The Stratum blog
How-tos, worked case studies, plain-language statistics explainers, and product news. The written companion to our video series — new posts every week.
🔖 Subscribe via RSS · New to Stratum? Start the 25-lesson tutorial →
Guide Me asks only what your file can't tell it — then builds the analysis and the chart.
Nov 4, 2026 · 5 min read
Same 2×2 table, p-values on opposite sides of 0.05. The expected counts decide.
Nov 6, 2026 · 6 min read
142 countries, six worth naming: mark the rows that matter and drag each label into place.
Nov 11, 2026 · 5 min read
Control charts and capability without a Windows-only subscription.
Nov 13, 2026 · 7 min read
“Color by continent” can mean analyze each group or just paint it. Stratum keeps them apart.
Nov 18, 2026 · 5 min read
1,146 GSS variables: find any one, read what it is, declare a whole battery in one pass.
Nov 20, 2026 · 5 min read
Modeling types, row states, Fit Y by X — each JMP habit mapped to its Stratum equivalent.
Nov 25, 2026 · 8 min read
One split, three models, one honest comparison on rows none of them saw.
Dec 2, 2026 · 5 min read
0% training error, 11% on unseen rows. Overfitting means the training number is wrong.
Dec 4, 2026 · 7 min read
From a chart that answers your question to a figure that answers it for someone else.
Dec 9, 2026 · 5 min read
R is the reference everyone checks against. Here's when a native app is the faster route.
Dec 11, 2026 · 7 min read
An outlier is a question about a row: reveal it, mark it, and measure how much it matters.
Dec 16, 2026 · 5 min read
From thirty parts, Cpk is a loose estimate — compare its lower bound with 1.33.
Dec 18, 2026 · 6 min read
Read variable and value labels straight off a .sav — no SPSS, no CSV round-trip.
Oct 2, 2026 · 6 min read
The four capability indices in plain language — and the assumption they all share.
Oct 7, 2026 · 7 min read
Classical ANOVA crowns a false winner (p=0.0005); Welch says it's noise (p=0.42).
Oct 9, 2026 · 6 min read
On unbalanced data the same effect gets three different F-tests. Which is right?
Oct 14, 2026 · 7 min read
A p-value says whether an effect exists, not how big. Report the size too.
Oct 16, 2026 · 7 min read
Compare group means the fair way — hold a covariate constant, straight from menus.
Oct 21, 2026 · 6 min read
Two free R-backed apps versus a paid native one — an honest head-to-head.
Oct 23, 2026 · 8 min read
PCA for categorical data: turn a big cross-tab into one readable map.
Oct 28, 2026 · 7 min read
Guide Me picks and draws the analysis, rows you select or mark show on every chart, a column index for wide files, and test sets with Model Comparison.
Oct 21, 2026 · 8 min readSPSS and Stata files with labels intact, Frequencies, Welch's ANOVA, equivalence tests, control-chart phases and TIFF export.
Sep 13, 2026 · 8 min read
Polynomial regression terms, a solver validated against NIST, coefficient intervals and Effect Tests, ANOVA means and effect sizes, and Type III sums of squares.
Aug 31, 2026 · 7 min read
The best-cut diamonds look cheapest — until you find the confounder hiding in plain sight.
Aug 21, 2026 · 6 min read
When the log transform earns its place — and why it isn't just cosmetic.
Aug 28, 2026 · 6 min read
Name each component from its loadings — and let PCA explain a real mystery.
Sep 4, 2026 · 6 min read
Add one variable and watch the R² climb — and the story flip.
Sep 11, 2026 · 6 min read
Let 54,000 diamonds carve their own rules — and confirm the finding from a new angle.
Sep 18, 2026 · 6 min read
Check whether your data is normal — read the line, spot skew and tails.
Sep 30, 2026 · 6 min read
Where SPSS's established workflows fit, and where a lighter native app wins on cost.
Sep 25, 2026 · 7 min read
An interpretable model: grow it, prune it, read importance, and predict.
Sep 23, 2026 · 7 min read
Both compare groups, but one shows summaries and the other shows shape.
Sep 18, 2026 · 6 min read
Compare groups by full distribution shape — and spot bimodality a box plot hides.
Sep 16, 2026 · 6 min readWhere Prism's biostatistics focus shines, and where a broader native app fits.
Sep 11, 2026 · 7 min read
See every variable pair at once with the Scatter chart's Matrix mode.
Sep 9, 2026 · 6 min read
Read every pair's relationship at once, with the significant ones highlighted.
Sep 4, 2026 · 6 min read
R², VIF, Cook's distance and residual plots — whether to believe the model.
Sep 2, 2026 · 7 min read
Build a model from menus, read R² and coefficients, and check the diagnostics.
Aug 28, 2026 · 7 min readWhere JMP's depth is worth it, and where a lighter native Mac & Windows app wins.
