Standard error: what it means and how to read it

In the report: se — The standard error of the estimate: how much it would vary from sample to sample.

How to read it

The precision of the difference: t is the difference divided by it, and the interval is built around it. Rarely reported on its own.

In plain words

A shop owner looked at 100 bills and found that the average was 40 dollars. She wondered how far another 100 bills could land from 40. She asked for se, the standard error, and got 2. Now she knows that her 40 is known to within about 2 dollars, so another 100 bills would usually average somewhere around 38 to 42. With 400 bills se would come out 1, so the average would be known twice as well. It is rarely written on its own, but the range around the average and the test of a difference are built on it.

Example

The cell with se is selected in each report; point at a label to see its note.

  • — the sample data (50 rows) the examples use
  • — =STATS_PAIRED(Data!A1:T51, "before,after",0.95,"two-sided")
  • — =STATS_INDEPENDENT(Data!A1:T51, "y,x1", "welch",0.95)
  • — =STATS_ONE_SAMPLE(Data!A1:T51, "score", 5, 0.95,"two-sided")

Where you see it

Get it in your sheet

One formula in a cell gives the whole report, Standard error included. ALS Stats is a free add-on for Google Sheets™.

Install ALS Stats from Google Workspace Marketplace (opens in a new tab)