DRM 04
Introduction to SPSS
Assignment - I
Assignment Code: 2017DRM04B1 Last Date of Submission: 15th November 2017
Maximum Marks: 100
Attempt all the questions.
SECTION – A (25 marks for each question)
1. a) Explain the steps that are needed in order to enter data in an SPSS file.
b) Explain how data from an Excel file can be imported into an SPSS file. Explain what precautions need to be taken for this.
2. Explain the difference between “Descriptive statistics” and “frequency” and “Explore” options that are available in SPSS when we click the Analyze button.
SECTION-B
Case Study (50 marks)
A company was interested in understanding the level of dissemination of information different between superior group, peer group and subordinate group. The data obtained was analysed using Analysis of variance technique. The results of such an analysis are given below.
measure of dissemination
Levene Statistic df1 df2 Sig.
3.253 2 21 .059
ANOVA
measure of dissemination
Sum of Squares df Mean Square F Sig.
Between Groups 44.645 2 22.323 58.210 .000
Within Groups 8.053 21 .383
Total 52.698 23
Multiple Comparisons
Dependent Variable: measure of dissemination
(I) level of employee (J) level of employee Mean Difference (I-J) Std. Error Sig.
Tukey HSD superior Peer 2.43125(*) .30963 .000
subordinate 3.20000(*) .30963 .000
Peer superior -2.43125(*) .30963 .000
subordinate .76875 .30963 .054
subordinate superior -3.20000(*) .30963 .000
Peer -.76875 .30963 .054
LSD superior Peer 2.43125(*) .30963 .000
subordinate 3.20000(*) .30963 .000
Peer superior -2.43125(*) .30963 .000
subordinate .76875(*) .30963 .022
subordinate superior -3.20000(*) .30963 .000
Peer -.76875(*) .30963 .022
*The mean difference is significant at the .05 level.
Tests of Normality
level of employee Kolmogorov-Smirnov(a) Shapiro-Wilk
Statistic df Sig. Statistic df Sig.
measure of dissemination superior .178 8 .200(*) .958 8 .795
Peer .277 8 .071 .899 8 .282
subordinate .151 8 .200(*) .910 8 .356
* This is a lower bound of the true significance.
a Lilliefors Significance Correction
Based on the above answer the following questions:
a) Write the null and alternative hypothesis for the above problem.
b) For the above analysis, several assumptions have been made. Check from the data given above whether these assumptions are met or not.
c) What is your conclusion based on the ANOVA test carried out?
d) Discuss the post hoc tests that have carried out and its implications.
DRM 04
Introduction to SPSS
Assignment - II
Assignment Code: 2017DRM04B2 Last Date of Submission: 15th November 2017
Maximum Marks: 100
Attempt all the questions.
SECTION-A (25 marks for each question)
1. Enumerate the steps that are required to perform Two way ANOVA with interaction effects.
2. If a data is to be converted from Scale information to Nominal information, discuss the steps by which this could be done in SPSS. For example age is collected from respondents in terms of years and this needs to be converted into “Young (15 to 30years)”, “middle age (31 to 50)” and “old (above 51 years)”. Explain how did data conversion will take place?
SECTION-B (50 marks)
A student after passing out from his MBA course had been placed decently in a reputed organization but was posted in the city of Jaipur which was not his home town. He had also recently got married and therefore needed family accommodation. Even though this salary payable to him by his employer was quite decent, the family nevertheless thought that they need not spend a lot of money in purchasing a flat, especially because the company was providing him free transport from his place of residence to work and back. The family all through being living in a luxury having a spacious flat and therefore decided to purchase an independent house for their stay. As the student had already read considerable amount of Statistics he thought he could estimate what would be the price of an independent house based on the data that he collected on the following variables from nearby locations.
The variables that he had collected data on included:
• Y = Actual sale value of the house (Rs.)
• X1 = Number of rooms
• X2 = number of bedrooms
• X3 = number of baths
• X4 = age of the building in months
• X5 = assessed value (Rs.)
