Morse(1991) suggests that four types of sampling are used in qualitative research: the purposeful sample, the nominated sample, the volunteer sample and the sample that consists of the total population. She states that ‘when obtaining a purposeful (or theoretical) sample, the researcher selects a participant according to the needs of the study. Morse sees both purposeful and theoretical sampling as being synonymous with each other. Sandelowski views all sampling in qualitative research as purposeful and suggests three kinds of purposeful sampling: maximum variation, phenomenal variation and theoretical variation. He suggested that the maximum variation is one of the most frequently employed kinds of purposeful sampling and researcher wanting maximum variation in their sample must decide what kind(s) of variation they want to maximize and when to maximize each kind. Examples of variation may be race. Class, gender or other personal-related characteristics. Phenomenal variation is variation of the targets phenomenon under study and decision to seek phenomenal variation is often made a priori in order to have representative coverage of variables likely to be important in understanding how diverse factors configure as a whole. This sampling resembles the Morse purposeful sampling. However it may be argued that Morse’s use of the phrase ‘or theoretical’ in connection with purposeful sampling is ambiguous.(Sandelowski, 1995) describes theoretical variation as variation on a theoretical construct that is associated with theoretical sampling, or the sampling on analytic grounds characteristics of grounded theory studies. Thus theoretical sampling may be seen as a variation of purposeful sampling but all purposeful sampling is not necessarily theoretical sampling.
Theoretical sampling is always purposeful and it could be said that some qualitative studies mat contain purposeful and theoretical sampling. However, other studies may contain only purposeful sampling since purposeful sampling is not always theoretical. It may be acceptable to view theoretical sampling as a variant within purposeful sampling. Glaser (1992) stated that theoretical sapling in grounded theory is the process by which data collection is continually guided(p.102). Therefore a more accurate term for theoretical sampling could be ‘analysis driven purposeful sampling’ or ‘analysis governed purposeful sampling’. According to Glaser (1978) the discovery of grounded theory implicitly assumes that the analyst will be creative (p.20). This author argues for researcher to be more adaptable and creative in designing sampling strategies that are aimed at being responsive to real-world conditions and that meet the information needs of the study.