1,500 scientists lift the lid on reproducibility

**pseudolus** · 04-06-2016, 03:19 AM

1,500 scientists lift the lid on reproducibility : Nature News & Comment

1,500 scientists lift the lid on reproducibility
Survey sheds light on the ‘crisis’ rocking research.

No... Fraud in science? Never.

**pulvarien** · 04-06-2016, 05:41 AM

A few years ago I read an article from forbes, its a magazine targeting businesses as there customer a serious hard headed group who want the truth since there businesses success depends on it.

The article was about the university of Illinois scientific article where 97 per of climate scientists believe in global warming, a figure thrown in our faces over and over. This has been the only article I ever saw giving the actual numbers and questions in the scientific article.

10300 climate scientists and scientists associated with global warming were sent the questionnaire. Impressive isn't it 97 per of 10300, EXCEPT over 7000 didn't answer the questionnaire so omg were now down to 97 per of just over 30 per and that was never explained to anyone. And then it was never clearly stated that of the over 3000 who did answer the questionnaire over 3000 responses were disqualified for one reason or another.

Soooo just how many responses is the 97 percent of all climate scientists actually based on. Drum roll please 79 is the magic number. 77 out of 79 answered the questionnaire in a recognizable useable way supporting global warming. In other words aprroxiametley 10200 pluss climate scientists were so disgusted or turned off bye this questionnaire that they ignored it or turned in answers that were unintelligible. Any sane person with a little thinking that 10200 out of 10300 answering the questionnaire in this way leads us to think that 97 percent actually think the opposite in regards to global warming.

But the greens here used Mark Twains rule to win the day, lies damn lies and statistics. And the very fact that greens/democrats throw such information in our faces over and over supported bye the full left wing media should set off the alarm bells to people. In fact the greens hold science in contempt and use the Soviet Unions opinion of it. Science must fit the soviet unions political philosophy or where it doesn't it much change to fit it.

**Cujo** · 04-06-2016, 07:44 AM

Here we go.

**baldrick** · 04-06-2016, 10:35 AM

Originally Posted by pseudolus

reproducibility

because there is no money available to redo experiments , especially if you have P hacked to give the result you desired

and no one becomes famous and wins the nobel prize for being the second person to discover something

Statisticians Found One Thing They Can Agree On: It?s Time To Stop Misusing P-Values | FiveThirtyEight

How many statisticians does it take to ensure at least a 50 percent chance of a disagreement about p-values? According to a tongue-in-cheek assessment by statistician George Cobb of Mount Holyoke College, the answer is two … or one. So it’s no surprise that when the American Statistical Association gathered 26 experts to develop a consensus statement on statistical significance and p-values, the discussion quickly became heated.

It may sound crazy to get indignant over a scientific term that few lay people have even heard of, but the consequences matter. The misuse of the p-value can drive bad science (there was no disagreement over that), and the consensus project was spurred by a growing worry that in some scientific fields, p-values have become a litmus test for deciding which studies are worthy of publication. As a result, research that produces p-values that surpass an arbitrary threshold are more likely to be published, while studies with greater or equal scientific importance may remain in the file drawer, unseen by the scientific community.

get published in a scientific journal and win a seat on a morning television show

http://projects.fivethirtyeight.com/p-hacking/

**BobR** · 04-06-2016, 10:43 AM

John Oliver did a great piece (as usual) about junk science vs. real science, and the selective and purposely misleading use of only part of, or a short statement from a scientific study.

Amusing and educational, it is well worth watching.

**thailazer** · 04-06-2016, 11:08 AM

I got fired from a Biosensor start up with a lot of promise in 2013 when I discovered that all the data taken over three years was biased with a mass transport effect making it useless. Company principle didn't like that bad news as the company funding was based on the data. It was certainly something that we could have dealt with, but spin is everything with start ups. Company ended up on the rocks.

**pseudolus** · 04-06-2016, 12:23 PM

Originally Posted by baldrick

because there is no money available to redo experiments , especially if you have P hacked to give the result you desired

Indeed - funding would be critical and I doubt that who ever is funding an experiment would continue footing the bill once a desired outcome has been produced once. Perhaps this why FRAUD counts in 70% of the respondents answers though.

**Cujo** · 04-06-2016, 12:42 PM

Originally Posted by BobR

John Oliver did a great piece (as usual) about junk science vs. real science, and the selective and purposely misleading use of only part of, or a short statement from a scientific study.

Amusing and educational, it is well worth watching.

Excellent.

**nidhogg** · 04-06-2016, 02:00 PM

Originally Posted by baldrick

Originally Posted by pseudolus

reproducibility

because there is no money available to redo experiments

https://osf.io/e81xl/wiki/home/

https://osf.io/ezcuj/wiki/home/

**thaimeme** · 04-06-2016, 05:19 PM

Science [especially the modern variety/mindset].

Best guess work, is all.

**pseudolus** · 04-06-2016, 05:45 PM

Originally Posted by thaimeme

Best guess work, is all.

Try and get a result that the people funding it desire. If you get lucky, then stop there and don't ever try to repeat it.

Thread: 1,500 scientists lift the lid on reproducibility

Thread Tools

Display

1,500 scientists lift the lid on reproducibility

forbes business magazine article

Thread Information

Users Browsing this Thread

Posting Permissions