• X6 = area of the house in square feet
He then decided to use SPSS to run a regression model so that he is able to predict what would be the actual sale value of the house based on the various independent variables as mentioned above. He decided to carry out this exercise both Stepwise as well as by incorporating all the independent variables. The relevant output for Stepwise is given in Table 1 to 4 and with all the independent variables in Table 5 to 7.
Questions:
a) To what extent each of the model help in explaining the predictive variable i.e. the price of the house.
b) Explain whether each of the models indicate significant relationship
c) Explain which of the variables help in significantly explaining the predictive variable.
d) How would you determine the relative importance of each of the variables.
e) If you were to choose a model from above, which one would you choose and why.
Model Summary Table -1
R R Square Adjusted R Square Std. Error of the Estimate Change Statistics
Model R Square Change F Change df1 df2 Sig. F Change
1 .694a .482 .460 8927.02 .482 21.41 1 23 .000
2 .759b .576 .538 8258.08 .094 4.87 1 22 .038
a Predictors: (Constant), number of rooms
b Predictors: (Constant), number of rooms , assessed value
ANOVA Table -2
Model Sum of Squares df Mean Square F Sig.
1 Regression 1706132093.562 1 1706132093.562 21.409 .000a
Residual 1832909506.438 23 79691717.671
Total 3539041600.000 24
2 Regression 2038729092.558 2 1019364546.279 14.948 .000b
Residual 1500312507.442 22 68196023.066
Total 3539041600.000 24
a Predictors: (Constant), number of rooms
b Predictors: (Constant), number of rooms , assessed value
c Dependent Variable: price charged for house
Coefficients Table -3
Unstandardized Coefficients Standardized Coefficients t Sig.
Model B Std. Error Beta Partial
1 (Constant) 116939.270 8703.932 13.435 .000
number of rooms 9567.167 2067.681 .694 4.627 .000 .694
2 (Constant) 103949.099 9971.443 10.425 .000
number of rooms 8568.479 1965.474 .622 4.359 .000 .681
assessed value .125 .056 .315 2.208 .038 .426
a Dependent Variable: price charged for house
Excluded Variables Table -4
Beta In t Sig. Partial Correlation
Model
1 number of bedrooms .196 .709 .486 .149
number of bathrooms .127 .803 .430 .169
age of building in months .153 .909 .373 .190
assessed value .315 2.208 .038 .426
carpet area in square feet .355 1.691 .105 .339
2 number of bedrooms .092 .349 .730 .076
number of bathrooms .072 .475 .640 .103
age of building in months .212 1.384 .181 .289
carpet area in square feet .219 1.005 .327 .214
a Predictors in the Model: (Constant), number of rooms
b Predictors in the Model: (Constant), number of rooms , assessed value
c Dependent Variable: price charged for house
Model Summary Table 5
R R Square Adjusted R Square Std. Error of the Estimate Change Statistics
Model R Square Change F Change df1 df2 Sig. F Change
A .794 .630 .506 8532.5127 .630 5.102 6 18 .003a
a Predictors: (Constant), carpet area in square feet, age of building in months, number of bathrooms, assessed value of flat, number of bedrooms in flat, number of rooms in flat
ANOVA Table 6
Model Sum of Squares df Mean Square F Sig.
A Regression 2228573701.721 6 371428950.287 5.102 .003a
Residual 1310467898.279 18 72803772.127
Total 3539041600.000 24
a Predictors: (Constant), carpet area in square feet, age of building in months, number of bathrooms, assessed value of flat, number of bedrooms in flat, number of rooms in flat
b Dependent Variable: price charged for flat
Coefficients Table -7
Unstandardized Coefficients Standardized Coefficients T Sig.
Model B Std. Error Beta Partial
A (Constant) 100162.048 11921.851 8.402 .000
number of rooms in flat 4910.839 4326.928 .356 1.135 .271 .258
number of bedrooms in flat 851.934 5650.598 .043 .151 .882 .036
number of bathrooms 2419.742 7058.835 .055 .343 .736 .081
age of building in months 91.181 78.757 .195 1.158 .262 .263
assessed value of flat .111 .067 .280 1.659 .114 .364
carpet area in square feet 12.292 15.172 .186 .810 .428 .188
a Dependent Variable: price charged for flat
Introduction to SPSS
Assignment - I
Assignment Code: 2017DRM04B1 Last Date of Submission: 15th November 2017
Maximum Marks: 100
Attempt all the questions.
