The report is where an analysis becomes a decision. The finding goes first, in a sentence, with the number that supports it and the number that would change it. Everything else exists to make that sentence checkable.
About 1 min of reading
Before this new lesson, one small question about the lesson you just finished. Recall it, do not look it up.
Write a finding with its falsifier.
The finding sentence
Before you run it, say out loud what it will print. Then open the answer.
The falsifier
Before you run it, say out loud what it will print. Then open the answer.
Read the first example one line at a time. A line that prints shows what appears on screen; the rest set things up quietly.
Say 'about 4 percent' rather than '4.03 percent' when the input has 2 percent noise. False precision invites decisions on a number that cannot support them, and it is the fastest way to lose a reader's confidence.
Write the question the reader asked, then the answer. If you cannot state the question, you have answered something else, and the analysis may be correct and useless.
Open with the sentence a reader would act on. Method and caveats follow. Burying the finding in the fourth paragraph of a methodology is how a correct analysis fails to change a decision.
'The conclusion flips if the 22 unknown rows are all in the north region' tells the reader what to check. That sentence is the cheapest way to make an analysis falsifiable.
Each figure in the report links to the stage that produced it. A number nobody can trace is a number nobody can fix, and when it turns out wrong the whole report has to be redone.