confidence interval

_{scroll ↓ to Resources}

Note

• confidence level
  • alpha risk = 1 - confidence level, the risk that population parameter (e.g. mean) is not within the CI
  • confidence LEVEL up ⇒ WIDER confidence interval ⇒ less practicall value
  • confidence level 68% ⇒ t-stats ~= 1 (from the T-table)
  • confidence level 95% ⇒ t-stats ~= 2
  • confidence level 99% ⇒ t-stats ~= 3
• CI(mu) = sample mean +- MOE = sample mean +- Tstats * SEmean
  • CI = 2*MOE
• Sample size n
  o   sample size n up ⇒ narrower confidence interval (by sqrt(n))
  o   at n = 25, reduction of 80% of CI is achieved
  o   if n<30, sample mean is a student-distribution and t-stats needs to be defined from the Z-table
• 
• 
• 

Resources

• karpov courses
• Design for Six Sigma

---

Links to this File

table file.inlinks, file.outlinks from [[]] and !outgoing([[]])  AND -"Changelog"