A distribution shown without losing the values behind it. How to read the stem and leaf units, what it catches that a histogram hides, and the kind of data it does not suit.
A stem-and-leaf display splits every value into a stem, the leading digits, and a leaf, the trailing digit. Values sharing a stem sit on one row, so the row lengths form a histogram lying on its side while the individual digits remain readable.
Quanta states the stem unit and leaf unit beneath the display. Read them before anything else, because they set the scale: a stem unit of 1 with a leaf unit of 0.10 means the row labelled 3 holds values from 3.0 to 3.9, and a leaf of 4 on that row is the value 3.4.
The count is given alongside, so you can confirm the display covers the cases you expect.
The actual values. A histogram bar tells you eleven cases fall between 40 and 50. A stem-and-leaf row tells you which eleven.
Digit preferences. Rows where leaves cluster on 0 and 5 reveal rounding by respondents, a very common artifact in self-reported ages, incomes, and durations, and one a histogram cannot show.
Isolated values. A single leaf sitting several rows away from everything else is an outlier you can identify and go look up, rather than a bar of height one.
Gaps. An empty stem in the middle of a distribution suggests two subpopulations or a data-handling problem, and it is visually obvious here in a way it is not in a smoothed plot.
Stem-and-leaf assumes values with meaningful trailing digits. On data that does not have them, it degenerates.
Ordinal items are the clearest case. A five-point Likert item has five possible values, all integers. Every leaf is then the same digit, and the display becomes five rows of identical characters whose only information is their length. That is a frequency table drawn inefficiently, and a frequency table is the better choice.
Large samples. Beyond a few hundred cases the rows run off the page and the detail that justifies the display stops being readable.
Continuous data with many decimal places loses precision to the leaf unit, though this is usually acceptable since shape is what you are after.
Used on the right data, roughly 20 to 200 continuous values, it remains one of the most information-dense summaries available.
Open Descriptives & Explore and select a numeric field. The stem-and-leaf display appears alongside the numeric summaries and the normality card.
Read the stem and leaf units first, then the shape, then look for gaps and isolated leaves.
Use it together with the normality card. The test tells you whether a departure is detectable; the display tells you what the departure actually is, which is the part that decides what to do.
Use the action bar to add the display to a report or copy it.
Stem-and-leaf displays are usually working tools rather than published figures. They belong in your own inspection and in supplementary material.
What belongs in the paper is what you learned from looking: the skew, the gap, the outliers, and what you did about them.
Inspection of the distribution showed a pronounced right skew with four isolated values above 90. These were verified against the source records and retained, and rank-based tests were used for the primary analyses.
If you do publish the display, give the stem and leaf units in the note. Without them the figure cannot be read.
Every result carries a ReliCheck Intelligence card with one action: explain this result in plain language. It runs entirely on your Mac with Apple Intelligence. No upload, no API key, nothing to configure. The model only explains the result Quanta has already computed and validated. It never computes a statistic, and it never applies a decision on your behalf.
From the action bar you can add the result to a report, copy the table, or copy the APA text. Exported reports carry the APA table, its note, and a caution specific to that analysis beneath it.
Quanta's engine is pure Swift on Apple's Accelerate framework, with no R or Python at runtime. Every engine is checked against an independent reference rather than internal consistency alone, and the automated suite exceeds 500 checks. Full record on the validation page.
Descriptives & Explore is part of every Quanta subscription, $9.99 a month or $79.99 a year after the 30-day trial. One price for everyone. See pricing.
The analysis, the report builder, and the on-device explanations all work with the network off. Your dataset is never uploaded.
Descriptive statistics the numbers behind the shape · Normality tests testing the shape rather than seeing it · Frequency tables for categorical fields · the complete list on the analyses page.