Risk Difference Pooling and NNT

Problem

Return [pooled, nnt] where pooled is the inverse-variance weighted risk difference sum(rd_i/var_i)/sum(1/var_i) and nnt = 1/|pooled|, or 0.0 when the pooled difference is zero. Return [0.0, 0.0] for empty or mismatched input or any variance <= 0.

Hint

Pooled NNT is the reciprocal of the absolute pooled risk difference.

Test cases

case 1

in: [[0.1,0.2],[0.01,0.01]]

expected: [0.15,6.666666666666667]

case 2

in: [[0.1,0.1,0.1],[0.04,0.01,0.0025]]

expected: [0.1,10]

case 3

in: [[0.2,0],[0.01,0.01]]

expected: [0.1,10]

case 4

in: [[0.05,-0.05],[0.01,0.01]]

expected: [0,0]

case 5

in: [[],[]]

expected: [0,0]

Starter codePython

def pool_risk_difference(rd, variances):
    # Your code here
    pass

5 test cases · run your code against them in the editor