Aug 26, 2026 · 7 min read
Loadings tell you what a component means; scores tell you where each observation sits.
Aug 21, 2026 · 7 min read
Reduce many variables to a few components; read the scree plot and biplot.
Aug 19, 2026 · 7 min read
344 real penguins, a bill correlation that runs backwards until you split by species, then a decision tree, random forest and PCA that classify three species at ~98% — no code.
Dec 1, 2026 · 11 min read
Turn the most famous scatter in statistics into 142 connected trajectories and watch the development gap close — a full Gapminder analysis, no code, no animation.
Jan 4, 2027 · 14 min read
The 2024 General Social Survey opened straight from its .sav and weighted with NORC's survey weight: chi-square, a mosaic, Welch ANOVA and logistic regression show more income doesn't raise the odds of being very happy once money feelings, health and marriage are in. No code.
Feb 1, 2027 · 10 min read
5,479 real days of US births: Friday the 13th looks like it has 5% more babies, until ANOVA, Welch and Games–Howell expose the weekday and holiday effects. Fridays vs Fridays: 5.3% fewer. No code.
Mar 1, 2027 · 12 min read
440 real wholesale customers: raw k-means finds only the whales, a log scale finds two real segments that k-means and Ward agree on, and a label the algorithm never saw validates them at V ≈ 0.72. No code.
Apr 1, 2027 · 11 min read
4,090,836 real NYC taxi rides, opened straight from Parquet: three recording traps that fake a 38% no-tip rate, a 20% default half the city taps, and a logistic regression and random forest that agree on the one thing that moves it — no code.
May 3, 2027 · 11 min read
Card & Krueger's 410 restaurants from a Stata .dta, reshaped to one row per store, then a difference-in-differences with standard errors clustered by store, checked against within-store change scores and the published tables. No code.
Jun 1, 2027 · 10 min read
1,186 people, 14 characters, one chart. Correspondence Analysis maps a whole survey — and Jar Jar sits alone in the corner. No code.
Nov 2, 2026 · 10 min read
53,940 real diamonds, three quality grades that all run backwards, and the charts, ANOVA, regression, PCA and decision tree that crack it — no code.
Jul 31, 2026 · 13 min read
2,139 patients in the ACTG 175 HIV trial: the overall average said the drug worked, one arm said it harmed, and the honest answer lived in the subgroups — paired t-test, effect size, responder rate, ANOVA, MANOVA and ANCOVA. No code.
Sep 1, 2026 · 13 min read
A capability report says Ppk 1.36 — a pass. On 200 real piston-ring measurements, SPC control charts catch the drift that single number hides. The Six-Sigma rule: control before capability. No code.
Oct 1, 2026 · 6 min read
How SPC tells ordinary variation from a real change — and what the Nelson rules detect.
Aug 14, 2026 · 7 min read
I-MR and X-bar charts with control limits and automatic Nelson-rule flagging.
Aug 12, 2026 · 7 min readNative apps vs Excel vs R/Python vs the big suites — an honest map of the options.
Aug 7, 2026 · 8 min read
What correlation does and doesn't mean, and when to use Pearson vs Spearman.
Aug 5, 2026 · 7 min read
Plot two variables, add a line of best fit, and read the correlation.
Jul 31, 2026 · 6 min read
Two measures of center that agree for symmetric data and diverge for skewed data.
Jul 29, 2026 · 6 min read
A guided first-run tour, on-screen Hints, panel-by-panel control-chart zoom, pixel-exact 16:9 / 4K chart export, and cleaner below-zero bar labels.
Aug 20, 2026 · 4 min readTwo new Pro analyses, Connected Scatter, custom categorical ordering, skewness & kurtosis, and drag-to-export cards.
Jul 28, 2026 · 5 min read
See the shape of a variable — pick bins, read skew, and export.
Jul 24, 2026 · 6 min readWhere Excel runs out of road for real statistics — and what a native Mac & Windows app does differently.
Jul 22, 2026 · 9 min read
Normality, equal variance, independence — what each assumption means and how to check it.
Jul 17, 2026 · 9 min read
Compare three or more group means, read F and p, and run a Tukey post-hoc.
Jul 15, 2026 · 8 min read
Compare two groups and read the result in under a minute — no code, no notebooks.
Jul 10, 2026 · 6 min read
Median, quartiles, the IQR box, whiskers and outliers — read a box plot at a glance.
Jul 8, 2026 · 8 min read
Compare groups and spot outliers with a box-and-whisker plot — in under a minute.
Jul 3, 2026 · 7 min readWhat Stratum is, who it's for, and why we built a native statistics app for Mac & Windows.
Jul 1, 2026 · 5 min readCase studies, explainers, and how-tos are on the way. Subscribe via RSS or follow the video series to keep up.
Stratum