Research

Podcast

Play an AI-generated podcast conversation about this lesson

Questions and Answers

What does 'credibility' in qualitative research primarily refer to?

The extent to which findings can be generalized

The neutrality of the research approach

The use of quantitative measures

The confidence in the truth of the findings (correct)

What is the main focus of 'transferability' in qualitative research?

The internal validity of study designs

The accuracy of data collection techniques

The ability to apply findings to similar contexts (correct)

The reliability of the research instruments

Which strategy is NOT commonly associated with enhancing credibility in qualitative studies?

Reflexivity journal

Prolonged engagement

Member checking

Random sampling (correct)

What term refers to the extent to which a qualitative study can consistently yield the same results across different contexts?

Reliability Signup and view all the answers

Which concept is associated with ensuring that qualitative findings are accurate representations of individual experiences?

Credibility Signup and view all the answers

What does 'objectivity' in qualitative research refer to?

The complete absence of bias Signup and view all the answers

What is a significant way to ensure rich descriptions in qualitative research for achieving transferability?

Providing thick descriptions Signup and view all the answers

What is the purpose of collating codes into potential themes?

To organize data around specific themes for further analysis Signup and view all the answers

Which criterion focuses on the researcher's ability to demonstrate the accuracy of their interpretations?

Credibility Signup and view all the answers

What does reviewing themes involve?

Creating a thematic ‘map’ based on initial findings Signup and view all the answers

What is a key aspect of defining and naming themes?

Refining the specifics and overall narrative of the analysis Signup and view all the answers

Which of the following is NOT a purpose of producing the report?

To generate unclear and vague themes Signup and view all the answers

Which strategy is NOT associated with ensuring dependability in qualitative studies?

Random sampling Signup and view all the answers

What does trustworthiness in research aim to establish?

Confidence in the findings and generalisability of results Signup and view all the answers

What characterizes longitudinal research?

Observing changes over an extended period Signup and view all the answers

What is the primary concern of confirmability in qualitative research?

The neutrality of data relative to the researcher Signup and view all the answers

Which of the following is an example of computer-assisted data analysis software?

Nvivo Signup and view all the answers

Which of the following best describes a retrospective study?

Examines data from past events Signup and view all the answers

Which of these aspects does NOT contribute to integrating the experience into new life?

Leaving behind all past experiences Signup and view all the answers

What aspect is critical in ensuring the generalizability of research findings?

Confirming the data set aligns with the research objective Signup and view all the answers

Which of the following strategies helps improve confirmability in qualitative research?

Peer debriefing Signup and view all the answers

What distinguishes experimental research from non-experimental research?

Experimental research manipulates variables Signup and view all the answers

Which description correctly defines cross-sectional studies?

They provide a snapshot of a population at one time. Signup and view all the answers

Which of the following aspects is NOT a key dimension in quantitative research design?

Qualitative vs quantitative Signup and view all the answers

What equation represents the relationship between obtained results, true result, and measurement error?

Obtained results = True result ± Error Signup and view all the answers

Which of the following is NOT a source of measurement error?

Participant training Signup and view all the answers

What does test-retest reliability measure?

The stability of scores over time Signup and view all the answers

Which statistic is used to measure internal consistency in surveys?

Cronbach’s alpha Signup and view all the answers

What does content validity refer to?

The adequacy of instrument content Signup and view all the answers

What is an acceptable value for Cohen’s Kappa to indicate strong agreement on categorical measures?

≥0.6 Signup and view all the answers

Which factor influences measurement error through personal circumstances like mood and hunger?

Transient personal factors Signup and view all the answers

What does the Intraclass Correlation Coefficient (ICC) measure?

Both B and C Signup and view all the answers

What is the purpose of the Shapiro-Wilk test?

To test for normality in a dataset Signup and view all the answers

Which visualization is best suited for presenting data to non-experts?

Histogram Signup and view all the answers

When using a Wilcoxon Signed Rank test, what is being compared?

Medians from the same group at different times Signup and view all the answers

Which of the following is a parametric test?

Independent samples t-test Signup and view all the answers

When should a non-parametric test be used instead of a parametric test?

When data does not meet parametric test assumptions Signup and view all the answers

Which statistical test would be appropriate to assess blood glucose levels before and after intervention within the same group?

