You are on page 1of 14

Q 1)

a)

Ho: There is no linear association between size of home and price of home. (ρ=0)

Ha: There is a positive linear association between size of home and price of home. (ρ>0)

As P value (0.005) is less than α value (0.01), we reject Ho. At 1% level of significance data provides evidence that there exist a strong positive
linear association (0.829) between size of home and price of home.

b)

Price of home= f (size of home)

Price of home= a +b (size of home)

Ho: The size of home is not a useful predictor for price of home. (β=0)

Ha: The size of home is a useful predictor of price of home. (β≠0)

Model Summary

Adjusted R Std. Error of the


Model R R Square Square Estimate

1 .829a .688 .636 63.54958

a. Predictors: (Constant), Area in ft2


ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 53423.577 1 53423.577 13.228 .011a

Residual 24231.298 6 4038.550

Total 77654.875 7

a. Predictors: (Constant), Area in ft2

b. Dependent Variable: Price in thousand of dollars

Coefficientsa

Standardized
Unstandardized Coefficients Coefficients

Model B Std. Error Beta t Sig.

1 (Constant) 146.867 132.520 1.108 .310

Area in ft2 15.768 4.335 .829 3.637 .011

a. Dependent Variable: Price in thousand of dollars

Only 69% variability can be explained using the given dependent variable. Remaining 31% is due to the other factors.

There is a strong positive linear dependent relationship between price of home and size of home.

Price of home= 146.867 +15.768 (size of home)

For every unit increase in size of home, the price of home increases by 15.768 units.

As P value(0.01) is less than α value (0.05), we reject Ho.

At 5% level of significance the data does provide evidence to conclude that the size of home is a useful predictor for price of home.
Q2)

a)

Ho: There is no linear association between magnitude of earthquake and depth of earthquake. (ρ=0)

Ha: There is a linear association between magnitude of earthquake and depth of earthquake. (ρ≠0)

Correlations

Magnitude in Km Depth in Km

Magnitude in Km Pearson Correlation 1 .848**

Sig. (2-tailed) .008

N 8 8

Depth in Km Pearson Correlation .848** 1

Sig. (2-tailed) .008

N 8 8

**. Correlation is significant at the 0.01 level (2-tailed).

As P value (0.008) is less than α value (0.01), we reject Ho. At 1% level of significance data provides evidence that there exist a strong positive
linear association (0.848) between the magnitude and depth of the earthquake.

b)

Depth pf earthquake= f (Magnitude of earthquake)

Depth of earthquake= a +b (Magnitude of earthquake)


Ho: The magnitude of earth quake is not a useful predictor of depth of earthquake. (β=0)

Ha: The magnitude of earth quake is a useful predictor of depth of earthquake. (β≠0)

Model Summary

Adjusted R Std. Error of the


Model R R Square Square Estimate

1 .848a .720 .673 5.71820

a. Predictors: (Constant), Magnitude in Km

ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 503.313 1 503.313 15.393 .008a

Residual 196.187 6 32.698

Total 699.500 7

a. Predictors: (Constant), Magnitude in Km

b. Dependent Variable: Depth in Km


Coefficientsa

Standardized
Unstandardized Coefficients Coefficients

Model B Std. Error Beta t Sig.

1 (Constant) -17.409 9.311 -1.870 .111

Magnitude in Km 5.834 1.487 .848 3.923 .008

a. Dependent Variable: Depth in Km

Only 72% variability can be explained using the given dependent variable. Remaining 28% is due to the other factors.

There is a strong positive linear dependent relationship between magnitude and depth of earthquake.

Depth of earthquake= -17.409 + 5.834 (Magnitude of earthquake)

For every unit increase in magnitude of earthquake, the depth of earthquake increases by 5.384 units.

As P value(0.08) is less than α value (0.05), we reject Ho.

At 5% level of significance the data does provide evidence to conclude that the magnitude of earthquake is a useful predictor for depth of
earthquake.

Q3)

a)

Ho: There is no linear association between sugar consumption and cavities. (ρ=0)

Ha: There is a linear association between sugar consumption and cavities. (ρ>0)
Correlations

Sugar
consumption in
KG Cavities

Sugar consumption in KG Pearson Correlation 1 .979**

Sig. (1-tailed) .000

N 7 7

Cavities Pearson Correlation .979** 1

Sig. (1-tailed) .000

N 7 7

**. Correlation is significant at the 0.01 level (1-tailed).

As P value (0.00) is less than α value (0.01), we reject Ho. At 1% level of significance data provides evidence that there exist a strong positive
linear association (0.979) between sugar consumption and cavities.

b)

Cavities= f (Sugar consumption)

Cavities= a +b (Sugar consumption)

Ho: The sugar consumption is not a useful predictor of cavities. (β=0)

Ha : The sugar consumption is a useful predictor of cavities (β≠0)


Model Summary

Adjusted R Std. Error of the


Model R R Square Square Estimate

1 .979a .959 .950 .14996

a. Predictors: (Constant), Sugar consumption in KG

ANOVAb

Model Sum of Squares df Mean Square F Sig.

1 Regression 2.599 1 2.599 115.591 .000a

Residual .112 5 .022

Total 2.712 6

a. Predictors: (Constant), Sugar consumption in KG

b. Dependent Variable: Cavities


Coefficientsa

Standardized
Unstandardized Coefficients Coefficients

Model B Std. Error Beta t Sig.

