CrossFit | 190402
Tuesday

190402

Workout of the Day

5

Rest Day

Post thoughts to comments.

The Cardinal Sins of Skewed Research, Part 2: Racking

4

Drs. Mary Dan and Michael Eades review the practice of “racking,” one of the cardinal sins of scientific research. In this sin, so termed for its similarity to the practices of medieval inquisitors, scientific data is “tortured until it confesses” a result desired by the researcher (or the researchers’ funder). Among the data manipulations discussed are the selective practices of axis stretching — spacing intervals on a graph to result in a more pronounced visual effect — and the use of relative risk reduction to obscure actual absolute results.

Read MoreThe Cardinal Sins of Skewed Research, Part 2: Racking

Comments on 190402

9 Comments

Comment thread URL copied!
Matthieu Dubreucq
December 25th, 2019 at 11:36 pm
Commented on: The Cardinal Sins of Skewed Research, Part 2: Racking

I never even though that you could choose to show a relative benefit v.s. a absolute for a drug study. I think that making it monitory to describe and interpret the data in absolute would make it easier to understand for the public (and even doctors who probably don't always have the time to go see the full study).

Comment URL copied!
Sam Pat
April 6th, 2019 at 2:55 am
Commented on: 190402

Rest Day

Comment URL copied!
Katina Thornton
April 3rd, 2019 at 9:42 pm
Commented on: The Cardinal Sins of Skewed Research, Part 2: Racking

This is very important information, particularly if you haven't had a statistics course and are not familiar with the various presentations of data. Relative risk seems disingenuous for decision-making about whether to undergo a therapy or not, hence the moniker "racking" for stretching the truth.

Comment URL copied!
Jesse Ward
April 3rd, 2019 at 9:25 pm
Commented on: The Cardinal Sins of Skewed Research, Part 2: Racking

Thank you very much for putting this out there. The final part about switching over the data on the rates of side effects made it immediately more clear as to why data racking is inherently unethical. The ultimate question I suppose is, which way should data be presented? Both sides, all sides, in a display where people can mess with the axis to see what they want to see? Or is it entirely up to the researcher to have enough scruples to know when he is fleecing the people with his/her statistics, or to know what a meaningful effect size actually is?

Comment URL copied!
Mary Dan Eades
April 5th, 2019 at 4:04 pm

Jesse Ward~ If the data is presented in absolute numbers as absolute risk we'd think it more transparent and ethical, because there is no attempt on the part of the concluders to stretch for something that isn't really there. It would be fine to say something like 'the x more deaths in the treatment group represent a y% reduction of risk, but in absolute numbers the risk in either group is very small.' In the end, researchers ought to feel honor bound to the cause of science to present as honest a representation of what's been uncovered as is possible. At least in a perfect world.

Comment URL copied!
Stacey Carpenter
April 3rd, 2019 at 12:21 pm
Commented on: 190402

Strict Pullups practice ppp program

3 goblet 35# wallsit

Then 4 rounds 100 single jump 400m 35# sled job 4th round increased weight Easton rode the sled (approx 85# )and 200 singles then 200m big ass tire flip (approx. 200#tire)

Comment URL copied!
Olivia Leonard
April 3rd, 2019 at 1:54 am
Commented on: 190402

For additional reading, the New York Times published a cool ‘Letter of Recommendation’ earlier this year on Old English poetry and “kennings”:


Kennings are essentially portmanteaus, Old English words made of two nouns that have been mashed together to create a new one…kennings were metaphors of circumlocution, a way to talk around the thing you want to represent. For example, hron means “whale.” Rad means “a road,” or “a path.” Put them together and you get hronrad, or “whale-road,” which means “the sea.” The ocean is not an empty space, hronrad says – it belongs to the whale. Human beings crisscross it on our adventures, but when we do it, we are trespassing on a very large mystery.


https://www.nytimes.com/2019/01/04/magazine/letter-of-recommendation-old-english.html

Comment URL copied!
Melanie Bibens
April 2nd, 2019 at 11:12 am
Commented on: 190402

But the sailor was well rested.

Comment URL copied!
Diego de León
April 2nd, 2019 at 10:31 am
Commented on: 190402

Smooth Seas Never Made A Skilled Sailor

Comment URL copied!