Go to Statistics Portal


Statistics Directorate    
French Equivalent: Non réponse

A form of nonobservation present in most surveys. Nonresponse means failure to obtain a measurement on one or more study variables for one or more elements k selected for the survey.

The term encompasses a wide variety of reasons for nonobservation: "impossible to contact", "not at home", "unable to answer", "incapacity", "hard core refusal", "inaccessible", "unreturned questionnaire", and others. In the first two cases contact with the selected element is never established.

Non-response leads to an increase in variance as a result of a reduction in the actual size of the sample and the recourse to imputation. This produces a bias if the non-respondents have characteristics of interest that are different from those of the respondents. Furthermore, there is a risk of significantly underestimating the sampling error, if imputed data are treated as though they were observed data. (Statistics Canada, "Statistics Canada Quality Guidelines", 4th edition, October 2003, page 59, available at http://www.statcan.ca:8096/bsolc/english/bsolc?catno=12-539-X&CHROPG=1)

are two types of non-response:

First, a sampled unit that is contacted may fail to respond. This represents "unit non-response".

Second, the unit may respond to the questionnaire incompletely. This is referred to as "item non-response".

Source Publication:
Sarndal C.E., Swensson B., Wretman J., "Model assisted survey sampling", Springer - Verlag, New York, 1992.

Cross References:
Item non-response
Non-response errors
Non-response rate
Refusal rate
Response rate, item


Statistical Theme: Methodological information (metadata)

Glossary Output Segments:

Created on Thursday, May 23, 2002

Last updated on Tuesday, June 11, 2013