Registered Health Information Administrator / Technician (RHIA / RHIT) Healthcare Statistics, Data Analytics, and Research Syllabus

What does a p-value represent, and what is the conventional significance threshold?

The probability of obtaining the observed results (or more extreme) if the null hypothesis were true. By convention, p < 0.05 is considered statistically significant, leading to rejection of the null hypothesis.

What is a Type I versus a Type II error in hypothesis testing?

Type I error (alpha): rejecting a true null hypothesis (false positive). Type II error (beta): failing to reject a false null hypothesis (false negative).

What does a confidence interval indicate?

A range of values, computed from sample data, that is likely to contain the true population parameter at a specified confidence level (e.g., 95%).

What does a correlation coefficient (r) measure, and what is its range?

The strength and direction of a linear relationship between two variables; it ranges from -1 (perfect negative) through 0 (no linear relationship) to +1 (perfect positive).

Which statistical test compares the means of two groups, and which compares means of three or more groups?

A t-test compares means of two groups; ANOVA (analysis of variance) compares means among three or more groups.

What is the chi-square test used for?

To test for an association or independence between two categorical (nominal) variables by comparing observed and expected frequencies.

Match each level of measurement to its description: nominal, ordinal, interval, ratio.

Nominal = named categories with no order (e.g., gender); Ordinal = ordered categories without equal intervals (e.g., pain scale); Interval = ordered with equal intervals but no true zero (e.g., temperature in °F); Ratio = equal intervals with a true zero (e.g., weight, age).

Which type of graph is best for displaying frequency distributions of continuous data, and how does it differ from a bar graph?

A histogram. Its bars touch (no gaps) because the data are continuous, whereas a bar graph has gaps between bars because it displays discrete or categorical data.

What is a pie chart best used to display?

Parts of a whole, showing the proportional contribution of each category to a total (data that sum to 100%).

What is a line graph best suited to display?

Trends or changes in data over time (time-series data).

What is a frequency polygon?

A line graph of a frequency distribution created by plotting points at the midpoint of each class interval and connecting them with straight lines; used to display continuous data trends.

What does a scatter diagram (scatter plot) display?

The relationship or correlation between two continuous numeric variables, with each point representing a paired observation.

What is a Pareto chart and what principle does it illustrate?

A bar graph with bars arranged in descending order of frequency combined with a cumulative line; it illustrates the Pareto principle (80/20 rule) to identify the most significant contributing factors.

What is a control chart used for in quality analytics?

To monitor a process over time and distinguish common-cause (random) variation from special-cause variation using a center line and upper and lower control limits.

When interpreting a data visualization, why should you always check the axis scale and starting value?

Because a truncated y-axis (not starting at zero) or distorted scale can exaggerate or minimize differences and mislead the viewer about the true magnitude of change.

What is a key principle when communicating analytic findings to a non-technical audience?

Tailor the message to the audience by avoiding jargon, leading with the key insight/actionable conclusion, and using clear visuals to support the narrative rather than presenting raw statistics.

Distinguish data, information, and knowledge in the analytics hierarchy.

Data are raw, unprocessed facts; information is data processed and given context/meaning; knowledge is information combined with experience and understanding to support decisions.

What is the difference between structured and unstructured data?

Structured data are organized in a defined format such as fields in a database (e.g., codes, lab values); unstructured data lack a predefined model (e.g., free-text clinical notes, images).

Define the four main types of analytics: descriptive, diagnostic, predictive, and prescriptive.

Descriptive (what happened), Diagnostic (why it happened), Predictive (what is likely to happen), and Prescriptive (what action should be taken).

What is data mining?

The process of analyzing large datasets to discover previously unknown patterns, relationships, and trends using statistical and computational techniques.

What is a key difference between a data warehouse and a data mart?

A data warehouse is a large, centralized, enterprise-wide repository of integrated data; a data mart is a smaller subset focused on a specific department or business function.

What does ETL stand for in data warehousing, and what does it do?

Extract, Transform, Load: the process of extracting data from source systems, transforming/cleaning it into a consistent format, and loading it into a data warehouse.

What is population health management?

An approach that aims to improve the health outcomes of a defined group of individuals by monitoring and managing care across the group, often through risk stratification and targeted interventions.

What is risk stratification in population health analytics?

The process of categorizing patients into risk groups (e.g., high, medium, low) based on health data to allocate resources and target interventions to those most likely to benefit.

What is the difference between a structure, process, and outcome measure (Donabedian model) in quality analytics?

Structure measures assess the setting/resources (e.g., staffing, equipment); process measures assess what is done to patients (e.g., % given aspirin); outcome measures assess the results of care (e.g., mortality, readmission rates).

What is benchmarking in healthcare performance analytics?

Comparing an organization's performance metrics against internal goals, peer organizations, or industry best-practice standards to identify improvement opportunities.

What is the difference between a dashboard and a scorecard in business intelligence reporting?

