MRPC (version 3.1.0)

CompareMethodsNodeOrdering: Comparison of inference accuracy using the same data but with different node orderings.

Description

Investigate the performance of five methods on the same data but with different node orderings: MRPC (Badsha and Fu, 2019; Badsha et al., 2021), pc, implemented in pcalg (Kalisch et al., 2012), and pc.stable, mmpc, mmhc, and hc, the last four all implemented in bnlearn (Scutari, 2010). See details in Badsha et al.(2021).

Usage

CompareMethodsNodeOrdering(N, signal, model, n_data, n_nodeordering)

Arguments

N

The number of observations.

signal

The signal strength which is the coefficient of the parent nodes in the linear model.

model

Either 'truth1' or 'truth2' to specify the model to generate data from.

n_data

The number of independent data sets to generate.

n_nodeordering

The number of times to reorder the nodes.

Value

Matrix

Details

We generated different data sets from each of the two graphs (V1-->T1-->T2-->T3 and V1-->T1<--T2-->T3), where V1 is the genetic varitant node and T1, T2 and T3 are the phenotype nodes. For each data set, we reordered the columns of the data matrix with different permutations of the T nodes, and thus generated new permuted data sets. We then applied all the methods to each of the data sets (restricting edge direction wherever necessary and possible), obtained different inferred graphs, and counted the number of unique graphs among the inferred graphs for each data set.

The output is the number of unique graphs inferred by each method across all permutations.The columns are indicates which methods (MRPC, pc, pc.stable, mmpc mmhc, and hc), and each rows are indicates the independent data sets under different node orderings. See details in Badsha et al., 2018.

References

1. Badsha MB and Fu AQ (2019). Learning causal biological networks with the principle of Mendelian randomization. Frontiers in Genetics, 10:460.

2. Badsha MB, Martin EA and Fu AQ (2021). MRPC: An R package for inference of causal graphs. Frontiers in Genetics, 10:651812.

3. Kalisch M, Machler M, Colombo D, Maathuis MH and Buhlmann P (2012). Causal Inference Using Graphical Models with the R Package pcalg. Journal of Statistical Software, 47, 26.

4. Scutari M (2010). Learning Bayesian Networks with the bnlearn R Package. Journal of Statistical Software, 35(3), 1-22.

Examples

# NOT RUN {
  
# }
# NOT RUN {
# Load the libraries
library(MRPC)    #  MRPC
library(pcalg)   #  pc
library(bnlearn) #  pc.stable, mmpc, mmhc, and hc

# For demonstration purposes, only 10 data sets
# are simulated from truth1 (V1-->T1-->T2-->T3) 
# with sample size N = 100, signal = 1.0, 
# and 6 different T nodes orderings
Output <- CompareMethodsNodeOrdering(N = 100,
                                     signal = 1.0, 
                                     model = 'truth1',
                                     n_data = 10,
                                     n_nodeordering = 6)
# }
# NOT RUN {
  
# }