Scribd
Upload
4 views18 pages

Chapter 12

Mixed-methods designs integrate both quantitative and qualitative research techniques to address complex research problems effectively. The document outlines various mixed-methods designs, including convergent, embedded, exploratory, explanatory, and multiphase iterative designs, emphasizing their unique characteristics and applications. It also discusses the challenges and benefits of conducting mixed-methods research, highlighting the importance of combining data types for a comprehensive understanding of research questions.

Uploaded by

7znws6b46s
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
4 views18 pages

Chapter 12

Mixed-methods designs integrate both quantitative and qualitative research techniques to address complex research problems effectively. The document outlines various mixed-methods designs, including convergent, embedded, exploratory, explanatory, and multiphase iterative designs, emphasizing their unique characteristics and applications. It also discusses the challenges and benefits of conducting mixed-methods research, highlighting the importance of combining data types for a comprehensive understanding of research questions.

Uploaded by

7znws6b46s
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
Mixed-Methods Designs Many research problems have both quantitative and qualitative dimensions. To fully ‘address them, then, the researcher must use both quantitative and qualitative tech- niques. Thus, quantitative and qualitative methodologies are not necessaatly a case of elther-or, but rather a case of more-or-less. Learning Outcomes 12.1. Identify situations in which and hypotheses, (b) conducting a ‘mixed-methods designs are literature review, (¢) choosing one oF especially useful, ‘more samples, (d) maximizing the 12.2. Describe general characteristics and overall validity of a research project, purposes of (a) convergene designs, and (e) addeessing porential echical (b) embedded designs, (c) explor- ‘concerns, arory designs, (d) explanatory 124 Wentify appropriate and efficient designs, and (c) multiphase iterative approaches to analyzing data in a designs. imixed-methods study. 12.3. Describe effective strategies 12.5. Explain how you might conduct a for conclucting mixed-methods systematic review of qualitative research, especially those related to research studies regarding a () identifying research questions particular topic. Some research problems practically scream for both quantitative and qualitative dara, These problems cal for Such teseatch involves not only collecting, analy ing, and incexpreting boch quantitative and qualiracive data bue also Amegrateng conclusions from ‘those dara inco a cohesive whole, AAs you may have noticed, this chapter isa relatively short ane. It is short nor because mixed- methods scudies ate quick and easy methods reseatch draws largely on quantitative and qualitative research sceategies addressed in previous chapters. For instance, ina typical mixed-mechods investigation, the tesearcher must be ‘well-versed in most ot all of the following skill sers (Creswell & Plano Clatk, 2011) chey definicely are noe quick and easy-—bue because mixed= Identifying focused and useful research questions Formulating and seravegically testing hypotheses (Choosing one or more samples that enable appropriate inferences about a larger population Controlling for confounding variables Creating and using measurement instruments that have validity and reliability for their purposes Conducting structured, semistructured, and open-ended interviews Analyzing qualitative data (identifying units suitable for coding, applying the codes, discerning general themes underlying the data, et.) Caleulating and drawing inferences from descriptive and inferential statistics swing and persuasively arguing for reasonable conclusions from qualitative data (¢hrough triangulation, negative case analysis, thick description, etc.) 330 Chapter 12. Mixed-Methods Designs Because « mixed-methods study requizes both quantitative and qualitative research skill, i can be an especially challenging undertaking fora novice researcher. The tickiese part of mixed- ‘methods research is in combining the two methodological taditions into a research endesvor in ‘which all aspects substantially coneribute to a single, greater whole. In other words, a good ‘mixed-methods study is one that effectively and convincingly “hangs together”! If you have the requisite skills and experience, however, we urge you to take on the chal- lenge, because you might very well obtain a more complete, compeehensive answer to your fe- search question than would be possible with only quanticative or only qualitative methodologies. WHEN MIXED-METHODS DESIGNS ARE MOST USEFUL AND APPROPRIATE In some disciplines, mixed-methods sesearch is becoming increasingly fashionable, reendy, hhip"—so much so that many universities now offer specific courses on mixed-methods ech- niques. But fashion and crendiness are hardly legitimate reasons to conduct a mixed-mechods scudy. Ultimately, decisions about research design must be driven by the research problem and its subproblems, Some problems and subproblems call for only quancicative data, some call for ‘only qualitative data, and some ate best addressed with doth kinds of daca, On average, a mixed-methods research study requites moce ofa tesearcher’s time and energy ‘chan a strictly qualitative of quancicative seudy. Why, then, would a researcher want c0 go t0 the trouble of collecting, analyzing, interpreting, and integrating both quantitative and qualitative data? Following are several good reasons (Bryman, 2006; Greene, Caracelli, & Graham, 1989) Completeness. A researcher can fully address a research problem and its subproblems only by collecting, analyzing, and interpreting both quantitative and qualitative data, Complementarity, Quantitative aspects ofthe study can compensate for wealenesses in qualitative reseazch, and vice verss. For example, the results of unsteuctured interviews swith only a small number of individuals (which might raise concerns about generaliz- bility) can be replicated by administering a questionnaire to a larger, more representa tive sample, | Hypothesis generation and testing. Qualitative data often provide insights that help a researcher form hypotheses