Back to Lean Six Sigma Green Belt (LSSGB)

Measure Phase

Process definition, statistical fundamentals, measurement system analysis, and capability studies.

The Measure phase focuses on quantifying the current state of processes. It includes process definition tools (SIPOC, process mapping, fishbone diagrams, FMEA), Six Sigma statistics (descriptive statistics, normal distributions, graphical analysis), measurement system analysis (Gage R&R, precision, accuracy, bias), and process capability analysis to establish baseline performance.
5 minutes 5 Questions

The Measure Phase is the second stage in the DMAIC (Define, Measure, Analyze, Improve, Control) methodology, which serves as the foundation for data-driven decision making in Lean Six Sigma projects. This phase focuses on establishing a clear baseline of current process performance and collecting r…

Concepts covered: Cause and Effect Diagrams (Fishbone/Ishikawa), Process Mapping, SIPOC Diagram, Value Stream Mapping (VSM), X-Y Diagram (Cause and Effect Matrix), Failure Modes and Effects Analysis (FMEA), Basic Statistics, Descriptive Statistics, Mean, Median, and Mode, Range and Standard Deviation, Normal Distributions, Normality Testing, Graphical Analysis, Histograms, Box Plots, Scatter Plots, Run Charts, Precision and Accuracy, Bias in Measurement, Linearity, Stability, Gage Repeatability, Gage Reproducibility, Gage R&R Studies, Variable Measurement System Analysis, Attribute Measurement System Analysis, Capability Analysis, Process Capability Indices (Cp, Cpk), Process Performance Indices (Pp, Ppk), Concept of Stability, Attribute Capability, Discrete Capability, Monitoring Techniques

Test mode:
Start practice test
LSSGB - Measure Phase Example Questions

Test your knowledge of Measure Phase

Question 1

A Six Sigma Green Belt is conducting capability analysis on a heat treatment process with LSL = 145°C, USL = 175°C, and target = 160°C. Historical data shows a process mean of 158°C with short-term standard deviation of 3.2°C and long-term standard deviation of 4.8°C. The team observes that Cpk = 1.35 while Ppk = 0.90. If the organization requires a minimum Ppk of 1.33 for process approval, and assuming the mean cannot be adjusted due to metallurgical constraints, what specific standard deviation reduction percentage would be required to achieve the minimum acceptable Ppk while maintaining the current process centering?

Correct Answer: The long-term standard deviation must be reduced by approximately 32% from 4.8°C to 3.25°C to achieve the required Ppk threshold

To solve this problem, we need to calculate the required standard deviation reduction to achieve Ppk = 1.33.

Given information:
- LSL = 145°C, USL = 175°C, Target = 160°C
- Process mean = 158°C
- Long-term standard deviation (σLT) = 4.8°C
- Current Ppk = 0.90
- Required Ppk = 1.33

Since the mean cannot be adjusted, we need to reduce the long-term standard deviation to improve Ppk.

Ppk is calculated as the minimum of:
- (USL - Mean) / (3 × σLT) = (175 - 158) / (3 × σLT) = 17 / (3 × σLT)
- (Mean - LSL) / (3 × σLT) = (158 - 145) / (3 × σLT) = 13 / (3 × σLT)

The limiting factor is the lower specification (13°C distance), which gives the smaller value and determines Ppk.

To find the required σLT for Ppk = 1.33:
1.33 = 13 / (3 × σLT_new)
3 × σLT_new × 1.33 = 13
σLT_new = 13 / (3 × 1.33) = 13 / 3.99 = 3.26°C

Percentage reduction required:
(4.8 - 3.26) / 4.8 × 100 = 1.54 / 4.8 × 100 ≈ 32%

The correct answer states that the long-term standard deviation must be reduced by approximately 32% from 4.8°C to approximately 3.25°C, which matches our calculation.

The other answers are incorrect because:
- Reducing short-term standard deviation affects Cpk, not Ppk, and Ppk is specifically what needs to meet the 1.33 requirement
- A 48% reduction would be excessive and is based on incorrect reasoning about target offset
- The suggestion about combined standard deviations and rational sampling strategies is not mathematically sound for addressing the Ppk deficiency

Question 2

A quality team collected the following cycle times in minutes for a process: 12, 15, 15, 18, 20, 15, 22. Which value represents the mode of this dataset?

Correct Answer: 15 minutes, as it appears most frequently in the data

The mode is the value that appears most frequently in a dataset.

Let's count the frequency of each value in the dataset: 12, 15, 15, 18, 20, 15, 22

  • 12 appears 1 time
  • 15 appears 3 times
  • 18 appears 1 time
  • 20 appears 1 time
  • 22 appears 1 time

Since 15 appears three times, which is more than any other value, 15 minutes is the mode of this dataset.

The other answers are incorrect because:

  • The answer stating 17 minutes calculated by averaging all values describes the mean, not the mode. The mean would actually be (12+15+15+18+20+15+22)/7 = 117/7 ≈ 16.7 minutes.

  • The answer stating 15 minutes because it falls in the middle when arranged in order describes the median, not the mode. While 15 happens to be both the median and mode in this case, the reasoning provided is incorrect for identifying the mode.

  • The answer stating 16.7 minutes as the central tendency describes the arithmetic mean (average), not the mode.

Question 3

A Lean Six Sigma Green Belt is reviewing an X-bar control chart for a packaging process. The chart shows 20 subgroups with all points within the upper and lower control limits. The Green Belt notices that 7 consecutive points are positioned above the centerline, followed by 6 points randomly distributed around the centerline. Based on standard run rules for process stability, what should the Green Belt conclude?

Correct Answer: The process shows evidence of a potential shift during the first 7 points but returned to stable behavior

The correct answer states that the process shows evidence of a potential shift during the first 7 points but returned to stable behavior.

This is correct because standard run rules for control charts include the rule that 7 or more consecutive points on one side of the centerline indicate a process shift or special cause variation. In this scenario, the first 7 points being above the centerline triggers this run rule, suggesting a potential shift occurred during that period. However, the subsequent 6 points being randomly distributed around the centerline indicates the process returned to normal, stable behavior.

The second option is incorrect because simply having all points within control limits does not guarantee process stability. Run rules exist specifically to detect patterns that indicate special causes even when points remain within limits. Seven consecutive points on one side of the centerline is a classic run rule violation that signals potential instability.

The third option is incorrect because the pattern of 7 consecutive points above the centerline actually indicates special cause variation, not common cause variation. There is no basis for recalculating control limits based on this observation.

The fourth option is incorrect because while the run of 7 points does indicate special cause variation for that portion of the data, the investigation should focus on that specific time period when the shift occurred. The subsequent 6 points showing random distribution around the centerline suggest the process has stabilized, so investigating all 20 subgroups equally would not be the most efficient approach. The focus should be on understanding what caused the shift during the first 7 subgroups.

More Measure Phase questions
664 questions (total)
Start 100 question test