Loading data in minitab: open existing worksheet and importing data
- open existing worksheet: file must be .MTW or .MPJ
- importing data: for non-minitab data, must be .xls, .txt, etc.
graphical summary gives you:
- histogram with dist. curve
- Box plot
- CI’s (for mean, median, stdv)
- Anderson-Darling normality test (A^2, P-value)
- mean, stdv, var, N, skewness, kurtosis
what is skewness?
measure of lack of symmetry (0 if completely symmetric)
what is kurtosis?
height/sharpness of peak (higher value means higher, sharper peak)
normality test
probability plot - normal if straight, diagonal line
run chart
- represents data over time - use to look for evidence of special-cause variation
- want points to vary randomly around center line (median)
ANOVA (minitab)
- used to compare equality of means for different variables
- look at p-value –> means are different if < alpha
- look at CI’s - if doesn’t contain 0, means different
- look at R2 - if small, model generates imprecise predictions for new observation
Time Series Plot
- graph used to evaluate patterns and behavior in data over time - displays observations on the Y-axis against equally spaced time intervals on X-axis
Dot Plot
- graph used to assess the distribution of continuous data
- useful for relatively small amounts of data
Individual value plot
graph you can use to examine individual values in each sample to assess sample distributions
brush tool
used to identify/look at one or more individual points
what is a balanced scorecard
- system for creating “strategic planning and management”
- provides both performance metrics while also helping identify what should be done
4 perspectives of balances scorecard
financial, customer, business process, learning and growth
financial perspective
- choice of a few high level financial metrics to reflect financial performance of the business
- how business looks from stockholders point of view
- how effective is business at using its resources
4 pieces for each perspective for balanced scorecard
objectives, measures, initiative, target
attribute gauge r&r uses what statistical tool to estimate what?
- uses ANOVA to estimate whether a metrics repeatability or reproducibility is the main contributor to variation
con of attribute gauge r&r
difficult to account for variance occurring from learning
for something to be consistently and reliably accurate, it must…
also be precise
3 parts of strategy statement
- objective
- scope
- competitive advantage
7 wastes (plus extra one)
- transportation (conveyance), inventory, motion, waiting, overproduction, overprocessing, defects
- underuse of talent
what can you do to the mean of a continuous metric…
you can shift the mean - a continuous metric will make it easier to see what is actually going on in the process
Z.ST vs. Z.LT
- Z.ST = capability = short term
- Z.LT = performance = long term
Variance (Observed) = ?
= Var (true process - 90%) + Var (measurement system - 10%)
Gauge R&R: Nested vs. Crossed
- if you need to use destructive testing, you must be able to assume that all parts within a single batch are identical
- if youre unable to make this assumption then part-to-part variation within a batch will mask the measurement system variation
- if you can make this assumption: then choosing between nested and crossed for destructive testing depends on how your measurement process is set up: if all operators measure parts from each batch = crossed. if each batch is only measured by a single operator = nested
- nondestructive testing = crossed
