Jason Polak <>
Tue, 6 Mar 2018 16:45:51 +1100
Possible, for sure. Here are some ideas that could be possible using the
1. You can use the total number of observers in a given area in a model
for sea eagles. With this number you could estimate the mean number of
sea eagles observed per individual, and see how this varies over time.
2. You could model each breeding year of the Sea-eagle more thoroughly
by assuming that observations of Sea-eagles for individual birders
follow a Poisson distribution for a specified area, and use a
generalised linear model, incorporating a few different factors. Then,
you could see how these models change over time.
Basically, if you get the data per individual report, you are treating
each observation as a random sampling from some unknown distribution and
use basic statistical methods to approximate the total population.
Some of it involves slightly advanced math, but it is accessible with a
little study and if anyone needs pointers or help getting started with
it, I'd be happy to provide some assistance---I am a postdoctoral fellow
in mathematics at the University of Melbourne.
P.S. Saw my first White-bellied Sea-eagle in Jabiru!
On 2018-03-05 11:22 PM, Judith L-A wrote:
> So… supposing I want to see how numbers of White-bellied Sea-Eagles might be
> varying across years – Given uncontrolled numbers of observers reporting
> variably to eBird, can it provide suitable long-term population info about
> the species ?
> SEQ 500m
> <BR> Birding-Aus mailing list
> <BR> To change settings or unsubscribe visit:
> <BR> http://birding-aus.org/mailman/listinfo/birding-aus_birding-aus.org
<BR> Birding-Aus mailing list
<BR> To change settings or unsubscribe visit:
The University of NSW School of Computer and Engineering
takes no responsibility for the contents of this archive. It is purely
a compilation of material sent by many people to the birding-aus mailing list. It has not been checked for accuracy nor its content verified in any way.
If you wish to get material removed from the archive or
have other queries about the archive e-mail
Andrew Taylor at this address: