Rehabilitation Research Boot Camp: Statistical Analysis Essentials

12-Month Subscription

Unlimited access to:

Thousands of CE Courses
Patient Education
Home Exercise Program
And more

Subscribe Now

First Chapter Free Buy Course

Video Runtime: ___ Minutes; Learning Assessment Time: ___ Minutes

This comprehensive course provides healthcare researchers and clinicians with a robust framework for navigating the complexities of data analysis in rehabilitation and medical research. In an era where evidence-based practice is paramount, the ability to accurately interpret and apply statistical findings is essential for optimizing patient outcomes and ensuring research fidelity. This course addresses the critical gap between raw data collection and clinical application by exploring hypothesis testing, the nuances of parametric and nonparametric statistics, and the distinction between statistical significance and clinical meaningfulness. Participants will learn to evaluate associations, identify differences between groups, and understand the impact of confounding variables on study results. Designed for a broad audience of healthcare providers—including physical therapists, physicians, and clinical researchers—this material is applicable across diverse settings such as academic institutions, private practices, and hospital-based research departments. By mastering these analytical tools, practitioners can better translate complex research findings into effective, evidence-driven clinical interventions.

Learning Outcomes

Define the purpose of a statistical analysis
Interpret the findings of a hypothesis test
Clarify characteristics of data types and how this influences the choice of statistics
Differentiate between parametric and non-parametric statistics
Interpret the results of common statistical tests used in rehabilitation research
Apply appropriate statistics related to the various research design types
Interpret specific statistics related to epidemiology such as odds ratios, relative risk, absolute risk, attributable risk
Recognize the impact of confounding, mediating, moderating variables, sampling variability and information bias in epidemiology studies
Differentiate between statistical significance and clinical meaningfulness

Meet your instructor

A smiling man in formal attire represents the future of digital healthcare for medbridge.

Kenneth E. Learman

Kenneth E. Learman is a professor of physical therapy at Youngstown State University, where he is responsible for teaching manual therapy, patient examination and clinical reasoning, and research design and data analysis in the curriculum. Ken is also affiliated faculty at Duke University Division of Physical Therapy. Ken has…

Read full bio

Chapters & learning objectives

1. Hypothesis Testing and the Goal of Statistical Analyses

This chapter introduces the fundamental mathematical models used to describe relationships between predictor and outcome variables while accounting for inherent systematic and random errors. It is essential for learners to understand that the p-value is a probabilistic estimate of the data to accurately determine whether a null hypothesis remains tenable.

2. Understanding and Describing Data

Participants will explore the characteristics of descriptive and inferential statistics, focusing on measures of central tendency, variability, and the various types of data scales. Mastering data visualization and understanding distribution shapes is a critical prerequisite for selecting the most appropriate analytical methods and correctly interpreting experimental outcomes.

3. Parametric and Nonparametric Statistics

This section details the specific assumptions required for parametric testing, such as normality and homogeneity of variance, and introduces nonparametric alternatives for categorical or skewed data. Understanding these distinctions ensures that researchers use the most powerful and familiar statistical tools available while remaining robust to common data violations.

4. Studies of Differences

This chapter examines experimental designs aimed at determining whether differences between or within groups are statistically significant and clinically relevant. By comparing means and proportions using tests such as ANOVA or chi-square, clinicians can better evaluate the true impact of their interventions relative to control groups.

5. Studies of Associations

Learners will investigate exploratory research methods that identify the strength and direction of relationships between multiple variables through correlation and regression. This is important for developing predictive models and understanding how various factors covary to influence patient risks or treatment hazards.

6. Clinical and/or Statistical Significance

This chapter addresses the vital distinction between a model’s mathematical significance and the actual meaningfulness of the change perceived by the patient. It provides the tools necessary to calculate effect sizes and minimal clinically important differences, ensuring that research findings translate into practical improvements in the clinical setting.

7. Course Summary and Discussion

The final chapter synthesizes the core analytical concepts covered throughout the series to reinforce a multimodal approach to interpreting evidence. This summary serves as a reflective conclusion that helps practitioners apply their newfound statistical literacy to the broader medical literature.

More courses in this series

Rehabilitation Research Boot Camp: A Renewed Look at Evidence-Based Practice

Chad E. Cook

Rehabilitation Research Boot Camp: Research Methodology I

Kenneth E. Learman

Rehabilitation Research Boot Camp: Research Methodology II

Chad E. Cook