HYPOTHESIS TESTS AND OPTIMALITY PROPERTIES IN DISCRETE MULTIVARIATE ANALYSIS

Author(s):  
Arthur Cohen ◽  
Constantine Gatsonis ◽  
John Marden
1977 ◽  
Vol 1 (2) ◽  
pp. 297-306 ◽  
Author(s):  
Yvonne M. M. Bishop ◽  
Stephen E. Fienberg ◽  
Paul W. Holland ◽  
Richard J. Light ◽  
Frederick Mosteller

Biometrics ◽  
1976 ◽  
Vol 32 (2) ◽  
pp. 491
Author(s):  
D. V. Gokhale ◽  
Y. M. M. Bishop ◽  
S. E. Fienberg ◽  
P. W. Holland

1980 ◽  
Vol 17 (3) ◽  
pp. 395 ◽  
Author(s):  
Rajendra K. Srivastava ◽  
Yvonne M. M. Bishop ◽  
Stephen E. Fienberg ◽  
Paul W. Holland ◽  
Stephen E. Fienberg ◽  
...  

2017 ◽  
Vol 25 (5) ◽  
pp. 741-757 ◽  
Author(s):  
Julio Michael Stern ◽  
Rafael Izbicki ◽  
Luis Gustavo Esteves ◽  
Rafael Bassi Stern

Abstract Although logical consistency is desirable in scientific research, standard statistical hypothesis tests are typically logically inconsistent. To address this issue, previous work introduced agnostic hypothesis tests and proved that they can be logically consistent while retaining statistical optimality properties. This article characterizes the credal modalities in agnostic hypothesis tests and uses the hexagon of oppositions to explain the logical relations between these modalities. Geometric solids that are composed of hexagons of oppositions illustrate the conditions for these modalities to be logically consistent. Prisms composed of hexagons of oppositions show how the credal modalities obtained from two agnostic tests vary according to their threshold values. Nested hexagons of oppositions summarize logical relations between the credal modalities in these tests and prove new relations.


Sign in / Sign up

Export Citation Format

Share Document