Andrew Gelman Quote: "If someone does a study which, for statistical ..."

Choose a background or upload your own photo, then download a shareable quote image.

Upload background image Your file stays in the browser; nothing is sent to the server.

Quote

If someone does a study which, for statistical reasons, I think is hopelessly underpowered or nonidentified, my best and most useful advice will not be tips on how to calculate p-values better, or how to construct an explanation for some particular data pattern. Rather, my advice will be to start over, to reconsider what you think you already know, maybe to question some prominent work in your subfield, and quite possibly to think a lot harder about measurement, and about the relation of your data to your underlying constructs of interest.
Andrew Gelman / Statistician
Data
Starting Over
Thinking
Copy Quote

Only Text Quote

If someone does a study which, for statistical reasons, I think is hopelessly underpowered or nonidentified, my best and most useful advice will not be tips on how to calculate p-values better, or how to construct an explanation for some particular data pattern. Rather, my advice will be to start over, to reconsider what you think you already know, maybe to question some prominent work in your subfield, and quite possibly to think a lot harder about measurement, and about the relation of your data to your underlying constructs of interest.
⇛ Andrew Gelman (Statistician)

Copy Quote Text

I just want to help people do better research.

Andrew Gelman Statistician

Authors of published papers and editors of scientific journals can, unfortunately, be slow to come to terms with criticism, and it's good that we can use blogs to express specific criticisms of published articles and to use social media to disseminate these criticisms.

Andrew Gelman Statistician

The man who has successfully solved the problem of his relations with the two worlds of data and symbols is a man who has no beliefs. With regard to the problems of practical life he entertains a series of working hypotheses, which serve his purposes, but are taken no more seriously than any other kind of tool or instrument. In other words, symbols should never be raised to the rank of dogmas, nor should any system be regarded as more than a provisional convenience.

Aldous Huxley Writer

A ten per cent reduction in military expenditures per year would be reasonable, coupled with a programme of retraining the workforce and redirecting the resources in a manner that creates employment and advances social welfare. I also encourage all States to contribute to the UN's annual Report on Military Expenditures by submitting complete data on national defence budgets.

Alfred-Maurice De Zayas Lawyer

Nuclear weapons production and testing has involved extensive health and environmental damage .... One of the most remarkable features of this damage has been the readiness of governments to harm the very people that they claimed they were protecting by building these weapons for national security reasons. In general, this harm was inflicted on people in disregard of democratic norms. Secrecy, fabrication of data, cover-ups in the face of attempted public inquiry, and even human experiments without informed consent have all occurred in nuclear weapons production and testing programs.

Arjun Makhijani

Whether we look at capitalism, taxes, business, or government, the data show a clear and consistent pattern: 70 percent of Americans support the free enterprise system and are unsupportive of big government.