mossspider.dgm.generate_observed

generate_observed(graph, seed=None)

Simulates the exposure and outcome for the uniform random graph (following mechanisms are from Sofrygin & van der Laan 2017).

\[\begin{split}A = \text{Bernoulli}(\text{expit}(-1.2 + 1.5 W + 0.6 W^s)) \\ Y = \text{Bernoulli}(\text{expit}(-2.5 + 0.5 A + 1.5 A^s + 1.5 W + 1.5 W^s))\end{split}\]

Parameters

• graph (Graph) – Graph generated by the uniform_network function.

• seed (int, None, optional) – Random seed to use. Default is None.

Returns

Return type

Network object with node attributes

Examples

Loading the necessary functions

>>> from mossspider.dgm import uniform_network, generate_observed

Generating the uniform network

>>> G = uniform_network(n=500, degree=[0, 2])

Generating exposure A and outcome Y for network

>>> H = generate_observed(graph=G)

References

Sofrygin O, & van der Laan MJ. (2017). Semi-parametric estimation and inference for the mean outcome of the single time-point intervention in a causally connected population. Journal of Causal Inference, 5(1).