Research in Nursing

Document Sample
Research in Nursing Powered By Docstoc
					NSR 338: Research in Nursing
Dennis Ondrejka, Ph.D., R.N.
    303-292-0015, ext. 3625 office

             Fall, 2009
          Is nursing a profession?

Q.#1: What are the criteria for a profession?
         Nursing: Profession or
         Technical Occupation?
Pavalko’s (1971) Continuum Model for a

   Theory
   Relevance to social values
   Education
   Motivation
   Autonomy
   Commitment
   Sense of community
   Code of ethics
             Explore the Meaning of a
         Professional vs. Technical Practice

   Describe the similarities
    or differences between      Cook
    the chef at the Brown
    Palace & the cook at
    the Village Inn?
           Professional vs. Technical
                       for all practice areas
   Professional Practices               Technical Occupations
   Have a culture that supports         Are more likely to have more
    professional activities:              OJT than formal education.
    frameworks, CE, research
                                         Are skill focused
   Has a defined body of
    knowledge gained by formal           Have trade journals or
    education                             technique trainings
   Is a discipline with peer            Do not focus on what
    review and a code of ethics           advances the practice
   Autonomy in practice with            Develop through
    legislative and legal sanctions       certifications
   Is an organized system of            Want less accountability
    practice recognized by
        Professional vs. Technical
                  Thinking and Valuing
   Professional thinking            Technical Thinking
       More is best                     Least is best
       Specialization in depth and      Specialization in depth
        breadth                          Experience is the primary
       Evidence-based education          educator
       Invests energy beyond the        Conserves energy beyond
        work-associations,                the workday
        research, reading                Prefers others be
       Expects self accountability       accountable
       Resilient with change and        Enjoys consistency and
        believes change is                believes change is
        valuable                          disruptive
Is research important to the
 Yes!! Research is important for
   building a unique, systematic
    body of knowledge about
           a discipline
     Nursing needs a systematic body of
              knowledge to ...

   Promote Evidence-based practice
   Give credibility to profession
   Provide accountability for practice
   Help document the cost-effectiveness of
    care (Nieswiadomy, 2008)
      What is Evidence Based
        Nursing Practice?
   Knowledge from science & research
   Knowledge from experts
   Knowledge from patients
   Knowledge arriving in many forms
   Has levels of power and rigor
             Evidence Based Practice:
   “…the integration of current best evidence
    with clinical expertise and patient values”
    (Sackett et al., 2000)

   “…a framework for clinical practice that
    incorporates the best available scientific
    evidence with the expertise of the clinician
    and the patient’s preferences and values to
    make decisions about health care.” (Levin,
          What is Research?
   Process of searching for new
    knowledge about phenomena
   Validates and refines existing
    knowledge (Burns & Grove, 2007)
   Systematic process of inquiry or study
   Builds new knowledge through the
    dissemination of findings
              Why Research???
   To Describe
       To identify and understand the nature of nursing
       What is the experience of growing up poor in
   To Explain
       Clarifies the relationship among phenomena,
        and why certain events occur
       What are the factors that supported DSN
        graduates to pass NCLEX at 95% in 2009?
              Why Research???
   To Predict
       This allows us to estimate the probability of a
        specific outcome in a given situation
       There is a statistical difference in baseline
        patient glucose levels when using basilar
        method over sliding scale.
   To Control or Manipulate
       If we can predict, the next goal would be to
        control or manipulate the situation to produce
        the desired outcome.
       We can reduce bed sores at all stages by
        rotating patients every two hours maximum.
Ways We Acquire Knowledge
   Tradition                Reasoning
   Authority                    Inductive-gather
   Borrowing                 

                                 Rational-logic
   Trial and error
                                 Unstructured
   Personal experience
                             Research
   Role-modeling &              Quantitative
    mentoring                    Qualitative
   Intuition                    Mixed / Other
             Research Defined

   Research is a systematic, diligent inquiry
    that is necessary to address:
       What needs to be known-what is the question,
        hypothesis, or interest area
       What research methods are needed to examine
        this question or phenomena
       What meaning can be extracted from the study
        through data analysis to build our knowledge
        base of that subject
   Generate outcomes and disseminate new
Ways to Study Research
   By its components (questions, rigors, sampling
    method, measurement method, etc)
   Divided into two major types
       Qualitative
       Quantitative
   By the name of the method (experimental,
    phenomenology, etc)
   By the philosophy it uses to inquire (positivistic,
    naturalistic, both, neither)
        Burns & Grove method:
          Examine Your Text
   Table of Contents 7 Ch. 1
   Ch. 2 = Quantitative Research
   Ch. 3 = Qualitative Research
    (philosophy discussed)
   CH. 4 = tries to address both qualitative
    and quantitative questions
   Ch. 5, 6 = Lit review, Study
    Frameworks & Theory
          Examine Your Text
   Ch. 7 = ethics
   Ch. 8 = Clarify Designs (quantitative)
   Ch. 9 = Outcomes Research
   Ch. 10 = Populations and Sampling for
    quantitative and qualitative methods
   Ch. 11 = Measurement of Data
    quantitative and qualitative
   Ch. 12 = Understanding Statistics
Examine Your Text
   Ch. 13 = Critiquing Research for
    qualitative (five Standards) and
   Ch. 14 = Building an Evidence Based
Ch. 14 Evidence Based Practice
   Research Utilization (RU) may have a lag time for
    Practice up to 20 years
   Involves being a Change Agent. (DSN uses the I2E2
    model for change in third quarter)
   Best Evidence by research type
       Integrative Reviews (many types of designs)
       Systematic Reviews (focused on a particular type of research
       Meta-Analysis (has statistical evaluation of quantitative
       Metasummaries & Metasynthesis (qualitative research)
      Hierarchy of Evidence
      Compare to Florczak article

