What is it about?

We randomized a sample of Veterans to receive different cover letters that differed what they were told about a postal survey's content, how we obtained their name for the project, and how much incentive they would receive for participating. We believed that more general descriptions of the survey's content, a more general description of how we obtained their name, and a higher incentive would reduce non-ignorable non-response bias.

Featured Image

Why is it important?

Non-ignorable non-response bias can skew scientific conclusions dramatically if it is not handled well. However, off-the-shelf software for non-ignorable non-response bias is not available. Thus, dealing with non-ignorable non-response bias after data are collected is time-consuming and expensive. Low-cost options, such as modifying the cover letter's content, to avoid non-ignorable non-response bias from even happening would tremendously simplify the analysis of postal data.


Although we had great hopes for the study's outcomes, results showed that substantial non-ignorable non-response bias still occurred in most of the study arms.

Dr. Maureen Murdoch
Minneapolis VA Health Care System

Read the Original

This page is a summary of: Impact of different cover letter content and incentives on non-response bias in a sample of Veterans applying for Department of Veterans Affairs disability benefits: a randomized, 3X2X2 factorial trial, BMC Medical Research Methodology, March 2022, Springer Science + Business Media, DOI: 10.1186/s12874-022-01531-x.
You can read the full text:



The following have contributed to this page