Suppose

the National Transportation Safety Board (NTSB) wants to examine the safety of comapct
cars, midsize cars and full size cars. It collects a sample of three for each of the treatments (cars
types). Using the hypothetical data provided below, test whether the mean pressure applied to
the driver's head during a crash test is equal for each types of car. Use 0.05 level of significance.

Compact Midsize Full-size

643 469 484
655 427 456
704 525 402

HYPOTHESES: Ho: µ Compact cars = µ Midsize Cars = µ Full-size Cars

H1: Atleast one of the mean differs from the other
ALPHA 0.05
P-VALUE 0.0012
TEST STATISTICS 24.9856
REJECTION REGION 5.1433
DECISION: REJECT THE NULL HYPOTHESIS
CONCLUSION: At 0.05 level of significance, there is sufficient evidence to support
the claim that the mean pressure applied to the driver's head during
crash test is not equal for each type of car.

ANOVA: Single Factor

SUMMARY
Groups Count Sum Average Variance
Compact 3 2002 667.3333333 1044.333
Midsize 3 1421 473.6666667 2417.333
Full-size 3 1342 447.3333333 1737.333

ANOVA
Source of Variation SS df MS F P-value F crit
Between Groups 86600.2222 2 43300.11111 24.98564 0.001232 5.143253
Within Groups 10398 6 1733

Total 96998.2222 8
 Anova: Two-Factor With Replication
Suppose you want to determine whether the brand of laundry detergent used and the temperature affects the amount
SUMMARY Cold Warm Hot Total
of dirt removed from your laundry. With this, you buy two different brand of detergent (Tide and Ariel) and choose three
Tide
different temperature levels (cold,warm and hot). Then you divide your laundry randomly abd assign each piles into the
Count 4 4 4 12
combination of (Tide and Ariel) and (cold, warm and hot).
Sum 20 36 42 98
Average 5 9 10.5 8.166667
Using the data provided, test the following hypotheses: Variance 0.666667 4.666667 1.66666667 7.787879

HOD: The amount of dirt removed does not depend on the type of detergent Ariel
Count 4 4 4 12
HOT: The amount of dirt removed does not depend on the temperature Sum 20 52 48 120
Average 5 13 12 10
HOI: The amount of dirt removed does not depend on the interaction between temperature and detergent Variance 1.333333 2 2 15.27273

Total
Cold Warm Hot Count 8 8 8
TIDE 4,5,6,5 7,8,9,12 10,11,12,9 Sum 40 88 90
ARIEL 6,6,4,4 13,15,12,12 12,13,10,13 Average 5 11 11.25
Variance 0.857143 7.428571 2.21428571

HOD: The amount of dirt removed does not

depend on the type of detergent ANOVA
HOT: The amount of dirt removed does not Source of Variation SS df MS F P-value F crit
HYPOTHESES depend on the temperature Sample 20.16667 1 20.1666667 9.810811 0.005758 3.006977
HOI: The amount of dirt removed does not depend on Columns 200.3333 2 100.166667 48.72973 5.44E-08 2.623947
the interaction between temperature Interaction 16.33333 2 8.16666667 3.972973 0.037224 2.623947
and detergent Within 37 18 2.05555556
Ha: μ1 ≠ μ2
Total 273.8333 23
ALPHA 0.1

P-VALUE ROW 0.00575844

P-VALUE COLOUMN 5.4398492716E-08
P-VALUE INTERACTION 0.037224336
TEST STATISTIC ROW 9.810810811
TEST STATISTIC COLOUMN 48.72972973
TEST STATISTIC INTERACTION 3.972972973
REJ. - ROW 3.006976592
REJ. - COLOUMN 2.623946985
REJ. - INTERACTION 2.623946985

Reject HOD: There is significant difference in the amount of

dirt removed depends on the type of
detergent used.
Reject HOT: There is significant difference in the amount of dirt
DECISION
removed depends on the remperature
Reject HOI: There is significant difference in the amount of dirt
removed depends on the interaction between
the type of detergent and temperature.

There is sufficient evidence to support the claim that the amount

CONCLUSION of dirt removed is not equal depends on type of detergent used
and temperature.
 The brightness of films produced by 3 different manufacturers has been compared using 3 different development
processes. Perform Analysis of variance-two way to test the manufacturer and development method have an impact to
brightness of films. Use 0.05 level of significance.
Anova: Two-Factor With Replication

SUMMARY A B C Total
Kodak
Kodak Fuji Agfa Count 5 5 5 15
A B C A B C A B C Sum 164 143 145 452
32 26 28 43 32 32 23 27 25 Average 32.8 28.6 29 30.13333
34 29 28 41 38 32 24 30 27 Variance 7.7 4.3 4 8.409524
31 27 27 44 38 36 25 25 26
30 30 30 50 40 35 21 25 22 Fuji
37 31 32 47 36 34 26 27 25 Count 5 5 5 15
Sum 225 184 169 578
Average 45 36.8 33.8 38.53333
Variance 12.5 9.2 3.2 31.12381

Ho: μ1 = μ2= μ3= μ4 Agfa

HYPOTHESIS
Ha: There is atleast one inequality Count 5 5 5 15
Sum 119 134 125 378
ALPHA 0.05 Average 23.8 26.8 25 25.2
P-VALUE - MANU 1.7E-16 Variance 3.7 4.2 3.5 4.885714
P-VALUE - DVT. 2.76E-05
P-VALUE - INT. 8.63E-06 Total
TS - MANU 117.3078 Count 15 15 15
TS - DVT. 14.25239 Sum 508 461 439
TS - INT. 10.62715 Average 33.86667 30.73333 29.26667
Variance 87.69524 25.35238 16.92381
CR - MANU 3.259446
CR - DVT 3.259446
CR - INT. 2.633532 ANOVA
Source of Variation SS df MS F P-value F crit
Reject Ho: There is a significant difference between the results of development Manufacturer 1363.378 2 681.6889 117.3078 1.7E-16 3.259446
methods on the brightness of the films Dvt. Method 165.6444 2 82.82222 14.25239 2.76E-05 3.259446
Reject Ho: There is a significant difference between the results of manufacturers Interaction 247.0222 4 61.75556 10.62715 8.63E-06 2.633532
DECISION
on the brightness of the films Within 209.2 36 5.811111
Reject Ho: There is a significant difference in the brightness of the films on the
interaction between the manufacturers and development methods. Total 1985.244 44

At 0.05 level of significance, there is suficient evidence to support the claim that there
CONCLUSION is inequality in the results of development methods and manufacturers on the
brightness of the films.