Tag Archives: statistics

Polar bear numbers, margins of error, & consequences for conservation status

Large margins of error in polar bear population estimates means the conservation status threshold of a 30% decline (real or predicted) used by the US Endangered Species Act and the IUCN Red List is probably not valid for this species.

Polar_Bear_Biologist_USFWS_working_with_a_Bear_Oct 24 2001 Amstrup photo

Several recent subpopulation estimates have shown an increase between one estimate and another of greater than 30% yet deemed not to be statistically significant due to large margins of error. How can such estimates be used to assess whether population numbers have declined enough to warrant IUCN Red List or ESA protection?

What do polar bear population numbers mean for conservation status, if anything?

Continue reading

Two technical critiques of the Harvey et al. polar bear Bioscience attack paper

Not much time for blogging, but two technical critiques  of the Harvey et al. paper have recently been posted, which you might like to read at your leisure. I will update this post when I can if more critiques appear plus I’ve provided a list of previous posts (my and others) on this issue.

Polar Bears, Inadequate data and Statistical Lipstick (18 Decemeber 2018, RomanM writing at ClimateAudit)

McIntyre guest blog on Harvey paper photo led_RomanM 18 Dec 2017

Polar bear attack paper invalidated by non-independent analysis” (Cross posted 14 December 2017 at ClimateScepticism from the blog of Shub Nuggarath, 12 December 2017).

UPDATE 19 December 2017: Richard Tol has posted a draft of his critique, which was itself updated 20 December “Lipstick on a bear” in which he concludes:

“In sum, Harvey et al. (2017) play a statistical game of smoke and mirrors. They validate their data, collected by an unclear process, by comparing it to data of unknown provenance. They artificially inflate the dimensionality of their data only to reduce that dimensionality using a principal component analysis. They pretend their results are two dimensional where there is only one dimension. They suggest that there are many nuanced positions where there are only a few stark ones – at least, in their data. On a topic as complex as this, there are of course many nuanced positions; the jitter applied conceals the poor quality of Harvey’s data. They show that these is disagreement on the vulnerability of polar bears to climate change, but offer no new evidence who is right or wrong – apart from a fallacious argument from authority, with a “majority view” taken from an unrepresentative sample. Once the substandard statistical application to poor data is removed, what remains is a not-so-veiled attempt at a colleague’s reputation.”

UPDATED 20 December 2017: Lead author of the Bioscience attack paper Jeff Harvey talked to an Amsterdam newspaper about the backlash to the paper, original Dutch and English translation here.

Fig 3 Sea ice prediction vs reality 2012

Predicted sea ice changes (based on 2004 data) at 2020, 2050, and 2080 that were used in 2007 to predict a 66% decline in global polar bear numbers vs. an example of the sea ice extent reality experienced since 2007 (shown is 2012). See Crockford 2017 for details.

Read a short summary of the paper that Harvey et al. don’t want you to know about here:

Crockford, S.J. and Geist, V. 2018. Conservation Fiasco. Range Magazine, Winter 2017/2018, pg. 26-27. Pdf here.

The paper they don’t want you to read is here:

Crockford, S.J. 2017. Testing the hypothesis that routine sea ice coverage of 3-5 mkm2 results in a greater than 30% decline in population size of polar bears (Ursus maritimus). PeerJ Preprints 2 March 2017. Doi: 10.7287/peerj.preprints.2737v3 Open access. https://doi.org/10.7287/peerj.preprints.2737v3

The paper being criticized (Harvey et al. 2017, in press: “Internet blogs, polar bears, and climate-change denial by proxy”, Bioscience, open access) is available here.  There is a supplementary data file available here and the data for the principal component analysis is available here  and (h/t to R. Tol), the R code is available here

More on this after Christmas but for now a list of previous blog posts of mine and others is provided below. Continue reading

Breaking: 2016 W. Hudson Bay polar bear survey shows the population is still stable

A just-released report on the most recent (2016) survey shows Western Hudson Bay polar bear numbers were still stable despite predictions that this subpopulation would be wiped out completely (reduced to zero) due to low Arctic sea ice.

Churchill_Polar_Bear_2004-11-15 Wikipedia

The authors of the report on the August 2016 aerial survey of the Western Hudson Bay polar bear subpopulation (Dyck et al. 2017) state clearly that the only trends they could find were that the number of adult males increased somewhat over 2011 estimates and the number of females either declined or remained stable. The overall population estimate was a bit lower (11% less) compared to the 2011 survey but the difference is not statistically significant. Therefore, the population status must be stable.

2011 estimate: 949 bears (using comparable data, range 618-1280), litter size 1.43

2016 estimate: 842 bears (using comparable data, range 562-1121), litter size 1.63

[cf. Foxe Basin [stable], from 2009-2010 survey (Stapleton et al. 2016) litter size was 1.54]

An 11% decline in WH numbers since 2011 is most definitely NOT the decline to ZERO (extirpation) we were told to expect with Arctic sea ice as low as it has been since 2007 (Crockford 2017, see list of annual minimum extents 2007-2017 here).

Note: The percentage decline from 2011 to 2016 for Western Hudson Bay polar bears is 11%, NOT 18% as claimed recently by Andrew Derocher on twitter: it is not appropriate to compare the official 2011 estimate of 1030 (Stapleton 2014) to the 2016 estimate of 842 because the methods used to generate the estimates were different (Dyck et al. 2017). The authors of the report state that the estimate for 2011 that’s comparable to 2016 is 949.

An 11% decline from 1030 would be 917 bears, a statistically insignificant decline that is also biologically insignificant and therefore, so slight as to indicate a stable population.

Predicted sea ice at 2050 and 2080 shown below (see Crockford 2017 for details):

Crockford 2017 sea ice graphic

Quotes, map, and table from the Dyck et al. 2017 report (pdf here) are copied below.

Continue reading