Week 10 - Mixed Methods Flashcards
what is mix-methods research
RESEARCH IN WHICH THE INVESTIGATOR COLLECTS AND ANALYZES DATA, INTEGRATES THE FINDINGS, AND DRAWS INFERENCES USING BOTH QUALITATIVE AND QUANTITATIVE APPROACHES OR METHODS IN A SINGLE STUDY OR PROGRAM OF INQUIRY
what is meta inference
THE CONCLUSION GENERATED BY INTEGRATING INFERENCES FROM THE RESULTS OF THE QUANTITATIVE + QUALITATIVE STUDY
what is pragmatism paradigm
The research question should drive the inquiry and
…the question is more important than the method”
(usually at least 2 research questions are involved)
what are the advantages to mixed methods research
- complimentarity
- practicality
- incrementality
- enhanced validity
- collaboration
what is complementarity
Promoting the “best of both worlds”: qualitative and quantitative research methods
what is practicality
Researchers can ask questions that cannot be studied using only one method
what is incrementality
Allows for use of feedback loops
what is enhanced validity
Support for a model or hypothesis from complementary data
what is collaboration
Combines expert methodology researcher talents; Very difficult to find someone who is an expert at both methods
what are the disadvantages of mixed methods research
Requires a researcher to be competent in both methods: methodologically bilingual
All members of the team need this dual-method expert skill set
Expensive
Mixed methods studies may be of longer duration than single method studies
what is the purpose of mixed methods research
- Use MM when there are conflicts in the research and don’t quite understand all that is going on
- Concepts new and poorly understood
- Neither qualitative nor quantitative approach adequate alone
- Enhanced with second source of data
- Quantitative results difficult to interpret
- Theoretical approach requires both methods
- Multiphase project is required to attain key objectives
explain the application of mixed methods
- Instrument developmental work: qualitative data may be useful for item generation for quantitative instruments
- Intervention development: relationship here with evidence-based practice that takes into account the patient’s, caregiver’s, etc., perspectives
- Hypothesis generation and testing: may be done through a coordinated set of studies
- Explication: helps researchers see why variables are related
- Theory building, testing, and refinement helps theories to escape disconfirmation
what are some considerations when it comes to mixed methods
- sequencing (what are you going to do first)
- prioritization
- integration
explain the consideration sequencing
Sequential: one before the other
Concurrent: at the same time
explain prioritization as a consideration
Equal
Dominant
explain integration as a consideration
Data collection
Data analysis
Interpretation
what are the three designs of mixed methods
- convergent (parallel)
- explanatory
- exploratory (3 phased approach)
+ indicates which design
convergent
-> indicated which design
sequential
what do capital letters indicate
priory strand of study
what do lower case letters indicate
non-dominant strand of study
what is an explanatory design
always have quantitative strand first
When you think you understand a phenomenon but want to understand it a different way, so asking the participants how they feel
what is a exploratory design
always have qualitative strand first
When you don’t understand the phenomenon
what does QUAL/quan mean
qualitative approach is dominant
what does QUAN/qual mean
quantitative approach is dominant
what does QUAL/QUAN mean
Both approaches are equal
The notation is QUAN (qual); is this an embedded design or not? Which strand is not the dominant one?
IS embedded design (parentheses mean embedded)
Qualitative is NOT dominant
what is the code for convergent (parallel)
QUANT + QUAL
Simultaneous and equal priority
what is the code for explanatory
QUANT → qual
quant → QUAL
what is the code for exploratory (3 phase approach)
QUAL → quant
qual → QUANT
what are the types of sampling you can do for mixed methods
- strategies
- generalizability (external validity)
- sample size (power analysis)
- relationships
expand on generalizability as a sampling style
Concerns the extent to which findings can be applied to people or settings other than the ones used in the research
what are the four types of relationships for sampling
- identical
- parallel
- nested
- multilevel
what is identical sampling
same people participate in the quant and qual parts of study
what is an example of identical sampling
Ex: Moreland and Santacroce (2018) studied illness uncertainty and posttraumatic stress disorder (PTSD) in young adults with congenital heart disease, using a convergent design. The 25 study participants completed a questionnaire that included a measure of posttraumatic stress. They were also asked to tell their stories in unstructured interviews. The narrative analysis revealed a relationship between the severity of PTSD and the appraisal and management of uncertainty.
what is parallel sampling
not the exact same people for the qual and quant (strains), may see this in a MM study that is happening simultaneously
what is an example of parallel sampling
Ex: In a sequential qual → QUAN study, VanDevanter and colleagues (2014) explored challenges of nurses’ deployment to New York City hospitals in the aftermath of a disaster, Hurricane Sandy. Initially, in-depth data were collected from a maximum variation sample of 20 nurses. Subsequently, an Internet-based survey was sent to all RNs employed at a New York Medical Center (N = 1,668)
what is nested sampling
participants in the qualitative strand are a subset of the participants in the quant strand
what is an example of nested sampling
Ex: Schneerson and Gale (2015) used framework analysis in their explanatory sequential study of cancer survivorship and self-management. Quantitative data were first collected in a survey of 445 adult cancer survivors with 10 different types of cancer. The researchers used purposive (nested) sampling to obtain a diverse sample for in-depth interviews. They sampled on three dimensions of diversity, using survey responses to guide the selection of 40 participants: cancer type, sociodemographic characteristics (age, gender, ethnicity), and patterns of cancer self-management
what is multilevel sampling
quant and qual samples selected from different levels of hierarchy (e.g. hospital administrators, clinical staff, and patients)
what is an example of multilevel sampling
Ex: Horne and co-researchers (2015) studied practices and experiences of mouth hygiene in stroke care units in the UK. Questionnaires about policies and practices were completed by senior nurses in 11 stroke units. Qualitative data were collected in two focus groups with 10 healthcare professionals and by in-depth interviews with 5 stroke survivors.
what is collection in mixed methods
Consider if bias introduced by design (closed ended questions influencing a focus group?)
explain analysis in mixed methods
- Separate vs. merged
- Interpretive integration – comparing and interpreting to inform next phase
- Converting data – quantitating and qualitizing
- Meta-matrix
what are the two types of quality in mixed methods
- Inference quality (believable & accurate)
- Inference transferability
what is inference quality
believable and accuracy of the conclusions
what are the two subgroups of inference quality
Quantitative- Internal validity & Statistical conclusion validity
Qualitative - Credibility