Download presentation
Presentation is loading. Please wait.
Published bySheryl Morris Modified over 6 years ago
1
The greatest blessing in life is in giving and not taking.
1-Way Anova 1-Way ANOVA 1 1
2
One-Way Analysis of Variance
Y= DEPENDENT VARIABLE (“yield”) (“response variable”) (“quality indicator”) X = INDEPENDENT VARIABLE (A possibly influential FACTOR) 2 2
3
= Many other factors (possibly, some we’re unaware of)
OBJECTIVE: To determine the impact of X on Y Mathematical Model: Y = f (x, ) , where = (impact of) all factors other than X Ex: Y = Battery Life (hours) X = Brand of Battery = Many other factors (possibly, some we’re unaware of)
4
Completely Randomized Design (CRD)
Goal: to study the effect of Factor X The same # of observations are taken randomly and independently from the individuals at each level of Factor X i.e. n1=n2=…nc (c levels) 1-Way ANOVA 4
5
Example: Y = LIFETIME (HOURS) BRAND
3 replications per level 5.8 1-Way ANOVA 5
6
Analysis of Variance 1-Way ANOVA 6
7
R observations for each level
Statistical Model C “levels” OF BRAND R observations for each level • • • • • • • • R 1 2 • C Y11 Y12 • • • • • • •Y1R Yij = + i + ij i = 1, , C j = 1, , R Y21 • YcI • Yij YcR • • • • • • • • 1-Way ANOVA 7
8
mi = AVERAGE associated with ith level of X (brand i)
Where = OVERALL AVERAGE i = index for FACTOR (Brand) LEVEL j= index for “replication” i = Differential effect associated with ith level of X (Brand i) = mi – m and ij = “noise” or “error” due to other factors associated with the (i,j)th data value. mi = AVERAGE associated with ith level of X (brand i) m = AVERAGE of mi ’s. 1-Way ANOVA 8
9
The experiment produces
Yij = + i + ij By definition, i = 0 C i=1 The experiment produces R x C Yij data values. The analysis produces estimates of ,c. (We can then get estimates of the ij by subtraction). 1-Way ANOVA 9
10
Let Y1, Y2, etc., be level means
Y • = Y i /C = “GRAND MEAN” (assuming same # data points in each column) (otherwise, Y • = mean of all the data) c i=1 1-Way ANOVA 10
11
These estimates are based on Gauss’ (1796) PRINCIPLE OF LEAST SQUARES
MODEL: Yij = + i + ij Y• estimates Yi - Y • estimatesi (= mi – m) (for all i) These estimates are based on Gauss’ (1796) PRINCIPLE OF LEAST SQUARES and on COMMON SENSE 1-Way ANOVA 11
12
If you insert the estimates into the MODEL,
MODEL: Yij = + j + ij If you insert the estimates into the MODEL, (1) Yij = Y • + (Yj - Y • ) + ij. < it follows that our estimate of ij is (2) ij = Yij – Yj, called residual < 1-Way ANOVA 12
13
{ { { Then, Yij = Y• + (Yi - Y• ) + ( Yij - Yi)
or, (Yij - Y• ) = (Yi - Y•) + (Yij - Yi ) { { { (3) TOTAL VARIABILITY in Y Variability in Y associated with X Variability in Y associated with all other factors + = 1-Way ANOVA 13
14
SUM OF SQUARES BETWEEN SAMPLES SUM OF SQUARES WITHIN SAMPLES
If you square both sides of (3), and double sum both sides (over i and j), you get, [after some unpleasant algebra, but lots of terms which “cancel”] {{ C R C C R (Yij - Y• )2 = R • (Yi - Y•)2 + (Yij - Yi)2 { i=1 j=1 i=1 i=1 j=1 TSS TOTAL SUM OF SQUARES ( SSB SUM OF SQUARES BETWEEN SAMPLES = + SSW (SSE) SUM OF SQUARES WITHIN SAMPLES ( ( ( ( ( 1-Way ANOVA 14
