Why Most Published Research Findings Are False
A very interesting paper with devastating conclusions:
Why Most Published Research Findings Are False
John P. A. Ioannidis
PLoS Med, August 2005
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1182327/
Abstract:
There is increasing concern that most current published research findings are false. The probability that a research claim is true may depend on study power and bias, the number of other studies on the same question, and, importantly, the ratio of true to no relationships among the relationships probed in each scientific field. In this framework, a research finding is less likely to be true when the studies conducted in a field are smaller; when effect sizes are smaller; when there is a greater number and lesser preselection of tested relationships; where there is greater flexibility in designs, definitions, outcomes, and analytical modes; when there is greater financial and other interest and prejudice; and when more teams are involved in a scientific field in chase of statistical significance. Simulations show that for most study designs and settings, it is more likely for a research claim to be false than true. Moreover, for many current scientific fields, claimed research findings may often be simply accurate measures of the prevailing bias. In this essay, I discuss the implications of these problems for the conduct and interpretation of research.
(with thanks to André Falcão)
Why Most Published Research Findings Are False
John P. A. Ioannidis
PLoS Med, August 2005
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1182327/
Abstract:
There is increasing concern that most current published research findings are false. The probability that a research claim is true may depend on study power and bias, the number of other studies on the same question, and, importantly, the ratio of true to no relationships among the relationships probed in each scientific field. In this framework, a research finding is less likely to be true when the studies conducted in a field are smaller; when effect sizes are smaller; when there is a greater number and lesser preselection of tested relationships; where there is greater flexibility in designs, definitions, outcomes, and analytical modes; when there is greater financial and other interest and prejudice; and when more teams are involved in a scientific field in chase of statistical significance. Simulations show that for most study designs and settings, it is more likely for a research claim to be false than true. Moreover, for many current scientific fields, claimed research findings may often be simply accurate measures of the prevailing bias. In this essay, I discuss the implications of these problems for the conduct and interpretation of research.
(with thanks to André Falcão)
A Style Guide for Students Writing Papers and Reports
A Style Guide for Students Writing Papers and Reports
Gernot Heiser
muito bom
http://www.cse.unsw.edu.au/~gernot/style-guide.html
Gernot Heiser
muito bom
http://www.cse.unsw.edu.au/~gernot/style-guide.html
Research funding: Making the cut
Research funding: Making the cut
Published online 22 September 2010 | Nature 467, 383-385 (2010) | doi:10.1038/467383a
Careers are made and broken by grant-funding committees. So how are the key decisions really made?
Kendall Powell
http://www.nature.com/news/2010/100922/full/467383a.html
Published online 22 September 2010 | Nature 467, 383-385 (2010) | doi:10.1038/467383a
Careers are made and broken by grant-funding committees. So how are the key decisions really made?
Kendall Powell
http://www.nature.com/news/2010/100922/full/467383a.html
How to get your papers accepted
Muito bom, leitura essencial para alunos de doutoramento:
How to get your papers accepted
só os tópicos:
1. Spellchcek.
2. Get the English right.
3. Make the figures readable!
4. "Related work" is not just a list of citations.
5. Make sure the intro kicks ass.
6. Get to the point.
7. State your contributions!
8. Don't bullshit.
How to get your papers accepted
só os tópicos:
1. Spellchcek.
2. Get the English right.
3. Make the figures readable!
4. "Related work" is not just a list of citations.
5. Make sure the intro kicks ass.
6. Get to the point.
7. State your contributions!
8. Don't bullshit.
Portuguese Research-Universities: Why Not The Best?
