Using Models to Create Historical Data

Megan McArdle points to this story about trying to create infant mortality data out of thin air:

Of the 193 countries covered in the study, the researchers were able to use actual, reported data for only 33. To produce the estimates for the other 160 countries, and to project the figures backwards to 1995, the researchers created a sophisticated statistical model. [1]What’s wrong with a model? Well, 1) the credibility of the numbers that emerge from these models must depend on the quality of “real” (that is, actual measured or reported) data, as well as how well these data can be extrapolated to the “modeled” setting ( e.g. it would be bad if the real data is primarily from rich countries, and it is “modeled” for the vastly different poor countries – oops, wait, that’s exactly the situation in this and most other “modeling” exercises) and 2) the number of people who actually understand these statistical techniques well enough to judge whether a certain model has produced a good estimate or a bunch of garbage is very, very small.

Without enough usable data on stillbirths, the researchers look for indicators with a close logical and causal relationship with stillbirths. In this case they chose neonatal mortality as the main predictive indicator. Uh oh. The numbers for neonatal mortality are also based on a model (where the main predictor is mortality of children under the age of 5) rather than actual data.

So that makes the stillbirth estimates numbers based on a model…which is in turn…based on a model.

This sound familiar to anyone?   The only reason it is not a good analog to climate is that the article did not say that they used mortality data from 1200 kilometers away to estimate a country’s historic numbers.

Smart, numerically facile people who glibly say they support the science of anthropogenic global warming would be appalled if they actually looked at it in any depth.   While gender studies grads and journalism majors seem consistently impressed with the IPCC, physicists, economics, geologists, and others more used to a level of statistical rigor generally turn from believers to skeptics once they dig into the details.  I did.

10 thoughts on “Using Models to Create Historical Data”

  1. Why is all science lumped together for credibility. We have experimental and directly measurable fields and values. Then we have predictive and even purely theoretical science. It is time to jump forward from the 17th century and separate the branches. The differences should be taught in school so everyone with an interest in the truth behind something can discuss it without emotional outbursts.

    Only when one realizes that their position is motivated by beliefs can they discuss things calmly. At this present time many do not even know they have belief because they are taught that it “just is”. Anyone who is different is allowed to be ridiculed and belittled.

    Religion … is it not just like minded people getting together with the current accepted truth and filling in the gaps. Then this is imparted to the masses to make us one. Then the people more interested in wealth and power distort all things and manipulate us . Does this not show that people are far worse than beliefs.

    I wish for a world where one can question “have you allowed enough for a known but unquantified variable .. because your models are not precise ” and then not be accused of hating science and be aligned with the holocaust.

  2. I work in technology in the finacial services industry … if a program ever gives a different result over multiple runs with the same input data then its back to the drawing board …

  3. Who needs science anyway, now that we have computers? We can program a computer to give any result we want (see Dr. Mann).

  4. “Smart, numerically facile people who glibly say they support the science of anthropogenic global warming would be appalled if they actually looked at it in any depth.”

    So very true! The reality is that the last thing they want to do is to actually look at it at all!

    Just to divert from the science a moment, look at Al Gore’s “An Inconvenient Truth”. We know the British High Court highlighted nine inconvenient lies in the movie… and most of us could readily name over 30 errors in the movie. But I can’t think of any prominent or semi-prominent global warming alarmist who has taken Al Gore to task over some of the claims made in the movie. Heck, instead, green California’s movie industry awards an OSCAR… and Gore gets a Nobel Prize… the establishment hailed Al Gore a global warming hero for his efforts in trying to fight catastrophic man-made global warming.

    Well, that told me everything I needed to know about these sorts of people and the task at hand.

    Let me say this… these people will continue to dominate the global warming issue, and the skeptics have absolutely no chance of beating these people by producing new studies that debunk the IPCC’s mantra. We know these studies are simply ignored… ignored by IPCC, by politicians, by the media, and by the bureaucrats pushing the agendas of green governments.

    The only effective to stop this global warming nonsense dead in its tracks is by taking the fight into the Law Courts and challenging the pseudo science of the IPCC relies.

    Imagine what a predicament the IPCC would be in if, for example, the following points were demonstrated in a Court of Law:

    1. That the IPCC cannot produce any empirical evidence proving Co2 emissions from the burning of fossil fuels is causing catastrophic global warming.

    2. That the IPCC cannot provide empirical evidence proving the supposition of a greenhouse effect in the atmosphere.

    3. That the IPCC cannot prove that the surface temperature record is reliable and not significantly corrupted.

    4. That the IPCC cannot prove that Co2 drives temperature and climate change.

    5. That the IPCC cannot prove that its model-based predictions (scenarios) that heavily influence policy makers are accurate let alone reliable.

    If it were demonstrated in a Court of Law that the IPCC cannot prove any of these points, the IPCC would be ‘up the creek without a paddle’… the whole basis of its mantra would collapse, and the great big global warming swindle of the last 20 years would collapse in a heap!

  5. Mervyn,

    You make the assumption that such a case would ever make it to court. You cannot sue the IPCC because they are beyond any jurisdiction. You’d have to sue your government, and I cannot think of a single government on earth that would allow itself to be dragged into court to defend that political position. If you DID manage to drag them into court, they’d simply say they were following the guidance of the IPCC and this or that treaty, and such things are beyond the jurisdiction of the court. Game, Set, Match. You lose.

  6. Yes. When you get to the point in your modeling that you use estimates of estimators you probably are pumping out garbage.

  7. A simple equation based on the physical phenomena involved, with inputs of accepted measurements from government agencies, calculates the average global temperatures (agt) since 1895 with 88.4% accuracy (87.9% if CO2 is assumed to have no influence). See the equation, links to the source data, an eye-opening graph of the results and how they are derived in the pdfs at (see especially the pdfs made public on 4/10/10, and 3/10/11).

    The future average global temperature trend that this equation calculates is down.

    This trend is corroborated by the growing separation between the rising CO2 and not-rising agt. From 2001 through Feb, 2011 the atmospheric CO2 increased by 22.2% of the total increase from 1800 to 2001 while the average global temperature has not increased. The 22.2% CO2 increase is the significant measurement, not the comparatively brief time period. The trend of the average of the five reporting agencies has declined steeply since the peak of the last El Nino in about March 2010.

    Some people are so blinded by ideology that they are unable to recognize reality. However, as the atmospheric CO2 continues to rise in the 21st century while the agt does not, more people will realize that they have been deceived.

  8. This movie describes a World Bank project that used 10 years of historical data on confirmed dengue cases to create a model that forecasts the risk of dengue case occurrence 9 weeks in the future in Leon, Nicaragua. Inputs to the model were mapped information about climatic, ecological, socioeconomic, and demographic factors. The models accurately predicted more than 80% of the cases of the past decade and indicate a clear seasonal pattern of risk that corresponds with the wet season.

  9. The gentleman is mistaken about Kennedy. Kennedy made no attempts to block central govt. activity. And given his background, he was more likely a supporter of such an idea. Its unimaginable, for someone to make such an enormous error in fact. I tracked where he picked that up, which is from a hacky conspiracy theorist, Jim Mars ,debunked a long time ago. I recommend you dismiss most of these sites that claim to have the “big picture.” I looked into Mars…

Comments are closed.