engleski

Impact of the number of shown questions on response rates in business web surveys

The response rates in web surveys tend to be low. In order to achieve higher response rates some improvements in the questionnaire design should be done. In the paper it has been investigated if different numbers of questions, which are shown to a respondent at once per questionnaire page or per questionnaire screen, have statistically significant impact on response rates. For the research purposes, response rates from business web survey, which was conducted on the sample of Croatian enterprises in 2016, were observed. Three different numbers of question levels were defined: one question per screen, group of questions, and all questions at once. The differences in achieved response rates were observed at overall enterprises level but the analysis according to size, main activity, legal form and place of headquarters of enterprises was conducted also. The analysis has shown that in most cases the lowest response rates were achieved when group of questions was presented to a respondent.

business web survey ; Croatian enterprises ; response rate ; statistical methods use

This work has been partially supported by Croatian Science Foundation under the project STatistical Modelling for REspoNse to Crisis and Economic GrowTH in WeStern Balkan Countries – STRENGTHS (No.: IP 2013- 9402). Sažetak rada dostupan je i u Book of Abstracts of the ISCCRO - International Statistical Conference in Croatia, Vol. 2, No. 1, p. 18, ISSN: 1849-9864 (print), ISSN: 2584-3850 (online).