   Level I: A systematic review or RCTs, meta-
    analysis of many randomized controlled trials
   Level II: Integrative Reviews of experimental
   Level III: from a well-designed controlled trial
    without randomization
   Level IV: From case-control or cohort studies
Hierarchy of Evidence
Compare to Florczak article
   Level V: From systematic reviews of
    descriptive or qualitative studies,
    metasummaries, metasynthesis,
   Level VI: a single descriptive or qualitative
   Level VII: It is an opinion from authorities on
    that subject, or expert committee
Recent Changes in Nursing
   Page 500, second paragraph, Using ASA
    81 mg. in at risk adults
   Page 517, I.V. flush using 0.9% NS vs.
    heparin. P & P on page 520.
   Algorithms on page 524 for tx HTN.
   I.V. skin prep using chlorhexidine vs.
    Iodine products like providone-iodine
   Strait cath urethra prep, NRS 338
   Evidence Based Research
    Research Philosophy Method:
Positivistic versus Naturalistic Inquiry

   This is a 100 year old debate
   It is often correlated to research methodology
   It is a philosophy on the way we think about
    human phenomenon & inquiry (research)
   We can integrate two different inquiry
    methodologies, but philosophically they are
    very different (mixed or blended design)
   Our philosophy is the foundation for how we
    design research
Positivistic Inquiry                                              Naturalistic Inquiry                          (Constructivism)

Quantitative                                     Triangulated                              Qualitative

Solomon Design                                   Blended Designs                                                      Post-modern
 -four group design                                 - use quantitative
 -pretest-treat-post test     Intervention Res       & qualitative                                                    -research self
 -pretest-no treat- post test                        methods                                                          -novel sounding
 -no pre- no treat- post test                                                                                         lacks theory
 -random group         Quasi-Experimental          Grounded Theory                         Phenomenology
 -validated tools          -two of three            -theory building                           - descriptive
                            Exp. controls            -Basic Social Process                     - interpretive
                                                                                              - hermeneutic
          Experimental Design                           - quantitative or                                Ethnography
                -random sample                           qualitative methods                             -living in the experience
                -control group                                                                           -cultural immersion
               -a treatment given                    Outcome Research

                                                      Case Study
          Epidemiology (humans & Ds)                 -single-double cases
           Analytic Epi                               -In-depth analysis
                        Descriptive Epi              - comparative analysis

                                                       Action Research
                                                 Adequate time commitment
                                                 Collaborative effort
                                                 Openness to change
                                                 Quality of data collection and analysis
                                                 Impact on one’s practice
Positivistic Inquiry                                   Naturalistic Inquiry              (Constructivism)

Quantitative                                 Triangulated            Qualitative
Solomon Design                               Blended Designs                                     Post-modern

              Quasi-Experimental              Grounded Theory            Phenomenology
                                             Constant Comparative
           Experimental Design                                                     Ethnography
                                              Case Study

                            Scientific Rigors by Design
Quantitative Research Rigor
Validity & Reliability (internal-external)             Qualitative Research Rigor
Conceptual Framewor k Developed                        Descriptive Vividness
Statistical Inference                                  Methodological Congruence
Generalizability                                       Analytical Preciseness
Temporality                                            Theoretical Connectedness
Selection and Bias                                     Heuristic Relevance
Measurement validity / reliability                     Trustworthiness, Credibility,
Controlling confounders                                and Auditability
Appropriate study design for the questions             Confirmability, transferability           Stylistic & Personal
                                                                                                 Relevance, Heuristic
                       Sample Size by Design
Positivistic Inquiry                           Naturalistic Inquiry   (Constructivism)

Quantitative                        Triangulated            Qualitative
Solomon Design                      Blended Designs                 Post-modern
 Power Analysis                              20-40                         1
               Quasi-Experimental    Grounded Theory      Phenomenology
                >40                      10-1000           10+saturation (10-30)
        Experimental Design                1-12               Ethnography
          Power Analysis                                         1

                                     Case Study

                                      Action Research
Assumptions of Positivistic
   Reality is singular,
    tangible, & and can      value free      singular
    be dissected                               reality
   The researcher and
    those being studied             Positivistic
    are independent                 thinking
   Time and context-
    free generalizations    independent     generalizable
    are possible            variables
   Inquiry is value-free
Assumptions of Positivistic
   There are real causes
    or at least high                            singular
    probability of a            value free      reality
   We believe we can                    Positivistic
    have independent
                               cause & thinking
    and dependent
    variables as separate      independent
    entities                   variables        generalizable
   Validity of a design is
    very critical to results
Assumptions of Positivistic
   Reliability is based value-free
    on how the design is  hypothesis        singular
    reproducible          testing           reality
   Generalizability is            Positivistic
    related to good                thinking
    internal validity and                     validity
                          & effect
    reliability with      independent      generalizable
    comparable samplesvariable
   Hypothesis testing
Assumptions of Naturalistic
   Realities are multiple,
    pluralistic, and holistic          multiple realities
   The researcher cannot
    really be separated
    from those being                       naturalistic
    studied and relation-     researcher inquiry          hypothesis
    ships are explained       & subject                   is a focus
   hypotheses are time       connected                   area
    and context bound -
    they are only working
Assumptions of Naturalistic
   All entities are in a
    state of mutual               multiple realities
    simultaneous                 inquiry is value bound
   Inquiry is value-
    bound                              Naturalistic
   Validity is designed
    into the process        researcher thick      hypothesis
   Reliability &           & subject description is a focus
                             connected            area
    general- izable are
    not concepts of
    value with this
Differences in Scientific Rigor
positivistic                      naturalistic
   Validity                    Descriptive Vividness
   Internal and external       Methodological
    reliability                  Congruence
   Hypothesis testing          Analytical Preciseness
   Statistical inferences      Theoretical
   Independent and              Connectedness
    dependent variables         Heuristic Relevance
   Variable controls           Others
   Generalizability
Data Collection Difference
positivistic                                 naturalistic
   Tools                            Tool
       surveys, questionnaires          is the investigator by
       objective assessment &            interview, focus groups, &
        identification                    observation
   Measure the dependent            Data is subjective and
    variable                          objective. It is collected &
   Convert to numeric                not measured
    symbols                          Themes or clusters are
   Apply statistical                 identified and data is
    inferences to numbers             sorted in a theme analysis
   Large sample sizes help          The themes are supported
                                      by participants or experts
    with confidence levels
Differences in Results
positivistic                    naturalistic
   Statistical                The exploration &
    significance for pre-       description of a
    post treatment              phenomenon
   Statistical                Identification of
    correlations &              linkages, relationships,
    relationships               or interpretations based
    identified                  on theory connections
   Probability of errors      Results are themes,
    & confidence                clusters of ideas, or
    identified                  theory constructs
   Causal relationships
Positivistic Discussion of
   250 nurses were surveyed with an 80%
    response rate or N=200. Questions were
    rated using the Likert 5 scale. Question 1
    had a mean of 4.2 with a S.D. of 0.5
    suggesting the nurses had favorable opinions
    about continuing education. Compared to a
    1994 survey asking the same question, there
    was a statistical difference that was less
    favorable (mean 3.1, S.D. 0.7, p<.05)
Naturalistic Description
   I sat in the classroom as a peripheral member
    staying as unobtrusive as possible. The
    instructor came out from behind her desk,
    sitting on the edge as she opened with a
    question that brought all eyes in the room to
    meet her own eyes. She paused - looked at
    the eyes of the students.
   The instructor displayed immediacy from the
    moment she started the class.
    Ethics and Research (Ch. 7)
   Starts with the study purpose, design, methods
    of measurement, and subjects
   Guidelines for all of these
   It is still a concern today
   More recent ethical issues are:
       Fabrication of a study
       Falsification or forging of data
       Dishonest manipulation of the design or methods
       Plagiarism
   50% of the top 50 research institutions in US
    have been investigated for research fraud
    Ethical Problems in History

