TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Why Most Published Research Findings Are False

89 pointsby marciovm123over 14 years ago

18 comments

llimllibover 14 years ago
The author's research is discussed in an excellent Atlantic article that many may find more accessible: <a href="http://www.theatlantic.com/magazine/archive/2010/11/lies-damned-lies-and-medical-science/8269/" rel="nofollow">http://www.theatlantic.com/magazine/archive/2010/11/lies-dam...</a>
评论 #1826169 未加载
vitaminjover 14 years ago
In statistics, you're supposed to come up with a statistical model first before running regressions on the data. But quite a few papers I've read (especially in finance) seem to go the other way around, i.e.<p>They run regressions on a data set, adding and subtracting independent variables until the t values and standard errors start looking good.<p>Then they construct the linear model, assume the Gauss-Markov assumptions and sometimes (though not always) try to explain the causal relationship between the variables.<p>This is obviously very wrong and nobody has any clue what the distribution of the least squares estimators to these models are. But I've seen plenty of examples of this, which is enough to void the results of the paper (even if the model they come up with is somewhat plausible).
评论 #1825254 未加载
评论 #1826065 未加载
jonhendryover 14 years ago
Well, that's why the whole "replication" thing is important. One published result is interesting, but rarely definitive, and possibly wrong. (Or at least unusual for possibly difficult-to-determine reasons.)<p>This is another good reason to ignore the media hype for every new paper that comes out. (Besides the fact that journalists perform lossy compression on data.)<p>But it seems like it's how science is supposed to work: publish your results, see if others confirm your findings, because <i>you might be wrong</i> even if you seem to have done everything correctly and honestly to the best of your ability.
评论 #1825737 未加载
ivankover 14 years ago
Related: "Frequentist Statistics are Frequently Subjective" <a href="http://lesswrong.com/lw/1gc/frequentist_statistics_are_frequently_subjective/" rel="nofollow">http://lesswrong.com/lw/1gc/frequentist_statistics_are_frequ...</a>
ramanujanover 14 years ago
This paper has gotten way too much press for an oversimplified model of science. Here's the thing: if results hold up to scrutiny, the authors are eager to share code and plasmids/samples. If not, they are a lot more squirrelly. Outside replication is what keeps the machine moving forward, is fairly readily proxied by citation rates, and yet is not captured by Ioannidis' simple model.
评论 #1825421 未加载
评论 #1825745 未加载
评论 #1825314 未加载
_deliriumover 14 years ago
This is an interesting followup as well: <a href="http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1808082/" rel="nofollow">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1808082/</a>
zbanksover 14 years ago
Self reference much? This <i>is</i> published research...<p>Clearly these findings are false... or maybe not? Dammit. <a href="http://en.wikipedia.org/wiki/Liar_paradox" rel="nofollow">http://en.wikipedia.org/wiki/Liar_paradox</a>
评论 #1825123 未加载
elbenshiraover 14 years ago
First of all, the author of this piece works in Department of Hygiene and Epidemiology. Research is done differently across different disciplines, so it's dangerous to try to expand this to other disciplines. For example, some fields find alpha &#60; 0.05 acceptable and other fields do not.<p>But research is very weird indeed. The more conference/journal articles you read, the less you trust them. I mean, say a field accepts results alpha &#60; 0.05. This means that 5% of everything shown is wrong.<p>Feel free to correct me if you have a better grasp of statistics find what I say to be wrong.
评论 #1825145 未加载
评论 #1825115 未加载
评论 #1827385 未加载
评论 #1825110 未加载
评论 #1825154 未加载
stretchwithmeover 14 years ago
Its not surprising that misrepresentation has become so common in what is now a largely political industry.
评论 #1825639 未加载
marzeover 14 years ago
So what are the implications of this information to the average individual? He is basically saying that the conventional wisdom on medical questions is most often incorrect.
smakzover 14 years ago
For some reason I was reminded of this blog post:<p><a href="http://jsomers.net/blog/it-turns-out" rel="nofollow">http://jsomers.net/blog/it-turns-out</a>
ck2over 14 years ago
It's because researchers slack just like everyone else at their jobs and need to pay the bills in the meanwhile. Now imagine your doctor or law enforcement and the mess they cause when they slack and cut corners just to produce "product" and justify their jobs.
drewseover 14 years ago
This title yelled "paradox!" at me. It's funny to see it coming from a ".gov" website.<p>For those who need clarification, if this published research and its title are true, than it is saying that research like itself are usually false. This contradicts the original assumption that it is true.<p>If this published research and its title are false, than research like itself is usually true since what it's saying must be wrong. This contradicts the original assumption that it is false.
评论 #1825443 未加载
mkramlichover 14 years ago
The OA has most likely reached a false conclusion.
fleitzover 14 years ago
Do the paper's findings apply to the paper itself?
fauigerzigerkover 14 years ago
So if this research is not false (unlikely according to the author) then mankind would be moving backwards, unless non scientific reasoning compensates for the failure of science. Medical treatment would get constantly worse, people would be misdiagnosed and mistreated more than ever, death rates after cancer and cardiac events would rise.
评论 #1825570 未加载
runcible_sporkover 14 years ago
And grant writers and heads of research departments everywhere disagree.
jakerocheleauover 14 years ago
This is also a published article and the same principles should be applied here, no?