Hiba Manjouri 5136 :

Exercise 2:
• Step 1: Organize the dataSort the data in ascending order:
5395,5538,5561,5612,5710,5816,6045,6106,6265,6320,6341,6632,6908,7220,7361,7439
• step2:Calculate the five-number summary:
1. Minimum: The smallest value is 5395.
2. Maximum:The largest value is 7439.
3. Median:The median is the middle value of the sorted data.Since there
are 16 data points , the median is the average of the 8th and 9th values:
Median=6106+6265/2=12371/2 =6185.5
1. First Quartile (Q1):Q1 is the median of the first half of the data
(lower 8 values):
Q1=5561+5612/2=11173/2 =5586.5
• Third Quartile (Q3):Q3 is the median of the second half of the data
(upper 8 values):
Q3=6320+6341/2=12661/2 =6330.5
• Five-number summary:
Minimum: 5395, Q1: 5586.5, Median: 6185.5, Q3: 6330.5, Maximum: 7439.
•Step 3: Calculate other statistical measures:
Mean=Sum of data/Number Of odata points
5395+5538+5561+5612+5710+5816+6045+6106+6265+6320+6341+6632+6908+7220+7361+7439
=100,069
Mean=100,069/16≈6254.31
Mode:The mode is the most frequently occurring value. In this dataset, no value
repeats, so there is no mode.
.Range:
Range=Maximum−Minimum=7439−5395=2044
• Variance and Standard Deviation:Variance is calculated as:
σ2=∑(xi−Mean)2/n
• Steps:
Find the squared deviations for each value:For example, for 5395:
(5395−6254.31)2=(−859.31)2. ≈738417.27 ( all values )
.Sum of Squared Deviations≈14,439,634.87
Variance:σ2=14,439,634.87/16 ≈902,477.18i
Standard Deviation:σ=/902,477.18≈949.99
•Step 4: Shape of the Distribution:
To determine the shape, consider the relationship between the mean, median, and
mode:
Mean = 6254.31, Median = 6185.5, No Mode.
⁃ The mean is slightly greater than the median, suggesting a slight
right skew.
⁃ The distribution is slightly skewed right because the mean is
greater than the median.

Exercise 3:

To construct a 99% confidence interval for the population mean, we use the
following formula:

Confidence Interval = xˉ ± t ×s/√𝑛

Where:
• xˉ: is the sample mean
• t: is the t-value for the given confidence level and degrees of freedom
• s:is the sample standard deviation
• n : is the sample size
We have :
• xˉ=9.75
• t=2.724 (for 99% confidence and df = 35)
• s=2.39
• n=36

•Step 1: Calculate the standard error :

Margin of Error :
(ME)=t⋅SE=2.720⋅0.3983≈1.083

Standard Error = s/√n = 2.39/√6=0.3983

•Step 2: Calculate the margin of error:

(ME)=t⋅SE=2.720⋅0.3983≈1.083

•Step 3: Construct the confidence interval

Confidence Interval = 9.75±1.085

⁃ Lower limit = 9.75−1.085=8.665

⁃ Upper limit = 9.75+1.085=10.835

•The final answer:

The 99% confidence interval for the population mean number of days the car model
sits on the dealership’s lot is:
(8.665,10.835).

Exercise 4:

1. Identify the null and alternative hypothesis:

The researcher claims that the mean annual cost of raising a child is $14,050. We
will test this claim at α=0.10 .

•Step 1: Identify the Null and Alternative Hypotheses The hypotheses are:
• Null Hypothesis (H0): μ=14,050 (The mean cost is $14,050.)
• Alternative Hypothesis (Ha): μ≠14,050 (The mean cost is not $14,050.)

•Step2:Find the critical value:

At α= 0.10 for a two-tailed test, the significance level for each tail is α2=0.05.
From the z-table:
zcritical =±1.645

•Step3:Find the standardized test statistic:

The formula for the z-test statistic is:

Z=𝐱 ̄-𝛍 / 𝛔/√𝐧

Where:
• xˉ=13,795 (sample mean)
• μ=14,050 (population mean under (H0)
• σ=2875 (population standard deviation)
• n=500 (sample size)

1. First, calculate the denominator (σ/√𝑛):

σ/√𝑛=2875/√ 500=2875/22,36 ≈128.63

2. Substitute the given values:

Z=13,795-15,050/2875/√500

Z=13,795-14,050/128,63
= -255/128,63≈-1,98

•Step4: Decide whether to reject or fail to reject the null hypothesis:

The test statistic z=−1.98 lies outside the critical region [−1.645,1.645].
Therefore:
Decision: Reject H0

•Step5 :Interpret the decision in the context of the original claim:

• At the 0.10 significance level, there is sufficient evidence to reject
the claim that the mean annual cost of raising a child by married-couple families
in the U.S. is $14,050. The sample data suggests the actual mean is likely
different from $14,050.

