Saturday, March 12, 2016

Lucia's sadly selective statistical showpersonship

Lucia Liljegren is spending the twilight of lukewarmism as a non-laughable position mostly posting recipes, and notifying her followers about the arrival of major holidays (three of her last ten posts.) But 'twas not always thus. During the "hiatus" Lucia was fond of comparing the IPCC's multi-modal mean with global temperatures, despite the fact that these were models of climate, not weather forecasts, and that patient people had explained to her over and over that "about 0.2C/decade over the next several decades" was not a prediction one could falsify based on a few years of data.

She liked making this mistake so much, she did it again and again and again (and again and again…and again.) But this all stopped rather abruptly in November of 2014, which funnily enough was exactly the time El Nino came to a stuttering start after a unprecedented 50-month absence:


As a result, every month after November 2014 (anomaly 0.68C) has been hotter (anomaly-wise) than November 2014 itself:

And yet despite the rather dramatic turn in the data, and despite the fact that she liked making this comparison well enough to make it over and over again with different temperature records and updates to the present, she never updated her final graph, which looked like this:


Why did Dr Liljegren suddenly lose interest in this exercise? Why the statistical-torture hiatus? We may never know, but said graph with more recent GISTEMP measurements superimposed looks like this:



It's a mystery, really.

UPDATE: MartinM has better graph-fu than I and has updated lucia's graph of the multi-model mean vs the 13-month mean.

 

5 comments:

  1. Are you sure you got the baseline right? Most figures I have seen had 2015 around the multi-model mean temperature, not that much above.

    The main "mistake" Lucia Lijegren is making is confusing the model spread and the model uncertainty.

    At least she wants to win debates, which avoids a large part of the utter nonsense we see on WUWT, which are no more than pledges of allegiance. A pledge signals the strongest support of the group, the more ridiculous the claim is.

    ReplyDelete
    Replies
    1. I hope the baseline is right. I calculated GISTEMP's average anomaly from 1980-1999 (+0.32C) & subtracted that from the current anomalies. But now that I'm looking at it again I think I forgot to subtract it from 2015. I'll fix it, thanks!

      Delete
  2. Here's a quick update of Lucia's graph, using the same 13-month running mean as she did. I didn't bother to include error bars on the multi-model mean, and it's GISTEMP only, but it gets the point across. GISTEMP trend is .17 K/decade from 2000 to present.

    Bear in mind that, as it's a running mean, the GISTEMP line ends in August 2015. So expect it to continue heading upwards for a while yet.

    ReplyDelete