Browse list of available series in The Biomedical & Life Sciences Collection
Recommend The Biomedical & Life Sciences Collection to your librarian
Request to be kept updated on The Biomedical & Life Sciences Collection
Apply for a free trial of The Biomedical & Life Sciences Collection
View all talks & series with full access

Guest (sample access)

Optional Login with Username


        
> Home  /  Biomedical & Life ...  /  Series  /  Design and Analysi...  /  Talk Details
SHARE:   Email via Outlook   Email via Web   Facebook   Twitter   |   more
Close SHARE
Please select one of the methods below to share the following page with your collegues:
Likelihood Ratios and the Strength of Statistical Evidence
Blogger Google Reader
Delicious Linked In
Digg MySpace
Favorites PDF Online
Gmail

Hello. As a guest, you do not have full access to this talk. Click the PLAY button below to watch the sample extract. Alternatively, you may login or review methods of obtaining more access.

    SPEAKER(S)

Prof. Jeffrey Blume - Brown University, USA

Jeffrey Blume received his PhD in Biostatistics from the Johns Hopkins School of Public Health where he was the recipient of a National Eye Institute Traineeship in Clinical Trials. He has extensive experience in the development, operation, analysis and methodological aspects of clinical trials. He has authored numerous peer-reviewed articles and regularly presents invited lectures on likelihood methods. Prof. Blume is co-founder and Chief Scientific Officer of Analytical Edge Inc., a software and consulting company focusing on likelihood methods for measuring the strength of statistical evidence. Prof. Blume is also Deputy Director of the Biostatistics and Data Management Center for the American College of Radiology Imaging Network (ACRIN), a NCI funded cooperative group that specializes in clinical trials evaluating new medical imaging technology.

Talk Online Publication: Oct 2007

TOPICS COVERED IN LIKELIHOOD RATIOS AND THE STRENGTH OF STATISTICAL EVIDENCE

Using likelihood ratios to measure the strength of statistical evidence in data - Paradigms for measuring statistical evidence: the three questions - Likelihood ratios - The law of likelihood - The likelihood principle - Misleading evidence - Probabilities of observing misleading evidence and their bounds - Sequential designs in the likelihood paradigm - Composite hypothesis and extensions - Example using real data from a well known clinical trial

How to cite this talk:
Blume, J. (2007), "Likelihood Ratios and the Strength of Statistical Evidence", in Berger, V. (ed.), Design and Analysis of Randomized Clinical Trials: Design, Analysis & Theory, The Biomedical & Life Sciences Collection, Henry Stewart Talks Ltd, London (online at http://hstalks.com/bio)

Direct talk access link:
http://hstalks.com/lib.php?t=HST44.1524_1_2&c=252

    DETAILED SLIDE INDEX

1. Introduction
2. Three questions
3. Hypothesis testing (1)
4. Hypothesis testing (2)
5. Significance testing (1)
6. Significance testing (2)
7. Bayesian inference (1)
8. Bayesian inference (2)
9. A diagnostic test (1)
10. A diagnostic test (2)
11. The law of likelihood
12. The law says
13. Degrees of strength
14. Three categories of the strength of evidence
15. Diagnostic test, revisited
16. A positive test result and disease presence
17. Irrelevant for data interpretation
18. The diagnostic test
19. Another diagnostic test
20. Question
21. Answer
22. An observed positive result can be misleading
23. The key to the argument
24. Three key concepts (1)
25. Three key concepts (2)
26. Old news
27. The University Group Diabetes Program
28. UGDP data
29. Binomial likelihood
30. Probability of cardiovascular death: placebo (1)
31. Probability of cardiovascular death: placebo (2)
32. Probability of cardiovascular death: tolbutamide (1)
33. Probability of cardiovascular death: placebo (3)
34. Probability of cardiovascular death: tolbutamide (2)
35. Relative risk of cardiovascular death (1)
36. Relative risk of cardiovascular death (2)
37. 'Undesirable' evidence
38. Design considerations
39. Probabilities of misleading and weak evidence (1)
40. Probabilities of misleading and weak evidence (2)
41. Efficiency of sequential designs
42. Simulation
43. Results
44. The universal bound
45. Universal bound holds for sequential designs
46. The bump function
47. Bump equations
48. Probabilities of generating misleading evidence (1)
49. The tepee function
50. Tepee equations
51. Probabilities of generating misleading evidence (2)
52. Probabilities of generating misleading evidence (3)
53. Composite hypothesis (1)
54. Composite hypothesis (2)
55. Relative risk of cardiovascular death (3)
56. So what?
57. Extensions
58. References
59. END