately made known and the person or group is shown to be untrustworthy on the topic, their credibility in general goes into the toilet.  Hilary Clinton's claim that she landed 'under fire' was shown to be false and public backlash over her exaggeration helped turn the tide in favour of Obama.

So if you think someone is twisting the facts about a scientific topic, as frustrating as it may be, don't try to ban them from talking. Let them have their say and then prove them wrong.  But that's just my opinion.


[1]  "Small spill of heavy water at Point Lepreau", CNSC, December 14th, 2011 [link]

Monday, January 9, 2012

Joe Oliver is Right

Joe Oliver's open letter is right on the money. Critics of his comments miss the point entirely (see here and here).

As I highlighted earlier using the example of the Darlington nuclear power plants or the Bruce Power steam generators, large segments of the environmental movement are no longer interested in the safe construction of oil pipelines, nuclear power plants or other industrial projects. They are simply interested in stopping them altogether based on a narrow ideology influenced by personal opinions and unfounded fears.  And they are interested in propagating their irrational fears to the general public.

Again, this is not to say that there aren't legitimate environmental concerns to industrial and energy projects. But separating legitimate concerns from the spurious ones is time consuming and costly, which is exactly what some want.

Nevertheless, overhauling the environmental assessment process is not necessarily going to change things so long as the radicals continue to look for ways to game the system.  What is needed is rather a change in attitude on the part of the Canadian public and especially the media.

Environmental radicals need to be called out when they cross the line into obstructionism.  When environmental groups calls for no time limits for all individuals and groups in public hearings (essentially giving any and every crackpot the ability to filibuster), the media should hound them for the absurdness of their demand.  When they insist on a full accounting for all greenhouse gas emissions in nuclear power plant construction, the media should highlight the hypocrisy in not demanding the same for their solar and wind projects.

But that's just my opinion.