census
when the entire population is selected for the study
parameter
a measure calculated from the population
discrete data
data that contains only integers or counting numbers
continuous data
any value over a particular range is possible
levels of measurement (4)
- nominal scale 2. ordinal scale 3. interval scale 4. ration scale
common causes
part of the system ex. poor design, measurement error, poor maintenance
special causes
unusual, not previously observed
stable system
a system governed only by common causes
problems created by variation (5)
- increases unpredictability 2. reduces capacity utilization 3. contributes to a “bullwhip” effect 4. difficult to find root causes 5. difficult to detect potential problems early
statistical spread
variability in a sample or population
bell shaped, mean and standard deviation control?
mean: controls the center standard deviation: controls the spread
68-95-99.7 rule
68% of observations fall within 1 sd of the mean 95% fall within 2 99.7% fall within 3
standard distribution mean and sd
mean of 0 sd of 1
point estimate
single value serves as “best guess” of an unknown population parameter
confidence interval
the amount of uncertainty associated with a sample estimate of a population parameter
2 fundamental management mistakes
- treating special causes and common causes 2. treating common causes as special causes
enumerative study
meant to explain the condition that exists with the existing population
analytic study
focused on improvement of the process
standard deviation
z score
finding a percentile
point estimate q
point estimate p
confidence interval
