Practice Flashcards

In a project report, a Black Belt practitioner notes, "we are 95% confident that the average age of consumers of Product A is between 34 and 38 years." What exactly is a confidence interval?

Answer: They are 95% confident about the average age of the population.

A confidence interval provides a range of values within which the true population parameter, such as the population mean, is estimated to lie with a certain level of confidence. In this example, being 95% confident means that if the sampling and interval calculation process were repeated many times, 95% of those intervals would contain the true average age of *all* consumers (the population), not just the sample.

The Central Limit Theorem states that, regardless of the population from which data is obtained, the sampling distribution of the mean is:

Answer: Normally distributed.

The Central Limit Theorem (CLT) is a cornerstone of statistics, stating that for a sufficiently large sample size, the sampling distribution of the sample mean will be approximately normally distributed. This holds true regardless of the shape of the original population distribution. This theorem is fundamental for inferential statistics, enabling hypothesis testing and the construction of confidence intervals.

Process capability (Cp) refers to a process that, in most cases, results in the production of a product that meets client and design standards. A perfect process will have the following Cp value:

Answer: Greater than one

Process capability (Cp) measures how well a process can meet specified limits. A Cp value of 1 indicates that the process spread exactly matches the specification spread, meaning the process is barely capable. For a process to be considered 'perfect' or highly capable of consistently meeting customer and design standards with minimal defects, its Cp value must be significantly greater than one, typically 1.33 or higher, to provide a buffer against variation.

Which of the control charts must include at least 20 subgroups of observed data to determine if a process is under control or not?

Answer: R-chart

R-charts (Range charts) are used in statistical process control to monitor the variability or dispersion of a process within subgroups. To establish reliable control limits and accurately determine if a process is in statistical control, it is generally recommended to collect at least 20 to 25 subgroups of observed data. This ensures sufficient data to capture the natural variation and provide a stable baseline for monitoring.

A basic linear regression line compares the rate of change of one variable to another. The resultant equation is shown below. What does (b0) stand for?

Answer: Intercept

In a basic linear regression equation, typically expressed as Y = b0 + b1X, the term (b0) represents the y-intercept. The intercept is the predicted value of the dependent variable (Y) when the independent variable (X) is equal to zero. It indicates where the regression line crosses the y-axis.

A Black Belt practitioner is engaged to discover a number of Critical to Price (CTP) variables in order to simplify and minimize costs connected with producing Product A. The following are CTP factors EXCEPT:

Answer: Loan refinancing costs

Critical to Price (CTP) factors are elements that directly contribute to the cost of producing a product or service and significantly influence its final price. Component costs, assembly costs, and shipping costs are direct expenses tied to manufacturing and delivery. Loan refinancing costs, however, are financial overheads related to the company's capital structure and not a direct cost of producing a specific unit of Product A, making it an exception.

According to the manager of a national grocery store chain, just 6% of consumers who have questionnaires addressed to them complete them entirely. What is the term for this sort of sampling error?

Answer: Non-response error

Non-response error occurs in surveys when a significant portion of the selected sample either refuses to participate or fails to complete the questionnaire. This can introduce bias into the results because the characteristics of those who respond may differ systematically from those who do not. A low completion rate, like 6%, indicates a high non-response error, potentially leading to an unrepresentative sample.

Which of the following components does not appear in implementation plans?

Answer: Cost/Benefit ratios

Implementation plans detail the 'how-to' of executing a project, outlining tasks, timelines, responsibilities, and resource allocation. While a cost/benefit analysis is crucial for the initial project justification and approval, the actual cost/benefit *ratios* themselves are part of the business case or project proposal, not a component within the detailed steps of the implementation plan. The plan focuses on the execution strategy rather than the initial financial justification metric.

A Belt needed to track the percentage of defectives in a specific sample set for her injection molding project, so she used a __________ to show the data.

Answer: P Chart

A P Chart (proportion chart) is specifically designed to track the percentage or proportion of defective items in a sample. It is used for attribute data (e.g., defective/non-defective) and can accommodate varying sample sizes. Since the Belt needed to monitor the 'percentage of defectives' in a sample, the P Chart is the most appropriate control chart for this type of data.

When a Belt Poka-Yoke completely removes a flaw from the process, she should monitor the activity using an effective SPC system on the trait of interest in the defect as a kind of early warning.

Answer: Incorrect

Poka-Yoke is a mistake-proofing technique aimed at preventing defects from occurring or making them immediately obvious. If a Poka-Yoke successfully and completely removes a flaw, it means the defect can no longer happen in the process. Therefore, continuously monitoring the 'trait of interest in the defect' using an SPC system becomes unnecessary, as the defect itself has been eliminated, making the statement incorrect.

Which of these graphs best exemplifies the circumstances that would enable OCAP for the process?

Answer: Xbar Chart

An Out-of-Control Action Plan (OCAP) is initiated when a process exhibits special cause variation, indicating it is out of statistical control. Xbar charts, which monitor the average of subgroups, are primary tools in Statistical Process Control (SPC) for detecting such special causes. When an Xbar chart shows points outside control limits or non-random patterns, it signals the need for an OCAP to investigate and address the root cause of the instability.

What kind of chart's control limits width changes depending on the sample size?

Answer: P Charts

P Charts (proportion charts) are used for attribute data, specifically the proportion of defective items. The calculation of their control limits depends on the sample proportion and the sample size. When the sample size varies from one sampling period to another, the width of the control limits on a P Chart will also change accordingly, making this a distinguishing characteristic.

The method utilized to ascertain whether Special Causes are present within the subgroups of the _____________ is range charts.

Answer: SPC Charts

Range charts (R charts) are a fundamental component of Statistical Process Control (SPC) charts, typically used in conjunction with Xbar charts. They are specifically designed to monitor the variation or spread within subgroups of data. By tracking the range, R charts help determine if special causes are affecting the consistency of the process, thus indicating whether the process variation is in control.

Statistical Process Control focuses on _____________ Cause Variation and Common Cause Variation.

Answer: Special

Statistical Process Control (SPC) is fundamentally concerned with differentiating between two types of variation: Common Cause Variation (inherent, random variation) and Special Cause Variation (assignable causes that indicate process instability). The primary goal of SPC is to detect and eliminate Special Cause Variation to bring a process into a state of statistical control, where only common cause variation remains.

Which Experimental Design is often most closely related to the design's fewest input variables or factors?

Answer: Response Surface Design

Response Surface Design (RSD) is typically employed in the later stages of experimentation, after initial screening experiments have identified the most significant factors. RSD focuses on optimizing a process by modeling the relationship between a few key input variables and the response, often involving fewer factors than initial screening designs but more complex models to find optimal settings.

Which assertion is false if a 2-level experimental design contains 16 experimental runs, 5 factors, and no replicates?

Answer: The Main Effects for the 5 factors are not aliased or confounded but the 2-way interactions are confounded with the 3-way interactions

A 2-level experimental design with 16 runs and 5 factors is a 2^(5-1) fractional factorial design, which is a Resolution V design. In a Resolution V design, main effects are aliased with 4-factor interactions, not completely unaliased. Therefore, the assertion that 'The Main Effects for the 5 factors are not aliased or confounded' is false, as they are indeed confounded with 4-way interactions, making the entire statement B false.