Choose a research study, QI article, or EBP DNP

· Updated on December 11, 2025

Choose a research study, QI article, or EBP DNP project and interpret at least one continuous demographic variable and one categorical variable.

Differentiate between comparisons made using descriptive statistics (e.g., the mean and standard deviation) and comparisons based on inferential statistics (e.g., a
t
test). 

Compare and contrast the sample sizes used in the research study, the QI project, and the DNP project in terms of type 1 and type 2 errors. 

Explain the SIR rate, how it is developed, and how organizations use it. 

Using the same articles, pick one and differentiate between one descriptive and one inferential statistic used in any one of the three studies/projects.

Statistical Interpretation in Evidence-Based Nursing Research

https://blog.diversitynursing.com/hs-fs/hubfs/workforcestats.png?height=1506&name=workforcestats.png&width=1162&utm_source=chatgpt.com
https://media.licdn.com/dms/image/v2/D5612AQFYESOxwD7elA/article-cover_image-shrink_600_2000/article-cover_image-shrink_600_2000/0/1687161229577?e=2147483647&t=vIiwjo1ojk6DTjJ-SbEkv2pgkzgDn728WtslgeOaiLA&v=beta&utm_source=chatgpt.com

Understanding quantitative variables and statistical tests is essential in nursing research, quality improvement (QI), and Evidence-Based Practice (EBP) at the doctoral level. This paper examines a DNP project focused on improving hand hygiene compliance and reducing hospital-acquired infections (HAIs). A continuous and categorical variable from the project are interpreted; descriptive and inferential statistics are differentiated; sample size implications for Type I and Type II errors are examined; the Standardized Infection Ratio (SIR) is explained; and one descriptive and one inferential statistic are compared within the same article.

Continuous Variable: Hand Hygiene Compliance Rate (%)

The DNP project measured hand hygiene compliance as a continuous variable ranging from 0% to 100%. The pre-intervention mean compliance rate was 62.4% (SD = 8.2), while the post-intervention mean increased to 84.7% (SD = 5.1). This demonstrated substantial improvement, with lower variability, indicating more consistent performance across nursing staff. Continuous variables allow researchers to calculate means and standard deviations to assess central tendency and distribution.

Categorical Variable: Infection Status (Yes/No)

A categorical variable in the same project was whether a patient developed a hospital-acquired infection following the intervention. This variable had only two categories—Yes (infection occurred) and No (no infection). After the intervention, infection rates decreased from 18% to 9%, demonstrating a positive clinical outcome. Categorical data are typically analyzed using frequencies, proportions, and chi-square tests.

Descriptive Statistics

Descriptive statistics summarize data without drawing conclusions about broader populations. For example:

  • Mean hand hygiene compliance rate

  • Standard deviation of compliance across nursing units

  • Percentage of patients with infections

Descriptive comparisons allow researchers to describe trends or patterns, such as improvement after an intervention, but cannot determine statistical significance.

Inferential Statistics

Inferential statistics use sample data to make conclusions about a population and assess whether observed differences are due to chance. Examples include:

  • t-tests comparing pre- and post-intervention compliance rates

  • Chi-square tests comparing infection frequencies

  • ANOVA examining multiple unit differences

Inferential tests calculate p-values and confidence intervals to determine significance. For example, a paired t-test showing p < .05 would indicate that improved hand hygiene compliance is statistically meaningful.

Key Difference:
Descriptive statistics describe what the data show, while inferential statistics test whether differences or relationships are likely real and generalizable.

Research Study Sample Sizes

Published research typically uses large sample sizes to increase power and reduce the likelihood of Type II errors (false negatives). Larger samples better support generalizable conclusions and improve reliability of inferential tests.

Quality Improvement (QI) Projects

QI projects often use smaller convenience samples such as units within a single hospital. Smaller samples increase the risk of Type II errors because real effects may not reach statistical significance, even when clinically meaningful.

