Introduction to Nursing Research
Research questions, Research Hypothesis. unit#05
Muhammad Rehan
Lecture
DIONAM, DUHS
Acknowledge Sir Amjad Ali
1
Objective
• At the completion of this unit learners will be able
to:
• Identify variables in the study, to formulate research
question and hypothesis
• Formulate research question, which is to be
answered statistically and logically
• Formulate null hypothesis and test able research
hypothesis, which is to be answered statistically.
• Explore and select the appropriate statistical
measures for selected research question
2
Cont.…
• Justify the appropriateness of selected
statistical test, chosen for the testing question
and hypothesis
• Interpret the selected statistical test, chosen
for the testing question and hypothesis in
statistical manner
• Inference the selected statistical test, chosen
for the testing question and hypothesis in
statistical manner
Introduction
• The best research starts with two words: “I wonder.”
A sense of curiosity is all that is needed to begin the
research process.
• Observations about a practice problem become
questions, and these questions lead to nursing
research that provides evidence to solve the
problem.
• Finding and developing significant problems for
nursing research is critical to improving outcomes for
patients, nurses, organizations, and communities.
4
Cont.…
• The evolution of a research problem from a general
topic of interest to the articulation of problem and
purpose statements serves to narrow the focus to a
researchable question.
• This progression moves the research problem from
the conceptual (abstract concepts) to the operational
(measurable concepts or variables).
5
Research question
A question that outlines the primary
components to be studied and that guides the
design and methodology of the study.
6
The Elements of a Good Research
Question
• Two guides are helpful in developing a good research
question.
• One of them is described by the acronym PICO, which
outlines the elements of a good quantitative question.
• PICO stands for population, intervention, comparison,
and outcome.
• Using preoperative education for short-stay patients
undergoing prostatectomy as an example, a research
question based on PICO might look like this:
7
PICO
• Population: In radical prostatectomy patients
staying in the hospital one day after surgery .
• Intervention: Does customized preoperative
teaching . . .
• Comparison: Compared to standard
preoperative teaching . . .
• Outcomes: Lead to better pain control as
measured by a visual analog scale?
8
FINER
• Another acronym—FINER—gives guidance in
the appraisal of a research question. This
model gives the nurse researcher a framework
for evaluating the desirable characteristics of a
good question:
9
Cont.…
• Feasible: Adequate subjects, technical expertise, time, and
money are available; the scope is narrow enough for study.
• Interesting: The question is interesting to the investigator.
• Novel: The study confirms or refutes previous findings, or
provides new findings.
• Ethical: The study cannot cause unacceptable risk to
participants and does not invade privacy.
• Relevant: The question is relevant to scientific knowledge,
clinical and health policy, or future research directions.
10
Hypothesis
A restatement of the research question in a form
that can be analyzed statistically for significance.
11
Types of Hypothesis
Nondirectional hypothesis:
A two-sided statement of the research question
that is interested in change in any direction.
Directional hypotheses:
A one-sided statement of the research question
that is interested in only one direction of
change.
12
Null hypothesis:
A statement of the research question that
declares there is no difference between groups
as a result of receiving the intervention or not
receiving the intervention.
13
Development of Hypothesis
• A good hypothesis statement includes the
population, variables (dependent and
independent), and the comparison.
• It is easy to see the analogy between a PICO
question and a hypothesis.
14
Examples of Hypotheses
15
16
From Question to Hypothesis
• Just as the research question guides the design of a
study, so a hypothesis guides the statistical analysis.
• A research hypothesis is a specific statement that
predicts the direction and nature of the results of a
study.
• It can be complex or simple, directional or
nondirectional, and stated in statistical symbols or
narrative form (Connelly, 2015).
• The way a hypothesis is written determines which
tests are run, which outcome is expected, and how
conservative the results are.
• A hypothesis is a restatement of the research question
in a form that can be analyzed statistically for
significance.
• It is specifically used in causal tests, such as
experimental designs and quasiexperimental designs.
• For example, the research question “What is the
association of environmental factors and reactive airway
disease in otherwise healthy adults?” can be rewritten
as the hypothesis “There is no association between
environmental factors and reactive airway disease in
otherwise healthy adults.”
• Although stating that no relationship exists might seem
a counterintuitive way to start a research analysis, it is,
in fact, the only way that statistical significance can be
measured.
• Although we can never be sure that a relationship
exists, we can calculate the probability that it does not.
• Testing a null hypothesis in effect tells us how much
uncertainty is present in the statistical conclusions, so
the researcher can judge if it is within an acceptable
range.
Type of Analysis
• Descriptive Analysis
• Inferential Analysis
Descriptive Analysis
Inferential Analysis
Rules of Quantitative Analysis
• Select tests a priori
• Run all the tests identified
• Report all the tests that were run
Types of Quantitative Analysis
• Quantitative analysis refers to the analysis of
numbers.
