JMP alternative · Native Mac & Windows
Stop paying $1,390 a seat every year — $8,820 for JMP Pro. Stratum is one-time from $119, so the budget conversation ends and the software stays yours. Everything you reach for day to day is in it, and every number it reports is checked against a named outside tool in a published validation record, so you can show your work rather than vouch for it. Free to try on your own data before you decide.





JMP lists at $1,390 per user per year in its own store, and JMP Pro at $8,820. The bill returns every year you keep using it, and the software stops when the license does.
Five years at list price: $6,950 — and no software left if you stop.
Bought once. The version you buy keeps working forever, online or off, on Mac and Windows alike.
$249 for Professional — once, and it's yours.
| JMP | Stratum | |
|---|---|---|
| Pricing | $1,390 per user / year; JMP Pro $8,820 | One-time, from $119 |
| Platform | Native Mac & Windows | Native Mac & Windows |
| Core statistics | Extensive | t-tests, one-way and factorial ANOVA with Type I/II/III SS, MANOVA, Kruskal-Wallis and Dunn, Pearson/Spearman/Kendall with FDR correction, chi-square, regression with full diagnostics and best-subsets selection |
| Numerical validation | Statistical details documented | Published validation record — the outside tool named for every statistic, plus all nine NIST StRD least-squares cases |
| Charts | Interactive, extensive | 30+ modern statistical charts, zoom on every continuous axis, publication-quality export |
| Linked selection (brushing) | Yes | Yes — one row selection across the datasheet and every chart, on the same click / ⌘-click / Shift-click / drag gestures, with aggregate marks shading to their selected share |
| Machine learning | Yes | PCA with KMO and Bartlett’s, k-means and hierarchical clustering, cross-validated trees, random forests with out-of-bag error, boosted trees with early stopping, partial-dependence plots (Professional) |
| Model validation | Yes | Seeded training / validation / test splits, optionally stratified, with confusion matrices, test AUC and model comparison on one partition |
| Quality & SPC | Yes | Nine control charts, all eight Nelson rules, Phase I/II staging, capability with Cpm, Z-bench and confidence intervals (Professional) |
| Data in | Many formats | CSV and delimited text, Excel, fixed-width ASCII, SPSS .sav, Stata .dta — to ~5 million rows |
Summary — mean, SD, quartiles, skewness and kurtosis for every column at once, with histograms and box plots alongside.
One-Way ANOVA — SS, df, MS, F and p, with Tukey HSD post-hoc comparisons, Levene's test and confidence intervals.
Scatter — OLS and LOESS fits with confidence bands, and the correlation reported on the legend.
Contingency Table — chi-square, expected counts, row / column percentages and a mosaic plot.
Linear Regression — coefficients with CIs, VIF, leverage, Cook's D, best-subsets, R², AIC and BIC — plus Two-Way ANOVA with interaction terms.
Correlation — Pearson, Spearman and Kendall matrices with confidence intervals, p-values and multiple-comparison correction.
Principal Components — loadings and variance explained, with a scree plot and biplot.
Clustering — K-means and hierarchical, with dendrograms.
Decision Tree, Random Forest, Boosted Trees — all three in Professional, with feature importance, ROC and prediction columns — where JMP keeps the forest and boosted variants in JMP Pro.
Control Charts — I-MR, X̄, p, c, CUSUM and EWMA with control limits and all eight Nelson rules.
30+ chart types — histogram, box, violin, density, ECDF, Q-Q, scatter with OLS/LOESS, treemap, mosaic, Pareto and more.
Point-and-click throughout — no JSL to learn, and nothing to re-run when you change a filter.
Stratum brings descriptive statistics, full inferential testing (t-tests, ANOVA, correlation, contingency, regression with diagnostics), 30+ publication-quality charts, and machine learning (PCA, clustering, decision trees, random forests, boosted trees) into one fast native app — on up to ~5 million rows. Import your .csv or .xlsx directly and try it on your own data before you buy.
Yes — Stratum is a native desktop statistics app at a one-time price, covering core analyses plus 30+ charts and built-in machine learning.
Yes — a native macOS app (macOS 14 or later) and a native Windows app (Windows 10/11, 64-bit).