chapter-1-2jalan.ppt statistika inferensia

statistika inferensia

1. “Nikmat manakah yang kamu dustakan? “

2. Review
Analisis Variansi dan Efek Utama
•Analisis variansi dengan 1 efek utama dikenal sebagai
analisis variansi satu jalan
•Analisis variansi dengan 2 efek utama dikenal sebagai
analisis variansi dua jalan
•Analisis variansi dengan 3 efek utama dikenal sebagai
analisis variansi tiga jalan
•Dan demikian seterusnya

3. Analisisvariansisatujalanhanyaterdiriatassatufaktor
denganduaataulebihlevel
Analisisvariansiduajalanterdiriatasduafaktor,masing-
masingdenganduaataulebihlevel
Faktormenghasilkanefekutamasehinggadisini
terdapatduaefekutama

4. FaktorUtamadanInteraksi
Dalamhallebihdarisatufaktor, faktoritudapatsajasaling
mempengaruhiatautidaksalingmempengaruhi
Apabilafaktoritutidaksalingmempengaruhimakakitamemperoleh
duafaktorutamasaja
Apabilafaktoritusalingmempengaruhi, makaselainefekutama,
kitamemperolehlagiinteraksipadasalingmempngaruhiitu
Dalamhalterdapatinteraksi, kitamemilikiefekutamadaninteraksi
•Efekutama(denganperbedaanrerata)
•Interaksi(denganinteraksidiantarafaktror)

5. Variansi dan Efek Utama
Variansi sebelum ada efek
Variansiantarakelompok
Kelompok 1 (level 1)
Kelompok 2 (level 2)
Kelompok 3 (level 3)
Ada variansi dalam
kelompok pada kelompok
masing-masing
Ada variansi antara
kelompok

6. Variansi Sesudah Ada Efek Utama
Variansiantarakelompok
Variansi dalam kelompok tidak berubah
Variansi antara kelompok
menjadi besar:
Ada efek,
Paling sedikit ada satu
pasang rerata yang beda










7. Variansi Total
Variansitotal
Dengan membuka batas semua
kelompok, diperoleh variansi total










8. So …Sources of variance
When we take samples from each population,
there will be two sources of variability
Within group variability -when we sample from a group
there will be variability from person to person in the
same group Sesatan
We will always have this form of variability because it is sampling
variability
Between group variability –the difference from group to
group Perlakuan
This form of variability will only exist if the groups are different
If the between group variability if large, the means of the two
groups is likely not the same

9. We can use the two types of variability to determine
if the means are likely different
How can we do this?
Look again at the picture
Blue arrow: within group, red arrow: between group

10. Rancangan
Percobaan
One-Way
Anova
(ANAVA 1 Jalan
Random Lengkap
RRL
Blok Random
RBRL
Two-Way
Anova
(ANAVA 2 Jalan
Faktorial

11. Eksperimen faktorial a x b melibatkan 2 faktor dimana
terdapat a tingkat faktor A dan b tingkat faktor B,
Eksperimen diulang r kali pada tiap-tiap tingkat faktor
kombinasi
Adanya replikasi inilah yang memungkinkan
terjadinya interaksi antara faktor A dan B
Rancangan Faktorial ax b

12. Interaction
OccursWhenEffectsofOneFactorVaryAccordingtoLevels
ofOtherFactor
WhenSignificant,InterpretationofMainEffects(A&B)Is
Complicated
CanBeDetected
InDataTable,PatternofCellMeansinOneRowDiffers
FromAnotherRow
InGraphofCellMeans,LinesCross
TheinteractionbetweentwofactorAandBisthetendency
foronefactortobehavedifferently,dependingonthe
particularlevelsettingoftheothervariable.
Interactiondescribestheeffectofonefactoronthebehavior
oftheother.Ifthereisnointeraction,thetwofactors
behaveindependently.

