Lec 03 - Tests for normal

Lec 03 - Tests for normal - X P X P ) 8231 . 5 ( ) 8231 . 5...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon
Is Data Normally Distributed? diam 11.5946 8.9121 9.6834 9.6545 8.0873 9.3021 5.8231 7.5982
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Histogram is Useless with only 8 observations! 2 diam Frequency 12 11 10 9 8 7 6 5 2.0 1.5 1.0 0.5 0.0 Mean 8.832 StDev 1.707 N 8 Histogram of diam Normal 
Background image of page 2
Normal Probability Plot diam Percent 16 14 12 10 8 6 4 2 99 95 90 80 70 60 50 40 30 20 10 5 1 Mean 8.832 StDev 1.707 N 8 AD 0.231 P-Value 0.708 Probability Plot of diam Normal - 95% CI X axis: data points (in units of the data) Y axis: cumulative % of data points < X a normal probability scale 3
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
How to Draw the Plot by Hand X axis is diameters Y axis is evenly spaced by standard deviations -2, -1, 0, 1, 2 Y axis is unevenly spaced by cumulative percent less than X .02, .16, .50, .84, .98 Step 1: Order points from low to high diam 11.5946 8.9121 9.6834 9.6545 8.0873 9.3021 5.8231 7.5982 4
Background image of page 4
Ordered from low to high (diam) 5.8231 7.5982 8.0873 8.9121 9.3021 9.6545 9.6834 11.5946 Calculate cumulative percent less than x: For each point i = (1), (2), . .. (n) P i n i ( ) ( . ) = - 100 0 5 n=10 example: lowest out of 8 points is 5.8231 5
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
6.25% or .5/8 - average correction point discrete
Background image of page 6
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Background image of page 8
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: X P X P ) 8231 . 5 ( ) 8231 . 5 ( 8 1 = &lt; = x value: 5.8231 y value: cumulative percent 6.25 use formula: P i n i ( ) ( . ) =-100 0 5 =5% try it for second point 6 Test of Hypothesis H : Data is normal with mean and sd as calculated from the sample Look at normal probability plot Do statistical tests: Ryan Joiner test: p&gt;0.10 Anderson Darling test p=.708 Kolmogorov-Smirnov p&gt;0.15 Conclusion: accept H Shapiro Wilks/Ryan Joiner compares quantiles of observed data to normal distribution Kolmogorov-Smirnov computes max distance between cumulative distribution function of data and of fitted normal 7 In a Perfect Data Set Suppose We Have Normal Data r.v. X distributed N(0,1) cumulative probability fraction of data points -2 .02 fraction of data points -1 .16 fraction of data points .50 fraction of data points 1 .84 fraction of data points 2 .98 8...
View Full Document

Page1 / 8

Lec 03 - Tests for normal - X P X P ) 8231 . 5 ( ) 8231 . 5...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online