Analysis of Variance

1. Suppose that a random sample of 5 was selected from the vineyard properties for sale in
Sonoma Country, California, in each of three years. The following data are consistent with
summary information on price per acre for disease-resistant grape vineyards in Sonoma
Country. Carry out an ANOVA to determine whether there is evidence to support the claim that
the mean price per acre for vineyard land in Sonoma Country was not the same for each of the
three years considered. Test at the 0.05 level and 0.01 levels.
1996: 3000 3400 3600 3800 4000
1997: 3000 3500 3700 3800 4000
1998: 4000 4100 4300 4400 5000
ANOVA Test
H0: 𝜇 1996 = 𝜇 1997 = 𝜇 1998
H1: H0 is not true
Test Value: ANOVA F = 6.834
P – Value: 0.01044
Conclude: At the 0.01 level. There is not enough evidence to reject the Null Hypothesis
That the mean price per acre is different in these years.
At the 0.05 level. There is enough evidence to reject the Null Hypothesis that
The mean price per acre was not the same in each year.

2. The following data on calcium content of wheat are consistent with summary quantities that
appeared in the article “Mineral Contents of cereal grains as affected by storage and Insect
Infestation” Four different storage times were considered. Is there sufficient evidence to
conclude that the mean calcium content is not the same for the four different storage times?
Test the appropriate hypotheses at the 0.05 level.

Storage Time OBSERVATIONS

0 months 58.75 57.94 58.91 56.85 55.21 57.30
1 month 58.87 56.43 56.51 57.67 59.75 58.48
2 months 59.13 60.38 58.01 59.95 59.51 60.34
3 months 62.32 58.76 60.03 59.36 59.61 61.95

ANOVA Test
H0: 𝜇0 = 𝜇1 = 𝜇2 = 𝜇3
H1: H0 is not true
Test Value: ANOVA F = 6.512
P – Value: 0.003
Conclude: There is enough evidence to reject the Null Hypothesis because the mean
calcium content is not the same for the four different storage times.
 3. Use the data below, Showing the summary of highway gas mileage for several
observation, to decide if the average highway gas mileage is the same for mid size cars,
SUV’s, and pickup trucks. Test the appropriate hypotheses at the 0.01 level.
Cars n Mean s
Mid size 31 25.8 2.56
SUV 31 22.68 3.67
Pickup 14 21.29 2.76

ANOVA Program
H0: 𝜇M = 𝜇S = 𝜇P
H1: H0 is not true.
Test Value: ANOVA F = 13.055
P – Value: 0.0000142
Conclude: There is enough evidence to reject the Null Hypothesis because the mean
Highway is not the same for the three types of vehicle.

4. To examine the effects of pets and friends in stressful situations, researcher recruited 45 people
to participate in a experiment. Fifteen of the subjects were randomly assigned to each of three
groups to perform a stressful task alone, with a good friend present or with their dog present.
Each subject’s mean heart rate during the task was recorded. Test the appropriate hypotheses
at the 0.05 level to decide if the mean heart rate differs between the groups.
Sample N Mean S
Control 15 82.52 9.24
Pets 15 73.48 9.97
Friends 15 91.325 8.34

ANOVA Program
H0: 𝜇C = 𝜇P = 𝜇F
H1: H0 is not true.
Test Value: ANOVA F = 14.08
P – Value: 0.000021
Conclude: There is enough evidence to reject the Null Hypothesis because the mean heart
rate is not the same for each of the three groups.