Paired sample t-test Signup and view all the answers

In the context of hypothesis testing, what does a Q-Q plot primarily help to assess?

The normality of the distribution of a dataset Signup and view all the answers

Which hypothesis test would determine if there is a significant difference in anxiety levels between first-year and fourth-year nursing students?

Independent samples t-test Signup and view all the answers

Which statistical test is appropriate for comparing the BMI among adults who underwent different types of interventions?

Kruskal-Wallis test Signup and view all the answers

What distinguishes a t-test from a z-test?

A t-test is used when the sample standard deviation is unknown. Signup and view all the answers

Which statement about the F-test is accurate?

It assesses the equality of variances among three or more groups. Signup and view all the answers

How does the sample size affect the similarity between standard normal distribution and t-distribution?

With larger sample sizes, they become more similar. Signup and view all the answers

For which scenario is the z-test predominantly used?

When the population standard deviation is known. Signup and view all the answers

What does the Friedman’s test assess?

Differences in medians across two or more groups. Signup and view all the answers

What is the primary use of the two-way ANOVA?

To analyze how two categorical independent variables affect a continuous dependent variable. Signup and view all the answers

Which statement is true about the t-distribution?

It is always symmetric around the population mean. Signup and view all the answers

Study Notes

NUR3202C Research and Evidence-Based Healthcare Consolidation Lecture

The lecture was presented by Asst. Prof Jocelyn Chew, PhD, BSN (Hons), RN.
She is an Assistant Professor at the National University of Singapore (NUS) in the Nursing and Biomedical Informatics departments.
She also holds a clinical lead role at the National University Health System (NUHS) and is an assistant professor at NUS's Behaviour and Implementation Science Interventions (BISI) department.

Week 1: Aims, Objectives, Questions, and Hypotheses

Aims are broad, general, and long-term.
Objectives are specific, focused, short-term, and measurable.
Research questions rephrase objectives with a focus on variables.
Research hypotheses, if applicable, are used in quantitative studies and specify relationships between variables.

Differences Between Qualitative and Quantitative Research

Qualitative research: descriptive, phenomenological, ethnographic, grounded theory, and participatory action research.
Quantitative research: experimental (hypothesis testing), randomized controlled trials, quasi-experimental trials, non-experimental (descriptive/correlational), cross-sectional, cohort, and case-control studies.

Qualitative vs Quantitative Research Characteristics

Qualitative research: inductive reasoning, small sample sizes, purposive sampling, subjective findings (interviews, observations), researcher's interpretation, verbatim quotes from interviewees
Quantitative research: deductive reasoning, large sample sizes, general sampling, objective findings (questionnaires, experiments), statistical methods, precise numbers

Quantitative Research Question (PICO)

PICO stands for Population/Problem, Intervention/Exposure, Comparison, and Outcome.
Example question: What is the effectiveness of HIIT on menopausal symptoms including hot flashes, insomnia, and brain fog among women undergoing menopause?

Qualitative Research Question (PICO)

PICO stands for Population/Problem, Interest, Context, and is without Outcome.
E.g. Research question: What is the experience of patients with type 2 diabetes on diet restriction to improve blood glucose control?

Literature Review

Purpose: Provides context/background information; not intended to answer the research question.
Systematic reviews: Identify, select, synthesize, and appraise studies that meet predefined inclusion criteria to answer the research question; create an a-priori protocol (published in PROSPERO).
Search: Well-defined, comprehensive search strategy using well-known articles.
Methodological appraisal: Uses tools like ROB (risk of bias) to judge study quality.
Synthesis: Typically narrative; not always reproducible.
Findings: Reproducible in systematic reviews.

Level of Evidence

Synthesized evidence, with systematic reviews of systemic reviews, umbrella reviews, meta-analysis, and meta-synthesis being the strongest level of evidence.
Randomised controlled trials, quasi-experimental studies, cohort studies, cross-sectional studies, case-control studies, and case reports are examples of empirical evidence.
Background information, expert opinions, textbooks, and editorials provide basic information.

Steps to Perform a Systematic Review

Formulate a clear and well-defined research question.
Develop a systematic review protocol.
Conduct a systematic search strategy.
Use a protocol and eligibility criteria to screen titles and full texts.
Methodologically appraise the included studies.
Extract and organise data.
Analyse the data.
Appraise the quality of evidence.
Integrate, synthesize, summarise, and write the review.

