WorkedStats is a set of browser-based statistics calculators built around a single idea: the working should stay visible. The median calculator takes a pasted dataset and returns the median alongside the sorted list, the exact middle position for an odd count or the middle pair for an even count, and the arithmetic that produces the final number. It is designed for students, teachers and anyone who needs to show how a median was reached rather than simply report the result. The page also reports the mean, range, IQR and a box-and-whisker plot for the same data.
The starting problem is a familiar one: most statistics calculators return one number. WorkedStats keeps the working visible instead — the sorted data, the formula substitution, the row-by-row deviation squares and the three quartile conventions that courses use. That distinction matters wherever the process is graded or reviewed. A homework answer of 23.5 is not worth much without the sorted line showing that positions 5 and 6 hold 22 and 25, and without the substitution (22 + 25) / 2 that turns the middle pair into the median. WorkedStats makes those intermediate artifacts part of the output, so the reasoning can be checked, copied or handed in.
The median calculator runs a three-step workflow that is displayed on the page. First it sorts the data and highlights the middle. Second it picks the middle: with an odd number of values the median is the single middle value at position (n + 1) / 2 — for nine values that is the fifth one — while with an even count there is no single middle value, so the two middle numbers are added and divided by two. The page prints the position arithmetic rather than only the final number. Third it reports the result, with a copy-result action so the outcome and its supporting steps can move into another document. For a ten-value sample the page shows n = 10, the middle positions 5 and 6, the substitution (22 + 25) / 2 and a median of 23.5.
Getting data in is deliberately undemanding. A dataset can be pasted with commas, spaces, tabs or as an Excel column, and blank lines and labels are ignored, so a copied gradebook column can go straight in without cleaning. Only numeric tokens are read: an empty value is not silently changed to zero, and if the count looks wrong the page suggests checking the pasted data rather than assuming a missing number was included. The dataset is stored only in the browser tab's session and is shared with the other five calculators, so the same numbers carry across the median, mean, standard deviation, average, IQR and z-score pages without retyping.
Each result is accompanied by a check on the shape of the distribution. A box-and-whisker plot places Q1, the median and Q3 inside a box beside the minimum and maximum, and marks any point outside the 1.5 × IQR fences as a potential outlier. In the sample dataset the plot reads min 12, Q1 18, median 23.5, Q3 31 and max 98, with the 1.5 × IQR fence at 50.5 and 98 flagged as a potential outlier. That is how one unusually high homework score stands out without changing the median.
WorkedStats is not a single page but a linked family of calculators, and each one keeps the worked-steps approach. The Mean Calculator takes a list of numbers and shows the mean with the sum, the count and every substitution in Σx / n. The Standard Deviation Calculator returns sample or population standard deviation with a row-by-row deviation table, the definition formula and the computational Σx² − n·x̄² formula, and it can copy an APA-formatted result or switch to population variance without re-pasting the data. The Average Calculator reports the arithmetic mean line by line and compares it with the median so that a skew does not fool the reader.
The Interquartile Range calculator compares Q1, Q2, Q3 and IQR under the TI-83/84 and AP Statistics exclusive rule, Tukey's inclusive hinges and Excel's QUARTILE.INC interpolation, and shows the 1.5 × IQR fences, potential outliers and a live box plot. The Z-Score Calculator turns an x value, a mean μ and a standard deviation σ into a z-score and a left-tail, right-tail or two-tailed probability, or standardizes every value in the dataset at once, with the standard normal curve filling the same area that the table reports. A live preview on the median page shows the current dataset's results for all five companion tools.
Two design decisions shape how the product behaves. The first is that everything runs in the browser tab: there is no upload endpoint on the page, and parsing, sorting and SVG drawing all happen in JavaScript in the tab, with the dataset kept in sessionStorage only so the other calculator pages can reuse it. A very large paste is limited by the browser rather than by an account or an upload quota. The second is that conventions are surfaced rather than hidden. The median page uses the TI-83/84 and AP Statistics convention for the box plot, and the IQR page sets the exclusive, Tukey hinge and linear-interpolation versions side by side, because those conventions can produce different Q1 and Q3 values.
The median page is also explicit about what a median is and is not. It notes that the median is a positional statistic: it does not use the size of the other values, so it is robust to outliers but throws away information that the mean keeps. A Quick Summary card shows the median beside the mean — in the sample, a median of 23.5 against a mean of 30.4, a difference of -6.9, with one outlier at 98 pulling the mean up. Seeing both numbers side by side is often the point of a homework question, and it is a faster way to notice a skew than reading a definition.
Concrete workflows follow from that. A student working through a homework set pastes a list of values once, reads the sorted line and position arithmetic for the median, then moves to the mean and standard deviation pages with the same dataset intact, copying APA-formatted results as needed. A teacher checking a copied gradebook column can paste it directly — labels and blank lines are ignored — and use the box plot to spot an unusually high score without that score distorting the median. Someone comparing quartile conventions can open the IQR page and see the exclusive, Tukey hinge and Excel interpolation results for the same numbers, alongside the fences that decide which points count as outliers.
The audience is students and instructors in statistics courses, particularly those working with TI-83/84 calculators or AP Statistics conventions, along with anyone who needs a defensible, step-by-step statistic from a pasted list. The tools require no account and no upload, and the interface is a web page. The underlying stack is plain JavaScript running client-side, SVG for the box-and-whisker drawing, and sessionStorage for carrying a dataset between calculator pages; no chart library is used.
WorkedStats treats a statistics answer as something to be demonstrated, not just produced. By pairing each result with its sorted data, position arithmetic, formula substitution and a distribution plot, it turns a single number into a checkable piece of work — and does so entirely inside the browser tab, with no upload, no account and no chart library.