Introduction to Root Cause Analysis
Expert-defined terms from the Professional Certificate in Root Cause Analysis for Safety Professionals course at Greenwich School of Business and Finance. Free to read, free to share, paired with a professional course.
**3 #
sigma limit:** A control limit that is three standard deviations away from the centerline in a control chart. It represents the upper and lower boundaries for expected variation in a process.
**Acceptance sampling #
** A statistical quality control method where a sample is taken from a batch of products to determine if the batch meets the required quality standards.
**Acid test ratio #
** A financial ratio used to assess a company's short-term liquidity by dividing its quick assets by its current liabilities.
**Activity #
based costing (ABC):** A costing method that allocates overhead costs to products or services based on the activities required to produce them.
**Affinity diagram #
** A tool used in root cause analysis to organize and cluster ideas or data into related groups.
**Agile #
** A project management approach that values flexibility, collaboration, and continuous improvement.
**Alpha error #
** The probability of rejecting a true hypothesis in statistical testing.
** Alternative hypothesis #
** The hypothesis that is tested against the null hypothesis in statistical testing. It represents the researcher's belief about the population parameter.
**Anova (Analysis of Variance) #
** A statistical technique used to compare the means of two or more groups.
**Aroot cause analysis (ARCA) #
** A systematic approach to identifying the underlying causes of problems or incidents.
**Balanced scorecard #
** A strategic management tool that measures a company's performance in four perspectives: financial, customer, internal processes, and learning and growth.
**Bar chart #
** A graphical representation of data using bars of equal width to depict the frequency or magnitude of different categories.
**Basic cause #
** A fundamental issue that underlies a problem or incident.
**Bayes' theorem #
** A mathematical formula used to calculate conditional probabilities.
**Benchmarking #
** A process of comparing a company's performance to that of other organizations or industry best practices.
**Beta error #
** The probability of failing to reject a false hypothesis in statistical testing.
**Brainstorming #
** A creative problem-solving technique that involves generating a large number of ideas in a short amount of time.
**Business process management (BPM) #
** A discipline that combines methods, techniques, and tools to discover, model, analyze, measure, improve, optimize, and automate business processes.
**Capability maturity model (CMM) #
** A framework for evaluating the maturity of an organization's software development processes.
**Cause #
and-effect diagram:** A visual tool used in root cause analysis to identify the relationships between causes and effects.
**Central limit theorem #
** A statistical principle that states that the distribution of sample means approaches a normal distribution as the sample size increases.
**Change management #
** A structured approach to managing changes to a system, process, or organization.
**Check sheet #
** A simple data collection tool used to record the frequency of events.
**Chi #
square distribution:** A continuous probability distribution used in statistical testing.
**Chi #
square test:** A statistical test used to determine if there is a significant association between two categorical variables.
**Closed #
loop corrective action (CLCA):** A systematic approach to corrective action that includes verification and validation of the solution.
**Cohen's d #
** A statistical measure used to quantify the effect size in a hypothesis test.
**Common cause #
** A factor that contributes to variation in a process that is inherent and expected.
**Confidence level #
** The probability that the true population parameter falls within a certain range of values.
**Confidence interval #
** A range of values that is likely to contain the true population parameter with a certain level of confidence.
**Confirmation bias #
** The tendency to seek out information that confirms pre-existing beliefs and ignore information that contradicts them.
**Control chart #
** A graphical tool used to monitor and control a process over time.
**Control limit #
** A boundary line on a control chart that indicates whether a process is in control or out of control.
**Correlation #
** A statistical relationship between two variables that measures the degree to which they move together.
**Correlation coefficient #
** A numerical value that measures the strength and direction of a correlation.
**Cost of quality (COQ) #
** The total cost of poor quality, including prevention, appraisal, and failure costs.
**Critical to quality (CTQ) #
** A characteristic of a product or service that is essential to its quality.
**Data mining #
** The process of discovering patterns and insights in large datasets.
**Defect #
** A non-conformance in a product or service that does not meet the required specifications.
**Defect density #
** The number of defects per unit of measure, such as defects per thousand lines of code.
**Defect per opportunity (DPO) #
** The number of defects per unit of measure, adjusted for the number of opportunities for defects.
**Defect rate #
** The percentage of units produced that contain one or more defects.
**Deming cycle (PDCA) #
** A continuous improvement model consisting of four stages: Plan, Do, Check, Act.
**Descriptive statistics #
** Statistical methods used to describe and summarize data.
**Design of experiments (DOE) #
** A statistical method used to optimize processes or products by systematically varying input factors.
**Detective control #
** A control that identifies and corrects defects after they have occurred.
**Discriminant analysis #
** A statistical technique used to classify observations into one of two or more categories.
**Distribution #
** A pattern of variation in a population or sample.
**Drill #
down analysis:** A process of examining data at increasingly detailed levels.
**Efficiency #
** The ratio of output to input.
**Empirical rule #
** A rule of thumb that states that in a normal distribution, 68% of the data falls within one standard deviation of the mean, 95% falls within two standard deviations, and 99.7% falls within three standard deviations.
**Event tree analysis (ETA) #
** A technique used to analyze the possible outcomes of a sequence of events.
**Experimental design #
** A plan for conducting an experiment that specifies the input factors, levels, and response variables.
**Exploratory data analysis (EDA) #
** A statistical approach to data analysis that involves visualizing and summarizing data to identify patterns and relationships.
**Failure mode and effects analysis (FMEA) #
** A systematic method for identifying and prioritizing potential failures in a system or process.
**Failure rate #
** The number of failures per unit of time or per unit of measure.
**Fault tree analysis (FTA) #
** A technique used to analyze the possible causes of a single event.
**Fishbone diagram #
** A visual tool used in root cause analysis to identify the possible causes of a problem.
**Five Whys #
** A root cause analysis technique that involves asking "Why?" five times to get to the root cause.
**Force field analysis #
** A tool used to identify the forces for and against a proposed change.
**Frequency distribution #
** A table that shows the frequency of each value in a dataset.
**Functional control #
** A control that prevents defects from occurring in the first place.
**Gaussian distribution #
** Another name for the normal distribution.
**Gantt chart #
** A graphical representation of a project schedule.
**Gemba #
** A Japanese term meaning "the actual place." In root cause analysis, it refers to going to the place where the problem occurred to gather data.
**Hazard analysis and critical control points (HACCP) #
** A systematic approach to identifying and controlling hazards in a food production process.
**Histogram #
** A graphical representation of data using bars of equal width to depict the frequency of different values.
**Hypothesis testing #
** A statistical technique used to test a hypothesis about a population parameter.
**Incident investigation #
** A process of determining the causes of an incident or accident.
**Inferential statistics #
** Statistical methods used to make inferences about a population based on a sample.
**Input #
process-output (IPO) model:** A model used to analyze processes by identifying the inputs, processes, and outputs.
**Interquartile range (IQR) #
** A measure of the spread of a dataset that excludes the top and bottom 25% of values.
**Interval scale #
** A level of measurement that has equal intervals between values but no true zero point.
**Just #
in-time (JIT):** A production system that aims to minimize inventory by producing products only when they are needed.
**Kaizen #
** A Japanese term meaning "continuous improvement."
**Kano model #
** A model used to classify customer requirements into three categories: must-haves, performance factors, and delighters.
**Kurtosis #
** A measure of the peakedness of a distribution.
**Lead time #
** The time