Qualitative Research Study Design:

Definition: Collects non-numerical data for in-depth understanding of phenomena in their natural setting.
Purpose: Exploring vague phenomena, laying groundwork for quantitative studies where insights are insufficient, and explaining quantitative results.

Formulating Research Questions (Qualitative)

Ontological inquiry focuses on understanding participant realities.
Epistemological inquiry focuses on understanding knowledge of a phenomenon.

Qualitative Designs

Descriptive: Describes and interprets perceptions/meanings.
Grounded theory: Collects rich data to inductively develop theories.
Phenomenological: Understands a phenomenon by describing and interpreting participants' lived experiences.
Ethnography: Researchers immerse themselves in target groups to understand cultures.
Participatory action: Both researchers and participants conduct research together to trigger social change.

Data Collection Methods (Qualitative)

In-depth interviews (individual & focus groups, semi- and unstructured)
Observations (using five senses)
Surveys (with open-ended questions)
Secondary data (texts, images, audio/video recordings)
Field notes

In-depth Interview Techniques

Build rapport and gather participant information.
Ensure anonymity & confidentiality.
Obtain permission to audio-record.
Develop interview guides with open-ended questions (e.g., "Why?", "How?").
Listen more than talk; use prompts and silence; avoid leading questions.

Sampling Methods (Qualitative)

Convenience: Volunteers through advertisements.
Purposive: Non-probability sampling based on criteria.
Snowball: Recruited participants recommend others (useful for sensitive topics).
Theoretical (grounded-theory): Decisions on next participants based on ongoing data analysis.

Sample Size (Qualitative)

Typically determined by data saturation (no more new information emerges).
Varies based on design (e.g., descriptive, grounded theory, phenomenological, ethnography).

Qualitative Data Analysis

Content analysis: Identifies and describes common ideas (manifest and latent).
Thematic analysis: Identifies, interprets, and analyses meanings and patterns within data (inductive, usually).

General Data Analysis Steps (Qualitative)

Prepare data (e.g., transcripts).
Familiarize with data (iterative reading).
Code data (labeling patterns/meaning units).
Identify themes and subthemes.
Produce the report.

6-Steps Thematic Analysis (Braun & Clarke, 2006)

Familiarize with the data.
Generate initial codes.
Search for themes.
Review themes.
Define and name themes.
Produce the report.

Computer Assisted Data Analysis Tools, e.g. Nvivo, Atlas.ti, MaxQDA

Trustworthiness (Qualitative)

Establishes trustworthiness with strategies (e.g., truth value, applicability, consistency, neutrality) to increase confidence and trust in the findings.

Rigor in Qualitative Studies

Credibility: Confidence in the truth of findings, accurate description, and recognition of interpretations by similar participants.
Transferability: Extent an analysis can be applied to another similar situation or context.
Dependability: Stability of findings across time and contexts.
Confirmability: Neutrality in data reporting.

Quantitative Research Study Design (Week 4)

Differentiate between experimental and non-experimental designs.
Describe experimental designs (e.g., RCT, quasi-experimental).
Explain non-experimental designs (e.g., descriptive, correlational, comparative).
Discuss cross-sectional vs. longitudinal designs.
Describe retrospective vs. prospective designs.

True Experimental Research (RCT)

Gold standard for testing causal relationships.
Also called pretest-postest design with randomization.
Characterized by intervention, control group, and random assignment.

Quasi-Experimental Research

Practical but lacks randomization, making causal relationships less certain.
Weakness is that there is no random assignment of participants, which could create bias or confounding from non-random errors.

One-Group Pretest-Posttest Design

Data are collected from a single group in the same group several times before and after an intervention is introduced.

Non-Experimental Research

Includes descriptive, correlational, and comparative research.
Descriptive: Reporting descriptive statistics/frequencies (e.g., examining quality of life among patients with CHD).
Correlational: Analyzing/examining relationships/associations/factors between variables (e.g., relationship between medication and quality of life).
Comparative: Comparing variables between groups (e.g., comparing health-related quality of life between patients with MI and DM).

Cross-Sectional vs. Longitudinal Research

Cross-sectional: Data collection done at a single point in time.
Longitudinal: Data collected over multiple points in time.

