Identify a research problem appropriate for a mixed methods research study and write a paper describing how you would address that research problem.
Mixed Methods
Qualitative and quantitative methods can be combined in a variety of ways to form what is called mixed research methods. This is an attempt to draw from multiple epistemologies to frame and understand phenomena. As a result, researchers are supposed to increase the validity of their studies (through triangulation) to allow them to reach generalizations that will support the formation of theories to accurately describe the phenomena under investigation. While combinations of methods seem to move away from the methodology and get closer to practice as an approach to examining a research problem, there are many researchers who view the methodology as a separate and independent epistemological way of approaching research. This brings mixed methods into the realm of pragmatism (somewhere in between positivism and constructionism). Others, though, believe that paradigms are not to be viewed as distinct, but rather as overlapping, or with fluid boundaries where one gives rise to and supports the other, so combining them is quite an acceptable way of conducting research. In any case, following a mixed methods approach should not be considered as an attempt to alleviate the disadvantages of one of the methodologies you have seen so far with the advantages of the other, but rather, as a need for properly addressing the research problem under investigation.
The main issue with mixed methods is the sequence and extent of applying the quantitative and qualitative components of inquiry. For example, you might be interested in understanding the context of a real-life phenomenon like leadership in transient teams (teams that are formed for a specific task and then dissolved). If you are not aware of the characteristics of leadership that lead to success or failure of leaders in such teams (or there is no strong research behind it), you might decide to begin with a qualitative methodology that through in-depth interviews with select leaders of transient teams will reveal key characteristics. You will then follow this with a quantitative methodology whereby with the development of a widespread questionnaire, you will prove that the identified characteristics (or some of them) exist universally in transient teams. Alternatively, you might already know (for example, from past research or similar cases) the range of possible characteristics, so you might decide to start with a quantitative methodology to identify the specific leadership characteristics that affect transient team performance, and then follow with a qualitative methodology (for example, in-depth interviews) to identify the reasons behind the influence of the specific characteristics.
There are three possibilities of mixed methods designs. You can start with a quantitative approach (large sample) that will provide findings like certain characteristics (attitudes, traits, perceptions, etc.) of a population and follow up with a qualitative approach (specific small sample) for explanations to surface, and thus the method is called explanatory sequential mixed methods. On the other hand, there are exploratory sequential mixed methods where you can start with a qualitative approach (small sample) to explore the range and depth of a phenomenon and continue with qualitative (to a wider sample) to provide the “proof” and confirm what you found. Finally, you can have both methods working in parallel (convergent parallel mixed methods) and aim at calibrating each of them and comparing their results to converge (or diverge) for an interpretation, enhancing in this way the validity of the research findings. An example of the parallel application of methods is when they are combined in one instrument, like a questionnaire that has both closed-ended and open-ended questions.
Apart from the sequence of execution of the various methodologies, of significant importance is dominance. The uncomplicated way of viewing dominance is in terms of the time devoted to each methodology. This is a simplistic view as their importance in research might be different. For example, one might dedicate plenty of time and resources in in-depth interviews to confirm past research findings while spending little time in posting a questionnaire online and processing the results. While the interviewing part might seem necessary, the importance of the quantitative part is at a much higher level.
Along with the advantages of mixed methods research like the well-rounded investigation of a phenomenon and the insight they could provide for guiding the future choice of methods, there are criticisms that need to be considered before adopting such methodologies. Prominent among them are the contradictions of the underlined paradigms that need to coexist and provide support for the research, as well as the competencies that the investigators need to have as they need to cover the full spectrum of quantitative and qualitative methodologies. Additionally, mixed methods studies take significantly more time and more resources to complete, making them unsuitable when time and resources are of the essence. In closing, mixed methods might be ideal for comparing quantitative and qualitative perspectives for instrument calibration, for discovering the parameters and variables involved in phenomena, for understanding and providing support with raw/quantitative data for the “how” and “why” of phenomena, and in support of interventions and change initiatives (like for marginalized populations).
Develop a Mixed Methods Research Strategy
Instructions
For this assignment, you must identify a research problem appropriate for a mixed methods research study and write a paper describing how you would address that research problem.
Be sure your paper includes the following:
Problem statement
Purpose statement
Data collection plan
Data analysis plan
Length: 3 to 5-page academic paper, not including title and reference pages
References: Include a minimum of 3 scholarly resources.
The completed assignment should demonstrate thoughtful consideration of the ideas and concepts presented in the course by providing new thoughts and insights relating directly to this topic. The content should reflect scholarly writing and current APA standards.
Requirements: Length: 3 to 5-page academic paper, not including title and reference pages
Sage Research Methods Qualitative and Mixed Methods in Public Health For the most optimal reading experience we recommend using our website. A free-to-view version of this content is available by clicking on this link, which includes an easy-to-navigate-and-search-entry, and may also include videos, embedded datasets, downloadable datasets, interactive questions, audio content, and downloadable tables and resources. Author: Deborah K. Padgett Pub. Date: 2014 Product: Sage Research Methods DOI: https://doi.org/10.4135/9781483384511 Methods: Case study research, Mixed methods, Grounded theory Keywords: social capital, surveying Disciplines: Health, Nursing, Sociology, Medicine Access Date: September 21, 2023 Publishing Company: SAGE Publications, Inc. City: Thousand Oaks Online ISBN: 9781483384511 © 2014 SAGE Publications, Inc. All Rights Reserved.
Mixed Methods The “new era” of method integration (Tashakkori & Creswell, 2007, p. 3) can be seen as a pragmatic response on the part of researchers wanting to maximize their understanding of a particular problem (Johnson & On-wuegbuzie, 2004; Morgan, 2007). Some research topics (such as public opinions about childhood vaccines) are manifestly quantitative; others (such as IV drug users’ needle–sharing practices) are undoubtedly qualita-tive. In the vast middle ground lie many opportunities to use both approaches for synergistic ends. At the same time, mixed methods designs are complicated and sometimes messy affairs (Creswell & Plano Clark, 2010). Integrating the quantitative and qualitative “sides” poses epistemological and logistical chal-lenges that few research courses address (Tashakkori & Teddlie, 2010). That said, the momentum behind this trend is unlikely to slow down anytime soon. The Rise of Mixed Methods and Their Rationale(s) Just as the term qualitative methods came of age in the 1970s, mixed methods is a fairly recent addition to the research lexicon (Tashakkori & Teddlie, 2010). Formerly (and sometimes still) referred to as “multimethod,” “multistrategy,” or “triangulation by method,” mixed methods studies currently offer a wide and at times con-fusing array of options (Bryman, 2006; Creswell, 2007; Tashakkori & Teddlie, 2010). Ethnographers and others have a long history of including quantitative data and analyses. This unheralded “mixing” lost favor as the methods became more interview–based with the rise of grounded theory and narra-tive approaches. In addition, mixing on the qualitative side was derogated in critiques asserting the incompat-ibility of positivist assumptions of realism with constructivist assumptions of multiple interpretations (Lincoln & Guba, 1985; Morgan, 2007). On the quantitative side, the soaring dominance of quantification and statistics by the mid–20th century cast doubt on the value of qualitative data with its small samples and presumed lack of generalizability. Pioneering quantitative methodologists (D. T. Campbell & Stanley, 1963; Cook & Campbell, 1979) acknowledged the util-ity of qualitative data, but only in a supplementary or minor role. Interestingly, D. T. Campbell (1979) recanted his earlier criticisms of case studies and went further to state that conflicting results in mixed methods studies should cast the quantitative results as suspect “until the reasons for the discrepancy are well understood” (p. Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 2 of 18Qualitative and Mixed Methods in Public Health
52). Caracelli and Greene (1997) discuss three reasons for carrying out mixed methods studies, which include triangulation, complementarity, and expansion. Triangulation, the earliest and most widely invoked of ratio-nales, refers to comparisons for purposes of corroboration (Morse, 1991). Because triangulation presumes a fixed point of reference waiting to be converged upon, its use has been criticized as naïve and sometimes misleading. It also raises questions when findings are divergent rather than convergent (Flick, 2004; Sande-lowski, 2000). Complementarity refers to enhancement or clarification. Thus, the quantitative and qualitative substudies represent different pieces of the puzzle. Expansion refers to presenting “side–by–side” or juxta-posed findings to keep them intact (Caracelli & Greene, 1997). Types of Mixed Methods Research All research designs operate from a premise of intentionality, and mixed methods designs point to the desire to link or integrate. As such, they portend specific procedures to carry this out (Haase & Myers, 1988). Inter-estingly, few mixed methods studies in the published literature use the terminology and notational systems promulgated by leaders in the field (Creswell, 2007; Morse, 1991; Tashakkori & Teddlie, 2010). Neverthe-less, it helps to recognize the many options and approach them in a systematic way. As shown in Table 3.1, the options in designing a mixed methods study involve two primary axes—sequential versus concurrent and dominant/subdominant versus equal (Creswell, 2003; Miller & Fredericks, 2006). Dominant refers to which method is given more weight and prominence in the study. When examining a study’s written report, this can be glaringly obvious or deeply ambiguous, depending on the study’s design and how clearly it is described. Sequential versus concurrent axes refers to the timing of the methods, whether used one at a time or simul-taneously. Table 3.1 Mixed Methods Designs Arranged by Timing and Dominance Sequential Concurrent DominantÐLess Dominant CELL 1 QUAL → quan qual → QUAN CELL 2—ÒNestedÓ QUAL + quan QUAN + qual Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 3 of 18Qualitative and Mixed Methods in Public Health
Using established notations of capital letters (for dominance or priority), arrows (for sequencing), and plus signs (for simultaneity; Morse, 1991), Table 3.1 shows various possibilities for the sequential and concurrent designs. As might be expected, QUAN–dominant designs are more common than QUAL–dominant designs and dominant/less–dominant designs are more common than equally weighted designs. Both of these obser-vations are a reflection of the way the research world is organized and the tendency to conserve resources and/or favor one method over another. A caveat before we go further: These design types are offered primar-ily as a heuristic device. In practice, mixed methods studies are complicated and not so easily categorized (Miller & Fredericks, 2006). Sequential Designs In sequential designs, how the study’s segments are prioritized and integrated depends on its priorities. As shown in Cells 1 and 4 of Table 3.1, this can occur in six different ways. Among the dominant/less–dominant designs, the most common (qual→QUAN and QUAN→qual) typically involve using focus groups or individual interviews to prepare for the “main event” (survey, instrument development, experimental trial, etc.) or to bet-ter understand it after the fact. The ecological validity of a quantitative study can be enhanced considerably by grounding the study in qualitative interviews and observation before or after. Conducting focus groups with students and teachers before implementing a safe–sex education program is one example of this approach; positioning the focus groups afterward is another example, albeit for a different purpose. QUAL→ quan and quan→ QUAL studies position their quantitative segments as less dominant. An example of the first would be an intensive qualitative case study of an innovative program for individuals with multiple sclerosis that is used to develop questions for a brief online survey of agencies serving MS patients. In the reverse sequence (quan→ QUAL), a telephone survey of parents in a school district might be used to select a QUAN → qual quan → QUAL Equal Weighting CELL 4 QUAL → QUAN QUAN → QUAL CELL 3 —ÒFully IntegratedÓ QUAL+QUAN Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 4 of 18Qualitative and Mixed Methods in Public Health
subsample willing to be interviewed in depth about their experiences with the district’s new program on child-hood obesity. Although less common, equal weighting in sequential designs (Cell 4 of Table 3.1) means that both qualitative and quantitative segments receive sufficient allocations of resources to meet their respective sampling and data quality needs. Concurrent Designs In concurrent designs, one method may be dominant over the other (QUAN+qual or QUAL+quan) or they may be given equal weight (QUAN+QUAL). As mentioned earlier, “dominant/less dominant” or nested designs (Cell 2 of Table 3.1) are much more common (Creswell, 2007). Box 3.1 offers an example of a QUAN+qual study carried out in different nations. Box 3.1 A Mixed Methods Study (QUAN+qual) Testing a Measure of Social Capital in Peru and Vietnam Mixed methods have an intrinsic appeal for instrument development and testing because most measures’ un-derlying constructs are complex and open to differing meanings and interpretations. One such concept, that of social capital, has become widely used as an indication of the ways that social relationships may confer health benefits, from fostering a sense of belonging to providing links to valuable resources. The measure-ment of social capital at the individual level is seen as a potential indicator of health in general and access to health care in particular (Szreter & Woolcock, 2004). DeSilva and colleagues (2006) developed a measure of social capital (the SASCAT), translated it into Spanish and Vietnamese, and administered it to a large sample of children’s caregivers (3,000 in Peru and 2,771 in Vietnam). In addition to psychometric tests of the mea-sure’s validity, the researchers criterion–sampled 20 Peruvian and 24 Vietnamese respondents for in–depth interviews. These “cognitive interviews,” lasting from 1 to 2 hours, elicited further thoughts and ideas related to each SASCAT item. An example of an item is, “In the past 12 months, have you joined together with other community members to address a common problem or issue?” The interviews were audiotaped and content analyzed to see if (and how often) open–ended comments diverged from the authors’ original intention re-garding each item’s meaning. The findings were revealing. Although the quantitative factor analysis results from the two countries were strikingly similar, the qualitative interviews brought several cultural misunder-Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 5 of 18Qualitative and Mixed Methods in Public Health
standings to the surface. The concept of “community,” for example, was readily accepted in Vietnam but not understood by many Peruvians (who defined it as one’s social support network, not the surrounding area). In both Peru and Vietnam, “trust” was not considered something one can impute to the “community” in general but only to known individuals. Similarly, “help from others” was largely defined as economic support—contrary to the measure’s inclusion of emotional support within the definition. The authors understandably concluded that cognitive validation needs to precede instrument development. Commentary: This study’s QUAN+qual design was an ambitious and successful application of mixed meth-ods. The two methods were used for corroboration as well as completeness (i.e., the researchers did not posit a single meaning for each item but instead sought out multiple meanings to improve the measure). The find-ings demonstrate the critical importance of qualitative methods in cross–cultural research in which subjective meanings can vary along cultural lines. If this is not taken into consideration, quantitative data collection will be prone to error and misunderstandings. In QUAN+qual designs, researchers typically collect qualitative data to enliven or illustrate their quantitative findings, for example, excerpts from responses to open–ended questions or case vignettes (Morgan, 1997). In the reverse QUAL+quan approach, qualitative researchers might collect some quantitative data via stan-dardized measures or they might use supplementary quantitative data from documents or archives. Snow and Anderson (1991) made use of tracking data from various agencies to supplement their intensive inter-views and ethnographic observation of the homeless. The resulting depictions contained both statistical and ethnographic descriptions of their lives. Using quantitative data can be risky with small samples, but if done judiciously it need not detract from the inductive, emergent nature of a qualitative study. Similarly, the inclu-sion of ancillary qualitative data does not challenge the primacy of a “big QUAN” study. A QUAL+QUAN study (Cell 3) is among the rarest of mixed methods types due to aforementioned demands on time and resources as well as the challenges of fully integrating the two “sides.” Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 6 of 18Qualitative and Mixed Methods in Public Health
Mixed Methods: Ways of Going About It Structural and Design Decisions: What, When, Where, and How? Leaving the abstract realm of design types for real–world decisions about mixing methods requires that we unravel the research process and decide which phases will (or should) intersect and which will remain intact. Are there constraints on doing this, or can one mix and match at will? Consider the following series of state-ments: • Paradigms (post–positivist, constructivist, critical) do not dictate methods (grounded theory, phenom-enological, experimental/quantitative, surveys, etc.). • Methods do not dictate data collection techniques (interviews, questionnaires, observation). • Techniques of data collection do not dictate data analyses. Such assertions are strongly opposed by postmodern contentions that one cannot mix positivist and construc-tivist epistemologies (Lincoln & Guba, 2000). But such objections have not