Random Numbers And Junk Science

Random number generators form the basis of much of science and engineering.

For example, you can’t design a nuclear weapon by modeling the behavior of each particle. Rather, they use very sophisticated random number generators to model the average behavior of the particles.

My approach to calculating temperatures from large data sets uses the same principle – I assume that the errors in the data set are distributed randomly and thus do not bias the absolute temperature or trend. That is the normal way which scientists deal with large data sets which have no systematic bias.

Zeke apparently can’t comprehend this, and believes that absolute temperatures can’t be calculated with data sets which have missing data.  His approach is to hide the missing data by calculating anomalies for each month. In doing this, he loses vast amounts of important information – like what I have been uncovering.

Zeke and Mosher think I should the same grossly flawed methodology which they use, and thus come up with the same wrong numbers which they do.

If there is a systematic human bias behind the post-1990 station data loss, their approach will not find it – and will in fact cover it up.


About stevengoddard

Just having fun
This entry was posted in Uncategorized. Bookmark the permalink.

21 Responses to Random Numbers And Junk Science

  1. gregole says:


    I don’t know Zeke’s background, but isn’t Mosh like an English major or something? I have a huge sympathy toward Mosh because the first book I read on climate was “CRU Tape Letters” he co-authored with Fuller and if you or anyone else has read it, it’s clear he is sincere on some level. I just don’t know if perhaps, just due to his lack of background early on, he just doesn’t understand that words and physical facts sometimes live in different realms of rational discourse. Mosh appears for example to be quite impressed with modeling. I actually do modeling and am quite unimpressed with models unaccompanied by either classical closed analytical methods, or better yet, testing. Stories I could tell. Oh my.

    My mom (and my step mom) were both English teachers. I have sympathy and some understanding of how their brains work, but I am an engineer. Worse yet, I am a mechanical engineer, a total barbarian! I must see the data. Speaking of which, I have a request. As an engineer, I am also horribly lazy and have been working on Arizona temperature data.

    Question: Does anyone have an easily accessible list of Anthony’s (wuwt.com) surfacestations.org temperature stations listing by their ranking? I can’t seem to stumble upon it with elementary searches and here’s what I am working on: I want to take the “best” stations across the lovely American desert southwest and compare the “raw” with the “not raw”, that is altered. I started with one station in Az and the results are so preposterous I am hesitant to even comment until I do some more checking, and (far) more important, thinking.

    Thanks in advance!

    • John Silver says:

      Look at slide 52 in Anthony Watts’:


      Rural MMTS, no Airports is the only data that isn’t junk.
      The difference between the no junk data and the NOOA “data” is the difference between 0.032 and 0.300, an order of magnitude.

    • Mark Albright says:

      Douglas ASOS is a first order climate observing site in SE Arizona. At the end of 2011 we were presented with these statistics concerning unusual warmth in Douglas AZ in a record report issued by the Tucson WFO:


      Well, maybe not! It now seems likely the Douglas AZ (KDUG) temperature sensor exhibited a +3 deg F warm bias from August 2011 through Feb 2012. Near the end of February 2012 the ASOS temperature sensor was replaced which seems to have corrected the problem of anomalously warm temperatures. This can be demonstrated by comparing daily max temperature measurements from KDUG with those from the Bowie 23 SSE regional Climate Reference Network (CRN) site (BWEA2) at the base of the Chiricahua Mtns in SE Arizona:

      KDUG elevation 4150 ft
      BWEA2 elevation 5150 ft

      TMAX: KDUG-BWEA2 (deg F)
      Jan 2011 6.3
      Feb 6.1
      Mar 6.1
      Apr 5.6
      May 5.6
      Jun 5.9
      Jul 6.2
      —-> Warm bias begins?
      Aug 8.4
      Sep 8.3
      Oct 9.8
      Nov 9.4
      Dec 8.8
      Jan 2012 9.9
      Feb 9.5
      —-> Temperature sensor replaced
      Mar 6.5
      Apr 6.9
      May 6.3
      Jun 6.1
      Jul 5.7
      Aug 1-13 5.5

  2. RokShox says:

    Freezing my ass off in Ft Collins today. OT, but good grief.

    • Ernest Bush says:

      Check the rest of the week at Weather Street. It’s only marginally better. I would rather put up with 110 degrees here in Yuma. At least I can sit out comfortably in the early morning hours. We’re back to “it’s a dry heat” this summer, so far, with humidity in single digits in the afternoon. This year has seen higher than normal temps so far and reminds me of the temps and humidity of the early 1990s. Maybe it’s welcome to a El Nino kind of year.

      • Gail Combs says:

        Same here in NC. After a very cold start we have seen three days @ 91 °F so far. Last year we had 4 days of 91 °F plus one day @ 95 °F for the entire summer. (Until they mucked with the temp record and added another ten days over 90 °F)

  3. tom0mason says:

    Steve, are you sure that Zeke and Mosher are aiming at the same goal as you here?
    If so then apparently Zeke and Mosher do not understand the concepts of verify and validate within the realms of the scientific method.