13. A drug manufacturer has three
supervisors who work at each of three
different shift times. Do outputs of the
supervisors behave differently, depending
on the particular shift they are working?
Example
Supervisor 1 always does better
than 2, regardless of the shift.
(No Interaction)
Supervisor 1 does better earlier in the
day, while supervisor 2 does better at
night.
(Interaction)

14. Graphs of Interaction
Effects of Motivation (High or Low) & Training
Method (A, B, C) on Mean Learning Time
Interaction No Interaction
Average
Response
A B C
High
Low
Average
Response
A B C
High
Low

15. Interaksi X terhadap Y
•Tanpa interaksi (dua efek utama)
•Dengan interaksi (bentuk interaksi)
X
1
X
2
Y
Y
X
1
X
2
Y

16. •Tanpa interaksi
•Ada interaksi
Y
X
X
Y
X
1
X
2
X
1
X
2
interaksi

17. Interaksi
•Interaksi terjadi apabila perbedaan rerata pada satu level (misalnya level 1)
tidak sama untuk dua level berbeda pada level 2 sehingga terjadi
perpotongan
Level 1
Level 2
Ada perpotongan karena tidak
sama

18. Two-Way ANOVA Assumptions
1.Normality
Populations are Normally Distributed
2.Homogeneity of Variance
Populations have Equal Variances
3.Independence of Errors
Independent Random Samples are Drawn

19. Two-Way ANOVA
Null Hypotheses
1.No Difference in Means Due to Factor A
H
0: 
1..= 
2..=... = 
a..
2.No Difference in Means Due to Factor B
H
0: 
.1.= 
.2.=... = 
.b.
3.No Interaction of Factors A & B
H
0: AB
ij= 0

20. Let x
ijkbe the k-threplication at the i-thlevel of A
and the j-thlevel of B.
i= 1, 2, …,a j = 1, 2, …, b, k= 1, 2, …,r
The total variation in the experiment is measured by
the total sum of squares:
The a x b Factorial
Experiment2
)( SS Total xx
ijk
 
ijkijjiijkx  

21. VariansiTotal
ANAVA 2 Jalan
PartisiVariansiTotal
JKS
JKA
VariansiA
VariansiSesatanVariansiInteraksi
JK(AB)
JKT
VariansiB
JKB

22. JKT dibagimenjadi4 bagian:
JKA(JumlahKuadratfaktorA) : variansi
antarafaktorA
JKB(JumlahKuadratfaktorB): variansi
antarafaktorB
JK(AB)(JumlahKuadratInteraksi): variansi
antarakombinasitingkatfaktorab
JKS(JumlahKuadratSesatan)SAB BAT JK JKJK JK JK 

23. X
ijk
Level i
Factor A
Level j
Factor B
Observation k
Faktor FaktorB
A 1 2...b
1 X111X121...X1b1
X112X122...X1b2
2 X211X221...X2b1
X212X222...X2b2
: : : : :
a Xa11Xa21...Xab1
Xa12Xa22...Xab2

24. Rumus-rumusABBATS
BA
2
AB
2
B
2
A
2
T
2
JK-JK-JK-JKJK
-ke tingkat Bfaktor dan -keA tingkat faktor aljumlah tot dengan
JK-JK- CMJK
-ke tingkat Bfaktor aljumlah totdengan CMJK
-keA tingkat faktor aljumlah tot dengan CMJK
CMJK
Gdengan
G
CM













jiAB
r
AB
jB
ar
B
iA
br
A
x
x
n
ij
ij
j
j
i
i
ijk
ijk

25. Contoh : Pabrik Obat
SupervisorPagiSiangSoreA
i
1 571
610
625
480
474
540
470
430
450
4650
2 480
516
465
625
600
581
630
680
661
5238
B
j 3267330033219888
Supervisor pabrikobatbekerjapada3 shift yang berbedadan
hasilproduksidihitungpada3 hariyang dipilihsecara
random
a=2
b=3 r=3

