Measurement equivalence of paper-and-pencil and internet organisational surveys: A large scale examination in 16 countries
In multinational surveys, mixed-mode administration modes (e.g. combining Internet and paper-and-pencil administration) are increasingly used. To date, no studies have investigated whether measurement equivalence exists between Internet data collection and data collection using the conventional pape...
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2009
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/lkcsb_research/5575 https://ink.library.smu.edu.sg/context/lkcsb_research/article/6574/viewcontent/internetpaper.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Summary: | In multinational surveys, mixed-mode administration modes (e.g. combining Internet and paper-and-pencil administration) are increasingly used. To date, no studies have investigated whether measurement equivalence exists between Internet data collection and data collection using the conventional paper-and-pencil method in organisational surveys which include a large number of countries. This paper examined the measurement equivalence of a truly global organisational survey across Internet and paper-and-pencil survey administrations. Data from an organisational survey in 16 countries (N = 52,461) across the globe were used to assess the measurement equivalence of an organisational climate measure within each country in which the survey was administered. The empirical data provided strong indications which support the measurement equivalence of the multi-item survey instrument across Internet and paper-and-pencil surveys in virtually all countries in which the survey was conducted. These findings suggest that merging data obtained through Internet and paper-and-pencil data administration in a particular country is legitimate as no evidence was found for differential effects across both modes of data collection. |
---|