You can run a flawless simulation and still change nothing. A technically perfect QSRA that a steering committee doesn't understand, doesn't trust, or doesn't act on has failed just as completely as one with the wrong logic — it has simply failed quietly. The last mile of schedule risk analysis is not the maths. It's getting a room of decision-makers to believe a number and do something about it.
Max Henrion, writing on why analytics projects underdeliver, puts the cause squarely on communication rather than capability. Analysts "spend too much time struggling to organize poorly structured data and debugging complex spreadsheets or code and too little time engaging directly" with the people who own the decision — so even sound work "may fail to address the issues they really care about," and "clients may not develop the confidence to rely on the insights" (Analytica, "Why big data analytics projects fail"). Every word of that transfers to schedule risk. The P80 is only as useful as the room's willingness to stand behind it.
A steering committee does not need your distribution family, your correlation matrix, or your iteration count in the first sixty seconds. It needs the decision the analysis informs: the date we can commit to, and the contingency behind it. Open with "we're 80% likely to finish by 22 August, which needs six weeks of contingency held against the deterministic plan" — then let anyone who wants the method follow you into the appendix. Method-first reporting is the single fastest way to lose a non-technical room.
A black box gets nodded at and ignored. Henrion's remedy is to help decision-makers "brainstorm better decision options, and explore, visualize and understand the results" rather than hand down opaque findings. For QSRA that means being able to say, on the spot, why the date is what it is: which activities drive it, which risks matter, what assumptions the ranges encode, and that the run is reproducible if anyone wants to check it. Defensibility isn't a compliance nicety — it's the thing that converts a plausible number into a committed one.
RunMonteCarlo is built for that last mile: a clean S-curve, risk-driver and criticality charts, a contingency read-out, and a defensible, reproducible report you can put in front of a committee — generated from your schedule in minutes.
RunMonteCarlo produces the S-curve, the risk drivers, the contingency read-out and a defensible reproducible report — the last mile of QSRA, done. Free tier included; your schedule never leaves your machine.
Launch RunMonteCarlo →Latin Hypercube's edge is largest when a few inputs dominate the output. When many variables contribute roughly equally, their independent errors partly cancel on their own, and the stratification advantage narrows — David Vose's nine-input test is the classic demonstration that with enough equally-weighted drivers, LHS and plain MC converge (Risk Analysis: A Quantitative Guide).
Here is the thing: schedule risk is almost never the equal-weight case. A project's completion distribution is driven by the handful of activities on and near the critical path. Everything else has float and contributes almost nothing to the finish date. That is the exact regime — a few dominant drivers — where Latin Hypercube pays the most. The property that makes hand methods fail (only a few paths matter, and they shift under risk — see merge bias) is the same property that makes LHS shine.
They should be — trades share weather, crews and productivity, and pretending otherwise understates the tail. A fair worry is whether stratifying each input separately breaks the correlation structure. It doesn't. Latin Hypercube composes cleanly with correlation: you stratify the marginals, then impose the dependency by reordering the samples to hit a target rank correlation — the Iman & Conover method (1982) — or, equivalently, drive the strata through a copula. RunMonteCarlo uses a Gaussian copula for correlation and still stratifies underneath it, so you get correlated and well-covered durations at once. Details are on The Maths.
Effectively no. The one-time cost is turning a uniform draw into a value on your distribution — the inverse CDF. For the Normal that has no closed form, but Acklam's rational approximation computes it to machine precision in a few multiplications, so an LHS draw costs about the same as a plain one. And in a schedule model the sampling is a rounding error next to the real work: re-solving the CPM network over thousands of iterations. You get the variance reduction essentially for free. RunMonteCarlo already cites Acklam's inverse-normal in The Maths for precisely this reason.
Latin Hypercube isn't a buried expert option in RunMonteCarlo — it's how the engine samples by default, and it's the same seeded, reproducible pipeline the rest of the tool runs on: