Connecting Scientific Reasoning and Causal Inference

Abstract

Literature on multivariable causal inference (MCI) and literature on scientific reasoning (SR) have proceeded almost entirely independently, although they in large part address the same phenomena. An effort is made to bring these paradigms into close enough alignment with one another to compare implications of the two lines of work and examine how they might illuminate one another. The conclusion is that SR research stands to benefit from recognition that it addresses a broader set of cognitive phenomena than reasoning in contexts that are explicitly scientific, whereas MCI research stands to benefit from recognizing inter- and, especially, intra-individual variability that its methods may have masked. Data reported here based on a merging of the two methodological paradigms support a model in which individuals have available a repertory of different inference strategies or rules (reflecting different criteria for inferences of causality) from which they select variably across occasions, in a dynamic process of theory-evidence coordination.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 99 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.