Improving mail survey response rates in Japan: empirical tests for envelopes, request letters, questionnaires, and schedules

ABSTRACT

While many studies examine tools and techniques to improve survey response rates, it remains unclear as to which are effective, and response rates continue to decline. In this study, we examine the effect of four variables expected to influence mail survey response rates: (1) the use of semi-transparent envelopes versus ordinary paper envelopes for delivery, (2) the level of content in the request letter (simple or detailed), (3) the length of the questionnaire, and (4) the survey schedule. We found that the total response rate was 45.4%, while those of the experimental conditions were as follows: (1) semi-transparent versus ordinary paper envelopes, 46.2% versus 44.7%; (2) simple versus detailed request letters, 44.7% versus 46.2%; (3) 4-page versus 8-page questionnaires, 46.0%versus 44.8%; and (4) holiday versus ordinary day, 45.6% versus 45.3%.We found no significant differences in response rates for any of the experimental variables; that is, the logistic regression analysis revealed no relationship between the four experimental conditions and the response rate.

KEYWORDS:

• Response rate
• mail survey
• semi-transparent envelope
• questionnaire
• survey schedule

Acknowledgments

We express our sincere thanks to all respondents of this survey for their cooperation. We also thank the anonymous reviewers for their thoughtful advice.

Disclosure statement

No potential conflict of interest was reported by the authors. This study was financially supported by the Department of Statistical Data Science at the Institute of Statistical Mathematics, Japan.

Additional information

Notes on contributors

Yoosung Park

Yoosung Park is an associate professor in the Department of Statistical Data Science at the Institute of Statistical Mathematics, Japan. She holds a Ph.D. in Engineering from Tokyo Institute of Technology, Japan. Her main research focuses on survey methodology AND statistical analysis of survey data; she is currently interested in social psychological aspects of human behaviour through social survey, especially with regard to public officials, local residents AND the Japanese national character.

Takahiro Tsuchiya

Takahiro Tsuchiya is a professor in the School of Data Science at Yokohama City University. After his postdoctoral studies at Tokyo University, he had worked as a survey statistician at the Institute of Statistical Mathematics and has been a board of a number of educational institutions, e.g. the Education Policy Section of the Ministry of Education, Culture, Sports, Science and Technology and the National Institute for Educational Policy Research, to name a few.