<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
<style type="text/css" style="display:none;"><!-- P {margin-top:0;margin-bottom:0;} --></style>
</head>
<body dir="ltr">
<div id="divtagdefaultwrapper" style="font-size:12pt;color:#000000;font-family:Calibri,Helvetica,sans-serif;" dir="ltr">
<p style="margin-top:0;margin-bottom:0">Good afternoon:</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">I ran roughly a year ago some models with BaSTA to some data I have around. I was using a subset of the data (truncated to not include all years that spans 1984:2017). </p>
<p style="margin-top:0;margin-bottom:0">The model specs were: model: GO, shape: bathtub, covs structure: fussed, and the only covariate was sex.</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">This configuration never converged, but the results were consistent with the species ecology, pointing the big differences in the mortality hazzard rate curve shapes between sexes.</p>
<p style="margin-top:0;margin-bottom:0"><br>
</p>
<p style="margin-top:0;margin-bottom:0">I initially though it could be just a matter of running longer chains, but some months ago I guy I know told me that he tried to fit a Siler model in a similar dataset (same species, less data, using his own code), but
it was not very stable. So recently I have gone back to it and check some models output</p>
<p style="margin-top:0;margin-bottom:0"><span style="font-size: 12pt;"><br>
</span></p>
<p style="margin-top:0;margin-bottom:0"><span style="font-size: 12pt;"> Settings</span><br>
</p>
<p style="margin-top:0;margin-bottom:0"></p>
<div> mod1 mod2 mod3</div>
<div>niter 200000 400000 1000000</div>
<div>burnin 197000 397000 990000</div>
<div>thinning 20 20 20</div>
<div>nsim 2 2 2</div>
<div><br>
</div>
<div>and this is the potential scale reduction factor <span style="font-size: 12pt;">(for clarity</span><span style="font-size: 12pt;">, I split it into Females and males</span><span style="font-size: 12pt;">):</span></div>
<div><br>
</div>
<div>females:</div>
<div>
<div> mod1 mod2 mod3</div>
<div>a0.f 0.9982876 1.1061251 0.9999246</div>
<div>a1.f 1.5281294 1.1214647 0.9992686</div>
<div>c.f 0.9971761 4.7816934 1.1177012</div>
<div>b0.f 1.6284601 2.8833760 1.1821780</div>
<div>b1.f 3.8061436 2.4666239 1.2615155</div>
<div><br>
</div>
<div>Males</div>
<div> mod1 mod2 mod3</div>
<div>a0.m 1.0421634 1.0033493 1.1864240</div>
<div>a1.m 1.0001222 0.9985314 1.3429417</div>
<div>c.m 1.0671795 0.9966957 2.4725801</div>
<div>b0.m 1.0945299 0.9968903 2.5274575</div>
<div>b1.m 1.0742245 0.9966948 2.3528640</div>
<div><br>
</div>
<span style="font-family: Calibri, Helvetica, sans-serif, EmojiFont, "Apple Color Emoji", "Segoe UI Emoji", NotoColorEmoji, "Segoe UI Symbol", "Android Emoji", EmojiSymbols; font-size: 16px;">for the females, 400.000 iterations gave worse convergence than 200.000
(unexpected). 1 million iterations, as expected, gets the better values and close to converge. On the other side, for males, 400.000 better than 200.000 (but both offered convergence), but 1 million goes pretty bad. To add some 'fun', I have checked a model
with the same structured with 20.000 iterations and very similar data (I included those individuals of unknown sex as a third sex category, very very few) and it converged as a champ.</span><br>
</div>
<div><span style="font-family: Calibri, Helvetica, sans-serif, EmojiFont, "Apple Color Emoji", "Segoe UI Emoji", NotoColorEmoji, "Segoe UI Symbol", "Android Emoji", EmojiSymbols; font-size: 16px;"><br>
</span></div>
<div>To add some info of the dataset, it is roughly 20.000 individuals, and I have only used data from 1984 to 2009. It is pretty well balanced in terms of covariates (close to 50% males 50% females). <span style="font-size: 12pt;">Roughly 1/3 of the animals
had never been re-observed, which is fair as they are marked when they are weaned</span><span style="font-size: 12pt;"> and nobody will check for them till next breeding season, when they still may be or not at the colony as they won't became adults until
