Using the internet for data collection in business research

Introduction Imagine a master’s degree student facing the need to collect primary data to proceed into quantitative analysis in the business field. The tight deadline for getting the degree and the inherent difficulty in research planning and collecting data can both be frightening. Before the internet, the alternative would be a convenience non-probabilistic sampling, which is a generally easier and faster way to obtain data than probabilistic sampling. Thus, considering the internet’s use to speed up data collection and reduce costs, what are the advantages and recommendations to be accounted for by business researchers? The use of the internet to conduct surveys is attractive for business researchers due to its benefits in speed, access to respondents and the large amounts of data it can gather. The main advantages of online versus offline data collection are time-saving, cost reduction, simplified data tabulation and purification processes, flexibility and format control. However, there are issues related to respondents’ attention, sample representativeness and control, which can be amplified as most of the data collection for business research on the internet occurs through convenience sampling. Also, self-selection bias can represent severe jeopardy in online surveys. In this short essay, we draw on the problem of sample representativeness on Web-based data collection, and then we discuss it with emphasis on two common procedures to mitigate its risks and challenges: