Step 1: Infer Temporal Order For each variable Z_i, calculate the score for number of events that precede it as: Score(Z_k )=_(jk)C (Z_jZ_k )-C((Z_kZ_j )) The higher the score the more variables precede Z_k. Sort the variable based on the score to produce the order of the variables so that the first occurring variable is 1 (least events before it) and the last independent variable is indexed as n (most independent variables occurring before it). Y is assumed to be a dependent variable and occurring after all independent variables. The order of variables will be: Z_1Z_2Z_nY Example Data Analysis for Temporal Order Using the data provided in Table 1, we computed how many times the row variable occurs before any column variable, see results in Total column in Table 2. For example, Anesthesia procedure occurs 212 times before and 168 times after response to citalopram, thus the net times it occurs before response to citalopram is 168 - 212 = -44. The total for each row indicates the number of events that occur before the row heading. Thus, for anesthesia procedure on balance there are 57 events where anesthesia occurs after the other 3 events. The variable that occurs last