Exercise 5:
•Step 1: Identify the null and alternative hypothesis:
Let μd represent the mean difference in vertical jump heights (after - before).
• H0 :μd =0 (The shoes do not improve vertical jump height.)
• Ha :μd >0 (The shoes improve vertical jump height.)
This is a one-tailed test at α=0.10.

•Step 2: Find the critical value

For a one-tailed t-test with n−1=8−1=7 degrees of freedom, the critical value
tcritical at α=0.10 is:
tcritical=1.415( from t-tables)

•Step 3: Find the standardized test statistic:

t= 𝐃 ̄/𝐬𝐃/√𝒏
The formula for the paired t-test statistic is:

Where:
• dˉ = mean of the differences.
• sd = standard deviation of the differences.
• n=8 = number of athletes.

•Step 3.1: Calculate the differences (d=after−before):

d=[26−24,25−22,25−25,29−28,33−35,34−32,35−30,30−27]
d=[2,3,0,1,−2,2,5,3]

Dˉ=∑D/n=2+3+0+1-2+2+5+3/8 =1.75

•Step 3.2: Calculate sDsD (Standard Deviation of Differences) :

sD= √∑(di −dˉ)2/n-1

Step 3.3: Calculate sf (standard deviation of the differences):

• (Di−Dˉ)=[ 2−1.75,3−1.75,0−1.75,1−1.75,−2−1.75,2−1.75,5 −1.75,3−1.75] =
[0.25,1.25,−1.75,−0.75,−3.75,0.25,3.25,1.25]

• (Di−Dˉ)^2=[0.0625,1.5625,3.0625,0.5625,14.0625,0.0625,10.5625,1.5625]

-∑(Di − D ̄)^2=31.4375

-sD=√31.4375/8-1≈ √4,491 ≈ 2.12

•Step 3.4: Calculate the t-statistic:

t=D’ /𝐬𝐃/√𝒏=1,75/2,12 √8=1,75/0,7942 ≈2,34

•Step 4: Decide whether to reject or fail to reject the null hypothesis:

• The calculated t=2.33 is greater than
tcritical =1.415.
Decision: Reject H0 .

•Step 5: Interpret the decision in the context of the original claim:

• At the α=0.10 significance level, there is enough evidence to support
the claim that the training shoes improve vertical jump heights.

Exercise 6:

•Step 1: Scatter Plot and Correlation Type:

• To create the scatter plot, plot x (hours spent studying) on the x-axis
and
y (test scores) on the y-axis. Each pair of values (x,y) represents a data point.
The data appears to show a positive correlation because as x increases, y also
increases.

•Step 2: Calculate the Correlation Coefficient (r):

The formula for the correlation coefficient :

r= n∑xy−∑x∑y / √[ n∑ x2−(∑x)2][n∑y2(∑y)2]

Where:
• n=10 (number of data points)
• x = hours spent studying
• y = test scores

•Step 2.1: Compute necessary values:

∑x=51, ∑y=747 ,∑ x2=361 ,∑y2=57491, ∑xy= 4093

•Step 2.2: Plug values into the formula:

r= 10(4093)−(51)(747) / √[10(361)−51^2][10(57491)−747^2]
r= 40930−38097 / √[3610−2601[ 574910−558009]
r= 2833 /√ [1009][16901]
r= 2833 / √ 17060809= 2833 / 4129,3 ≈0,686

•Step 2.3: Test the significance of r:

To test the significance, use the t-test for correlation:
T= r√n-2/√1-1^2
T= 0.686 √10-2 / √1-0,686^2
=0.686 √8 / √1-0.4706
= 0.686* 2.828/ √0.5294 ≈ 1.94/ 0.7277
T ≈ 2.67

For n−2=8 degrees of freedom and α=0.05, the critical t-value is tcritical =2.306

Decision: Since t=2.67>2.306, we reject the null hypothesis. There is significant

evidence to suggest a positive correlation between hours spent studying and test
scores.

•Step 3: Find the Regression Line. Equation The regression line equation is:
 y=a+bx

Where:
• b=n∑xy−∑x∑y /n∑x^2−(∑x)^2
• a=∑y−b∑/ n

•Step 3.1: Calculate b:

b=10(4093)−(51)(747) / 10(361)−51^2

=40930−38097 / 3610−2601 =2833 / 1009 ≈2.81

•Step 3.2: Calculate a:

a= 747−2.81(51) / 10 = 747 -143.31 / 10 = 603.69/ 10 ≈ 60.3

•Step 3.3: Write the equation:

y=60.37+2.81x

Final Results
1. Scatter Plot: The scatter plot shows a positive correlation between
hours spent studying and test scores.
2. Correlation Coefficient: r≈0.686, significant α=0.05.
3. Regression Line: y=60.37+2.81x.

