ϖ Research that integrates qualitative and quantitative data and strategies in a single study or coordinated set of studies (qualitative first and see where that leads then follow it up with a quantitative study)
Mixed Method Research
advantages of mixed method research
complementarity
incrementally
enhanced validity
to measure content two different ways using mixed methods (some quantitatively and some qualitatively)
• Triangulation
Purposes and Applications of Mixed Method Research
developmental work
hypothesis generation and testing
explication
theory building, testing, and refinement
• Qualitative and quantitative data are collected at the same time
concurrent
• Qualitative and quantitative data are not collected at the same time, but in sequence
(one after another)
sequential
o QUAL + QUAN
o Collected simultaneously with equal priority
same time and equally important
convergent parallel design
convergent parallel design are often called
triangulation design
o QUAL (quan) or QUAN (qual) o One type of data is being used to support the other data
ϖ Embedded design
o QUAN —> qual
o Quantitative collected first -priority
ϖ Explanatory design
QUAL—> quan or
QUAL —->QUAN
ϖ Exploratory design
what always comes first in exploratory design
qualitative
• Studies that develop clinical interventions and test their efficacy and effectiveness
clinical trials
clinical trials May be conducted in ___ phases
4
♣ Designed to establish safety, tolerance, and dose
♣ Focus – developing best treatment
phase I
♣ Usually looking for side-effects, does treatment hold promise, identify possible refinements
phase II
♣ Often in multiple sites; sometimes called an efficacy study
phase III
♣ Effectiveness of an intervention in general population
♣ Emphasis on generalizability
phase IV
• Examines how well a specific program, practice, procedure, or policy is working
evaluation research
♣ Gives us descriptive information about how a process is getting implemented and how it’s actually functioning
process analysis
♣ Seeking to identify the net impact of the program
♣ Did our program really work, or is something else cause the changes that I’m seeing? – Impacts can attribute to program
impact anlysis
♣ Same thing as cost analysis
♣ Assesses whether the programs benefits outweigh its monetary costs
economic analysis
o Designed to document the quality and effectiveness of healthcare and nursing services
ϖ Health services research
o Often focuses on parts of a health care quality model developed by Donabedian
ϖ Outcomes Research
key concepts in outcomes research
structure of care
processes
outcomes
o Broad organizational and administrative features
structure of care
involves clinical management
processes
end results of patient care
outcomes
o Obtains information (via self-reports) on the prevalence, distribution, and interrelations of variables in a population
survey research
o Secures information about people’s actions, intentions, knowledge, characteristics, opinions, and attitudes by self report
survey research
QUANTITATIVE data surveys may be?
cross-sectional or longitudinal
modes of collecting survey data:
Personal (face-to-face) interviews
• Telephone interviews
• Self-administered questionnaires
tend to yield the highest quality data but are very expensive
Personal interviews
o Study that used previously gathered data to address new questions
secondary analysis
o Can be undertaken with qualitative or quantitative data
secondary analysis
o Cost-effective; data collection is expensive and time-consuming
secondary analysis
disadvantage of secondary analysis
may not be aware of data quality problems
typically faces “if only” issues.
o Studies that focus on development, validation, and evaluation of research tools and instruments
o Can involve qualitative or quantitative data
ϖ Methodologic research
ex of Methodologic research
- Developing and testing a new data collection instrument
* Testing the effectiveness of stipends in facilitating recruitment
Which of the following would involve an intervention? A. Survey research B. Clinical trials C. Secondary analyses D. Methodologic research
clinical trials
During Which phase of a full clinical trial would an efficacy study be done?
phase III
ϖ The systematic and rigorous integration and synthesis of evidence is a cornerstone of EBP
Research Integration and Synthesis
ϖ Impossible to develop “_____ ______” guidelines, protocols, and procedures without organizing and evaluating research evidence through a systematic review
“best practice”
ϖ Forms of systematic reviews:
meta analysis
meta synthesis
o Statistical integration of results used to compute common effect size
QUANTITATIVE
meta-analysis
o Theoretical integration and interpretation of QUALITATIVE findings
meta-synthesis
meta analysis advantages:
offers objectivity
increased power
how does meta analysis offer objectivity:
o Statistical integration eliminates bias in drawing conclusions when results in different studies are at odds.
increased power of meta-analysis
• Reducing the risk of a type II error compared to a single study
research questions or hypothesis in meta-analysis should be essentially ____ across studies.
identical
o Must be a sufficient _____ ____ for statistical integration
♣ Must be enough studies of acceptable quality
(META-ANALYSIS)
knowledge base
♣ In a meta-analysis Results can be varied but not totally
at odds
ϖ Steps in a meta-analysis
problem formulation
design of meta analysis
search for evidence in literature
• Delineate research question or hypothesis to be tested
problem formulation
o Identify sampling criteria for studies to be included
design of meta analysis
• Develop and implement a search strategy in what step
o Search for Evidence in Literature
• Search Strategy
− Identify electronic databases to use
− Identify additional search strategies (ancestry approach)
− Decide whether or not to pursue to gray literature
− Identify keywords for the search
♣ Think creatively and broadly
unpublished reports
gray literature
• Meta-analysts must make decisions about handling _____ ____.
study quality
approaches for making decisions about handling study quality
o Omit low-quality studies (ex. in intervention studies, non-RCTs)
o Give more weight to high-quality studies
o Analyze low- and high-quality studies to see if effects differ (sensitivity analysis)
Analyze low- and high-quality studies to see if effects differ
sensitivity analysis
• Evaluations of study quality can use:
a scale approach or a
component approach
− Results (effects) inevitably vary from one study to the next
heterogeneity
major question for heterogeneity
: is heterogeneity just random fluctuations?
if yes: then a ____ ___ ____ of analysis can be used
fixed effects model
if no: then a ____ ____ model should be used
random effects
can be formally tested
− Heterogeneity
o Visual inspection relies on the construction of
forest plots
Low Heterogeneity
very similar data
GOOD
High heterogeneity
♣ studies had way different results – not appropriate to do meta analysis on “all over the map”
what your calculating in meta-analysis
effect size
− Factors influencing variation of affects is usually explored via ____ _____ (moderator analysis)
subgroup analysis
helps you understand where variations are coming from
subgroup analysis
do variations relate to:
participant characteristics
methods
intervention characteristics