Six-Sigma11 - Step-by-step procedure of the MultiVari Chart...

Info iconThis preview shows pages 1–13. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Step-by-step procedure of the MultiVari Chart Analysis: 1. Identify the single unit in which a set of multivariate data is collected, and select a good data collection plan so that each data set contains sufficient information for our study. 2. Select an appropriate graphical data visualization scheme. The selected data visualization scheme should provide problem analysts sufficient information to assess the magnitude of variation and the mutual relationship among multivariate variables, and the signature of the visualization should provides powerful clues for root cause analysis. 3. Select the inclusive categories of variations, for which all types of variations can be partitioned into these categories. The category partition of intra-piece, inter-piece and time to time is one such an example. 4. Collect multivariate data samples, and display the data visualization graphs under each category. 5. Determine the major category(ies) that accommodate most of variation, and using subject of matter knowledge to unlock the root cause of variation in that category. Example 2.9 Injection molding The plastic cylindrical connectors are made by injection modeling, the shape of connector is the following: d 1 d 2 d 3 And the diameters at the left, middle and right, that is, d 1 ,d 2 and d 3 are of major concern. The following graphical template is selected: Nominal USL LSL Perfect part Thick in the middle Thin in the middle Example 2.10 Elementary schools performance study As we discussed in Example 2.1, the achievement tests scores for elementary school students, they are scores in math, science, reading and writing tests and they are multivariate variables. The circular profiles that we developed in example 3.1 can be used as the template to display achievement tests scores. Strong well rounded students Students with some strengths and some weaknesses Weak students 1. Intra-student variation: variation among the 4 test scores, this variation relates the discrepancies of a student on different areas. 2. Student-to-student variation, but within a class. 3. Class-to-class variation, but within a school 5. School to school variation, but within a school district 6. School district to school district variation School 1 School 2 Class 1 Class 2 Class 1 Class 2 School dist 1 School dist 2 Verify Hypothesis Fundamental concepts Point and interval estimation Test for means, variances and proportions Paired comparison tests Goodness of fit tests Analysis of variance Contingency tables Nonparameteric test Null Hypothesis This is the hypothesis to be tested. The null hypothesis directly stems from the problem statement and is denoted as H o ....
View Full Document

Page1 / 59

Six-Sigma11 - Step-by-step procedure of the MultiVari Chart...

This preview shows document pages 1 - 13. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online