• Quantifying the values of variables involves counting
and measuring them; these counts and measures
result in numbers that can be mathematically
manipulated to reveal information.
• The researcher can think of quantitative analysis as
an interpreter that takes raw data and turns it into
something understandable.
• Many types of quantitative analyses are
possible.
• Those available to the researcher can be
categorized in several ways: by the goals of
the analysis, by the assumptions made about
the data, and by the number of variables
involved.
Goals of the Analysis
• Quantitative analyses are also classified as
descriptive or inferential based on the aims of the
study.
• Descriptive studies are concerned with accurately
describing the characteristics of a sample or
population.
• Inferential analyses are used to determine if results
found in a sample can be applied to a population—a
condition necessary for confidently generalizing
research as a basis for evidence for nursing practice
(Schmidt & Brown, 2012).
Assumptions of the Data
• Quantitative analyses are generally grouped into two
major categories based on assumptions about the
data: parametric and nonparametric.
• The key differentiating factor for these categories is
the assumptions made about the distribution, or
shape, of the data.
Parametric tests
Statistical tests that are appropriate for data that
are normally distributed (that is, fall in a bell
curve).
Nonparametric tests
Statistical tests that make no assumptions about
the distribution of the data.
Number of Variables in the Analysis
• Univariate analysis:
Analysis of a single variable in descriptive
statistics or a single dependent variable in
inferential analysis.
• Bivariate analysis:
Analysis of two variables at a time, as in
correlation studies.
Cont.…
• Multivariate analysis:
The simultaneous analysis of multiple variables.
Selecting the Appropriate Quantitative Test
• Conducting an appropriate quantitative analysis depends
on the ability of the researcher to select the appropriate
statistical test.
• This is often the most daunting part of the analysis
process because many tests are available to the nurse
researcher.
• Each has specific requirements and yields particular
information, which may then be appropriate in specific
circumstances.
• The researcher must make decisions about the
appropriateness of a statistical test based on the
following factors:
Cont..
• The requirements of the research question.
• The number of groups to be tested.
• The level of measurement of the independent
and dependent variables.
• The statistical and mathematical assumptions
of the test.
Tests of Differences Between Two Group
Means
Tests of Differences in Rates and
Proportions
• As just noted, healthcare variables are often
expressed as rates or proportions.
• Events that either do or do not occur (e.g., a
medication error), characteristics that are
either present or absent (e.g., risk factor or no
risk factor), and variables that describe
characteristics in a categorical way (e.g.,
ethnicity or gender) cannot be expressed as
intervals.
Tests of Differences in Means with Many
Groups
Tests of Differences in Means with Many
Groups
• In some cases, more than two groups are
involved in an experiment.
• ANOVA is one of the most frequently used
statistical tests in evidence-based research
studies.
• ANOVA is helpful when the research involves
more than two groups.
• Univariate ANOVA is applied to determine if groups differ
on a single numerical outcome.
• Repeated-measures ANOVA is used to determine if time is a
factor in treatment conditions. Because these data are not
independent, a different version of ANOVA must be applied.
• Analysis of covariance (ANCOVA) is used to determine if a
covariate— commonly an extraneous variable—has an
impact on the experiment. For example, a researcher might
want to determine if socioeconomic status— rather than
the treatment condition—was a reason for the poor
outcome in a treatment group.
• MANOVA, the multivariate version of ANOVA, is the
most complex version of the test.
• MANOVA can accommodate multiple groups and
multiple dependent variables, and it is particularly
useful when the researcher believes that multiple
dependent variables are related to one another.
• For example, a researcher could use MANOVA to
determine if a combination of music therapy and
relaxation techniques affected anxiety and panic
attacks during painful procedures.
References
• Chang, S., Carey, T., Kato, E., Guise, J., & Sanders, G. (2012). Identifying
research needs for improving health care. Annals of Internal Medicine, 157(6),
439–445.
• Curley, M. (2012). Clinical research: Together, stronger, bolder. American
Journal of Critical Care, 21(4), 234–241.
• Houghton, C., Hunter, A., & Meske, U. (2012). Linking aims, paradigm and
method in nursing research. Nurse Researcher, 20(2), 34–39.
• Krill, C., Raven, C., & Staffileno, B. (2012). Moving from a clinical question to
research: The implementation of a safe patient handling program. Medsurg
Nursing, 21(2), 104–116.
• Welford, C., Murphy, K., & Casey, D. (2011). Demystifying nursing research
terminology: Part 1. Nurse Researcher, 18(4), 38–43.
• Facchiano, L., & Snyder, C. (2012). Evidence-based practice for the busy nurse
practitioner: Part two: Searching for the best evidence to clinical inquiries.
Journal of the American Academy of Nurse Practitioners, 24, 640–648.
43
44