   Nazi medical experiments (1933-
   Tuskegee syphilis study by the
    USPHS (1932-1972)
   Willowbrook study (1950-1970)
    Hepatitis study
   Jewish Chronic Disease Hospital
    study with live CA cells in 1960s
           Ethical Problems in History
   University –Atomic Energy Government Exp.
       18 men and women injected with plutonium to
        determine body distribution (at the time said to be
        terminal) 1945-47
       20 subjects ages 63-83 given doses of radioactive
        radium and thorium inj. or oral. 1961-65
       64 male inmates at Washington St. Prison had
        testicular radiation to determine the smallest does
        to makes someone sterile. 1963-70
       125 retarded residents were fed radioactive ir9n
        and calcium to see if a diet rich in cereal would
        block the digestion of those two minerals. 1946-56
            Nuremberg Code-1949
   Voluntary consent
   Must yield fruitful results for society
   Anticipated results justify the type of experiment
   Avoids all unnecessary physical-mental injury
   Cannot do studies that have a known injury or death
    unless the exp. Physician is a subject
   Risk does not out weight humanitarian benefit
   Proper precautions to prevent injury, dis., death
   Conducted by qualified persons
   Subjects can always stop the study
   Researcher must always be ready to stop the study
    Declaration of Helsinki-1964-84
   Differentiated therapeutic vs. non-therapeutic
       Clinical vs. Basic
   Greater care to protect subjects in non-
    therapeutic research
   There must be a strong, independent
    justification for exposing a healthy vol. to
    substantial risk
   The investigator is to protect the health and life
    of research subjects
               The Belmont Report
              Three Ethical Principles
   Principle of respect for persons
       Right to self determination and freedom to participate or not
   Principle of Beneficence
       Do no harm to others
   Principle of Justice
       Treat everyone fairly without discrimination
   Led to USDHHS Code on Ethics
       Title 45, Part 46 (45 CFR 46)
       Office of Human Subjects Research (OHSR) within NIH
Institutional Review Board (IRB)
   Provides oversight on all ethical issues
    related to someone doing research
   Consent forms (voluntary subjects)
   Disclosure forms
   Confidentiality
   Compensation disclosure
   Ethics documented in the research
   Accountability to rules, regulations, and
    legal entities
   Protects at risk populations
        The Literature Review
   Primary Sources
   Secondary Sources
   Theoretical literature
   Empirical (Research) literature
   Evidence Based Research Sites
           Definition of a
     Literature Review (Ch. 5)
   A systematic and explicit approach
    to the identification, retrieval, and
    bibliographical management of
    independent studies … locating
    information … synthesizing …
    developing guidelines …
    Purposes of the Lit. Review
   Facilitate development of the Conceptual
    Framework by summarizing knowledge
   Clarify the research topic
   Clarify the research problem
   Verify the significance of the research problem
   Specify the purpose of the study
   Describe relevant studies or theories
   Develop definitions of major variables
   Select a research design, data measurement,
    data collection & analysis, & interpret findings
           Literature Searches
   Ebscohost with CINAHL:
   Log in: DSN
   Password: evidence
       NRS 338
       Data bases
Understanding Research Designs
   Can have confusing terms
   Research Methodology
       The entire process from question to analysis
   Research Design
       Clearly defined structures within which the
        study is implemented
       Is a large blueprint, but must be tailored to the
        study and then mapped out in detail
Quantitative Designs (Ch. 2)

    What are the four types of
     Quantitative Designs?
Quantitative Designs
   Experimental
   Quasi-experimental
   Descriptive
   Correlational

Aim to describe, compare, and predict in
  order to understand or control
Quantitative Designs

  What characterizes true
   Experimental Research
       True Experimental Research

Are characterized by:
 Random assignment of subjects to groups

   Comparison of treatment group(s) with a

   Control or “business as usual” group
     True Experimental Research
     Designs (cont.)
Also characterized by …

   Strict control of extraneous variables
    to obtain true representation of “cause
    and effect”
   Note: use “causality” language with
    caution!!! (there is always a P-value)
           Ex: Smoking and cancer
    Randomized Controlled Clinical
    Trials (RCT)
   True Experimental Design

  Large N (# of subjects)
 Draw subjects from reference population

 Randomly assign subjects to
treatment/experimental or control group
 Examine for baseline equivalence

 Multiple sites used for generalizability
      Research Designs
Are characterized by:
   Treatment or intervention
   Comparison of treatment group(s) with a
     control or “business as usual” group
   Non-equivalence of groups--not randomly
    assigned; group assignment often evolves
    naturally “convenience” sampling)
         Ex: Pts. on one unit compared to pts. on another
Research Designs (cont.)
Also are characterized by…

   Aiming to represent “cause and effect”
    in situations where less control over
    variables exists

Most frequently used design in nursing
Correlational Designs
   Descriptive correlational designs
       Used to describe variables and to examine
        relationships between or among variables
   Predictive correlational designs
       Used to predict value of one variable based
        on values obtained for another variable
       Independent variable used to “predict”
        Dependent variable  Regression
       Model-testing design
       Looks at relationships among a # of variables
Correlational Designs
   Descriptive correlational designs
       Used to describe variables and to examine
        relationships between or among variables
   Predictive correlational designs
       Used to predict value of one variable based
        on values obtained for another variable
       Independent variable used to “predict”
        Dependent variable
Quantitative Design Concerns
   Primary purpose (check question)
   Is there a treatment (intervention)
   Will the treatment be controlled
   Is there a control (untreated) group
   Is there a pre or post test (or both)
   Is sample random
   Will sample be a single group or divided into
    several groups
Quantitative Design Concerns-2
    How many groups will there be
    What is the size of each group
    Will groups be randomly assigned
    Will there be repeated measurements over
     time or will the data be collected cross-
     sectionally at one or two points in time
    Have extraneous variables been identified
     and controlled for
    What strategies are being used to compare
     variables or groups
Research Question
   Ethics
   Significance
   Motivation
   Qualifications
   Feasibility
Hypotheses and Research Qs
   Hypotheses: Intelligent guesses about
    predicted relationships

   Problem statement  what the
    issue/concern/problem is and why it
    should be addressed

   Research Qs: “Burning question”
       What are Criteria for
       Hypotheses? (Ch. 4)
   Declarative
   Written in present tense
   Include population
   Identify variables
   Reflect the problem/concern
   Are empirically testable
        Independent & Dependent
   Independent (IV)
       The treatment
       The intervention
       That which is manipulated
   Dependent (DV)
       Outcome
       What is being measured
       The difference
    Types of Hypotheses:
    Simple & Complex
   Simple
       One Independent Variable (IV) and one
        Dependent Variable (DV)

   Complex
       Two or more IVs, two or more DVs, or
        both, being investigated at same time
Hypothesis: #1
   Average length of gestation is
    shorter for infants of mothers who
    use cocaine than among mothers
    who use alcohol during the last six
    months of pregnancy.
   Population? IV?      DV?
   Simple or complex?
Hypothesis: #2
   The greater the degree of sleep
    deprivation, the higher the anxiety
    levels of intensive care unit
   Population? IV?      DV?
   Simple or complex?
      Hypothesis: #3
   The total wt. loss of overweight elementary
    students who follow a reduced calorie diet
    and exercise 20 minutes four times a week
    will be greater than those students who do
    not follow a reduced calorie diet and do not
    exercise 20 minutes four times a week.

   Population? IV?      DV?

   Simple or complex?
      Hypothesis: #4
   The degree of stress reported by flight-
    for-life nurses is greater than the
    degree of stress reported by ICU
   Population? IV?      DV?

   Simple or complex?
      Name that Hypothesis: #5
   More domestic violence and levels of
    anger are reported by veterans who
    served in the military in Iraq compared
    to those in the military who served in
   Population? IV?      DV?
   Simple or complex?
              Sample of Research Topic &

   Topic: Adolescent sexuality
   Problem statement: (e.g., pregnancy rates in US are
    much higher compared to most Western countries)
   Research Question:
       Will high school adolescent males report higher levels of
        comfort with their own sexuality than will females?
   Hypothesis:
       Adolescent males in grades 9 – 12 will report statistically
        higher levels of comfort with their own sexuality than will
        females in the same grades.
Quantitative Design Concerns
   Primary purpose (check question)
   Is there a treatment (intervention)
   Will the treatment be controlled
   Is there a control group (untreated)
   Is there a pre or post test (or both)
   Is the sample a random sample
   Will the sample be a single group or
    divided into several groups
Quantitative Design Concerns-2
    How many groups will there be
    What is the size of each group
    Will groups be randomly assigned
    Will there be repeated measurements
    Will the data be collected cross-sectionally
     or over time
    Have extraneous variables been identified
     and controlled for
    What strategies are being used for
     comparison of variables or groups
Components of Study Validity
   Definition: It is an examination of the
    approximation of truth or falsity of the
       Statistical Validity (right stats used)
       Internal Validity (sample represents the
        population being studied)
       Construct Validity (concept & Operational def.
        of variable match, & instrument accuratly
        measures theoretical constructs it purports to
       External Validity (methods allow for
            (Cook and Campbell, 1979)
        Statistical Validity Errors
   Violate assumptions about the data
       Nominal, ordinal, interval, ratio data
   Type I and Type II errors
   Need for Power Analysis
       Predicts the necessary N value
   Inappropriate use of certain statistics for the
    various types of data
   Random irrelevancies in setting
   Random heterogeneity of respondents
        Statistical Conclusion Validity
        Type I and Type II Errors

            Accept the Null Hypothesis Reject the Null Hypothesis
Reality is:                             Type I Error
No              Desired                 There is no difference
difference                              caused by fishing

Reality is:   Type II Error, there is
There is a    difference often caused          Desired
Difference    by a low N value
            Internal Validity
   Definition:
    *It is the extent to which the effects
    detected in the study are a true
    reflection of reality rather than the
    result of extraneous variables;
    * The independent variable did have an
    impact on the dependent variable and it
    was not by random chance (p value)
Threats to Internal Validity
   History: Natural events over time impacting
    the subjects
   Maturation: A person’s growth in any area
    impacting his/her response
   Testing effect caused by subjects
    remembering previous testing
   Instrument reliability of treatment
   Selection process (randomized)
   Mortality threat
   Interaction with subjects
   No equalization of treatment
            External Validity
   Definition:
    To provide development of the
     design that allows it to be
     generalized beyond the sample
     used in the study.
    Most serious threat is that the results
     can only be said of the group being
Threats to External Validity
   Small N
   No randomization when it is needed
   Poor sample representation either by
    type, geography, or some other
   Cannot be replicated for some
    extraneous variable
         Factors Influencing
            Sample Size
   Effect Size
       The degree to which the phenomenon is
        present in the population or to which the
        null hypothesis is false.
       It is hard to detect an effect from an
        intervention if the sample is small
   Type of study conducted
       Case study, phenomenology,
        experimental, Descriptive
           Factors Influencing
              Sample Size
   The number of variables
       This requires a power analysis to determine the
        necessary N
   Measurement Sensitivity
       The ability of the measurement to find what it
        thinks it is finding.
   Data Analysis Techniques
       The various statistics can impact the number of
        subjects needed.
Types of Probability Sampling
   Simple Random Sampling (select those with
    specific characteristics)

   Stratified Random Sampling (2 or more strata
    of population)

   Cluster Sampling (all states, cities)
   Systematic Sampling (every nth)
   Random Assignment to Groups (Treatment
    and Control)
     Types of Non-probability
   Convenience (Accidental) Sampling
   Quota Sampling
   Purposive Sampling
   Network Sampling
   Theoretical Sampling
    Non-Probability Sampling

Theoretical Sampling      Quota

Purposive Sampling (Non-Randomized)

   Convenience Sampling     Network
       Caution Areas on Data
   You see what you look for
   You look for what you know
   Appropriate statistical strategies for
    certain types of numbers
   If you are a hammer, the world looks
    like a nail
Dealing With Data (ch. 11)
   Developing Data Collection Forms
   Planning Data Collection Process
   Planning he Organization of Data
   Planning Data Analysis
   Planning Interpretation &
    Communication of Findings
   Evaluation of the Plan
       Data Collection Tasks
   Recruiting Subjects
   Maintaining Consistency
   Maintaining Controls
   Protecting Study Integrity
   Problem-Solving
          Physiological Measures:
           Reliability and Validity
   Accuracy
       measurement that has the most precise identifiers for the
        level of measurement sought
   Selectivity
       the ability to identify that which is really want to
        sometimes called specificity
   Precision
       the amount of reproducibility in measurement
   Sensitivity
       The amount of a changed parameter that can be detected
   Sources of Error
Data Collection Problems
   People Problems
   Researcher Problems
   Institutional Problems
   Event Problems
   Measurement Validity
   Measurement Reliability
Computer Support for Data
   Data Input
   Data Storage
   Data Retrieval
   Statistical Analysis
Numbers and Use of Numbers
   Nominal (subjective)
       A Named category given a number for convenience, e.g.
        males are 1 and females are 2
   Ordinal (subjective)
       A scale that is subjective but shows a direction, e.g. pain
        scale, cancer staging, all Likert scales
   Interval (objective)
       Numbers where the interval between them is meaningful,
        and there is no absolute zero but an arbitrary zero, e. g. a
        temperature. These numbers can be less than zero.
   Ratio (objective)
       Numbers where there is an absolute zero which means it
        is absent or there is a denominator that allows for
        comparison of meaning and . e. g. number of cases or
        infections per 100 hospital days, stage 2 skin breakdown
        per 100 patients.
        Bivariate Data Analysis
         Independent Groups
   Nominal Data
       Chi squared (Two or more samples)
       Phi (Two samples)
       Cramer’s V (Two samples)
       Contingency Coefficient (Two samples)
       Lambda (Two samples)
        Bivariate Data Analysis
         Independent Groups
   Ordinal Data
       Mann-Whitney U
       Kolmogorov-Smirnov (two-sample test)
       Wald-Wolfowitz Run Test
       Spearman Rank-Order Correlation
       Kendall’s Tau
       Kruskal-Wallis One-Way Analysis of
        Variance by Rank (three or > samples)
        Bivariate Data Analysis
         Independent Groups
   Interval or Ratio Data
       t Test for independent samples
       Pearson’s Correlation
       Analysis of Variance (Two or more
        samples) ANOVA
       Simple Regression
       Multiple Regression Analysis (two or more
        Bivariate Data Analysis
          Dependent Groups
   Nominal Data
       McNemar Test
       Cochran Q Test (three or more samples)
   Ordinal Data
       Sign Test
       Wilcoxon Matched-pairs, Signed-Ranks
       Friedman Two-Way Analysis of Variance
        by Ranks (for three or more samples)
        Bivariate Data Analysis
          Dependent Groups
   Interval or Ratio Data
       t Test for Related Samples
       Analysis of Covariance (for three or more
        samples) ANCOVA
    Multivariate Data Analysis
    Interval or Ratio Data
        Multiple Regression Analysis
        Factorial Analysis of Variance
        Analysis of Covariance
        Factor Analysis
        Discriminate Analysis
        Canonical Correlation
        Structural Equation Modeling
        Time-Series Analysis
Working with Descriptive Data:
A Toolkit for Health Care Professionals
Using Descriptive Statistics

      Correlational Descriptive
       Predictive Descriptive
      Model Testing Descriptive
Statistics vs. Tools
   Inferential Statistic Analysis
       Statistics (regression, correlation, t-test, F-
        test, Multivariate testing etc.)
   Descriptive Statistic Analysis
       Tools to display information
     Critical Path Process (p. 524)
1.    Select the process
2.    Define the process
3.    Form a team
4.    Create the critical path
5.    Make the path a working document
    Critical Pathway for
Complaints of Chest Pain in ED
                        ED Patients
                       c/o chest pain

  No previous           Previous            Previous CAD
   symptoms            symptoms               many risk
 Good Health          Has some risk            factors
Min. Risk factors        factors

    O2, IV,         O2, IV, Bloods, EKG   O2, IV, ASA, Beta,
 Bloods, EKG         ASA, Nitroglycern    Blocker, Morphine,
                                          Cardiac Cath Lab
    Force Field Analysis
     Driving Issues for Moving Minimum Grade at DSN
     From 72% to 74%

    Driving Forces            Restraining Forces
      (support efforts)           (conflict with efforts)
Comparable to Other Schools   Significant Change in Policy
                                More students would fail
 Recent drop in NCLEX rates
                                DSN had 90-94% NCLEX
     Faculty requests                 rates with 72%

                                          
    Indicators to be Used in Hospitals
   Quantitative measures
   Related to one or more dimensions of
   Help provide data that (when analyzed)
    give information about quality
   Direct attention to potential problems
    Types of Indicators
   Sentinel-event indicators
       Serious injury or death indicator
   Aggregate-data indicators
       Rating for med errors and patient complaints
   Continuous-variable indicators
       Number of new bed sores per day
   Rate-based indicators
       Infections per 1000 patient days
     Run Charts
   Probably most
    familiar/used tool
   Used to identify
    trends/patterns in a
    process over time
   Helps track if target
    level has been
Run Chart – Trend Chart
Used for Self Comparison
 Quarterly report of new bed sores for Unit X 2008

20                                                 Unit X
                                          Unit X
1st Qtr   2nd Qtr    3rd Qtr    4th Qtr
Comparison Run Charts – Trend
Charts-(Dangerous because these
are not ratio numbers)
 Quarterly report of new bed sores for Units
 A, B, & X for 2008

                                                        Unit X
20                                                      Unit A
                                               Unit B
                                                        Unit B
10                                         Unit A
                                        Unit X
1st Qtr   2nd Qtr   3rd Qtr   4th Qtr
   Bar charts that display:
       Patterns of variation
       The way measurement data are distributed
       Snapshot in time
   May be more complex to establish;
    consult statistics textbook if needed
Comparison Run Charts – Trend
Charts-(Dangerous because these
are not ratio numbers)
 Quarterly report of new bed sores for Units
 A, B, & X for 2008


                                                Unit X
15                                              Unit A
                                                Unit B


     1st Qtr    2nd Qtr    3rd Qtr    4th Qtr
Comparison Run Charts – Trend
Charts for Delta Hospital (can be
compared equally)
 Quarterly report of new bed sores per 1000 patient
 days for Units A, B, & X for 2008.
10                                              Unit X
 8                                              Unit A
 6                                              Unit B
     1st Qtr   2nd Qtr    3rd Qtr    4th Qtr
               Control Chart
         This is the control chart for infections from I.V.s on Unit X
         With 3 case per 1000 patient days as the standard (std)
         for 2008.

0.005          Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
               x   x                x

        Std.           x   x   x        x   x
0.003                                           x   x       x
Pie Charts
   Descriptive data
   Shows a distribution by category
   Compared to the Whole
Pie Distribution of new bed sores for
hospitalized patients at Delta Hospital
 Total of 140 new bed sores reported in 2008

                    36        43               Unit X
                                               Unit A
                                               Unit B

    Scatter Diagrams
   Graphs that show statistical correlation
    between 2 variables
   Used when group wants to:
       Test a theory
       Analyze raw data
       Monitor an action taken
  Scatter Diagram Process
Min. Program Passing rates in %




     NCLEX Scores by %   100%

Survey’s can carry a risk to them. Also know what Likert
Scale you are using and why (1-4, 1-5, 1-10 most common).
These are Ordinal Numbers
Naturalistic Inquiry— (Ch. 3)
Qualitative Research Methods

   Phenomenology
   Ethnography
   Auto-ethnography
   Grounded Theory
   Descriptive Qualitative
   Historical ?
    Non-Probability Sampling

Theoretical Sampling      Quota

Purposive Sampling (Non-Randomized)

   Convenience Sampling     Network
    Observational Measurement
   Unstructured
   Structured
       Category Systems
       Checklists
       Rating Scales
   Emic (from within)
   Etic (from external view point)
    Phenomenology Research:
     “The Lived Experience”
   Phenomenology is a science whose purpose
    is to describe the appearance of things as a
    lived experience.
   It allows nursing to interpret the nature of
    consciousness in the world.
   It can be descriptive or interpretive
   It is a philosophy, an method, and an
    inductive logic strategy
        Design Characteristics
   Purposive samples of 7-20 usually going for
   Instrument is the researcher
   Data collection is by interview of groups or
    individual that are verbatim, taped, and
    field notes.
   Data collection is directly tied to analysis,
    that eventually is coded or structured into
              Unique Features of
   Most of the literature review is conducted at
    the end of the data collection. It is believed
    the CF biases the data collection and
       Like Grounded Theory but without a BSP or bias
        already in mind.
   It is conducted by gathering interview data
    from others.
   It is never quantitative, but some would
    prefer to try and keep it objective.
      Five Steps of the Method
   Shared Experience is presented
   Transform the lived experience into an
    experience the subject would agree with
   Code the data
   Put it into written form and create
    confirmation of the data texts.
   Create a complete integration of all of these
    for a research document
   NOTE: In come cases, researchers need to
    have Bracketing to control an over-riding
    bias or emotional response
     Qualitative Research Rigors
     The Five Standards (Ch. 13)

   Descriptive Vividness
   Methodological Congruence
   Theoretical Connectedness
   Analytical Preciseness
   Heuristic Relevance
Defining Naturalistic Rigor
Standards 1 and 2
   Descriptive vividness
     narratives are texturized, thick, and full of

     the writer shows connections and level of

   Methodological congruence
     details of exactly how the data is gathered

      with ethical rigor. Does the method match
      the design?
    Defining Naturalistic Rigor
    Standards 3, 4 and 5
   Analytical preciseness
      the data is transformed across several levels of
      moving raw data to clusters, interpretations, or
   Theoretical connectedness
      ensuring the theoretical schema is clear and
       related to the data being collected and a lens for
   Heuristic relevance
      readers must recognize the phenomenon as
       applicable, meaningful, & recognizable
      Other Types of Rigor Using
   Trustworthy questions
   Trustworthy approach
   Trustworthy in analysis
   Trustworthy and authenticity of data
Ethnography Research

          Defined as:
     “Learning from People”
           By Spradley
           Four Types of Ethnography
   Classical
       Years in the field, constantly observing and making sense of
        actions. Includes description and behavior. Attempts to describe
        everything bout the culture.
   Systematic
       Defines the structure of a culture.
   Interpretive (hermeneutic)
       To study the culture through inference and analysis looking for
        “why” behaviors exist.
   Critical
       Relies on critical theory. Power differentials, who gains and who
        loses, what supports the status quo.
             Historical Roots
   Early 1900s had several introductions
   Herodotus wrote about travel in Persia
   Malinowski’s Study of Trobriand Islanders
   Hans Stade wrote about his being in captivity
    by the wild tribes of Eastern Brazil
   The School of Sociology in Chicago, where
    the city was a laboratory from all the
    immigrants (dancers, muggers, case studies)
           Observation Methods
   Emic
       From within the research itself as a
        member or participant of some type.
   Etic
       From the outside looking in like a camera.
        It can be a peripheral issue or external
        observer member.
      Fundamental Constructs
   Is usually “etic” on the outside like a
   Sometimes they are “emic”, on the inside as
    one of the actors (more in sociology)
   Researcher is the instrument
   Fieldwork is where the work occurs
   Focus is on culture
   Involves cultural immersion
   There is a tension and reflexivity between
    the researcher as a member or researcher
    as researcher
       Stages of Ethnography
   Participant observation (gain access,
    rapport, trust)
   Descriptive observation (9) (space, actors,
    activities, objects, act, event, time, goal,
    and feelings)
   Ethnographic record (field notes, verbatim,
    old records, amalgamate the information)
   Domain analysis
   Focused observation (what is now critical)
Stages in Ethnography-2
   Taxonomic analyzing (categorize)
   Componential analysis (components
    of the selected areas)
   Discover cultural themes
   Take a cultural inventory
   Write up the ethnography
         Rigors for Ethnography
   Plausibility
       It is very easy to accept as truth
   Credibility
       Not exactly self evident, so you look at sources
        of evidence
   Thick Description
       Writing in such detail as to know exactly what is
        going on.
   We could also use the Five Standards
          Sources of Errors
   Personal reactivity
   False inferences
   Gaps in writing, remembering, and
   Going Native
    Grounded Theory Research
   Started by Glaser and Strauss in 1967
   Used extensively in nursing research
   Takes into account the concepts of George
    Herbert Mead (1934) regarding symbolic
    interaction theory- how we give meaning to
    situations, words, objects, symbols
   Is very individualistic in meaning
   Most often used to study areas which
    previous research exists
Steps in Grounded Theory are
  conducted simultaneously
   Observation
   Collection of data
   Organization of data
   Review of additional literature
   Forming theory from the data
   Using Constant Comparative
Data Collection Methods Have qualitative
      and quantitative properties

   Interviews (one on one, groups)
   Observation
   Records (retrospective analysis)
   Surveys (quantitative)
   Questionnaires (could be quantitative)
   Demographic data
Constructs of Grounded Theory
   Conceptual framework comes from the data
    rather than the literature review
   There is always an over-riding social issues
    being addressed called the Basic Social
    Process (BSP)
   Researcher focuses on dominate processes
    rather than describing the setting, or unit
   You compare all data with all other data
Constructs of Grounded Theory
   You may change data collection methods in
    mid stream to be more appropriate to what
    has already been discovered
   The researcher is to be doing most
    sequential tasks all at the same time
Constant Comparative Analysis
   Get data, look at it, look at the
    literature, look at previous data, go
    get more data, look at more literature,
    look at all the data, etc.
   Revise the question, collection
    method, and keep collecting data,
    look at literature, compare to old data,
          Sampling Methods
   Called Theoretical Sampling
      Based on the current question

      Add new groups to the sample based on
       what it is you have learned (may need
       more men in the sample, or more people
       over the age of 70, etc.)
   The sample being used moves as the theory
           Coding the data
   Look for positive AND negative cases
    related to your social process
   Step One: read, describe, and
   Step Two: constant comparison and
   Step Three: reduce it to a BSP
      Conducting Grounded Theory
   Be aware of the social life of the participants
   Make less assumptions in the beginning
   Sensitizing to the literature, Bracket if needed
   Layers of reality are explored, assess your own
    energy to go further
   Spend enough time with participants and data
   Be observant to how the participants are doing
   Learn the symbols being used to create this
   Sample across time
                 Case Studies
          from Stake (2000) and Yin (1994)

   These are OBJECT or METHOD issues
       Object: Has to do with what you want to
        study not an approach to how to study it
       Method: Can be quantitative or
        qualitative method (analytically, vs.
   Questions are aimed at “How” or
    “Why”(rarely “What”)
   Single or multiple cases-usually1or 2
               Purpose of Case Studies
   Seeks the unique features (particular) while also
    describing the common by describing:
       The nature of the case
       The case’s history and background
       The physical setting
       Other contexts (economics, political, legal, aesthetic
       Other cases through which this case is recognized
       Through the informants by which the case is known
   Examine changes across time (multiple case)
       Same group of different group
               Case Study Rigor
   Yin (1994) treats this as a positivistic
    activity, therefore:
       Construct, Internal, and external validity
       Reliability
       This is not just a pilot study for quasi- or full
        experimental designs. It is different.
   Stake (2000) treats it more naturalistic
       Thick description is key
       Auditability (can it be followed by the reader)
        Observational Measurement
          Could Use all of These
   Unstructured
   Structured
       Category Systems
       Checklists
       Rating Scales
   Emic (from within)
   Etic (from external view point)
        Interview Data Collection
   Unstructured
   Structured
       Describing interview questions
       Pretesting the interview protocol
       Training interviewers
       Preparing for an interview
       Probing
       Recording interview data
   Coding methods
          Problem Revisions
   I am curious about the standardized
    treatment protocols for circumcision of
    a new borne.
     Problem Statements-Questions
           dictates the design
   What is experience of police officers who were
    wounded in the line of duty related to their ability to
    return to work?
   What are the unique features of Hospitals that have
    NP conducting all surgical admission assessments?
   There is (is no) statistically significant difference in
    iatrogenic diseases between nurse to patient ratios of
    1:5 vs 1:8 on General Medical Units.
    Does the birthing center philosophy show a
    relationship to the type of care provided and if so,
    what is the relationship.
   How did the July 08 BSN cohort at DSN obtain a 99%
    NCLEX pass rate?
Special Research Designs
   Triangulated, Mixed, Blended
   Historical Research
   Action Research
   Outcome Research
   Intervention Research
               Blended Designs
   First used by Campbell and Fiske in 1959.
   Denzin in 1989 identified four different
       Data Triangulation
       Investigator triangulation
       Theoretical triangulation
       Methodological Triangulation
   Kimchi, Polivka, and Stevenson (1991) have
    suggested a fifth type
       Multiple Triangulation
          Data Triangulation
   Collection of data from multiple
   Intent is to obtain diverse views of the
    same phenomenon. (Longitudinal is
    different and is looking for change)
   Validate data by seeing if it occurs
    from different sources
     Investigator Triangulation
   Two or more investigators with
    different research backgrounds
    examining the same phenomenon
   Clarifies disciplinary bias
   Adds to validity of data
     Theoretical Triangulation
   Using all the theoretical
    interpretations that could conceivably
    be applied to a given area
   Each view is critically examined for
    utility and power
   Increased the confidence of the
   Can lead to even greater T. F. beliefs
    Methodological Triangulation
   The use of two or more research
    methods in a single study
       Design level
       Data collection level
   Two major types
       Within-method (all are one philosophy)
       Across-method (across philosophies)
Pros and Cons of Triangulation
   Very trendy in the 90’s
   Can be used with smaller N
   Combined methods may just be the
    rise of a new method
   There are philosophical risks
   Complex designs and therefore
    complex analysis
     Action Research: AKA clinical
       research, clinical inquiry,
   A systematic investigation conducted by
    practitioners involving the use of
    scientific techniques in order to improve
    their performance.

   Kurt Lewin (1946).
    Advantages of Action Research:
      The reflective practitioner
   Contributes to the knowledge base of
    teaching practice-self awareness
   Supports the professional development of
    practitioners –more competent in research
   Builds a collegial network
   Identifies problems and seeks solutions in a
    systematic fashion
   It can be used at all levels and in all areas of
Examples of Action Research
   Pick a topic
   Define the problem
   Select a design
   Select subjects
   Collect the data
   Analyze the data
   Application of results
What Makes it Action Research
   Invested in rigorously empirical
    (positivistic), and reflective and
    interpretive (naturalistic)
   Engages people who have traditionally
    been called “subjects” who are active in
    the research process.
   Results have a practical outcome
    related to lives or work of participants.
      Outcome Research p.272-317
    Came from evaluation research of the 70’s and 80’s

   Focuses on the end result of patient care and
    linked to the process that caused the
   Momentum is from policy makers, insurers,
    and the public
   Level of concern: 1. Care by clinician, 2.
    Amenities, 3. Care by the patient, 4. Care
    received by community
   More complex that it may appear
Evaluation of Outcome Research
   Process Evaluation
       Involves Standards of Care
       Involves Practice Styles
       Involves Cost of Care
   Structure Evaluation
       Elements of the Structure
       Philosophies of Management & Decision Making
       Evaluate Structure Issues and their impact on the
        care provided
   Lacks a set methodology
Indicators of Outcome Research
   Many Descriptive Indicators for Nursing
    Care: NDNQI, Picker,
       Stage all bed sores on patients at
        admission vs. during stay and at discharge.
   There must be a clear link between
    outcome and process
   We see practice based web sites:
    AHRQ, APRNet, PBRN group,
Sampling in Outcome Research
   Large heterogeneous samples, but not
    randomized. They want a full spectrum of the
   However, they want samples who were
    treated and those who were not treated to
    compare differences in outcomes.
   Risks, no random sample, small sample sizes
    are often used putting all their inferential
    statistics at risk for error.
Intervention Research
   It is used to give “Causal Explanations”
    for what is being seen
   Uses quantitative and qualitative
   It is more than a single research event,
    but it deals with multiple issues over
Intervention Research Process
   Extensive search of what information is
   Heavy emphasis on the intervention and
    refining its use
   Field tested to see if it will work
   It will involve a host of studies over time
   Has a host of informants who explain the
    local culture and what it will take to get data
      Intervention Research Methods
   Integrative lit. reviews       Observation
   Consumer publications          Case study
   Standards/ guidelines          Focus groups
   Meta-analysis                  Qual. Studies
   Health policy analysis         Concept analysis
   Personal exp. Reflections      New media
   Consensus conferences          Position Papers
   Retrospective chart            Delphi studies
    reviews                        Outcome studies
   Descriptive-Correlational
Risk for Use of Intervention
   Risk is asking the wrong question
   Inadequately trained interveners
   Poorly defined intervention
   Many confounding variables that can show up
   Too complex to manage and integrate
   Long time can change many factors: i.e. who
    is doing it, where can you still collect data,
    level of commitment by locations, etc.
Criteria for Intervention Research
Design: The intervention is---
   Effective
   Replicable
   Simple to use
   Practical
   Generalizability
   Compatible with local customs and
Historical Research
   Thought of as qualitative because it lacks
    sampling, treating, and controls.
   Uses Quantitative language, i.e. validity and
    reliability of data—best primary sources of
   Looks at external criticism of data (where,
    when, by whom), and internal criticism of
    data (reliability, authentic, biased lens of
Process of Historical Research
No Visible Rigor from Qualitative or Quantitative
   Research Outline
   Watch for cross-referencing
   Be prepared to spend months to years
    collecting the data
   Careful attention to note taking for all data
   A synthesis of all the data collected and may
    need an interpretive strategy
   Develop a writing outline
   Write your Historiography
“The beautiful thing about
learning is that nobody can take
it away from you.”
                --BB King
                  US jazz musician

Shared By: