Inconsistency Factor

Problem

Return the network meta-analysis inconsistency factor (d_direct - d_indirect)/sqrt(se_direct^2 + se_indirect^2). Return 0.0 when the combined variance is not positive.

Hint

The factor standardizes the direct-indirect gap by its combined uncertainty.

Test cases

case 1

in: [0.5,0.1,0.3,0.15]

expected: 1.1094003924504583

case 2

in: [0.5,0.2,0.5,0.2]

expected: 0

case 3

in: [1,0.1,0.5,0.1]

expected: 3.535533905932737

case 4

in: [0.2,0,0.2,0]

expected: 0

case 5

in: [-0.3,0.2,0.1,0.1]

expected: -1.7888543819998317

Starter codePython

def inconsistency_factor(d_direct, se_direct, d_indirect, se_indirect):
    # Your code here
    pass

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