5. An investigation carried out to study the toxic effects of mercury was described in the article
“Comparative Responses of the Action of Different Mercury Compounds on Barley”
(International Journal of Environmental Studies [1983]) Ten different concentrations of mercury
were compared with respect to their effects on average dry weight (per 100 seven-day-old
seedlings). The basic experiment was replicated 4 times for a total of 40 observations. The
article reported an ANOVA F statistic of 1.895. Using a significance level of 0.05, test the
hypothesis that the true mean dry weight is the same for all 10 concentration levels.
ANOVA Test
First of all, note that DF1 = 10-1 = 9 and DF2 = 40 – 10 = 30. So we can find the P – Value for this
scenario by calculating FCDF = 0.0916.
H0: 𝜇 1 = 𝜇 2 = 𝜇 3 = 𝜇 4 = 𝜇 5 = 𝜇 6 = 𝜇 7 = 𝜇 8 = 𝜇 9 = 𝜇 10
H1: H0 is not true.
Test Value: ANOVA F = 1.895
P – Value: 0.0916
Conclude: There is not enough evidence to reject the Null Hypothesis because the mean
Dry weight is not the same for each of the concentration levels.

6. High productivity and carbohydrate storage ability of the Jerusalem artichoke make it a
promising agricultural crop. The article “Leaf Gas Exchange and Tuber Yield in Jerusalem
Artichoke Cultivars” (Field CropsResearch [1991]) reported on various plant characteristics.
Consider the following data on chlorophyll concentration (in grams per square meter) for four
varieties of Jerusalem artichoke:
Variety N Mean S
1 5 0.3 0.12
2 5 0.24 0.089
3 4 0.41 0.1
4 7 0.33 0.054

Do the data suggest that true average chlorophyll concentration depends on the variety? State and test
the appropriate hypotheses at a level of 0.05.

ANOVA Program
H0: 𝜇1 = 𝜇2 = 𝜇3 = 𝜇4
H1: H0 is not true.
Test Value: ANOVA F = 2.6566
P – Value: 0.0836
Conclude: There is not enough evidence to reject the Null Hypothesis that the mean
chlorophyll concentration depends on the variety.

7. Many businesses have music piped into the work areas to improve the environment. At
a company an experiment is performed to compare different types of music. Three
types of music – country, rock, and classical – are tried, each on four randomly selected
days. Each day the productivity, measured by the number of items produced, is
recorded. The results appear below.
 A. Can we conclude from this information that the mean number of items produced
differs for at least two of the three types of music? Use a = .05.

B. Carefully explain what the p-value found in part a means.

C. Which type(s) of music seem to be best?

D. Which type(s) of music seem to be worst?

Solutions

A. The parameters of interest are m1 , the mean number of items produced for all days
when country music is played; m2, the mean number of items produced for all days
when rock music is played; and m3, the mean number of items produced for all days
when classical music is played.

H0: m1 = m2 = m3 Ha: At least two of the means are not equal

Decision Rule: Accept Ha if the calculated p-value < .05.

Calculations from StatCrunch: F = 10.66, p-value = 0.0042 < .05 ---> Accept Ha

Interpretation: At the .05 level of significance I conclude that the mean number

B. If the mean productivity were the same for all three types of music (the null
hypothesis is true), then the probability of observing three sample means as varied, or
more varied, as those obtained in this experiment is 0.0042. Therefore it is extremely
unlikely (smaller than α = .05) that the sample means would have such diverse values if
all the population means are equal. This is why the alternative hypothesis was accepted.

C. The results of the multiple comparison tests of the mean numbers of items produced
for each of the three types of music are shown below. Interpretations are listed in
terms of which are largest because "best", in this application, means largest.

Comparison Value of t p-value Interpretation

Country vs. Rock 2.81 0.020 Country > Rock
Country vs. Classical -1.77 0.110 NS
Rock vs. Classical -4.58 0.001 Classical > Rock
 From these analyses we see that rock music is certainly not the best in terms of worker
productivity. Classical music may be best, but perhaps country music could be.