15
ANOVA TABLE SSB SSB C - 1 = MSB C - 1 SSW MSW SSW (R - 1) • C =
SOURCE OF VARIABILITY SSQ DF Mean square (M.S.) Between samples (due to brand) SSB SSB C - 1 = MSB C - 1 Within samples (due to error) SSW MSW SSW (R - 1) • C = (R-1)•C TOTAL TSS RC -1 1-Way ANOVA 15
16
Example: Y = LIFETIME (HOURS) BRAND
3 replications per level 5.8 SSB = 3 ( [ ]2 + [ ] 2 + • • • + [ ]2) = 3 (23.04) = 1-Way ANOVA 16
17
SSW =? ( )2 = ( )2 = ( )2 = 2.56 ( )2 = ( )2= .64 • • • • ( )2 = 0 ( )2 = ( )2= ( )2 = 2.56 Total of ( • • • ), SSW = 46.72 1-Way ANOVA 17
18
ANOVA TABLE Source of Variability df SSQ M.S. BRAND 69.12 7 9.87 ERROR
= 9.87 ERROR 46.72 16 = 2 (8) 2.92 TOTAL = (3 • 8) -1 1-Way ANOVA 18
19
{ ( ( { We can show: i “VCOL” E (MSB) = 2 + R C-1 E (MSW) = 2
MEASURE OF DIFFERENCES AMONG LEVEL MEANS ( R ( • (i - )2 { C-1 i E (MSW) = 2 (Assuming Yij follows N(j , 2) and they are independent) 1-Way ANOVA 19
20
> 1 , < 1 , E ( MSBC ) = 2 + VCOL E ( MSW ) = 2
This suggests that There’s some evidence of non-zero VCOL, or “level of X affects Y” if MSBC > 1 , MSW if MSBC No evidence that VCOL > 0, or that “level of X affects Y” < 1 , MSW 1-Way ANOVA 20
21
With HO: Level of X has no impact on Y
HI: Level of X does have impact on Y, We need MSBC > > 1 MSW to reject HO. 1-Way ANOVA 21
22
(All level means are equal) HO: 1 = 2 = • • • • c
More Formally, HO: 1 = 2 = • • • c = 0 HI: not all j = 0 OR (All level means are equal) HO: 1 = 2 = • • • • c HI: not all j are EQUAL 1-Way ANOVA 22
23
The distribution of MSB = “Fcalc” , is MSW
The F - distribution with (C-1, (R-1)C) degrees of freedom Assuming HO true. C = Table Value 1-Way ANOVA 23
24
In our problem: ANOVA TABLE Source of Variability SSQ df M.S. Fcalc
BRAND 69.12 7 9.87 3.38 ERROR 46.72 16 = 1-Way ANOVA 24
25
F table: table 8 = .05 C = (7,16 DF) 1-Way ANOVA 25
26
Hence, at = .05, Reject Ho . (i.e., Conclude that level of BRAND does have an impact on battery lifetime.) 1-Way ANOVA 26
27
MINITAB INPUT life brand 1.8 1 5.0 1 1.0 1 4.2 2 5.4 2 . . 9.0 8 7.4 8
1.8 1 5.0 1 1.0 1 4.2 2 5.4 2 . . 9.0 8 7.4 8 5.8 8 1-Way ANOVA 27
28
ONE FACTOR ANOVA (MINITAB)
MINITAB: STAT>>ANOVA>>ONE-WAY Analysis of Variance for life Source DF SS MS F P brand Error Total Estimate of the common variance s^2 1-Way ANOVA 28
29
1-Way ANOVA 29
30
Assumptions Yij = + i + ij 1.) the ij are indep. random variables
MODEL: Yij = + i + ij 1.) the ij are indep. random variables 2.) Each ij is Normally Distributed E(ij) = 0 for all i, j 3.) 2(ij) = constant for all i, j Run order plot Normality plot & test Residual plot & test 1-Way ANOVA 30
31
Normal probability plot & normality test of residuals
Diagnosis: Normality The points on the normality plot must more or less follow a line to claim “normal distributed”. There are statistic tests to verify it scientifically. The ANOVA method we learn here is not sensitive to the normality assumption. That is, a mild departure from the normal distribution will not change our conclusions much. Normal probability plot & normality test of residuals 1-Way ANOVA 31
32
Minitab: stat>>basic statistics>>normality test
1-Way ANOVA 32
33
Diagnosis: Constant Variances
The points on the residual plot must be more or less within a horizontal band to claim “constant variances”. There are statistic tests to verify it scientifically. The ANOVA method we learn here is not sensitive to the constant variances assumption. That is, slightly different variances within groups will not change our conclusions much. Tests and Residual plot: fitted values vs. residuals 1-Way ANOVA 33
34
Minitab: Stat >> Anova >> One-way
1-Way ANOVA 34
35
Minitab: Stat>> Anova>> Test for Equal variances
1-Way ANOVA 35
36
Diagnosis: Randomness/Independence
The run order plot must show no “systematic” patterns to claim “randomness”. There are statistic tests to verify it scientifically. The ANOVA method is sensitive to the randomness assumption. That is, a little level of dependence between data points will change our conclusions a lot. Run order plot: order vs. residuals 1-Way ANOVA 36
37
Minitab: Stat >> Anova >> One-way
1-Way ANOVA 37
38
KRUSKAL - WALLIS TEST (Non - Parametric Alternative)
HO: The probability distributions are identical for each level of the factor HI: Not all the distributions are the same 1-Way ANOVA 38
39
BATTERY LIFETIME (hours)
Brand A B C BATTERY LIFETIME (hours) (each column rank ordered, for simplicity) Mean: (here, irrelevant!!) 1-Way ANOVA 39
40
HO: no difference in distribution. among the three brands with
HO: no difference in distribution among the three brands with respect to battery lifetime HI: At least one of the 3 brands differs in distribution from the others with respect to lifetime 1-Way ANOVA 40
41
Ranks in ( ) Brand A B C 32 (29) 32 (29) 28 (24)
32 (29) (29) (24) 30 (26.5) (29) (18) 30 (26.5) (22) (10.5) 29 (25) (22) (10.5) 26 (22) (19) (7) 23 (20) (16.5) 14 (7) 20 (16.5) (14.5) (7) 19 (14.5) (12) (3) 18 (13) (7) (2) 12 (4) (7) (1) T1 = T2 = T3 = 90 n1 = n2 = n3 = 10 1-Way ANOVA 41
42
TEST STATISTIC: 12 • (Tj2/nj ) - 3 (N + 1) H = N (N + 1)
K 12 H = • (Tj2/nj ) - 3 (N + 1) N (N + 1) j = 1 nj = # data values in column j N = nj K = # Columns (levels) Tj = SUM OF RANKS OF DATA ON COL j When all DATA COMBINED (There is a slight adjustment in the formula as a function of the number of ties in rank.) K j = 1 1-Way ANOVA 42
43
[ [ H = = 8.41 (with adjustment for ties, we get 8.46)
30 (31) [ + + - 3 (31) = 8.41 (with adjustment for ties, we get 8.46) 1-Way ANOVA 43
44
What do we do with H? We can show that, under HO , H is well approximated by a 2 distribution with df = K - 1. Here, df = 2, and at = .05, the critical value = 5.99 = H = .05 c21-adf df F1-adf, = 8 Reject HO; conclude that mean lifetime NOT the same for all 3 BRANDS 1-Way ANOVA 44
45
Minitab: Stat >> Nonparametrics >> Kruskal-Wallis
Kruskal-Wallis Test: life versus brand Kruskal-Wallis Test on life brand N Median AveRank Z Overall H = DF = 7 P = 0.078 H = DF = 7 P = (adjusted for ties) 1-Way ANOVA 45
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.