at least age 3 (females). Also, that cames from DataCheck:</span></div>
<div><span style="font-size: 12pt;"><br>
</span></div>
<div><span style="font-size: 12pt;">
<div>*DataSummary*</div>
<div>- Number of individuals = 20,504 </div>
<div>- Number with known birth year = 18,261 </div>
<div>- Number with known death year = 0 </div>
<div>- Number with known birth</div>
<div> AND death years = 0 </div>
<div><br>
</div>
<div>- Total number of detections</div>
<div> in recapture matrix = 38,362 </div>
<div><br>
</div>
<div>- Earliest detection time = 1985 </div>
<div>- Latest detection time = 2009 </div>
<div>- Earliest recorded birth year = 1985 </div>
<div>- Latest recorded birth year = 2005 </div>
<br>
</span></div>
<div><span style="font-size: 12pt;">and this too (I have modify DataCheck locally to avoid printing row numbers, I just want the number of rows with issues, not to have printed >1800 row numbers):</span></div>
<div><span style="font-size: 12pt;"><br>
</span></div>
<div><span style="font-size: 12pt;">
<div>17 rows have observations that occur before the year of birth</div>
<div>Observations that pre-date year of birth have been removed.</div>
<div>18320 rows have a one in the recapture matrix in the birth year</div>
<div>135 rows have caterogical covariates adding to 0</div>
<div>These records have been removed from the Dataframe</div>
<br>
</span></div>
<div><span style="font-size: 12pt;"><br>
</span></div>
<div><span style="font-size: 12pt;">Given that, any suggestion? I did try to run more chains, shorter, with no luck either. I cannot find those model objects</span><span style="font-size: 12pt;">. So I wonder it has to do with the data or with the model itself?
Now I have more computer free time to run these models (they take a lot of time) so I want to give it another go. I was wondering about splittiing the dataset by sex before modelling, and run different, independent modelling for each sex. I think that would
be sensible, as males and females are quite different and are expected to have different curves of mortality
</span>hazard<span style="font-size: 12pt;"> rates, but not sure still, specially looking to the males pattern (1 million iters being </span><span style="font-size: 12pt;">worse than 200.000</span><span style="font-size: 12pt;">)</span></div>
<div><span style="font-size: 12pt;"><span><br>
</span></span></div>
<div><span style="font-size: 12pt;"><span>Best regards and thanks in advance:</span></span></div>
<div><span style="font-size: 12pt;"><span>Fer</span></span></div>
<div><span style="font-size: 12pt;"><br>
</span></div>
<div><span style="font-size: 12pt;">This is how the table of the factors looks from R</span></div>
<div><span style="font-size: 12pt;"><br>
</span></div>
<div><span style="font-size: 12pt;">
<div>> scaleRedFactor</div>
<div> mod1 mod2 mod3</div>
<div>a0.f 0.9982876 1.1061251 0.9999246</div>
<div>a0.m 1.0421634 1.0033493 1.1864240</div>
<div>a1.f 1.5281294 1.1214647 0.9992686</div>
<div>a1.m 1.0001222 0.9985314 1.3429417</div>
<div>c.f 0.9971761 4.7816934 1.1177012</div>
<div>c.m 1.0671795 0.9966957 2.4725801</div>
<div>b0.f 1.6284601 2.8833760 1.1821780</div>
<div>b0.m 1.0945299 0.9968903 2.5274575</div>
<div>b1.f 3.8061436 2.4666239 1.2615155</div>
<div>b1.m 1.0742245 0.9966948 2.3528640</div>
<div>pi.1984 0.9989825 0.9969165 0.9991626</div>
<br>
</span></div>
<br>
<p></p>
</div>
<p style="font-size:10pt; line-height:10pt; font-family: Calibri,sans-serif;"><br>
<br>
University of Tasmania Electronic Communications Policy (December, 2014). <br>
This email is confidential, and is for the intended recipient only. Access, disclosure, copying, distribution, or reliance on any of it by anyone outside the intended recipient organisation is prohibited and may be a criminal offence. Please delete if obtained
in error and email confirmation to the sender. The views expressed in this email are not necessarily the views of the University of Tasmania, unless clearly intended otherwise.
</p>
</body>
</html>