From Observational Studies to Causal Rule Mining

Jiuyong Li, Thuc Duy Le, Lin Liu, Jixue Liu, Zhou Jin, Bing-Yu Sun, Saisai Ma

Abstract

Randomised controlled trials (RCTs) are the most effective approach to causal discovery, but in many circumstances it is impossible to conduct RCTs. Therefore observational studies based on passively observed data are widely accepted as an alternative to RCTs. However, in observational studies, prior knowledge is required to generate the hypotheses about the cause-effect relationships to be tested, hence they can only be applied to problems with available domain knowledge and a handful of variables. In practice, many data sets are of high dimensionality, which leaves observational studies out of the opportunities for causal discovery from such a wealth of data sources. In another direction, many efficient data mining methods have been developed to identify associations among variables in large data sets. The problem is, causal relationships imply associations, but the reverse is not always true. However we can see the synergy between the two paradigms here. Specifically, association rule mining can be used to deal with the high-dimensionality problem while observational studies can be utilised to eliminate non-causal associations. In this paper we propose the concept of causal rules (CRs) and develop an algorithm for mining CRs in large data sets. We use the idea of retrospective cohort studies to detect CRs based on the results of association rule mining. Experiments with both synthetic and real world data sets have demonstrated the effectiveness and efficiency of CR mining. In comparison with the commonly used causal discovery methods, the proposed approach in general is faster and has better or competitive performance in finding correct or sensible causes. It is also capable of finding a cause consisting of multiple variables, a feature that other causal discovery methods do not possess.

Introduction

Discovering causality in large datasets usually requires either expensive experiments or complex models that struggle with high-dimensional data. This paper introduces CR-CS, an algorithm that merges the efficiency of association rule mining with the statistical rigor of retrospective cohort studies to automatically uncover "causal rules" (including complex, multi-variable causes) from observational data.

What Problem Does This Paper Address?

The "gold standard" for proving cause-and-effect is the Randomized Controlled Trial (RCT), but RCTs are often unethical or prohibitively expensive. Researchers instead turn to observational studies, but these typically require a pre-existing hypothesis and only work with a handful of variables.

On the other side, association rule mining is great at finding patterns in massive, high-dimensional datasets, but it famously suffers from the "correlation is not causation" trap. Spurious correlations—often caused by hidden "confounders" or the Simpson’s Paradox—make it hard to tell if a pattern is a true cause or just a coincidence.

Table 1: Aggregate association between Gender and Salary, a potential candidate for causal rule mining.

For example, an aggregate table might show a strong association between gender and salary (as seen in Table 1), but this relationship could be spurious when controlling for other factors like education level. This paper aims to bridge the gap: how can we automate the discovery of causal relationships in big data without needing a hypothesis upfront?

Methods

The authors propose the concept of Causal Rules (CRs) and the CR-CS (Causal Rule mining with Cohort Study) algorithm. The process works in three main stages:

  1. Hypothesis Generation: The algorithm uses association rule mining to find potential relationships (e.g., "If $A$ and $B$ occur, then $Z$ is likely").
  2. Creating "Fair Data Sets": To test if a rule is truly causal, the algorithm simulates a controlled experiment. It uses matching (either exact matching or Jaccard distance) to create a sub-dataset where every "exposed" record (where the cause is present) is paired with a "non-exposed" record that is identical in all other respects (the control variables).
  3. Causal Validation: It calculates the odds ratio on this "fair" dataset. If the relationship holds up even when all other variables are controlled for, it is classified as a Causal Rule.
Table 2: Contingency table for a potential causal rule $p \to z$ used to calculate the odds ratio.

As shown in Table 2, the validation step relies on the support of the cause $p$ and outcome $z$ within the matched cohort. To keep the algorithm fast, the authors utilize anti-monotone properties. For example, if a general rule (e.g., "College Degree $\to$ High Salary") is found to be causal, more specific versions (e.g., "Male + College Degree $\to$ High Salary") are considered redundant and pruned from the search.

Key Insights and Ideas

  • Synergy of Paradigms: Causal discovery is traditionally "top-down" (testing a theory), while data mining is "bottom-up" (finding patterns). This paper shows that data mining can provide the "candidates" for causal testing, effectively automating the hypothesis generation phase.
  • The "Fairness" Filter: By blinding the outcome variable during the matching process, the algorithm mimics the "ceteris paribus" (all other things being equal) requirement of scientific experiments.
  • Handling Combined Causes: Most causal discovery methods look for single-variable causes ($X \to Y$). CR-CS can identify complex causes where multiple factors must coincide.
  • Efficiency through Pruning: By recognizing that causal relationships are persistent, the algorithm can skip millions of redundant checks, allowing it to scale to datasets with 1,000+ variables.

Key Results

The authors evaluated their approach using a mix of synthetic and real-world data, including the UCI Adult and Census Income datasets.

  • Superior Scalability: CR-CS was significantly faster than traditional constraint-based methods. While the popular PC-select algorithm failed to return results for datasets with more than 100 variables within 24 hours, CR-CS handled 1,000 variables with ease.
  • Accuracy: On synthetic data, CR-CS achieved significantly higher precision and recall than CCC and CCU.
  • Real-World Logic: On the "Adult" dataset, CR-CS correctly identified "Education" as a cause for high income but correctly filtered out "Native Country," which other association-based methods incorrectly flagged as a strong predictor.

Limitations and Future Work

The matching process relies on finding "twins" in the data. If the data is extremely skewed or sparse, the "fair data set" might become too small to be statistically significant. Future work could integrate more sophisticated techniques like propensity score matching to further improve robustness against selection bias and hidden confounders.

Summary updated

Abstract

Randomised controlled trials (RCTs) are the most effective approach to causal discovery, but in many circumstances it is impossible to conduct RCTs. Therefore observational studies based on passively observed data are widely accepted as an alternative to RCTs. However, in observational studies, prior knowledge is required to generate the hypotheses about the cause-effect relationships to be tested, hence they can only be applied to problems with available domain knowledge and a handful of variables. In practice, many data sets are of high dimensionality, which leaves observational studies out of the opportunities for causal discovery from such a wealth of data sources. In another direction, many efficient data mining methods have been developed to identify associations among variables in large data sets. The problem is, causal relationships imply associations, but the reverse is not always true. However we can see the synergy between the two paradigms here. Specifically, association rule mining can be used to deal with the high-dimensionality problem while observational studies can be utilised to eliminate non-causal associations. In this paper we propose the concept of causal rules (CRs) and develop an algorithm for mining CRs in large data sets. We use the idea of retrospective cohort studies to detect CRs based on the results of association rule mining. Experiments with both synthetic and real world data sets have demonstrated the effectiveness and efficiency of CR mining. In comparison with the commonly used causal discovery methods, the proposed approach in general is faster and has better or competitive performance in finding correct or sensible causes. It is also capable of finding a cause consisting of multiple variables, a feature that other causal discovery methods do not possess.
BibTeX
@article{li2016from,
  author = {Jiuyong Li and Thuc Duy Le and Lin Liu and Jixue Liu and Zhou Jin and Bing-Yu Sun and Saisai Ma},
  title = {{From Observational Studies to Causal Rule Mining}},
  journal = {ACM Trans. Intell. Syst. Technol.},
  year = {2016},
  url = {https://openreview.net/forum?id=vItoUpwamwK},
}
Figure