Beyond qualitative and quantitative data linking: An example from a mixed method study of family recreation

Therapeutic Recreation Journal, Second Quarter 2000 by Mactavish, Jennifer B, Schleien, Stuart J

In addition to collecting information about family recreation, the survey instrument invited families to participate in a series of follow-up interviews. Forty-four families indicated an interest in being interviewed and from this pool 16 were ultimately selected using a sequential-purposive sampling technique (Patton, 1990).4 That is, the first 8 families were selected using a criterion approach, which sought to ensure that the families interviewed reflected the overall socio-demographic diversity of the sample. Subsequently, 8 additional families were selected based on survey responses that indicated potential for extending insights about one or more of the research questions of interest (i.e., a theory-based purposive technique).

The interviews were used to intensively explore issues arising from the questionnaire data while being flexible enough to accommodate emerging issues and questions. To fulfill these aims, an interview guide, which included questions specific to each of the areas of interest (nature, benefits, constraints), was used to facilitate the interviews (Patton, 1990). In most cases (68%), the interviews involved multiple adult members of the same family, usually two parents, and were conducted in the families' homes.

Analyzing the Questionnaire and Interview Data

Data analysis in quantitative and qualitative research typically includes one or more approach depending on the nature of the data and the research questions. Within quantitative studies, at least two basic approaches to analysis are commonly used: (a) descriptive statistics for summarizing information, and (b) comparative statistics for examining differences between groups and/or relationships between variables (Babbie, 1989; Kerlinger, 1986). In qualitative research, there are a variety of established procedures for analyzing data (Huberman & Miles, 1994). Generally, these procedures involve converting raw narrative data (e.g., field notes, audiotapes) into partially processed data (e.g., transcripts), which are then coded and subjected to any one of a number of analysis schemes (e.g., key theme analysis, constant comparative; Huberman & Miles; Merriam, 1988; Yin, 1991).

Mixed method research, as would be expected, may draw on one or more of the data analysis approaches found in the quantitative or qualitative research traditions. In an effort to capture the range of possible applications, Tashakorri and Teddlie (1998) described four different approaches for combining data analysis techniques from both traditions within mixed method research:

1. Conducting quantitative and qualitative data analyses on the same data simultaneously.

2. Confirming/expanding the results from one method of data analysis (e.g., quantitative) through a secondary analysis of the same data using a different approach (e.g., qualitative).

3. Using, sequentially, the findings obtained through one approach to data analysis (e.g., quantitative) as a starting point for the analysis of other data generated via an alternative approach (qualitative).