Archive for the ‘Data science’ Category

#4 – Why I’m lukewarm to climate change…

June 9, 2017

Reason #4: Dinking with the data


I’m neither a denier nor a zealot …  so, according to British writer (& phrase-coiner) Matt Ridley, I’m a “lukewarmer”.

In a prior posts, I covered:

Reason #1Unsettling Science … I’ve gotten  cognitive whiplash from “Ice Age” u-turning to  “Global Warming”  …  which was slowed by an “18-year Pause” … and then wrapped in a catch-all “Climate Change”.

Reason #2Al Gore and his doomsday prediction …  in 2016 we passed his point of no return towards a true planetary emergency  … without the planet melting or exploding … and with Manhattan still above water (I think).

Reason #3The “97% of scientists” baloney … an oft-repeated claim based on bad data science: a very small,  hand-picked sample of climate change papers, not a projectable sample of scientists … which literally put words into authors’ mouths … i.e. bad data science.

Let’s move on…


Reason #4: Dinking with the data

Here’s a case in point:

Remember the 18-year “”Global Warming “Pause”?

Raw recorded temperature data slowed that temperatures had flattened out for a recent 18 year period.

English translation: no evidence of global warming.



Well, in 2015,  a team of scientists from the National Oceanic and Atmospheric Administration’s (NOAA) National Centers for Environmental Information* (NCEI) made some “adjustments” to global surface temperature data. Source

English translation: they dinked with the data.

Among the results:  the 18-year pause that was evident in the raw data went away (chart above).

More broadly, the revised (i.e. manually manipulated) data reversed an 80-year cooling trend evident in the raw data … and validated a warming trend that was not  evident until the temperature data was revised. Source

As Gomer Pyle would say: “Surprise, surprise, surprise.”

Scientists that I know wouldn’t think of manually “adjusting” their data when they didn’t get the results they expected.

That would be bad science, right?

But, it doesn’t seem to deter the climate scientists.

Maybe the adjustments are legit … I don’t know.

Nonetheless, they seem pretty fishy to me.

And, gives me another reason to be lukewarm.



Follow on Twitter @KenHoma            >> Latest Posts


Nums: Ask why … not just how many.

April 10, 2013

Some highlights from an HBR article:  The Hidden Biases in Big Data 

These days the business and management science worlds are focused on how large datasets can decode consumers’ behavior patterns … enabling marketers to laser-target high potential prospects with finely-honed messages, offers, and “attention”.

“Big data” … becomes problematic when it adheres to “data fundamentalism” … the notion that correlation always indicates causation, and that massive data sets and predictive analytics always reflect objective truth … that  “with enough data, the numbers speak for themselves.”


Big data has hidden biases in both collection methods and analysis …