Chapter 6 Notes
©2008 by
Normal Distribution
! = Important Note
! These Notes are not meant to replace
6-2
1) Bell-Shaped & Symmetric (Frequency Polygon with zero skewness)
2) Total Area Under the curve is 100% or 1 (so each half is 50% or .5)
3) Continuous
4) Asymptotic to the horizontal axis (runs infinitesimally close to but never touches)
Standard
Steps to find Area Under Curve (as a decimal) or Probability of selecting 1 item @ random from the population,
1) Sketch
2) Use 1 of the 2 Table A-2's and look up the given z score.
! Tables can be found in Chapter Contents (in left margin) - Formulas and Tables Fold-Out Card
! Body of table gives Area Under Curve to 4 decimal places.
! Normal curve is Symmetric so you can use the "NEGATIVE z Scores" table for positive z scores
and the "POSITIVE z Scores" table for negative z scores
! You can also use the extra Table (A-2.3) I've posted on the Web.
! Table must correspond to your sketch.
! Triola teaches subtracting from 1 to get sketched region.
! You may also have to add or subtract 2 found Areas to get the sketched region.
To find z score when given the percentile or probability:
! This is the reverse of the above procedure.
1) Find the CLOSEST prob value in the body of 1 of the Table A-2's (to 4 decimal places)
2) the corresponding z score tenth spot is in the first column, hundredth spot in top row
! If the z score is to the left of the mean 0, then it will be negative.
6-3
To find Area Under Curve (as a decimal) or Probability of selecting 1 item @ random from the population
when μ ≠ 0 or σ ≠ 1, or both, convert Original Score (X) to a z score using z = (X-μ)/σ
then follow steps above to find the area.
To find Original Score (X) when given the percentile or probability, follow same steps above
then use X = μ ± z*σ to convert the z score into the original x score.
6-5
To find Area Under Curve (as a decimal) or Probability of selecting N items @ random from the population
when μ ≠ 0 or σ ≠ 1, or both, convert Original Mean Score (xbar) to a z score using z = (xbar-μ) / (σ/√n)
then follow steps above (6-2) to find the area.
(σ/√n)
= σxbar is called the Standard Error.
Central Limit Theorem (CLT) = for sample sizes greater than 30, the sampling distribution can be approximated by a Normal Distribution even if the original population is not normally distributed.
TECHNOLOGY
using StatCrunch:
! Don't need to enter any info in StatCrunch spreadsheet for this procedure
to find Prob, z, or original X score:
Stat - Calculators -
EXCEL commands:
! enter the given value inside the parentheses
! Excel Probability commands will only give area to the Left of z or x
Find Excel Command
Standard Probability =NormSdist(z score)
z score =NormSinv(prob)
any Probability =NormDist(x, μ, σ, true)
original X score =NormInv(prob, μ, σ)