Understanding statistics and statistical myths : how to become a profound learner

Bibliographic Details
Main Author: Castaneda-Mendez, Kicab (Author)
Format: Book
Language:English
Published: Boca Raton : CRC Press 2016
Subjects:
Table of Contents:
  • 1. Two types of data : attribute/discrete and measurement/continuous
  • 2. Proportions and percentages are discrete data
  • 3. : s = v (xi
  • x)2/(n -1) is the correct
  • 4. Sample standard deviation
  • 5. Variances can be added but not standard deviations
  • 6. Parts and operators for an MSA do not have to be randomly selected
  • 7. %study (% contribution, number of distinct categories) is the best criterion for evaluating a measurement system for process improvement
  • 8. Only sigma can compare different processes and metrics
  • 9. Capability is not percent/proportion of good units
  • 10. p = probability of making an error
  • 11. Need more data for discrete data than continuous data analysis
  • 12. Nonparametric tests are less powerful than parametric tests
  • 13. Sample size of 30 is acceptable (for statistical significance)
  • 14. Can only fail to reject Ho, can never accept Ho
  • 15. Control limits are +3 standard deviations from the center line
  • 16. Control chart limits are empirical limits
  • 17. Control chart limits are not probability limits
  • 18. +3 sigma limits are the most economical control chart limits
  • 19. Statistical inferences are inductive inferences
  • 20. There is one universe or population if data are homogeneous
  • 21. Control charts are analytic studies
  • 22. Control charts are not tests of hypotheses
  • 23. Process needs to be stable to calculate process capability
  • 24. Specifications don't belong on control charts
  • 25. Identify and eliminate assignable or assignable causes of variation
  • 26. Process needs to be stable before you can improve it
  • 27. Stability (homogeneity) is required to establish a baseline
  • 28. A process must be stable to be predictable
  • 29. Adjusting a process based on a single defect is tampering, causing increased process