Analysis & Verification (mgsci-data-analysis)

When to trigger

• Results are ready to be derived/estimated and reported
• You are unsure whether the analysis actually supports the claim
• Reviewers will probe proof correctness, identification, or robustness
• You must assemble the replication package the Data Editor will verify

Because Management Science is bimethodological, "analysis" means proving/computing results in the analytical lane or estimating/validating in the empirical lane. Both are held to their Department's rigor bar.

Analytical lane — prove, then illustrate

• Proofs first. Every proposition/theorem needs a correct, checkable proof (main text or appendix). Reviewers verify the algebra and the logic.
• Comparative statics carry the managerial insight — report how the optimal policy/equilibrium moves with each primitive, with sign and intuition.
• Numerical illustration. Where closed forms run out, provide computational examples; report parameter ranges and confirm the qualitative result is not knife-edge.
• Robustness of the model. Show the insight survives relaxed assumptions / alternative timing / heterogeneity.
• Reproducible numerics. Code/notebooks must regenerate every figure and computed example.