Exercise 7:

•Step 1: Calculate the Expected Frequency for Each Cell:

The formula for the expected frequency for a cell is:

Eij=Row Total×Column Total / Grand Total

Step 1.1: Given Data

• Row totals: Male = 1069, Female =1128
• Column totals: Cup = 978, Cone = 688, Sundae = 340, Sandwich = 88,
Other = 103
• Grand total: 2197

Step 1.2: Compute Expected Frequencies

Eij =Row Total×Column Total / 2197

Gendre Cup Cône Sundae Sandwich Other Row total

Male 1069×978/2197
≈475.7 1069×688 /2197
≈334.7 1069×340/2197 ≈165.3 1069×88/2197 ≈42.8
1069×103 /2197
≈50.1 1069
Female 1128×978 /2197
≈502.3 1128×688 /2197
≈353.3 1128×340 /2197 ≈174.7 1128×88/2197≈45.2
1128×103/2197
≈52.9 1128
Total 978 688 340 88 103 2197

•Step 2: Hypothesis Test (Chi-Square Test of Independence):

 1. Hypotheses:
• H0 : The variables (favorite way to eat ice cream and gender) are
independent.
• Ha : The variables are related.

2. Chi-Square Test Statistic:

χ2=∑ (Oij −Eij )^2/ Eij
Where Oij is the observed frequency and Eij is the expected frequency.

3. Degrees of Freedom (df):

df=(Number of rows−1)×(Number of columns−1)=(2−1)(5−1)=4

4. Critical Value at α=0.01: From the chi-square table, the critical value
for df=4 and α=0.01 is approximately 13.28.

5. Compute the Chi-Square Statistic:

Using observed frequencies and expected frequencies for each cell:
χ^2=∑ (Oij −Eij )^2/ Eij

After calculating for all cells (details omitted for brevity): χ2≈15.87

1. Decision Rule:
• If χ2>critical value, reject H0 .
• Here : χ2=15.87>13.28.

Step 3: P-Value and Interpretation

1. P-Value:Using a chi-square distribution table or software for df=4 and
χ2=15.87, the p-value is approximately 0.003.
Conclusion:
• Since p<α(0.003<0.01), reject H0 .
• There is enough evidence to conclude that favorite way to eat ice cream
and gender are related.

Exercise 8 : one-way ANOVA Test :

Step 1: Hypotheses
1. Null Hypothesis (H0 ):The mean costs per ounce for the three stain
removal groups (very good, good, and fair) are the same.
H0 :μVery Good =μGood =μFair
Alternative Hypothesis (Ha ):
At least one mean cost per ounce is different.
Ha:At least one μ differs.
Step 2: Organize Data
Group the data:
• Very Good: 0.47, 0.49, 0.41, 0.37, 0.48, 0.51 (n1 =6)
• Good: 0.60, 0.64, 0.58, 0.75, 0.46 (n2=5)
• Fair: 0.34, 0.46, 0.44, 0.60 (n3 =4)
Step 3: Compute Group Means and Overall Mean
1. Calculate the group means:
•XˉVeryGood=0.47+0.49+0.41+0.37+0.48+
0.51 /6 = 0.455
•XˉGood=0.60+0.64+0.58+0.75+0.46/5
=0.606
•XˉFair=0.34+0.46+0.44+0.60/ 4=0.46

2. Calculate the overall mean (Xˉ):

•Xˉ=Sum of all values/ Total sample size
=(0.47+0.49+...+0.60)/15=7.195/15=0.48
•Step 4: Compute the ANOVA Table Components:
1. Total Sum of Squares (SST):

SST=∑(X−Xˉ)^2=Sum of squared deviations of each observation from the overall mean.

SST≈0.06186

2. Between-Group Sum of Squares (SSB):

SSB=∑ni (Xˉi −Xˉ)^2
=6(0.455−0.48)^2+5(0.606−0.48)^2+4(0.46−0.48)^2
SSB≈0.01697

3. Within-Group Sum of Squares (SSW): SSW=SST−SSB

SSW≈0.04489

4. Degrees of Freedom:
• dfB =k−1=3−1=2
• dfW =N−k=15−3=12
• dfT =N−1=15−1=14

5. Mean Squares:
• MSB=SSB/ dfB =0.01697/2 ≈0.008485
• MSW=SSW /dfW=0.04489/12≈0.003741

6. F-Statistic:
F= MSB/MSW=0.008485/0.003741≈ 2.27

Step 5: Find the P-Value

Using an F-distribution table with dfB =2 and dfW =12, the critical value for
α=0.05 is approximately 3.89. The p-value for F=2.27 is greater than 0.05.
Step 6: Conclusion
1. Decision: Fail to reject H0 .Since F=2.27<3.89, there is not enough
evidence to reject the null hypothesis.

2. Interpretation:At the 0.05 significance level, we cannot conclude that

there is a significant difference in the mean costs per ounce for the three stain
removal groups.