Sampling in Mixed Methods Research

Sampling in this type of research requires knowledge of sampling in qualitative and quantitative research because quali tative and quantitative sampling methods and strategies are systematically combined in mixed research. Typically, the mixed methods researcher selects the qualitative sample using one of the qualitative-sampling techniques and the quantitative sample using one of the quantitative-sampling techniques. We focus here on classifying mixed methods sampling using a typology of sampling designs developed by Anthony Onwuegbuzie and Kathleen Collins.

According to the Onwuegbuzie and Collins (2007) scheme, sampling in mixed research is classified into “mixed sampling designs.” The sampling designs are classified on the basis of two major criteria: time orien tation and sample relationship. Time orientation is deter mined by answering this question: “Do the qualitative and quantitative phases in the mixed research study occur concurrently or sequentially?” If the data are collected for the qualitative and quantitative phases of the study at approximately the same time, then this is [Page 458]known as a concurrent time orientation. In this situation, both sets of data are interpreted during data analysis and during the data interpretation stage. If the data are obtained in stages and the data from the first stage are used to shape selection of data in the second stage then this is known as a sequential time orientation. The second major criterion used in determining one's mixed sampling design is sample relationship, which is deter mined by answering this question: “Is the relationship between the quantitative and qualitative samples identical, parallel, nested, or multilevel?” In an identical sample relation, the same people participate in the quantitative and qualitative phases of the study. In a parallel sample relation, separate quantitative and qualitative samples are drawn from the same population for the study. In a nested sample relation, the partici pants selected for one phase are a subset of the participants selected for the other phase.

In a multilevel sample relation, the quantitative and qualitative samples are selected from different levels of a population.

The mixed sampling design matrix is constructed by combining the two major criteria just provided—time orientation (which has two types) and sample relationship (which has four types)—to form the eight mixed sampling designs: (1) identical concurrent sampling design, (2) identical sequential sampling design, (3) parallel concurrent sampling design, (4) parallel sequential sampling design, (5) nested concurrent sampling design, (6) nested sequential sampling design, (7) multilevel concurrent sampling design, and (8) multilevel sequen tial sampling design. Once the mixed sampling method has been determined, the researcher determines the qualitative and quantitative sampling methods and sample sizes. Then, the samples are located, and data are collected and analyzed using mixed methods data analysis. For more information, see Onwuegbuzie and Collins (2007).