3

Background

I want customers to be able to construct and view a histogram. There are two inputs I need for this histogram: interval, which defines the total date range for the diagram, and granularity, which defines the scope of each bar of the histogram.

Example granularities include, daily, monthly, yearly and so on.

Question

What is a word for granularity that spans the entire interval?

To clarify, this would mean that there is only one bar in the histogram.

Less than perfect answers

Possibilities include unbounded, all, total, aggregate, and everything.

Update

To clarify, this makes sense outside of the context of a histogram as well.

For example, you might ask a friend "How was average attendance in your class this year?"

They might ask back, "At what granularity?" (Or maybe there is a better way to ask this, but it escapes me.)

"Semester."

"Well, the the Fall semester was great. Almost everyone attended all the time. 95%. Spring, however, is another story. An abysmal 45%."

Alternatively, you might have answered back, "Everything." In which case, your friend may have responded, "Overall, it wasn't great. About 70%."

This response of "Everything." is the word or phrase I am looking for. A word referring to the granularity that spans an entire range.

We're looking for long answers that provide some explanation and context. Don't just give a one-line answer; explain why your answer is right, ideally with citations. Answers that don't include explanations may be removed.

  • 1
    I can't even suss out what it is you're asking. "Granularity" seems to be being used similar to how we use "resolution" to refer to the level of detail in computer graphics. By definition, "granularity" doesn't refer specifically to time and doesn't mean "all" or any of those other words but instead seems to indicate the levels of detail available in the timeline, drilling down to daily or expanding upwardly to yearly or beyond. Greater spans would be "deccenially," "centennially," etc. The span of all time is "forever" or "eternity," but it is not an interval since it's all-inclusive. – Billy Aug 23 '18 at 18:30
  • How about simply all time? – Roger Sinasohn Aug 23 '18 at 18:32
  • Finer grained is smaller intervals; coarse grained is larger intervals. If you are preenting a slider to go through all possibilities, you may want to label one end fine and the other coarse (though the latter is confusing). However, presenting only a single bar is poor dataviz; you'd have to be pretty sure the context makes that meaningful (and it's likely never meaningful). – Mitch Aug 23 '18 at 19:20
  • I updated the post to clarify. The suggestions for 'all time' or equivalents are close, but I would love to indicate that the histogram bin is still limited by the interval (or range) provided by the user. – Dan Aug 29 '18 at 2:46
1

Cumulative

Nice explanation by Forbes.

What histogram represent?

Histograms are used to show distributions of variables while bar charts are used to compare variables. Histograms plot quantitative data with ranges of the data grouped into bins or intervals while bar charts plot categorical data.

The Wikipedia article on Cumulative Histogram.

A cumulative histogram is a mapping that counts the cumulative number of observations in all of the bins up to the specified bin.

So, data range that represents entire bin or the only bin spreading across the histogram is called cumulative range of time.

  • Hey, I really like 'cumulative'. I think bin ranges (what I've been calling granularity) of 'daily', 'yearly', and 'cumulative' make sense. Can you update the answer to include just 'Cumulative' as an option? – Dan Aug 29 '18 at 2:50

protected by tchrist Aug 24 '18 at 0:58

Thank you for your interest in this question. Because it has attracted low-quality or spam answers that had to be removed, posting an answer now requires 10 reputation on this site (the association bonus does not count).

Would you like to answer one of these unanswered questions instead?

Not the answer you're looking for? Browse other questions tagged or ask your own question.