26. Tabel ANAVA
db Total = Rataan Kuadrat
db Faktor A =
db faktor B=
db Interaksi =
db Sesatan ?
n–1 = abr-1
a–1
(a-1)(b-1)
RKA= JKA/(k-1)
RKS =JKS/ab(r-1)
Sumber
Variansi
db JK RK F
A a -1 JKA JKA/(a-1) RKA/RKS
B b -1 JKB JKB/(b-1) RKB/RKS
Interaksi(a-1)(b-1)JK(AB)JK(AB)/(a-1)(b-1)RK(AB)/RKS
Sesatanab(r-1) JKE JKS/ab(r-1)
Total abr-1 JKT
b–1
RKB = JKB/(b-1)
Dengan pengurangan
RK(AB) = JK(AB)/(a-1)(b-1)

27. Two-way ANOVA: Output versus Supervisor, Shift
Analysis of Variance for Output
Source DF SS MS F P
Supervis 1 19208 19208 26.68 0.000
Shift 2 247 124 0.17 0.844
Interaction 2 81127 40564 56.34 0.000
Error 12 8640 720
Total 17 109222

28. Tests for a Factorial
Experiment
We can test for the significance of both
factors and the interaction using F-tests
from the ANOVA table.
Remember that s
2
is the common
variance for all abfactor-level
combinations. MSE is the best estimate of
s
2
, whether or not H
0is true.
Other factor means will be judged to be
significantly different if their mean square
is large in comparison to MSE.

29. Tests for a Factorial Experiment
The interaction is tested first using F =
MS(AB)/MSE.
If the interaction is not significant, the
main effects A and B can be individually
tested using F = MSA/MSE and F =
MSB/MSE, respectively.
If the interaction is significant, the main
effects are NOT tested, and we focus on
the differences in the abfactor-level
means.

30. Source of
Variation
Degrees of
Freedom
Sum of
Squares
Mean
Square
F
A
(Row)
a -1 SS(A) MS(A) MS(A)
MSE
B
(Column)
b -1 SS(B) MS(B) MS(B)
MSE
AB
(Interaction)
(a-1)(b-1)SS(AB)MS(AB)MS(AB)
MSE
Error n -ab SSE MSE
Total n -1 SS(Total)
Same as Other
Designs

31. The Drug Manufacturer
Two-way ANOVA: Output versus Supervisor, Shift
Analysis of Variance for Output
Source DF SS MS F P
Supervis 1 19208 19208 26.68 0.000
Shift 2 247 124 0.17 0.844
Interaction 2 81127 40564 56.34 0.000
Error 12 8640 720
Total 17 109222
The test statistic for the interaction is F = 56.34 with p-value = .000.
The interaction is highly significant, and the main effects are not
tested. We look at the interaction plot to see where the differences
lie.

32. The Drug Manufacturer
Supervisor 1 does better
earlier in the day, while
supervisor 2 does better at
night.

33. Revisiting the
ANOVA Assumptions
1.The observations within each population are
normally distributed with a common variance
s
2
.
2.Assumptions regarding the sampling
procedures are specified for each design.
•Remember that ANOVA procedures are fairly
robust when sample sizes are equal and when
the data are fairly mound-shaped.

34. Diagnostic Tools
1.Normal probability plot of residuals
2.Plot of residuals versus fitor residuals
versus variables
•Many computer programs have graphics
options that allow you to check the
normality assumption and the
assumption of equal variances.

35. Residuals
•The analysis of variance procedure takes
the total variation in the experiment and
partitions out amounts for several important
factors.
•The “leftover” variation in each data point
is called the residualor experimental error.
•If all assumptions have been met, these
residuals should be normal, with mean 0 and
variance s
2
.

36. If the normality assumption is valid, the
plot should resemble a straight line,
sloping upward to the right.
If not, you will often see the pattern fail
in the tails of the graph.
Normal Probability Plot

37. If the equal variance assumption is valid,
the plot should appear as a random
scatter around the zero center line.
If not, you will see a pattern in the
residuals.
Residuals versus Fits