Analyze Phase Quizzes

 

Root Cause 6 Questions

Hypothesis testing is used to determine which process factors are the cause of the variation in our output that is causing defects. TRue

Statistical data analysis enables us to validate the root causes with 95% confidence in the results.True

In hypothesis testing we are trying to determine if we can reject the alternative hypothesis (groups are different).

False

“r-squared” is the square of the correlation coefficient and is the measure of how much variation in the process output is accounted for by the model.

True

An r = +0.86 would indicate which of the following (choose one). |

Strong positive relationship

When conducting a hypothesis test, we usually treat "P is less than 0.05" as indicative that the difference between groups is insignificant.

False

Regression analysis takes correlation one step further by developing a mathematical model that represents the relationship between the X and Y.

True

Multiple regression is the same concept as linear regression, but it is an equation to

show the mathematical relationship between (choose one).

Several X's and One Y

A correlation coefficient is used to measure the degree of linear association between discrete sets of data.

False

Multiple regression is the same concept as linear regression, but it is an equation to

show the mathematical relationship between (choose one).

A. Root Cause Analysis, B. Lean Process Analysis, D. Graphical Data Analysis, D.

Statistical Data Analysis

Have you completed and documented the SI Project Deliverables for the Analyze

Phase?

Yes

"How were you able to use Regression for your analysis?"

"We used Regression to statistically validate that there is a relationship or

correlation between the LP Cycle Time and Total Cycle Time in Singapore."

"The Home Loan processing department already is over staffed. How can they not |

handle the current volume?" |

"This problem is being driven by 2 causes. First, the staffing is not aligned to the

incoming volume which leads to periods of when the associates are under worked

and over worked. Second, all of the non-value added time leads to unnecessary

delays and duplicate efforts by the associates.”

"What did the Regression analysis tell you?"

"The analysis told us that 47.1% of the variation in the Singapore Overall Cycle 

Time is accounted for by the LP Cycle Time. This isn't the only cause of the 

variation, however we need to focus our analysis/improvements efforts in this

area since the relationship is very strong." 

"What did the additional graphical analysis tools tell you about the process that you 

didn't already know from Measure Phase tools?" 

"We were able to identify which Final Determination Package errors were leading

to most of the issues. In addition, by stratifying the cycle time performance

between the 3 sites we were able to determine that London is performing better

then Chicago and Singapore. Finally, there is a correlation between the LP cycle

time and overall cycle time for Singapore which will help us narrow our analysis

efforts for that site.”

"Are we going to fix all of the Final Determination Package errors?"

"We are going to focus on the Loan Amount and Name errors since those 2 ‘account for 90% of the errors.”

"Reviewing the application is an important step to ensure the loan is correctly

approved. How can it be non-value added? Are you just going to eliminate

reviews?"

"We focused our value-added analysis on the customer's perspective. Although

this may be a value-added step for the business, it causes delays in the process

which ultimately leads to dissatisfaction for the customer. If we can solve the

problems that lead to the need for these reviews, we can reduce time for the

customer and cost to the business which will meet both expectations.”