The question studied was whether opinions and attitudes of persons interviewed about educational interests and perceived needs at randomly selected geographic locations in a metropolitan area differed from those of three other persons living in the immediate vicinity. The study provides empirical information concerning the use of cluster sampling for this purpose in a metropolitan area compared to simple random sampling when a reliable list of population elements is available. With few insignificant exceptions, no statistically significant differences were found between the two groups. Study precision might have been improved and resources conserved had more household units rather than clusters been selected.
No takes yet. Share an insight, caveat, or question.
Raymond J. Young (1986) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: