NHR 4811 Health Research Methods - Comprehensive Study Guide

Examination Details and Overview

• Institution: University of Namibia (UNAM), Faculty of Health Sciences, Department: School of Nursing, General Nursing Science.
• Module: Health Research Methods (NHR 4811).
• Exam Period: May/June 2022 Regular Examinations.
• Duration: 3 Hours.
• Total Marks: $100$.
• Examiners: Takaedza Munangatire and Mr. Epafras Anyolo.
• Internal Moderator: Dr. K. Amakali.
• External Moderator: Dr. RR. Marie Modeste (Cape Peninsula University of Technology, South Africa).

Foundations of the Research Process

• Initial Step in Research: Identifying the research problem is considered the initial and one of the most significant steps in conducting the research process.
• Researcher Roles in Nursing Practice:
  • Consumer: A nurse who reads research articles and incorporates research findings into clinical practice.
  • Primary Investigator: The lead individual responsible for the conduct of the research.
  • Collaborator: An individual working with others to produce research.
  • Producer: An individual who designs and executes research studies.
• Reasoning Types:
  • Inductive Reasoning: Reasoning from specific observations to broader generalizations (e.g., reasoning from a single diabetic patient to all diabetic patients).
  • Deductive Reasoning: Reasoning from the general to the specific (e.g., reasoning from all chronically ill patients to a single chronically ill patient, or using a standard care plan for a specific patient).
• Comparison to Nursing Process: Problem identification in the research process is equivalent to the Nursing Diagnosis step in the nursing process.

Research Sources and Documentation

• Primary Sources: A journal article about a study that used large, previously unpublished databases generated by a statistics bureau is an example of a primary source. Textbook and commentaries are generally secondary sources.
• APA Formatting References: In the reference Harris, R. M., Bausell, R. B., Scott, D. E., Hetherington, S. E., & Kavanagh, K. H. (1998). An intervention for changing high-risk HIV behaviours of African American drug-dependent women. Research in Nursing and Health, 21(3), pp. 239-250.:
  • 21: Refers to the Volume number.
  • 3: Refers to the Issue number.
  • pp. 239-250: Refers to the page range.
• Academic Attention: The Abstract (or sometimes the Title) is the portion of the research report used to capture the reader's attention.

Qualitative vs. Quantitative Research Paradigms

• Qualitative Research Characteristics:
  • Studies are conducted in natural settings.
  • Data collection involves relating perceptions and exploring meanings (e.g., "Subjects were asked to relate their perceptions of pain").
  • Phrases common in reports: "Researchers sought to explore the meaning of the hospital experience."
  • Research approaches include Phenomenology (describing lived experiences) and Grounded Theory (study of processes, social structures, and interactions).
• Quantitative Research Characteristics:
  • Systematic and objective design with an emphasis on control and precision (Rigor).
  • Data tend to be numeric.
  • Phrases common in reports: "A convenience sample was chosen," or "The hypothesis of this study is…"
  • Rigor: Defined as the amount of control and precision exerted by the methodology.

Variables and Definitions

• Conceptual Definitions: These are important because the meanings of terms may differ depending on the study framework; they provide the theoretical meaning of a concept.
• Operational Definitions: Specified what the researchers must do to measure the concept and collect needed information.
• Types of Variables:
  • Continuous Variable: Can take on values from zero to more than $100$, where values are not restricted to whole numbers ($1.2.4$).
  • Discrete Variable: A variable with a finite number of values between any two points, representing distinct quantities ($1.2.1$).
  • Categorical Variable: Variables that take on a handful of discrete non-quantitative values ($1.2.2$).
  • Dichotomous Variable: Categorical variables that take on only two values (e.g., yes/no, treated/untreated) ($1.2.3$).
  • Dependent Variable: The outcome variable (e.g., in a study on preoperative support, the dependent variables are "perception of pain" and "request for analgesics").

Research Design, Hypotheses, and Control

• Levels of Researcher Control:
  • Experimental Research: High researcher control, random sampling, and often a laboratory setting. Involves at least partial control to implement study treatment.
  • Quasi-experimental: Involves manipulation of an independent variable but lacks either random assignment or a control group.
  • Correlational: Examines relationships between variables without manipulation.
  • Descriptive: Describes characteristics of a population or phenomenon.
• Hypothesis Types:
  • Directional Hypotheses: Specifies the expected direction of the relationship (e.g., "The risk of falling increases with the age of the patient").
  • Non-directional Hypotheses: Predicts a relationship exists but does not specify the direction (e.g., "There is a relationship between the age of a patient and the risk of falling").
  • Experimental Design Indication: Hypotheses comparing groups (e.g., "The incidence of UTIs will be greater in patients whose catheters are irrigated frequently than in those irrigated less frequently") indicate experimental or quasi-experimental designs.
• Research Categories:
  • Applied Research: Aimed at solving practical problems (e.g., "Does telephone follow-up improve medication compliance?").
  • Basic Research: Aimed at extending the base of knowledge for the sake of knowledge.

Feasibility and Ethics

• Feasibility: Determined by examining the availability of subjects, researcher expertise, time, and resources. Obtaining written permission from facilities to access patients is an example of establishing the feasibility of a study.
• Research Settings:
  • Natural/Field Setting: Data collection in a participant's home (e.g., studying caregivers of stroke victims).
  • Highly Controlled/Laboratory: Specialized environments designed to minimize extraneous variables.

Statistical Analysis and Interpretation

• Test for Comparing Two Means: A T-test (Independent T-test) is applied to compare mean knowledge scores between two groups (e.g., Male $56\%$ vs Female $66\%$).
• Test for Comparing More Than Two Means: ANOVA (Analysis of Variance) is used when comparing means among three or more groups (e.g., comparing scores across four different years of study).
• P-Value Interpretation:
  • If $p = 0.03$: The result is statistically significant (usually $p < 0.05$), indicating a low probability that the difference occurred by chance.
  • If $p = 0.07$: The result is not statistically significant (usually $p > 0.05$), indicating that differences among groups might be due to chance.
• Correlation:
  • Pearson’s r: Used to test the relationship between two continuous variables (e.g., Knowledge scores and Practice scores).
  • Interpretation of $+0.7$ at $p = 0.05$: A strong positive correlation that is statistically significant.
• Chi-Square ($\chi^2$): A non-parametric test used for cross-tabulations to determine the association between categorical variables (e.g., the relationship between gender and smoking status).
• Cause and Effect: Regression analysis (specifically Linear or Logistic Regression) is an inferential statistical test used to determine the predictive relationship or cause-and-effect among variables.

The Research Problem Statement

• Definition: A situation in need of a solution, improvement, or a discrepancy between the way things are and the way they need to be (Brink, 2018).
• Purpose: To provide a clear rationale for the study and identify the gap in knowledge or practice that the research intends to fill.
• Key Questions to Answer:
  1. What is wrong with the current situation?
  2. Where is the gap in knowledge?
  3. Why is the problem important?
  4. Who is affected by the problem?
  5. What are the consequences of not solving the problem?
  6. What is the evidence that the problem exists?

Sampling Concepts

• Target Population: The entire group of individuals or objects to which researchers are interested in generalizing the conclusions (e.g., all registered female nurses in teaching hospitals).
• Accessible Population: The portion of the target population that is available to the researcher (e.g., nurses in the six specific hospitals that granted permission).
• Sampling Error: The difference between a sample statistic used to estimate a population parameter and the actual but unknown value of the parameter. It is important because it indicates the precision of the research findings.
• Stratified Random Sampling: A technique where the population is divided into subgroups (strata) to ensure that specific groups are adequately represented.
• Sample Adequacy Criteria:
  • Representativeness of the population.
  • Sample size (power analysis).
  • Homogeneity vs heterogeneity of the population.
  • Nature of the research (qualitative vs quantitative).
  • Resources and time available.
  • Sampling method used (probability vs non-probability).
  • Expected attrition/response rates.
  • Sensitivity of the measurement tools.
  • Number of variables being studied.
  • Level of precision/significance required.

Data Collection Instruments

• Questionnaire Design: Typically organized into sections such as Demographic Data (Section A), Knowledge (Section B), Attitudes (Section C), and Practices (Section D).
• Validity: Ensuring the instrument measures what it is intended to measure (e.g., Content validity through expert review).
• Reliability: Consistency of the measurement.
  • Cronbach’s Alpha: A measure of internal consistency.
  • Score Interpretation: A Cronbach alpha of $0.5$ is generally considered poor or unacceptable reliability (usually $\alpha > 0.7$ is required for a reliable instrument).