slowed the movement toward mix-ing below the paradigmatic level (Morgan, 2007). (The reader might want to return to Figure 1.1 in Chapter 1 on page 15, which shows the downward line or spiral of a study.) Thus, a grounded theory study can be car-ried out using post–positivist or constructivist epistemologies; some studies appear to do both simultaneously. At a lower level, many a study has transformed qualitative data into numbers. To be sure, some combinations do not work, for example, narrative analysis and quantitative data. Moreover, one should not mix and match willy–nilly without considerations of fit and appropriateness. According to Sandelowski (2000), most mixing takes place “on the shop floor of research” (p. 246) during sampling, data collection, and data analysis. Tashakkori and Creswell (2007) discuss dual dimensions to sam-pling (probability and purposive), data collection (quantitative and qualitative), data analysis (statistical and thematic), and presentation of the findings (numeric and narrative). The points of contact between the quantitative and qualitative sides can be many or few. Sequential designs leave open the opportunity for each substudy to remain intact (assuming a reasonable connection is made). In concurrent designs, the parallel processes, or “strands” (Tashakkori & Creswell, 2007, p. 3), may intersect at one or more phases. The lowest level of mixing intensity is when the two sides stay separate and come together only at the end when findings are juxtaposed. Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 7 of 18Qualitative and Mixed Methods in Public Health
Mixing at the data analysis level, according to Tashakkori and Teddlie (2010), may include “qualitizing” quan-titative data and its opposite process of “quantitizing” qualitative data. The latter of these, which refers to converting qualitative data into numbers or variables, has a long history in content analysis. (An example of “quantitizing” is provided in Box 3.2.) Sandelowski (2000) “qualitized” her quantitative data by creating profiles or categorical types from scores on standardized measures. Box 3.2 ÒQuantitizingÓ Data in a Grounded Theory Study of Breast and Prostate Cancer Online Discussion Boards Online chat rooms and discussion boards offer an abundance of narrative data for qualitative analysis. Good-en and Winefield (2007) used grounded theory and a “quasi–numeric” (p. 103) approach to examine gen-der differences in language styles and communication among cancer survivors communicating online. They started with a hypothesis positing greater use of emotional communications by women and greater use of informational communications by men. They examined online communications among 69 women with breast cancer and 77 men with prostate cancer by using open, axial, and selective coding conducted independent-ly by two readers. The number of codes per message (or posting) and the frequency with which individuals posted were calculated and displayed in tables in the published article. From these analyses, two selective codes (“information support” and “emotional support”) were identified along with their respective axial and open codes. Examples of axial codes included “facts about the disease” (under information support) and “cop-ing philosophies” (under emotional support). Instances of open codes were counted in each database and categorized proportionately under each of these two main headings. As a result, Gooden and Winefield found that information communication comprised 60% of women’s communications and 64% of men’s communica-tions. Thus, there were modest (and probably non–significant) gender differences in the frequency of emo-tional (versus informational) communication. Virtually all of the results section of the article was devoted to describing the codes, thereby revealing subtle but meaningful aspects of gender. Under “information support,” for example, men were likely to offer detailed factual information compared to briefer informational summaries supplied by women. Under “emotional support,” women used warm dialogue and affectionate phrasing, while men suggested to their peers that they “keep their chin up” and “beat the bastard.” In other code domains, such as use of humor and group spirit, men and women did not differ. Commentary: This study’s use of a hypothesis and a QUAL+quan design set the stage for the “quantitizing” that followed. However, the quantitative findings comparing men and women were modest and anticlimactic. Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 8 of 18Qualitative and Mixed Methods in Public Health