about cause-and-eflect relationships—hypotheses that the researcher can subsequently test through controlled, quantitative eesearch, Development of appropriate research tools and strategies, One type of data can in form and guide subsequent collection of another type of data. For example, unstructured interviews (yielding qualitative data) can guide the construction of appropriate questions for a survey (which will yield quantitative data) | Resolution of puzzling findings. In a quantitative study, vatious results can some ‘times seem inconsistent or contradictory; qualitative data may reveal underlying nuances sand mesnings that can help the researcher make sense of the numbers. | Triangulation. A researcher can make a more convincing case for pasticular conclu sions if both quantitative and qualitative data lead to those conclusions. COMMON MIXED-METHODS DESIGNS In previous chapters we have touched on a few ways in which quantitative and qualitative meth- ‘ds might be combined into a single study For example, in a large-scale survey, questionnsaites might include both (a) racing scales or checklists that yield numerical data and (b) open-ended questions that yield verbal responses requiring qualitative analysis (see Chapter 6), Historical reseatchets often make use of both qualitative and quantitative data in a single reseatch inguity (Gee Chapter 10), And the effectiveness of people's study strategies might be measured both "Tedaie and Thoakkes (2010) have sggerted chat a ody that dvr alec otegzate Findings ad conclusion rm qancirativ and quale daa igh bere be cle quasi, ‘Common Mixed-Methods Designs 331 ‘quantitatively (e.g., by the aumber of facts they recall) and qualitatively (e.g, by the content of ‘heir think-aloud study sessions; see Chapter 7). ‘The ways in which a researcher might combine quantitative and qualitative methods are almost limicless, restricted only by the researcher's imagination and creativity, as well as by the nature of the research problem. To help you envision some of the possibilities, we describe five _general types of mixed-methods designs, based on categories suggested by Creswell (2014) Convergent Designs Ina convergent design, a researcher collects both quantitative and qualitative data in parallel, usually at the same time and with respect ¢o the same general research problem. The ceseazcher gives similar o equal weight to the two types of data and strives for triangulation, with the Ihope chat analyses of both data sets lead to similar conclusions about the phenomenon under investigation, Embedded Designs ‘An embedded design is similar to a convergent design, in that both quantitative and quali- tative data aze collected within the same general time frame, However, one general spproach dominates—perhaps a qualitative approach, but more often a quantitative one—with the other approach serving in a secondary, supplementary role. For example, when planning a large-scale survey of people’ attitudes or opinions about « controversial copic, a researcher might create a seties of ststements with which participants either “agree” or “disagree” at various points along a sating-scale continuum, Withia this generally quantitative instrument, however, the researcher ‘could embed several open-ended items in which pazticipants explain their ratings. Such qualits- tive data could help the researcher make better sense of the numerical findings Exploratory Designs An exploratory design typically encompasses two phases, In Phase 1, a researcher uses one or ‘mote qualitative methods to get a general sense of characteristics, phenomena, and/or issues related (0 the topic of study. The qualitative data—pethaps [rom observations, interviews, of bboth—provide a basis for a more systematic, quantitative study in Phase 2. For example, quali- tative observations of s phenomenon in a real-world setting might help a researcher develop hy- ppotheses co be systematically tested in an experimental study, or che results of a few unstructured interviews might help the researcher develop appropriate questions for a questionnaite adminis- tered toa much laeger sample—and possibly also to determine important subgroup differences to keep in mind when identifying the Phase 2 sample. Explanatory Designs Like an exploratory design, an explanatory design is usually a ewo-phase process, but in this case the quantitative phase comes fist, Mote specifically, Phase 1 involves collecting consider able quancicative daca, perhaps in an experiment, ex post facto study, of survey. However, this first phase yields only numbers (e.g, percentages and/or averages). Collecting qualicative daca in a Phase 2 follow-up—for instance, asking a subsample of Phase 1 participants co describe ‘whac they were thinking or feeling duting an experimental intervention or to elaborate on theit answers to survey questions —can help the researcher give greater substance and meaning to the numbers Multiphase Iterative Designs A multiphase iterative design includes three or mote phases, with eatly ones providing foun- QUAN. 2, This can best be categorized as an embedded devign: ‘The rating-scale responses yield ‘quantitative data; the responses to the open-ended questions yield qualitative data that help to explain why participants responded ¢o particular rating-scale items as they did Because qualitative data ate collected for only 10% of the rating-scale items and appear to carry less weight than the quantitative data, chis design might be symbolized as QUAN(qual) 3, This is an explanatory design: The initial questionnaite yields quantitative data regard ing apparently popular and unpopular individuals, and the subsequent interviews yield {qualitative data that might shed light on why certain individuals ace well-liked and disliked, The design might be depicted ss QUAN-9QUAL, 4, This is a mulbiphaveiterasve design with three phases. In Phase 1, the progsam is admin- istered and quantitative data (GPAs) are collected for program participants and nonpar- ticipants, In Phase 2, qualitative data ace collected from unsteuctuced interviews to gain insights about how the program might be improved. In Phase 3, the revised program is offered, and once agsin quantitative data are collected to determine the program's effectiveness, The design might be depicced as QUAN-QUAL>QUAN.

You might also like