CRBIND_________
  1. Technical Information
  2. Purpose of the tables
  3. References

 

CRBIND. Technical information


  Version: 1.0  (2000)  
  Authors:  J. M. Tapia García 
 A. Martín Andrés
 
  Download: File name: CRBIND.PDF Download now
File size: 220Kb
File type: MS-WORD '97
Time (aprox):  
 

 


CRBIND. Purpose



The tables provides the unconditional critical region for testing the independence in a 2´ 2 table (multinomial case).
If the cell probabilities and the observed values for the four cells in a 2´ 2 table are, respectively,  

 

the aim is to test:
                             Ho º OR =1 (independence or not association)
                         vs Ha º OR < 1 or Haº OR > 1 (one tail)
                     or vs Ha º OR ¹ 1 (two tails)  
with OR= p11 p22 / p12 p21 the poblational odds-ratio.  

Under Ho:
                                P( n11, n12, n21, n22 | n.. ) =  n..! p.1n.1 p.2n.2 p1.n1. p2.n2. /( n11! n22!  n12! n21!)
 
For a target error a the critical region is a set, CR, of triplet (n11, n12, n21), with n11+ n12+ n21 £ n.., so the error a is:
                                                           a (p1., p.1) = SCR P( n11, n12, n21, n22 | n.. )
and de size of the test will be:
                                                                a *= Max a (p1., p.1) in 0< p1., p.1 < 1  

This tables gives the CR for the Barnard's test following the optimal procedure. The one-sided Ha considered is that indicate by the data:

Ha º OR<1   if   (n11 n22 / n12 n21) < 1

 ---o0o---


CRBIND. References



 For further details see:
 

  1. MARTÍN ANDRÉS, A. and TAPIA GARCIA, J. M. (1998). 'On determining the P-value in 2x2 multinomial trials'. Journal of Statistical Planning and Inferences 69(1), 33-49.
  2. MARTÍN ANDRÉS, A. and TAPIA GARCIA, J. M. (1999). 'Optimal unconditional test in 2x2 multinomial trials'. Comput. Statis. & Data Anal. 31(3), 311-321.
  3. TAPIA GARCIA, J. M. and MARTÍN ANDRÉS, A. (2000). ''Optimal unconditional critical regions for 2x2 multinomial trials'. Journal of Applied Statistics 27(6), 689-695..

 


Volver