A thorough treatment of how science goes bad

Nature did a very comprehensive essay, here, on the problems of unreliable science, fallacious thinking, biases, data torturing and other important matters.

I think in many instances, the author hit on essential matters related to doing good and reliable research.

The essay also suggested methods to help reduce confirmation bias, and the effects of intellectual passion.

As an example, the problems created by computers and the ‘just so’ results that can be achieved by parsing and slicing the data to get nothing more than elaborate confirmation biased results. Another Computer trap is the game of modeling that can be done with computers–a great opportunity to give answers that look like they are the result of robust analysis.

Computers can make data torturing easy.

Just redo and redo until you get something you like or know is right.

I was impressed, you will be too. A longer and better treatment is in the wonderful Judging Science by Foster and Huber. I provided a book review here.

I went to school on Milloy’s books that are on this web site on the left with covers. That is how I became a fan–when Milloy was writing for CATO.

The first books were CATO Books, Silencing Science, Science without Sense Then a few years later Junk Science Judo about scams and scares and Green Hell, about the environmental movement junk science and scaremongering.

Being a good skeptic about science is essential to adult functionality–if you are easily duped and don’t know how things work, you cannot be prudent.


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