Ted et al., I have not finished reading the paper linked below, but it does look very interesting. I notice it is from 2005. A colleague recently sent me a news account of a recent study of bias in research reports. I can retrieve it if anyone would like to have a look.
It indicated that authors were choosing statistical tests to apply to their data according to the tests' reporting of 'significant' results. The levels of significance reported, based on some large number of research papers analyzed - may have been 1800 or so- did not fit a normal (Gaussian for those who persist in using the older terminology) distribution. I interpreted that statement to mean the significance levels did not fit a tail of a normal distribution. Such behavior would indicate the authors were picking which statistical test to perform from a set of tests for significance, and picking the one that would allow them to claim an 'important' finding.
For example, for a one-way designed experiment, a number of statisticians have each devised a test of significance, such as those of Newman-Keuls or Duncan. An author might find only one of the tests showed significance, and report the analysis of that test alone. Given that the tests are all trying to accomplish much the same thing, the probability of gross misjudgments or dangerous mistakes resulting would seem to be low. But the significance level analysis the study reports does indicate authors are consciously selecting tests which show their results are significant and dismissing tests which do not show their results are significant. Louis Hart
-----Original Message-----
From: TechNet [mailto:[log in to unmask]] On Behalf Of Theodore J Tontis
Sent: Thursday, April 09, 2015 4:54 PM
To: [log in to unmask]
Subject: Re: [TN] "Game Changer" solder paste?
I have a list of questions I would like to ask before accepting any of the information as fact. I am guessing, but I am willing to bet the information they are providing was taken in a controlled environment or had a very limited sample size. If it wasn’t, someone on this forum would have heard about or been part of the evaluation process.
Interestingly enough, I had to read the following for a research and writing class I am taking.
Why Most Published Research Findings Are False http://www.plosmedicine.org/article/fetchObject.action?uri=info:doi/10.1371/journal.pmed.0020124&representation=PDF
And
Secondary research : information sources and methods / David W. Stewart, Michael A. Kamins.
Ted T.
-----Original Message-----
From: TechNet [mailto:[log in to unmask]] On Behalf Of Nutting, Phil
Sent: Thursday, April 09, 2015 3:08 PM
To: [log in to unmask]
Subject: Re: [TN] "Game Changer" solder paste?
Steve,
I hope they bought you a real nice lunch too.
Phil
-----Original Message-----
From: TechNet [mailto:[log in to unmask]] On Behalf Of Steve Gregory
Sent: Thursday, April 09, 2015 3:27 PM
To: [log in to unmask]
Subject: [TN] "Game Changer" solder paste?
Hi All,
I'm wondering if I'm the only who is getting slammed by salespeople who are pushing this new GC10 solder paste from Loctite?
I know the proof is in the testing and qualifying, but they are making some pretty hefty claims about this paste, like you can leave it on the stencil for 3-days, or that you don't have to refrigerate it and it has a year shelf life.
http://www.eis-inc.com/files/pdf/supplier_showcase_page_downloads/loctite_electronics/henkel_ae_loctite_gc10_product_fact_sheet.pdf
Just curious if any of you have tried this stuff, and does it live up to it's claims?
Steve
--
This email and any attachments are only for use by the intended
recipient(s) and may contain legally privileged, confidential, proprietary or otherwise private information. Any unauthorized use, reproduction, dissemination, distribution or other disclosure of the contents of this e-mail or its attachments is strictly prohibited. If you have received this email in error, please notify the sender immediately and delete the original.
______________________________________________________________________
This email has been scanned by the Symantec Email Security.cloud service.
For more information please contact helpdesk at x2960 or [log in to unmask] ______________________________________________________________________
______________________________________________________________________
This email has been scanned by the Symantec Email Security.cloud service.
For more information please contact helpdesk at x2960 or [log in to unmask] ______________________________________________________________________
______________________________________________________________________
This email has been scanned by the Symantec Email Security.cloud service.
For more information please contact helpdesk at x2960 or [log in to unmask] ______________________________________________________________________
______________________________________________________________________
This email has been scanned by the Symantec Email Security.cloud service.
For more information please contact helpdesk at x2960 or [log in to unmask]
______________________________________________________________________
|
