ChrisM

A confidence interval is a range of values that will contain a parameter assumed to be non-random. A prediction interval is associated with a random variable with a specific probability of that variable lying within the interval. Prediction intervals are confidence intervals for predictions derived from regression models. Prediction intervals are always wider than the confidence intervals of equal percentage. For example, if you have data for how many cigarettes a person smokes per day as the independent variable and the number of years they lived as the dependent variable, the life expectancy of people who smoke 10 cigarettes per day will fall within the tighter tolerances of the confidence interval. The life expectancy of a single person who smokes 10 cigarettes per day will fall within the wider prediction interval.

Regression using Historical Data will show correlation in data - it does not necessarily control for each variable independently. Regression via DOE will show causation in data - parameters are analyzed to show their impact on the final result independently and interactively with other variables.

You can perform a Power Analysis to determine if your have a suitable sample size. Knowing the number of predictors, alpha, power, and effect size, the sample size can be determined.

Z scores allow for comparison between the performance of different processes from different normal curves. The Z score normalizes data to output a single value that can be used to compare processes that are distinct from one another.

FMEA can be applied in at least 2 steps of the DMAIC process: A - Analyze: To assess the current risk I - Improve: To assess the risk that will be present after the improvements are implemented

A cause is considered a root cause when any further analysis of that cause requires assessing problems that are outside of the control of the process. If further analysis calls for assessment of the suppliers antecedent to the main process, then the deliverable of those suppliers is the root cause. Once asking "why" to a cause carries the process engineer beyond the scope of their control, that cause is a root cause.

An instance in which X significantly impacts Y but does not warrant changing X includes instances in which a manufacturer would have to compromise the integrity of their product for the sake of improving Y. For example, using copper wiring is significantly more costly to building a house than using aluminum wiring. However, the builder should not switch to aluminum because aluminum degrades significantly faster than copper and will demand more maintenance. Additionally, the interface of that aluminum with any non-aluminum wiring will create a voltage potential and possibly a fire hazard.

Attribute Agreement Analysis can be used for determining the most common items to fail assessments. This can indicate that there are other factors involved in assessing the subjects than simply the appraiser.

An airline has the normally distributed data of the price of jet fuel/barrel for each year of the past 20 years. The airline can use this data to anticipate how much jet fuel will cost for a specific time of year and adjust their ticket prices accordingly. They can also use this data to change their purchasing strategy on jet fuel futures as to beat the market.