breslowday(A)

Computes the Homogeneity of Odds Ratio using both the Breslow-Day test and Tarone's test using data in array A. Array A must be an array of contingency tables 2x2.


See also chi2_kappa chi2_risk chi2_mantel 


Example


The following data was collected regarding results of new medication:


Female
Outcome
Total
Better
Same
Active
16
11
27
Placebo
5
20
25
Total
21
31
52


Male
Outcome
Total
Better
Same
Active
12
16
28
Placebo
7
19
26
Total
19
35
54

Entering the first data in a matrix we obtain:


a1=(16,11;5,20)

/ 16 11 \

\  5 20 /


We now use function chi2_totable to transform the matrix into a proper contingency table


a1=chi2_totable(a1)

/ "" "" "" "" \

| "" 16 11 27 |

| ""  5 20 25 |

\ "" 21 31 52 /


Entering the second data in a matrix we obtain:


a2=(12,16;7,19)

/ 12 16 \

\  7 19 /


We use function chi2_totable another time,


a2=chi2_totable(a2)

/ "" "" "" "" \

| "" 12 16 28 |

| ""  7 19 26 |

\ "" 19 35 54 /


We put the matrices in an array and call the breslowday function,


A=(a1,a2)

/ / "" "" "" "" \ / "" "" "" "" \ \

| | "" 16 11 27 | | "" 12 16 28 | |

| | ""  5 20 25 | | ""  7 19 26 | |

\ \ "" 21 31 52 / \ "" 19 35 54 / /


breslowday(A)


Test of Homogeneity of Odds Ratio.

Results:


Breslow-Day statistic : 1.492928497986823

Asymp. Sig. (2-sided) : 0.22176264220904673

Tarone's statistic : 1.4905373373471231

Asymp. Sig. (2-sided) : 0.22213310764123495

df : 1