A dashboard displays real-time or current operational metrics for monitoring at a glance; a scorecard tracks performance against predefined targets/goals over time, often tied to strategic objectives.

What are KPIs (key performance indicators)?

Quantifiable measures selected to evaluate progress toward an organization's critical objectives and overall performance.

What is business intelligence (BI)?

The technologies, applications, and practices for collecting, integrating, analyzing, and presenting business data to support better organizational decision-making.

What is the difference between a retrospective and a prospective research study?

A retrospective study looks backward at data already collected (past events/records); a prospective study follows subjects forward in time to collect new data on outcomes as they occur.

What distinguishes a cohort study from a case-control study?

A cohort study follows groups defined by exposure status forward to compare outcome incidence; a case-control study starts with people who have an outcome (cases) and those who don't (controls) and looks backward to compare prior exposures.

What is the gold standard study design for establishing causation, and what is its defining feature?

The randomized controlled trial (RCT); its defining feature is random assignment of subjects to intervention or control groups, which minimizes bias and confounding.

Differentiate qualitative and quantitative research.

Qualitative research explores non-numeric data (interviews, observations) to understand experiences and meanings; quantitative research collects numeric data and uses statistical analysis to test hypotheses and measure variables.

What is the difference between reliability and validity in research measurement?

Reliability is the consistency/reproducibility of a measurement; validity is whether the measurement actually measures what it is intended to measure. A measure can be reliable without being valid.

What is the role of an Institutional Review Board (IRB)?

To review and oversee research involving human subjects to ensure ethical conduct, protection of subjects' rights and welfare, and informed consent.

What is a confounding variable?

An extraneous variable associated with both the exposure and the outcome that can distort or falsely suggest a relationship between them.

What is the difference between incidence and prevalence?

Incidence is the number of new cases of a condition occurring in a population over a specified period; prevalence is the total number of existing cases (new and old) in a population at a given point or period.

Define a healthcare registry.

An organized system for the collection, storage, retrieval, analysis, and dissemination of data on individuals with a particular disease, condition, or exposure for a defined purpose.

What is the primary purpose of a cancer (tumor) registry?

To collect, manage, and analyze data on cancer patients (diagnosis, treatment, and outcomes) to support cancer surveillance, research, and quality care, often reporting to state and national programs.

In cancer registry operations, what is the difference between case finding and the accession (case) registry?

Case finding is the process of identifying patients with reportable cancers; the accession registry is the chronological listing of all cancer cases entered into the registry, each assigned a unique accession number.

What is the purpose of follow-up in a cancer registry, and what minimum follow-up rate is typically expected for accreditation?

Follow-up tracks patients' survival and treatment outcomes over time; accredited programs typically must maintain follow-up on at least 90% of all eligible analytic cases (and 80% from the reference date).

What is a trauma registry used for?

To collect data on traumatic injury cases to improve trauma care quality, support injury prevention programs, evaluate outcomes, and supply data for research and trauma system planning.

What is the difference between a primary and a secondary data source in healthcare?

A primary data source is the original record of patient care, such as the health record itself; a secondary data source is derived from primary records, such as a registry, index, or database created for a specific purpose.

What are a disease index and an operation index?

A disease index is a listing of patients arranged by their diagnosis codes; an operation index is a listing of patients arranged by their procedure codes. Both are secondary data sources used to locate cases by condition or procedure.

What is the Master Patient Index (MPI) and what is its primary function?

A permanent database listing every patient ever treated by a facility, linking each patient to their unique medical record number; it ensures accurate patient identification and serves as the key to locating records.

What is the difference between a facility-based registry and a population-based registry?

A facility-based registry collects data only on patients treated within a specific institution; a population-based registry collects data on all cases of a disease within a defined geographic population.

Name two large national/federal secondary databases used for healthcare research and analytics.

Examples include the National Practitioner Data Bank (NPDB), the Healthcare Cost and Utilization Project (HCUP), Medicare Provider Analysis and Review (MEDPAR) file, and the NCDB (National Cancer Database).

What is the difference between an internal and an external data source for benchmarking?

Internal data come from within the organization (its own records and registries); external data come from outside sources such as state databases, national registries, or peer-organization comparisons.

What does a rate express, and how does it differ from a ratio and a proportion?

A rate measures the frequency of an event relative to a population at risk over time (often per 1,000 or 100,000). A ratio compares two quantities (a:b) that may be unrelated. A proportion is a type of ratio where the numerator is included in the denominator (a part of the whole).

What is data integrity, and why is it critical to healthcare analytics?

Data integrity is the accuracy, completeness, consistency, and reliability of data throughout its lifecycle; it is critical because analytic outputs and decisions are only as trustworthy as the underlying data quality.

What does it mean for data to be 'normalized' or for a process to use data standardization?

It means transforming data into a consistent format, terminology, or scale so that data from different sources can be accurately compared, aggregated, and analyzed.