SECTION – A (25 marks for each question)
1. a) Explain the steps that are needed in order to enter data in an SPSS file.
b) Explain how data from an Excel file can be imported into an SPSS file. Explain what precautions need to be taken for this.
2. Explain the difference between “Descriptive statistics” and “frequency” and “Explore” options that are available in SPSS when we click the Analyze button.
SECTION-B
Case Study (50 marks)
A company was interested in understanding the level of dissemination of information different between superior group, peer group and subordinate group. The data obtained was analysed using Analysis of variance technique. The results of such an analysis are given below.
measure of dissemination
Levene Statistic df1 df2 Sig.
3.253 2 21 .059
ANOVA
measure of dissemination
Sum of Squares df Mean Square F Sig.
Between Groups 44.645 2 22.323 58.210 .000
Within Groups 8.053 21 .383
Total 52.698 23
Multiple Comparisons
Dependent Variable: measure of dissemination
(I) level of employee (J) level of employee Mean Difference (I-J) Std. Error Sig.
Tukey HSD superior Peer 2.43125(*) .30963 .000
subordinate 3.20000(*) .30963 .000
Peer superior -2.43125(*) .30963 .000
subordinate .76875 .30963 .054
subordinate superior -3.20000(*) .30963 .000
Peer -.76875 .30963 .054
LSD superior Peer 2.43125(*) .30963 .000
subordinate 3.20000(*) .30963 .000
Peer superior -2.43125(*) .30963 .000
subordinate .76875(*) .30963 .022
subordinate superior -3.20000(*) .30963 .000
Peer -.76875(*) .30963 .022
*The mean difference is significant at the .05 level.
Tests of Normality
level of employee Kolmogorov-Smirnov(a) Shapiro-Wilk
Statistic df Sig. Statistic df Sig.
measure of dissemination superior .178 8 .200(*) .958 8 .795
Peer .277 8 .071 .899 8 .282
subordinate .151 8 .200(*) .910 8 .356
* This is a lower bound of the true significance.
a Lilliefors Significance Correction
Based on the above answer the following questions:
a) Write the null and alternative hypothesis for the above problem.
b) For the above analysis, several assumptions have been made. Check from the data given above whether these assumptions are met or not.
c) What is your conclusion based on the ANOVA test carried out?
d) Discuss the post hoc tests that have carried out and its implications.
DRM 04
Introduction to SPSS
Assignment - II
Assignment Code: 2017DRM04B2 Last Date of Submission: 15th November 2017
Maximum Marks: 100
Attempt all the questions.
SECTION-A (25 marks for each question)
1. Enumerate the steps that are required to perform Two way ANOVA with interaction effects.
2. If a data is to be converted from Scale information to Nominal information, discuss the steps by which this could be done in SPSS. For example age is collected from respondents in terms of years and this needs to be converted into “Young (15 to 30years)”, “middle age (31 to 50)” and “old (above 51 years)”. Explain how did data conversion will take place?
SECTION-B (50 marks)
A student after passing out from his MBA course had been placed decently in a reputed organization but was posted in the city of Jaipur which was not his home town. He had also recently got married and therefore needed family accommodation. Even though this salary payable to him by his employer was quite decent, the family nevertheless thought that they need not spend a lot of money in purchasing a flat, especially because the company was providing him free transport from his place of residence to work and back. The family all through being living in a luxury having a spacious flat and therefore decided to purchase an independent house for their stay. As the student had already read considerable amount of Statistics he thought he could estimate what would be the price of an independent house based on the data that he collected on the following variables from nearby locations.
The variables that he had collected data on included:
• Y = Actual sale value of the house (Rs.)
• X1 = Number of rooms
• X2 = number of bedrooms
• X3 = number of baths
• X4 = age of the building in months
• X5 = assessed value (Rs.)
