Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/323399 
Year of Publication: 
2020
Citation: 
[Journal:] Croatian Review of Economic, Business and Social Statistics (CREBSS) [ISSN:] 2459-5616 [Volume:] 6 [Issue:] 2 [Year:] 2020 [Pages:] 43-57
Publisher: 
Sciendo, Warsaw
Abstract: 
In the autumn 2017, The Statistical Office of the Republic of Slovenia (SURS) has conducted for the first time a survey on daily passenger mobility of Slovenian residents. The key statistics are on persons' daily traveling habits, such as number of trips, travelled distance, time spent on traveling, and so on. Two independent samples were selected for the simultaneous collection of data by two modes, face-to-face interview (CAPI) and online questionnaire (WEB). The goal of this study is to identify the possible sources of mode measurement errors, with the objective to better design and thus improve the whole data collection process. The detailed mode effect analysis is performed by the comparison of the key statistic estimates and the use of regression models. Usually the measurement mode effect is an issue in surveys on the more sensitive topics or persons' opinions. This work points out that, first, the mode measurement effect can be an issue also in a more factual survey content, and second, the corresponding statistical data processes can have an important contribution to minimising measurement errors. The results show that WEB respondents are inclined to join two or more trips into one reported, which gives lower estimate of average number of daily trips. The main reason is the demanding questionnaire content. Additionally, the complex data editing process was still insufficient to correct completely for such measurement error. The possible improvements of the data collection process are also discussed.
Subjects: 
data comparability
mixed mode surveys
mode measurement effect
mode selection effect
JEL: 
C10
C18
C83
R41
Persistent Identifier of the first edition: 
Creative Commons License: 
cc-by-nc-nd Logo
Document Type: 
Article

Files in This Item:
File
Size





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.