Posts Tagged ‘ Errors ’

Dead man tells no tales but dead statistician had the story down

June 12, 2018
By
Dead man tells no tales but dead statistician had the story down

Kaiser Fung, author of Numbersense and founder of Principal Analytics Prep, explains the preliminary finding about the death of a Tesla driver, and warns about drawing the wrong conclusions due to a biased sample.

Read more »

Dead man tells no tales but dead statistician had the story down

June 12, 2018
By
Dead man tells no tales but dead statistician had the story down

Kaiser Fung, author of Numbersense and founder of Principal Analytics Prep, explains the preliminary finding about the death of a Tesla driver, and warns about drawing the wrong conclusions due to a biased sample.

Read more »

Misinformed, and mal-intentioned: the proposed EPA policy on disclosures

May 29, 2018
By

EPA commissioner Scott Pruitt sinks to a new low in his dogged campaign against evidence-based decision-making. (See my previous posts in which I dissected his other tactics here and here.) He directs his agency to propose new rules for disclosure of data and methods for climate science, placing himself in charge of opining whether a given study has enough disclosure to be allowed into evidence. Slate’s Daniel Engber, someone I…

Read more »

Misinformed, and mal-intentioned: the proposed EPA policy on disclosures

May 29, 2018
By

EPA commissioner Scott Pruitt sinks to a new low in his dogged campaign against evidence-based decision-making. (See my previous posts in which I dissected his other tactics here and here.) He directs his agency to propose new rules for disclosure of data and methods for climate science, placing himself in charge of opining whether a given study has enough disclosure to be allowed into evidence. Slate’s Daniel Engber, someone I…

Read more »

Laplace on behavioral psychology channeled through Miller and Gelman

April 17, 2018
By

Kaiser Fung, founder of Principal Analytics Prep, and author of Numbersense, discusses a recent paper by Miller and Gelman about Laplace's view on cognitive illusions.

Read more »

The discontent of engineering uncertainty

March 14, 2018
By
The discontent of engineering uncertainty

Kaiser Fung, author of Numbersense and founder of Principal Analytics Prep, warns against over-interpreting the precision of formula outputs, and advocates embracing uncertainty. He is reacting to passages from the book, Algorithms to Live By.

Read more »

The discontent of engineering uncertainty

March 14, 2018
By
The discontent of engineering uncertainty

Kaiser Fung, author of Numbersense and founder of Principal Analytics Prep, warns against over-interpreting the precision of formula outputs, and advocates embracing uncertainty. He is reacting to passages from the book, Algorithms to Live By.

Read more »

Visible and invisible errors, and the nefarious power of suggestion

December 20, 2017
By
Visible and invisible errors, and the nefarious power of suggestion

Kaiser Fung, founder of Applied Analytics at Columbia University and Principal Analytics Prep, the premier data analytics bootcamp from Harvard Business School Startup Studio, discusses how a software vendor uses the power of suggestion to seduce users into believing the accuracy of predictive analytics; and how such a tactic got exposed by the visibility of errors.

Read more »

Visible and invisible errors, and the nefarious power of suggestion

December 20, 2017
By
Visible and invisible errors, and the nefarious power of suggestion

Kaiser Fung, founder of Applied Analytics at Columbia University and Principal Analytics Prep, the premier data analytics bootcamp from Harvard Business School Startup Studio, discusses how a software vendor uses the power of suggestion to seduce users into believing the accuracy of predictive analytics; and how such a tactic got exposed by the visibility of errors.

Read more »

Overselling predictive models (Hint: future performance matters)

December 18, 2017
By

Kaiser Fung, author of Numbersense and founder of Principal Analytics Prep, discusses the rejection of a predictive model used to find vulnerable children at risk for child abuse in Chicago.

Read more »


Subscribe

Email:

  Subscribe