In the study’s write–up, the numbers told a small story, but the qualitative themes and interpretations were the main event. Box 3.3 The Difficulty in Ascertaining Research Designs in Mixed Methods: An Example from a Study of Rural Bangladeshi Couples and Pregnancy Termination Few published reports of mixed methods studies use the typologies and design notations described in this chapter. Journal reviewers are not likely to demand them, and the complexities of mixing methods do not al-ways map onto extant typologies. A mixed methods study published in the American Journal of PublicHealth in 2008 offers a case in point. In the article, the authors Gipson and Hindin report using mixed methods to understand how rural Bangladeshi couples make family planning decisions including pregnancy termination. To do so, they draw upon health survey and surveillance data from 3,052 couples as well as 84 in–depth interviews conducted with 19 couples. Quantitative survey questions about childbearing and pregnancy ter-mination were a key interest in the qualitative interviews, but the investigators used a life history technique in the latter to avoid appearing intrusive or invading of the couples’ privacy. Although the authors do not say, the design appears to be sequential in that the quantitative data came from surveys (conducted from 1998 to 2003), and the qualitative purposive sample was drawn from a roster of couples who were enrolled in the survey as of 2004. On the other hand, the study design could be seen as concurrent since it juxtaposes the two “sides” without reference to the time lapse rather than presents them as temporally separate. It is also difficult to decide whether the design is dominant or equally weighted. It appears to be QUAN–dom-inant, since the findings section gives full coverage to the statistical analyses in tabular and text format fol-lowed by reference to the qualitative findings with selected illustrative quotes. The size and volume of the quantitative data, combined with a foreshortened qualitative data analysis (described by Gipson and Hindin [2008] as “focused” [p. 1828]), reinforces this notion of QUAN–dominance. However, this scenario is not en-tirely borne out in the weight the authors give to the two sides while discussing the findings and their impli-cations. For example, the qualitative results offer insightful perspectives on a number of topics including the stigma of having a child when the older children are nearing marital age (thereby hurting the older children’s Sage© 2012 by SAGE Publications, Inc.Sage Research MethodsPage 9 of 18Qualitative and Mixed Methods in Public Health
marital prospects), the use of traditional forms of abortifacients such as roots and homeopathic tablets, and the hidden ways that women terminate pregnancy without telling their husbands. All of these were the result of multiple in–depth interviews conducted with husbands and wives separately. It is hard to imagine how sur-veys could have brought forth such deeply sensitive information. With regard to the “what” question, Bryman (2006) reports that the concurrent mixing of standardized surveys and qualitative interviews is most common, the latter often based on a purposively selected subsample from the larger survey sample. From the qualitative side, focus groups are a popular choice for mixing; life history interviews and ethnographic observation are less amenable to mixing. From the quantitative side, random-ized clinical trials offer less fit for mixed methods compared to standardized interviews and surveys. Some Examples of Mixed Methods Studies The following are a few iterations of mixed methods designs with hypothetical examples. • A sequential design in which scores on an instrument administered during a survey are subsequently used for criterion sampling of a small subsample for qualitative interviews. For example, a study of depression in college students might use scores on the depressive symptom scale to identify stu-dents at highest and lowest risk. These students could then be interviewed in depth about their col-lege experiences and life stressors. • A concurrent design at the data collection stage in which inÐdepth interviews are paired with Lik-ertÐtype survey questions. For example, a study of South African women might administer measures of exposure to partner violence in a community meeting along with post–meeting focus groups for
Collepals.com Plagiarism Free Papers
Are you looking for custom essay writing service or even dissertation writing services? Just request for our write my paper service, and we'll match you with the best essay writer in your subject! With an exceptional team of professional academic experts in a wide range of subjects, we can guarantee you an unrivaled quality of custom-written papers.
Get ZERO PLAGIARISM, HUMAN WRITTEN ESSAYS
Why Hire Collepals.com writers to do your paper?
Quality- We are experienced and have access to ample research materials.
We write plagiarism Free Content
Confidential- We never share or sell your personal information to third parties.
Support-Chat with us today! We are always waiting to answer all your questions.