• X6 = area of the house in square feet
He then decided to use SPSS to run a regression model so that he is able to predict what would be the actual sale value of the house based on the various independent variables as mentioned above. He decided to carry out this exercise both Stepwise as well as by incorporating all the independent variables. The relevant output for Stepwise is given in Table 1 to 4 and with all the independent variables in Table 5 to 7.
Questions:
a) To what extent each of the model help in explaining the predictive variable i.e. the price of the house.
b) Explain whether each of the models indicate significant relationship
c) Explain which of the variables help in significantly explaining the predictive variable.
d) How would you determine the relative importance of each of the variables.
e) If you were to choose a model from above, which one would you choose and why.
Model Summary Table -1
R R Square Adjusted R Square Std. Error of the Estimate Change Statistics
Model R Square Change F Change df1 df2 Sig. F Change
1 .694a .482 .460 8927.02 .482 21.41 1 23 .000
2 .759b .576 .538 8258.08 .094 4.87 1 22 .038
a Predictors: (Constant), number of rooms
b Predictors: (Constant), number of rooms , assessed value
ANOVA Table -2
Model Sum of Squares df Mean Square F Sig.
1 Regression 1706132093.562 1 1706132093.562 21.409 .000a
Residual 1832909506.438 23 79691717.671
Total 3539041600.000 24
2 Regression 2038729092.558 2 1019364546.279 14.948 .000b
Residual 1500312507.442 22 68196023.066
Total 3539041600.000 24
a Predictors: (Constant), number of rooms
b Predictors: (Constant), number of rooms , assessed value
c Dependent Variable: price charged for house
Coefficients Table -3
Unstandardized Coefficients Standardized Coefficients t Sig.
Model B Std. Error Beta Partial
1 (Constant) 116939.270 8703.932 13.435 .000
number of rooms 9567.167 2067.681 .694 4.627 .000 .694
2 (Constant) 103949.099 9971.443 10.425 .000
number of rooms 8568.479 1965.474 .622 4.359 .000 .681
assessed value .125 .056 .315 2.208 .038 .426
a Dependent Variable: price charged for house
Excluded Variables Table -4
Beta In t Sig. Partial Correlation
Model
1 number of bedrooms .196 .709 .486 .149
number of bathrooms .127 .803 .430 .169
age of building in months .153 .909 .373 .190
assessed value .315 2.208 .038 .426
carpet area in square feet .355 1.691 .105 .339
2 number of bedrooms .092 .349 .730 .076
number of bathrooms .072 .475 .640 .103
age of building in months .212 1.384 .181 .289
carpet area in square feet .219 1.005 .327 .214
a Predictors in the Model: (Constant), number of rooms
b Predictors in the Model: (Constant), number of rooms , assessed value
c Dependent Variable: price charged for house
Model Summary Table 5
R R Square Adjusted R Square Std. Error of the Estimate Change Statistics
Model R Square Change F Change df1 df2 Sig. F Change
A .794 .630 .506 8532.5127 .630 5.102 6 18 .003a
a Predictors: (Constant), carpet area in square feet, age of building in months, number of bathrooms, assessed value of flat, number of bedrooms in flat, number of rooms in flat
ANOVA Table 6
Model Sum of Squares df Mean Square F Sig.
A Regression 2228573701.721 6 371428950.287 5.102 .003a
Residual 1310467898.279 18 72803772.127
Total 3539041600.000 24
a Predictors: (Constant), carpet area in square feet, age of building in months, number of bathrooms, assessed value of flat, number of bedrooms in flat, number of rooms in flat
b Dependent Variable: price charged for flat
Coefficients Table -7
Unstandardized Coefficients Standardized Coefficients T Sig.
Model B Std. Error Beta Partial
A (Constant) 100162.048 11921.851 8.402 .000
number of rooms in flat 4910.839 4326.928 .356 1.135 .271 .258
number of bedrooms in flat 851.934 5650.598 .043 .151 .882 .036
number of bathrooms 2419.742 7058.835 .055 .343 .736 .081
age of building in months 91.181 78.757 .195 1.158 .262 .263
assessed value of flat .111 .067 .280 1.659 .114 .364
carpet area in square feet 12.292 15.172 .186 .810 .428 .188
a Dependent Variable: price charged for flat
No comments:
Post a Comment