  4. Stephen Richards says:

    gregole says:

    June 8, 2014 at 4:37 am

    Mosher was turned by the fame of the BEST data analysis before that he appeared to be reasonably sensible. In fact, several years ago I thought he was really quite logical. Zeke How’syerfather is another proposition, IMHO. He has carried the AGW baggage from the outset and pushes the agenda as much as he can.

    • kuhnkat says:

      MoshPup has always been convinced of the danger of CO2. His most favorite statement was all you needed to know about Gorebull Warming was Radiative Transfer Equations.

      He was more reasonable in the past. Hard to say if he is becoming desperate also or whether he just needs to show appropriate religious zeal to get on the gravy train of Best, whose head has also ALWAYS believed CO2 is the most dangerous issue humanity has to face!!

  5. Billy Liar says:

    Mosher has an extraordinarily eclectic background:


  6. Eliza says:

    Posted thia at WUWT
    Steven Goddard =1, Zeke + Mosher = 0 science value
    As of today Zeke and Mosher should be considered warmist trolls with entertainment value only. Somewhat similar to William Conolley at most. LOL.
    After this is all over in 5 years they will fade away into nothingness just like the famous “Phil” at Lucia’s babbling away about disappearing arctic ice about 5 years ago was 100% wrong. We haven’t heard from him in years LOL

    Nb” The trouble with “lukewarmers” is that they too are loosing the battle and are just beginning to come to terms with it That is why they do not like your site or for that matter WUWT showing a cooling in USA temps.LOL (ie most a “Lucia’s” site are lukewarmers and in my view is one of the worst climate sites Ive ever had the experience to come accross with incredible stupid security issues and banal irrelevant subjects except their monthlytemp bet which 99% lose every time. hahaha

  7. Steve, Any knowledge about physical world around us can only be extracted from the data generated by the calibrated instrument, in this case thermometer, and NOT by calculating. If you read the first paper ever published that does proper numerical analysis of the daily Tmax/Tmin data, excluding all missing data, you will see that every single year, as represented by 365 Tmax and 365 Tmin reading has unique fingerprint. Free pdf can be found on http://www.l4patterns.com. Enjoy. Dr Darko Butina

  8. Mark Albright says:

    I have plotted 82 years of nearly complete daily max temperature data from the Salem Oregon Airport. After considerable warming from about 1976-1992, the past twenty years have seen pronounced cooling with a small cooling trend (red line) across all 82 years. I have chosen Max temperature since it is more representative of a deeper layer of the atmosphere than min temperature. In addition, max temperature is generally less sensitive than min temperature to urban heat island effects. 1934, 1958, and 1992 were all very warm years at Salem, with 1934 the warmest of all 82 years from 1932-2013. Observations began in Aug 1928 at Salem Airport, but due to a considerable number of missing observations, I have chosen not to include 1929, 1930, and 1931.

    I like to work with airport data since there is generally no time of observation adjustment to worry about and there is virtually no missing data.

  9. emsnews says:

    It is obvious that the 100 year high was in the 1930’s Dust Bowl Years.

    And we have been in a decline since then with small uphill events but the trend has been lower sun spot activity and a gradual dropping of the overall temperatures. This is hard to notice except years when the sun really goes quiet then it is very obvious like this spring.

    This was one of the hardest springs I can remember and I recall some hard springs mainly in the mid 1970’s.

  10. Gail Combs says:

    A History of Solar Activity over Millennia

    Ilya G. Usoskin
    Sodankyl ̈ Geophysical Observatory (Oulu unit)
    FIN-90014 University of Oulu, Finland

    Leif S. Blows this paper off but I like it because they use more than one independent method to validate the results.

    3.7 Verification of reconstructions
    Because of the diversity of the methods and results of solar-activity reconstruction, it is vitally important to verify them. Even though a full verification is not possible, there are different means of indirect or partial verification, as discussed below. Several solar-activity reconstructions on the millennium timescale, which differ from each other to some degree and are based on terrestrial cosmogenic isotope data, have been published recently by various groups. Also, they may suffer from systematic effects. Therefore, there is a need for an independent method to verify/calibrate these results in order to provide a reliable quantitative estimate of the level of solar activity in the past, prior to the era of direct observations….

    3.7.1 Comparison with direct data

    The most direct verification of solar-activity reconstruction is a comparison with the actual GSN sunspot data for the last few centuries. However, regression-based models (see Section 3.5.1) cannot be tested in this way, since it would require a long set of independent direct data outside the “training” interval. It is usual to include all available data into the “training” period to increase the statistics of the regression, which rules out the possibility of testing the model. On the other hand, such a comparison to the actual GSN since 1610 can be regarded as a direct test for a physics-based model since it does not include phenomenological links over the same time interval. The period of the last four centuries is pretty good for testing purposes since it includes the whole range of solar activity levels from the nearly spotless Maunder minimum to the modern period of a very active sun.

    Then add in William McClenney’s comment about the Little Ice Age being at half precession, about when the Holocene should have ended….

    I often wonder if the movers and shakers are… “Hey LOOK a squirrel!”

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s