D. From these same analyses we see that rock music is the worst in terms of worker
productivity.

8. Susan Sound predicts that students will learn most effectively with a constant
background sound, as opposed to an unpredictable sound or no sound at all. She
randomly divides twenty-four students into three groups of eight. All students study a
passage of text for 30 minutes. Those in group 1 study with background sound at a
constant volume in the background. Those in group 2 study with noise that changes
volume periodically. Those in group 3 study with no sound at all. After studying, all
students take a 10 point multiple choice tests over the material. Their scores follow:

group test scores

1) constant
74686629
sound
2) random
55344722
sound
3) no sound 24712155
Solutions:

x1 x12 x2 x22 x3 x32

7 49 5 25 2 4
4 16 5 25 4 16
6 36 3 9 7 49
8 64 4 16 1 1
6 36 4 16 2 4
6 36 7 49 1 1
2 4 2 4 5 25
9 81 2 4 5 25
Sx1 = 48 2
Sx1 = 322 Sx2 = 32 2
Sx2 = 148 Sx3 = 27 2
Sx3 = 125
(Sx1)2 = 2304 (Sx2)2 = 1024 (Sx3)2 = 729
M1 = 6 M2 = 4 M3 = 3.375

= 595 - 477.04

SStotal = 117.96
 = 507.13 - 477.04

SSamong = 30.08

SSwithin = 117.96 - 30.08 = 87.88

Conclusion: Susan can conclude that her hypothesis may be supported.

The means are as she predicted, in that the constant music
group has the highest score.

9. Three types of medium sized cars assembled in New Zealand have been test driven by a
motoring magazine and compared on a variety of criteria. In the area of fuel efficiency
performance, five cars of each brand were each test driven 1000 km; the km per litre
data are obtained as follows: Kilometres per litre Total Mean Brand A 7.6 8.4 8.0 7.6 8.4
40.0 8.0 Brand B 7.8 8.0 9.1 8.5 9.6 43 8.6 Brand C 9.6 10.4 9.2 9.7 10.6 49.5 9.9 The task
is to determine if there is a difference in the mean fuel consumption for the three
makes of car.

State hypotheses: H0:  Brand a   Brand b   Brand c

H1:  Brand a   Brand b   Brand c

Test Values: dftreatment  2; dftotal 14; df error  dftotal  dftreatment 12

Compute: (132.5)2 /15 = 1170.42

1184 – (132.5)2 /15 = 13.69

402/ 5 + 432/ 5 + 49.52/ 5 + 132.52/ 5 = 9.43

SS error  SStotal  SStreatment 13.69  9.43  4.26

9.43/2 = 4.715 4.26/12 = 0.355

4.715/0.355 = 13.28

P – Value: Since the calculated value for F (13.28) is greater than 12.97, the level of
significance, p, is less than 0.001. This can be written as simply 0.001 or
p < 0.001.

Conclusion: Since this result is highly significant, we can reject H0 in favour of HA.
That is, there is strong evidence that the mean km/l is different in at
least one of the three makes of car.
 10. Four brands of flashlight batteries are to be compared by testing each brand in five
flashlights. Twenty flashlights are randomly selected and divided randomly into four
groups of five flashlights each. Then each group of flashlights uses a different brand of
battery. The lifetimes of the batteries, to the nearest hour, are as follows. Brand A Brand
B Brand C Brand D 42 28 24 20 30 36 36 32 39 31 28 38 28 32 28 28 29 27 33 25
Preliminary data analyses indicate that the independent samples come from normal
populations with equal standard deviations. At the 5% significance level, does there
appear to be a difference in mean lifetime among the four brands of batteries?

State the Hypothesis: H0: µ1 = µ2 = µ3 = µ4 the mean lifetimes are equal.

H1: Not all of the means are equal.

Significance Level: α = 0.05

Compute Test Value: F 0.05 = 3.24 (Reject the null hypothesis)

One Way Anova: ((168)2/5 + (154)2/5 + (149)2/5 + (143)2/5) – (614)2/5 = 68.2

SSE = SSTo− SSTr = 560.2 − 68.2 = 492.0

. Decision: Since 0.7393 < 3.24 (p-value > 0.05), there is not enough evidence to

Reject the Null Hypothesis that the mean lifetimes of the brands of

Batteries differs.