CAPA Trending & Data Analysis 3 — Questions and Answers
Question 1: A quality team discovers that CAPA cycle time data is right-skewed. Which measure of central tendency best represents the 'typical' cycle time for trending purposes?
- Mean
- Median (Correct answer)
- Mode
- Range
Correct answer: Median
The median is resistant to the influence of extreme high values in right-skewed distributions, making it a better representation of typical cycle time.
Question 2: In CAPA trending, a fishbone (Ishikawa) diagram is most useful for which analytical step?
- Displaying frequency of defect categories over time
- Organizing potential root cause categories before data collection (Correct answer)
- Calculating the correlation coefficient between variables
- Plotting process output against specification limits
Correct answer: Organizing potential root cause categories before data collection
A fishbone diagram helps teams systematically categorize and brainstorm potential root causes prior to data-driven analysis.
Question 3: Which type of control chart is most appropriate for monitoring the proportion of nonconforming units when the subgroup size varies?
- X-bar and R chart
- np-chart
- p-chart (Correct answer)
- c-chart
Correct answer: p-chart
The p-chart tracks the proportion of nonconforming units and accommodates varying subgroup sizes, unlike the np-chart which requires constant subgroup size.
Question 4: A CAPA analyst calculates an R-squared value of 0.92 for a regression model predicting defect rate from process speed. How should this be interpreted?
- Process speed causes 92% of all defects
- 92% of the variance in defect rate is explained by process speed (Correct answer)
- The model will predict defect rates with 92% accuracy always
- 8% of data points are outliers in the regression
Correct answer: 92% of the variance in defect rate is explained by process speed
R-squared indicates the proportion of variance in the dependent variable explained by the independent variable(s) in the regression model.
Question 5: When performing stratified trend analysis on CAPA data, what is the primary benefit of stratification?
- It eliminates the need for a control chart
- It reduces the total number of CAPAs required
- It uncovers hidden patterns masked when data is combined (Correct answer)
- It increases the statistical confidence interval
Correct answer: It uncovers hidden patterns masked when data is combined
Stratification separates data into meaningful subgroups, revealing patterns or root causes that are invisible when all data is analyzed together.
Question 6: A CAPA team finds that 80% of customer complaints originate from 3 product lines out of 15 total. This finding is best visualized and acted upon using which tool?
- Control chart
- Pareto chart (Correct answer)
- Histogram
- Scatter diagram
Correct answer: Pareto chart
A Pareto chart ranks categories by frequency and highlights the vital few contributors, directly supporting prioritization of corrective actions.
Question 7: Which statistical test is most appropriate for determining if CAPA closure times follow a normal distribution before applying parametric trend analysis?
- Chi-square goodness-of-fit test or Shapiro-Wilk test (Correct answer)
- F-test for equality of variances
- Mann-Whitney U test
- Pearson correlation coefficient
Correct answer: Chi-square goodness-of-fit test or Shapiro-Wilk test
The Shapiro-Wilk or chi-square goodness-of-fit test assesses whether data follows a normal distribution, a prerequisite for many parametric methods.
CAPA Trending & Data Analysis 3
A quality team discovers that CAPA cycle time data is right-skewed.
Which measure of central tendency best represents the 'typical' cycle time for trending purposes?