1 (Constant) .252 .152 1.660 .158

Sugar consumption in KG .221 .021 .979 10.751 .000

a. Dependent Variable: Cavities

96% variability can be explained using the given dependent variable. Remaining 4% is due to the other factors.

There is a strong positive linear dependent relationship between sugar consumption and cavities.

Cavities= 0.252 +0.221 (Sugar consumption)

For every unit increase in sugar consumption, the cavities increases by 0.221 units.

As P value(0.00) is less than α value (0.05), we reject Ho.

At 5% level of significance the data does provide evidence to conclude that the of sugar consumption is a useful predictor of cavities.

Q4)

Ho: The current distribution of age of individuals is not different from the previous survey

Ha: The current distribution of age of individuals is different from the previous survey

α = 5%
Expected frequency:

Age Group Percentage Total No of observation Expected Frequency


2-17 0.267 1000 267
18-24 0.198 1000 198
25-39 0.197 1000 197
40-49 0.14 1000 140
50+ 0.198 1000 198

As P-value for the chi-Square test is greater than α value we donot reject Ho.

At 5% level of significance the data does not provide evidence to conclude that the current distribution of age of individuals is different from the
previous survey.

Q5)

Ho: The current distribution of reasons for workers to leave their job is not different from previous survey

Ha: The current distribution of reasons for workers to leave their job is different from previous survey

α = 1%

Expected frequency:

Reason Percentage Total No of observation Expected Frequency


Limited advancement potential 0.41 200 82
Lack of recognition 0.25 200 50
Low Salary/benefits 0.15 200 30
Unhappy with management 0.10 200 20
Bored/ Don’t Know 0.09 200 18
At α = 5%

As P-value for the chi-Square test is greater than α value we donot reject Ho.

At 5% level of significance the data does not provide evidence to conclude that the current distribution of reasons for workers to leave their job
is different from previous survey.

At α = 1%

From table

@ df= 4, α=0.01, chi-Square Value= 13.28

Calculated Chi-Square value= 2.025

As the calculate chi-square value lies within acceptance region we donot reject Ho.

At 1% level of significance the data does not provide evidence to conclude that the current distribution of reasons for workers to leave their job
is different from previous survey.

Q6)

Ho: Basic skill level and the location of school are independent.

Ha: Basic Skill level and the location of school are dependent.
Chi-Square Tests

Asymp. Sig. (2-


Value df sided)

Pearson Chi-Square .297a 2 .862

Likelihood Ratio .298 2 .862

Linear-by-Linear Association .296 1 .587

N of Valid Cases 317

a. 0 cells (.0%) have expected count less than 5. The minimum expected
count is 39.97.

As P-value (0.862) for the chi-Square test is greater than α value (0.05) we donot reject Ho.

At 5% level of significance we can conclude that Basic skill level and the location of school are independent.

From chi square Table:

@df=2, α=0.05, chi square value= 5.99

Chi-square value from the table= 0.297

As the calculated value lies within acceptance region we donot reject Ho. Hence Basic skill level and the location of school are independent.

Q 7)

Ho: The current distribution of days of week people order food is not different form previous survey

Ha: The current distribution of days of week people order food is different from previous survey

α = 1%
Expected frequency:

Reason Percentage Total No of observation Expected Frequency


Sunday 0.07 500 35
Monday 0.04 500 20
Tuesday 0.06 500 30
Wednesday 0.13 500 65
Thursday 0.1 500 50
Friday 0.36 500 180
Saturday 0.24 500 120

At α = 5%

As P-value for the chi-Square test is less than α value we reject Ho.

At 5% level of significance the data provides evidence to conclude that the current distribution of days of week people order food is different
from previous survey.

At α = 1%

From table

@ df= 6, α=0.01, chi-Square Value= 16.81

Calculated Chi-Square value= 17.595

As the calculate chi-square value lies in the rejection we reject Ho.

At 5% level of significance the data provides evidence to conclude that the current distribution of days of week people order food is different
from previous survey.
Q 8)

Ho: µ1= µ2= µ3

Ha: Atleast one mean is different

α = 5%

Test for Normality

Ho: Data set 1, data set 2, data set 3 are normally distributed.

Ha: Data set 1, data set 2, data set 3 are not normally distributed.

Tests of Normality

Kolmogorov-Smirnova Shapiro-Wilk

Statistic df Sig. Statistic df Sig.

Cost1 per ounce in dollars .342 5 .057 .761 5 .038

Cost 2 per ounce in dollars .330 5 .079 .698 5 .009

Cost 3 per ounce in dollars .331 5 .078 .762 5 .039

a. Lilliefors Significance Correction

As P value for Kolmogorov Test for the three variables (0.057,0.079,0.78) is greater than α-value (0.05) the data is normally distributed. At 5%
level of significance the data set are normally distributed. We proceed with Anova

Anova:

For homogeneity test:


Ho: Population variances are same.
Ha: Population variances are different.
Test of Homogeneity of Variances

Cost per ounce

Levene Statistic df1 df2 Sig.

1.424 2 26 .259

At 5% level of significance the P-value (0.259) is greater than α-value (0.05), hence donot reject Ho, hence we conclude the variances are
same.

ANOVA

Cost per ounce

Sum of Squares df Mean Square F Sig.

Between Groups .518 2 .259 1.017 .376

Within Groups 6.629 26 .255

Total 7.148 28

As the P-value (0.376) is greater than α-value (0.05), hence we donot reject Ho. At 5% level of significance data provides evidence to
conclude that the mean of data set are same.

You might also like