S N D G S: O SI TH E E D M H W ED ARC VIE IX E RM ES VE R O A N DR. GUSTAVO DANIEL CONSTANTINO CIAFIC-CONICET ARGENTINA
MMR: THE NAMESMultitrait/multimethod research (Campbell & Fiske, 1959)Integrated/combined research (Steckler et al.,1992; Creswell, 1994)“Quantitative & Qualitative Methods” (Fielding & Fielding, 1986)Hybrids ( Ragin, Nagel & White, 2004 )Methodological Triangulation (Morse, 1991)Mixed Methods Research (Tashakkori & Teddlie, 2003, 2010; Cresswell & Plano Clark, 2007; Tedlie & Tashakkori, 2009)
MIXED METHODS RESEARCH: A DEFINITIONMMR is a research design with philosophical assumptions (pragmatism) as well as methods of inquiry.As a methodology, it involves philosophical assumptions that guide the direction of the collection and analysis of data and the mixture of qualitative and quantitative approaches in many phases in the research process.
MIXED METHODS RESEARCH: A DEFINITION (CONT.)As a method, it focused on collecting, analyzing, and mixing both quantitative and qualitative data in a single study or series of studies.Its central premise is that the use of quantitative and qualitative approaches in combination provides a better understanding of research problems than either approach alone.
MMR PRAGMATISMConsequences of actions Problem centered Pluralistic Real-world practice orientedOntology: singular and multiple realitiesEpistemology: Practicality (what works)Axiology: Multiple stances (biased and unbiased perspectives)Methodology: combiningRhetoric: formal (quan) or informal (qual)
MMR: CENTRAL PREMISEThe combination of QUAN and QUAL approaches provides a better understanding of research problems than either approach alone.But, in what way is it better?3. MMR provides strengths that offset the weaknesses of both approaches4. MMR provides more comprehensive evidence because there isn’t data restriction.5. MMR can help to answer complex questions that cannot be answered by QUAN or QUAL approaches alone.6. MMR encourages researchers to collaborate in despite of their paradigmatic posture7. MMR encourages the use of multiple worldviews or paradigms8. MMR is “practical”: free to use any research method and any type of thinking (inductive – deductive)
TYPES OF RESEARCH PROBLEMS AND MATCHINGMETHODS OR DESIGNS (CRESSWELL & PLANO CLARK, 2007) Type of Research Problem Type of Methods (Designs) suited to study the problemTo see if a treatment is effective Experimental designTo see what factors influence an Correlation designoutcomeTo identify broad trends in a Survey designpopulationTo describe a culture-sharing group Ethnography designTo generate a theory of a process Grounded theory designTo tell the story of an individual Narrative Research
MMR: THE FOUR MAJOR TYPESTriangulation DesignUseful when a researcher needs to directly compare and contrast quan statistical results with qual findings or to validate or expand quan results with qual data.Embedded DesignUseful when a researcher needs to embed a qualitative component within a quantitative design (correlational or experimental design)Explanatory DesignTwo different (QUAN-QUAL) sequential phases for Follow-up Explanations (QUAN emphasized) or Participant Selection (QUAL emphasized)Exploratory DesignTwo different (QUAN-QUAL) sequential phases for Instrument Development (QUAN emphasized) or Taxonomy Development (QUAL emphasized)
MMR: THE TRIANGULATION DESIGNPurpose: to obtain different but complementary data on the same topicRationale: to bring together the differing strengths and non-overlapping weaknesses of QUAN methods (large sample size, trends, generalization) with those of QUAL methods (small N, details, in depth).
MMR: VARIANTS OF THE TRIANGULATIONDESIGNThe convergence model ( traditional; to end up with well-substantiated conclusions about a single phenomenon)Data transformation model (to quantify Qual data or to qualify Quan data)Validating quantitative data model ( including qual data to validate main quan data)Multilevel model / multilevel research (different methods (quan/qual) are used to address different levels within a system)
MMR: TRIANGULATION DESIGN: CONVERGENCE MODELQUAN QUAN QUAN Data ResultsData Analysiscollection Compare Interpretation And QUAN+QUAL ContrastQUAL QUAL QUALData Data Resultscollection Analysis
MMR: TRIANGULATION DESIGN: DATA TRANSFORMATION MODELQUAN QUAN DataData Analysiscollection Compare and Interpretation Interrelate two QUAN+QUAL quan data setsQUAL QUAL TransformData Data QUAL intocollection Analysis quan Data
MMR: TRIANGULATION DESIGN: VALIDATING QUANTITATIVE DATA MODEL QUAN QUAN QUAN Data Data Results Collection: Analysis Survey Validate Interpretation QUAN QUAN + qual results with qual resultsQual data qual qualCollection: data resultsopen-ended analysissurveyitems
MMR: TRIANGULATION DESIGN: STRENGTHS ANDCHALLENGES The design makes intuitive sense. It is an efficient design in both types of data. Much effort and expertise (QUAL and QUAN) is required. To converge two sets of very different data and their results in a meaningful way. Researchers need to develop procedures for transforming data and make decision about how the data will be transformed. What to do if the quantitative and qualitative results do not agree?
MMR: INCONSISTENCIES AND CRITIQUES(BRYMAN, 2007; DENSCOMBE, 2008; CONSTANTINO, 2008) The dividing lines are much fuzzier that typically suggested in the literature (for example, from post- positivism or interpretative research paradigms) Positions are not nearly as “logical” and as distinct as is frequently suggested in the literature (idem) The problem of “commensurability” between quantitative and qualitative methodologies Incompatibility of philosophical premises leads to use QUAN e QUAN “in parallel”, each playing to its respective strengths (as Bryman has demonstrated in his study) The 4 senses of “pragmatism”: fusion of approaches; a third alternative; a new orthodoxy; expedient (lack of principles underlying a course of action). The retrospective framing of past studies is not strong evidence for validate mixed method models
MMR: THE QUESTIONS TO MY OWN RESEARCH• Which of the major paradigms (QUAN, QUAL, MMR) frames your study?• What challenges are associated with your design choice?• Do you think that relevant data could be collected and analyzed if you choose an alternative research design?• Are you really satisfied with the design model that you have drawn?• Are you doing your research with a pragmatic (naïve or commonsense) point of view?
MMR: CONTENT ANALYSIS VS.(?) DISCOURSE ANALYSISConsider a study in which only one type of data is collected (QUAL data - texts)The researcher would analyze the data both qualitatively (developing themes using discourse analysis)and quantitatively (counting words or rating responses on predetermined scales, using content analysis).Are these mixed methods data analysis a MMR?