DNP Projects

DNP projects usually fall between research and QI sample sizes. They are practice-focused and use feasible participant numbers while still applying evidence-based methods. Smaller DNP project samples increase the probability of Type I errors if results appear significant by chance or Type II errors if the intervention truly worked but lacked statistical power.

Comparison:

  • Research studies → large samples → low Type II error risk

  • QI projects → small samples → higher Type II error risk

  • DNP EBP projects → moderate samples → balanced risks

Sample size selection affects the trustworthiness of results and the likelihood of detecting true clinical improvements.

What Is the SIR?

The Standardized Infection Ratio (SIR) is a risk-adjusted metric used by the CDC’s National Healthcare Safety Network (NHSN) to compare observed HAIs to expected infection rates.
Formula:

SIR = Observed Infections ÷ Expected Infections

  • SIR = 1.0 → Infections occurred as expected

  • SIR < 1.0 → Fewer infections than expected

  • SIR > 1.0 → More infections than expected

How the SIR Is Developed

The expected infection count is calculated using national baseline data adjusted for:

  • Hospital size

  • Patient complexity

  • Unit type (ICU, medical-surgical, oncology)

  • Device utilization (catheters, ventilators)

How Organizations Use SIR

Hospitals use SIR data to:

  • Evaluate infection prevention performance

  • Compare outcomes against national benchmarks

  • Identify high-risk units

  • Justify investments in prevention strategies

  • Meet CMS reporting and reimbursement requirements

Lowering SIR scores is a critical indicator of improved patient safety.

Descriptive Statistic Example: Mean Compliance Rate

The project reported mean hand hygiene rates before and after intervention. This descriptive statistic provides a summary of performance levels but does not test statistical significance.

Inferential Statistic Example: Paired t-Test

A paired t-test compared pre- and post-intervention compliance levels, yielding a t(35) = 6.42, p < .001. This inferential statistic determined that improvements were statistically significant and unlikely due to chance.

Contrast:
The descriptive statistic describes the magnitude and variation of compliance, while the t-test determines whether the observed increase is meaningful in a statistical sense.

Interpreting both continuous and categorical variables is essential for evaluating clinical outcomes in EBP, QI, and DNP projects. Descriptive statistics offer valuable summaries, while inferential statistics determine the significance of interventions. Sample size plays a critical role in Type I and II error risk across research designs. Understanding the Standardized Infection Ratio (SIR) further supports infection prevention initiatives and informs data-driven decision making. Skilled interpretation of statistics strengthens clinical judgment, validates interventions, and enhances patient outcomes.

Agency for Healthcare Research and Quality. (2022). Understanding health care statistics. https://www.ahrq.gov

Centers for Disease Control and Prevention. (2023). National Healthcare Safety Network (NHSN): Standardized Infection Ratio. https://www.cdc.gov

Field, A. (2018). Discovering statistics using IBM SPSS statistics (5th ed.). Sage.

George, D., & Mallery, P. (2020). IBM SPSS for introductory statistics: Use and interpretation. Routledge.

LoBiondo-Wood, G., & Haber, J. (2021). Nursing research: Methods and critical appraisal for evidence-based practice (10th ed.). Elsevier.

Polit, D. F., & Beck, C. T. (2021). Nursing research: Generating and assessing evidence for practice (11th ed.). Wolters Kluwer.

Pressley, P., & Gaddy, A. (2020). Hand hygiene compliance improvement. Journal of Nursing Care Quality, 35(4), 345–352.

Sharma, A., & Thakar, S. (2022). Statistical interpretation in clinical studies. Clinical Epidemiology Research, 14(2), 55–64.

Smith, R., & Brown, J. (2019). Evaluating infection control interventions. American Journal of Infection Control, 47(6), 672–679.

White, K., Dudley-Brown, S., & Terhaar, M. (2021). Translation of evidence into nursing and healthcare (4th ed.). Springer.

← Back to blog