Lean Six Sigma Green Belt Free Sample Questions

The median is the most appropriate measure of central tendency for skewed data. The mean is sensitive to outliers and extreme values, so the few complex applications would pull the mean higher, making it unrepresentative of a 'typical' value. The median, being the middle value, is not affected by these extreme values and thus provides a more accurate representation of the central point in a skewed distribution.

An Affinity Diagram is the most suitable tool for this situation. Its purpose is to organize a large number of ideas, opinions, or issues into natural groupings based on their inherent relationships. This allows the team to structure the 50+ causes into logical categories, making them easier to understand, discuss, and prioritize for further analysis with tools like a Fishbone diagram or Pareto chart.

A Control Chart is the primary tool used in the Control phase for monitoring a process over time. It helps distinguish between common cause variation (inherent in the process) and special cause variation (due to specific, identifiable causes). By plotting cycle time data on a control chart, the team can visually track performance, verify the stability of the improved process, and quickly react to any signals that indicate the process has gone out of control.

This statement accurately defines an interaction effect in DOE. It's a crucial concept because it means factors cannot be optimized independently. For example, the optimal temperature for a chemical reaction might be different depending on which catalyst is used. Ignoring interactions can lead to incorrect conclusions and suboptimal process settings.

An effective problem statement should be SMART (Specific, Measurable, Achievable, Relevant, Time-bound). This statement is vague. It doesn't quantify the problem (e.g., 'delivery times average 10 days against a target of 3'), specify the scope (e.g., 'for North American customers'), or indicate the time frame over which the problem has been observed. Without these measurable and specific details, the team cannot establish a baseline or measure success.

A Cpk value less than 1.0 indicates that the process is not capable of consistently meeting its specification limits. A common industry benchmark for a capable process is a Cpk of 1.33 or higher. The 'k' in Cpk specifically accounts for how centered the process average is relative to the specification limits. A low Cpk value implies either the process variation is too wide, the process average is not centered between the specification limits, or both. Therefore, a Cpk of 0.45 definitively means the process is not capable and likely off-center.

The 2-sample t-test is used to compare the means of two independent groups. Since the data is normally distributed, a parametric test like the t-test is appropriate. Because the variances are unequal, the specific version of the 2-sample t-test that does not assume equal variances (often called Welch's t-test) must be used. A Paired t-test is for dependent samples, ANOVA is for three or more groups, and the Mann-Whitney U test is a non-parametric alternative used when the data is not normally distributed.

A Fractional Factorial Design is an experiment where only a subset (a fraction) of the runs from a full factorial design are performed. In this case, a full factorial experiment with three factors at two levels each would require 2^3 = 8 runs. By conducting only 4 runs, the team is using a half-fraction design. This is done to save time and resources, at the cost of confounding some effects (usually higher-order interactions are confounded with main effects).