Retrospective vs. Prospective Research

Retrospective: Looks back at existing data.
Prospective: Collects data moving forward.

Quantitative Sampling

Population: Entire set of individual objects or events of interest.
Parameter: Numerical characteristic of population.
Variable: Characteristic being measured.
Sample: Representative subset of a population.
Statistic: Measure that describes the sample.

Why Use Sampling in Clinical Research?

Impractical to study every person in a whole population.
Sampling gathers a representative subset of the population to gain insights about the total.

Sampling

Probability sampling (random)
Non-probability sampling (convenience, consecutive, snowball)
Sampling errors (sampling bias, sampling error)

Sample Size Calculation

Ensure sufficient sample representation/statistical power to detect true effects.
Avoid overpower, underpower, and excessive selection/unavoidable errors.

Data Collection Instruments (Quantitative)

Self-report surveys (open-ended, questionnaires, scales/visual analogue scales).
Observations (unstructured/structured).
Biophysiological measures.

Response Set Biases

Social desirability: Misrepresenting attitudes to fit social norms.
Extreme response set bias: Consistently expressing extreme opinions unrelated to true values.
Acquiescence response set bias: Consistently agreeing with survey questions.

Levels of Measurement

Nominal: Categorical, no order (e.g., gender, disease).
Ordinal: Categorical, with order (e.g., pain scale).
Interval: Numerical, with equal intervals (e.g., temperature).
Ratio: Numerical, with a true zero point (e.g., height).

Reliability and Validity (Week 6)

Reliability: Consistency of measurement across subjects, time, & observers
Stability: Test-retest reliability.
Internal consistency: Cronbach's alpha.
Equivalence: Cohen's kappa/ intraclass correlation (ICC).
Validity: Accuracy of measurement (e.g., content validity, criterion-related, construct validity).
Content validity: Expert panel reviews for appropriateness.
Criterion-related validity: Correlations with established metrics/future outcomes.

Measurement Error

Obtained results are influenced by true values and measurement errors.
Sources: Situational, environmental, transient personal factors.

Week 7 (Descriptive and Inferential Statistics)

Descriptive: Describes and summarizes data (e.g., central tendency, variability, frequency distribution).
Types: Frequencies, cross-tabulations, histograms, boxplots, mean, median, mode, range, standard deviation, variance
Inferential: Uses sample data to make inferences/generalizations about a population.
Types: hypothesis testing (t-test, ANOVA, Chi-square, z-test), regression anaylsis.

Hypothesis Testing

Null Hypothesis (H₀): No effect/relationship.
Alternative Hypothesis (H₁): Effect/relationship exists.
Significance Level (α): Probability of rejecting H₀ when it is true (e.g., 0.05).
P-value: Probability of observing the found data, if H₀ is true.

Types of Errors in Hypothesis Testing

Type I Error (false positive): Rejecting H₀ when it is true.
Type II Error (false negative): Failing to reject H₀ when it is false.

Parametric vs Non-Parametric Tests

Parametric: Assumes normal distribution, uses data from numerical variables, high statistical power, require homogeneity and normality.
Non-parametric: Does not assume normal distribution, uses ranks or ordinal data (lower power), doesn't require normality.

Common Parametric Test Assumptions

Continuous DV.
DV follows normal distribution.
Homogeneity of variance between groups.
Independent comparison groups.
Absence of significant outliers.

Checking for Normality

Visualization (e.g., Q-Q plots, histograms).
Statistical hypothesis tests (e.g., Shapiro-Wilk test).
Assess data for outliers/symmetry/distribution.

z-test vs t-test

Z-test: Used when the population standard deviation (SD) is known.
T-test: Used when the population SD is unknown.

F-test (ANOVA)

Used to compare variances or mean equality among 3+ groups/conditions/interventions.

Measures of Linear Association

Bivariate correlation
Chi-square test
Regression

Logistic Regression

Estimate associations between a binary DV and one or more IVs.

Comparisons

Correlation (r): Describes and infers relationships between variables.
Regression (β): Predicts outcomes based on other variables.
Effect sizes (e.g., Cohen's d): Quantifies magnitude of effects.

Studying That Suits You

Use AI to generate personalized quizzes and flashcards to suit your learning preferences.