Skip to content
Quantoros

If missing observations are omitted, which n belongs in an independent-sample standard error?

StatisticsLevel: IntermediateRobust summaries

If missing observations are omitted, which n belongs in an independent-sample standard error?

Hints
  • Count actual measurements.
  • Deletion is not automatically unbiased.

Answer

Use the number of retained observations, not the original row count. Omission still needs a defensible missing-data assumption.

Source and licence: SciPy — statistical estimators and hypothesis tests · BSD-3-Clause · answer: Quantoros editorial

Related questions