Apresentação:
http://www.math.ist.utl.pt/~rfern/athans/
Artigo:
ATHANS, Michael (2002), "Universidades portuguesas: por que não as melhores?”, Gazeta de Física, vol.25, fascículo 1, Abril. Disponível aqui (PDF)
http://www.math.ist.utl.pt/~rfern/athans/
Artigo:
ATHANS, Michael (2002), "Universidades portuguesas: por que não as melhores?”, Gazeta de Física, vol.25, fascículo 1, Abril. Disponível aqui (PDF)
sobre o processo de peer review
Conference reviewing considered harmful
ACM SIGOPS Operating Systems Review
Volume 43 , Issue 2 (April 2009)
This paper develops a model of computer systems research to help prospective authors understand the often obscure workings of conference program committees. We present data to show that the variability between reviewers is often the dominant factor as to whether a paper is accepted. We argue that paper merit is likely to be zipf distributed, making it inherently difficult for program committees to distinguish between most papers. We use game theory to show that with noisy reviews and zipf merit, authors have an incentive to submit papers too early and too often. These factors make conference reviewing, and systems research as a whole, less efficient and less effective. We describe some recent changes in conference design to address these issues, and we suggest some further potential improvements.
ACM SIGOPS Operating Systems Review
Volume 43 , Issue 2 (April 2009)
This paper develops a model of computer systems research to help prospective authors understand the often obscure workings of conference program committees. We present data to show that the variability between reviewers is often the dominant factor as to whether a paper is accepted. We argue that paper merit is likely to be zipf distributed, making it inherently difficult for program committees to distinguish between most papers. We use game theory to show that with noisy reviews and zipf merit, authors have an incentive to submit papers too early and too often. These factors make conference reviewing, and systems research as a whole, less efficient and less effective. We describe some recent changes in conference design to address these issues, and we suggest some further potential improvements.
Research Evaluation for Computer Science
artigo interessante na Communications of the ACM:
Research Evaluation for Computer Science
Reassessing the assessment criteria and techniques traditionally used in evaluating computer science research effectiveness.
Bertrand Meyer, Christine Choppy, Jørgen Staunstrup, Jan van Leeuwen
Communications of the ACM
Vol. 52 No. 4, Pages 31-34
Research Evaluation for Computer Science
Reassessing the assessment criteria and techniques traditionally used in evaluating computer science research effectiveness.
Bertrand Meyer, Christine Choppy, Jørgen Staunstrup, Jan van Leeuwen
Communications of the ACM
Vol. 52 No. 4, Pages 31-34
A Arte de Escrever Artigos Científicos
"A Arte de Escrever Artigos Científicos"... para iniciados:
http://homepages.dcc.ufmg.br/~mirella/doku.php?id=escrita
(Prof. Mirella M. Moro, UFMG)
http://homepages.dcc.ufmg.br/~mirella/doku.php?id=escrita
(Prof. Mirella M. Moro, UFMG)
orientação de alunos de doutoramento
Dois artigos muito interessantes sobre o assunto. Tirados da CACM de Março 2009:
Your Students Are Your Legacy
This Viewpoint boils down into a few magazine pages what I've learned in my 32 years of mentoring Ph.D. students.
David A. Patterson
Pages 30-33
Advising Students for Success
Some advice for those doing the advising (and what the advisors can learn from the advisees).
Jeffrey D. Ullman
Pages 34-37
reviews de artigos
Genial:
How NOT to review a paper: the tools and techniques of the adversarial reviewer
Graham Cormode
How NOT to review a paper: the tools and techniques of the adversarial reviewer
Graham Cormode
ACM SIGMOD Record archive
Volume 37 , Issue 4 (December 2008)
Pages 100-104
rankings de universidades
BREAKING RANKS: ASSESSING QUALITY IN HIGHER EDUCATION
The OECD international forum designed for higher education institutions
imhe info Dec. 2008
The OECD international forum designed for higher education institutions
imhe info Dec. 2008
a good paper, according to the SOSP cfp
A good paper will demonstrate that the authors:
- are attacking a significant problem,
- have devised an interesting, compelling solution,
- have demonstrated the practicality and benefits of the solution,
- have drawn appropriate conclusions,
- have clearly described what they have done, and
- have clearly articulated the advances beyond previous work.
source: SOSP'09 CFP
Subscrever:
Mensagens (Atom)