Background: Establishing representative samples for Software Engineering surveys\nis still considered a challenge. Specialized literature often presents limitations on\ninterpreting surveys� results, mainly due to the use of sampling frames established by\nconvenience and non-probabilistic criteria for sampling from them. In this sense, we\nargue that a strategy to support the systematic establishment of sampling frames\nfrom an adequate source of sampling can contribute to improve this scenario.\nMethod: A conceptual framework for supporting large scale sampling in Software\nEngineering surveys has been organized after performing a set of experiences on\ndesigning such strategies and gathering evidence regarding their benefits. The use of\nthis conceptual framework based on a sampling strategy developed for supporting\nthe replication of a survey on characteristics of agility and agile practices in software\nprocesses is depicted in this paper.\nResult: A professional social network (Linkedln) was established as the source of\nsampling and its groups of interest as the units for searching members to be\nrecruited. It allowed to deal with a sampling frame composed by more than\n110,000 members (prospective subjects) distributed over 19 groups of interest.\nThen, through the similarity levels observed among these groups, eight strata\nwere organized and 7745 members were invited, from which 291 have confirmed\nparticipation and answered the questionnaire.\nConclusion: The heterogeneity and number of participants in this replication\ncontributed to improve the strength of original survey�s results. Therefore, we\nbelieve the sharing of this experience, the instruments and plan can be helpful for\nthose researchers and practitioners interested on executing large scale surveys in\nSoftware Engineering.
Loading....