BRM ASSIGNMENT

Group 9

- Pritish Jain (40)

- Annabelle D’Souza (17)
- Pezan Dolasha (38)
- Nimisha Nagpal (35)
- Mahak Sonkar ()
- Ayushi Gaur (08)
- Mehek Kaur Sethi (30)
QUESTION 1
The purpose of factor analysis is to simplify data by minimising the number of dimensions of
individual items. The amount of variance in each variable that is accounted for is shown by
communalities in Factor Analysis.
There are two pre requisites while doing the factor analysis:

1. All the variable should be in ratio or interval Scale

2. All the variable should be co-related to each other

The given data fulfils both the criteria therefore the scale is sufficient to run the factor analysis:

Table 1.1: KMO and Bartlett's Test

Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .744
Bartlett's Test of Sphericity Approx. Chi-Square 359.121
df 78
Sig. .000

Interpretation: The KMO test indicates that the result is 0.744, which is higher than the
minimum, as shown in Table 1.1. 0.50 was required as a cutoff. As a result, the sample size is
sufficient to do the factor analysis. The purpose of Bartlett's Test of Sphericity is to see if the
variables under investigation are linked. The result is significant since the significant value is
0.00. As a result, we can proceed with factor analysis. (p 0.05) p 0.05 p 0.05 p 0.05 p 0.05

Table 1.2: Rotated Component Matri

Component
Communalities Process Appearance Facility
Waiting time 0.657 0.809
Simplified processes 0.616 0.760
Timely resolution of you query 0.557 0.736
Hospitable and friendly employees 0.617 0.658 0.473
Equal facility to all customers 0.694 0.571
Knowledge level of employee 0.817 0.505 0.461
Vicinity of the branch 0.794 0.480
Single counter resolution 0.671 0.406
Ambience 0.287 0.882
Appearance and layout of the branch 0.359 0.859
Cleanliness in the branch 0.481 0.476 0.592
Facility for Senior Citizens 0.615 0.832
Adequate signage and brochures 0.740 0.762
Explained Variance (factors) 60.815 39.899 11.773 9.143
Extraction Method: Principal
Component Analysis.
Rotation Method: Varimax with Kaiser
Normalization.
a. Rotation converged in 7 iterations.
Interpretation: Total Explained Variance (60.815) suggests that three elements, namely
Process, Appearance, and Facility, account for 60% of the variance in the preceding table 1.2.
The Process component accounts for 39.899 percent of the variance, with Appearance
(11.773 percent) and Facility (9.143 percent) following closely behind. The Rotated
Component Matrix is used to determine what the components represent and to gain a better
knowledge of the variable.

QUESTION 2
Hypothesis:

Factor I: Packaging

Ho: Average Sales is same across different packaging types

H1: Average sales is not same across different packaging types

Factor II: Region

Ho: Average Sales is same across different region

H1: Average Sales is different across at least two regions

Interaction Effect

Ho: Average Sales is same across interaction effect.

H1: Average Sales is not same across interaction effect

Measurement Scale: Nominal and Ratio Scale

Table 2.1: Between-Subjects Factors
Value Label N
Type of packaging 1 Plastic 9
2 Glass 11
3 Tetra 10
Region 1 North & Central 10
2 East 10
3 West & South 10

Interpretation: From the table 2.1, we can conclude that values are nearly about
equally distributed among different variables.

Table 2.2: Descriptive Statistics

Dependent Variable: Sales
Type of packaging Region Mean Std. Deviation N
Plastic North & Central 126.67 20.817 3
East 138.33 7.638 3
West & South 119.00 8.544 3
Total 128.00 14.569 9
Glass North & Central 110.00 18.257 4
East 111.50 10.279 4
West & South 99.33 1.155 3
Total 107.64 12.683 11
Tetra North & Central 129.33 16.773 3
East 125.33 5.033 3
West & South 111.75 9.069 4
Total 121.10 12.767 10
Total North & Central 120.80 18.908 10
East 123.70 13.865 10
West & South 110.20 10.497 10
Total 118.23 15.480 30
Interpretation: From Table 2.2, We can analyse that average sale in east region is the
highest and lowest in west & south region.

Table 2.3: Tests of Between-Subjects Effects

Dependent Variable: Sales
Type III Sum of
Source Squares df Mean Square F Sig.
Corrected Model 3640.283a 8 455.035 2.888 .024
Intercept 417300.568 1 417300.568 2648.260 .000
Packaging_Type 2383.960 2 1191.980 7.565 .003
Region 1238.742 2 619.371 3.931 .035
Packaging_Type * Region 210.472 4 52.618 .334 .852
Error 3309.083 21 157.575
Total 426323.000 30
Corrected Total 6949.367 29
a. R Squared = .524 (Adjusted R Squared = .342)

Interpretation: When the kind of packing and the region are examined separately, their
values are significant (p 0.05), but the combined value is inconsequential (Refer Table
2.3). As a result, average sales for different package types are not the same, and average
sales varied across at least two regions.

Table 2.4: Multiple Comparisons

Dependent Variable: Sales
Scheffe

Mean 95% Confidence Interval

(I) Type of packaging (J) Type of packaging Difference (I-J) Std. Error Sig. Lower Bound Upper Bound

Plastic Glass 20.36* 5.642 .006 5.51 35.22

Tetra 6.90 5.768 .500 -8.29 22.09
Glass Plastic -20.36* 5.642 .006 -35.22 -5.51
Tetra -13.46 5.485 .071 -27.91 .98
Tetra Plastic -6.90 5.768 .500 -22.09 8.29
Glass 13.46 5.485 .071 -.98 27.91
Based on observed means.
The error term is Mean Square(Error) = 157.575.
*. The mean difference is significant at the .05 level.
Interpretation: From Table 2.4, We can understand that there is significant difference
between plastic and glass.

Table 2.5: Sales

Scheffea,b,c
Subset

Type of packaging N 1 2

Glass 11 107.64
Tetra 10 121.10 121.10
Plastic 9 128.00
Sig. .080 .484
Means for groups in homogeneous subsets are displayed.
Based on observed means.
The error term is Mean Square(Error) = 157.575.
a. Uses Harmonic Mean Sample Size = 9.933.
b. The group sizes are unequal. The harmonic mean of the group sizes is used. Type I error levels are not guaranteed.
c. Alpha = .05.

Interpretation: The Table 2.5 shows that the marginal mean value for type of
packaging is highest for plastic and lowest for glass.

Table 2.6: Sales

Scheffea,b
Subset

Region N 1

West & South 10 110.20

North & Central 10 120.80
East 10 123.70
Sig. .078
Means for groups in homogeneous subsets are displayed.
Based on observed means.
The error term is Mean Square(Error) = 157.575.
a. Uses Harmonic Mean Sample Size = 10.000.
b. Alpha = .05.
 Interpretation: Table 2.6 indicates that the marginal mean value is highest for the east
region followed by north & central region.

Interpretation: Plastic packaging is having highest mean marginal sale in all the
regions compared to other packaging i.e., glass and tetra pack.

QUESTION 3

Table 3.1: Case Summary

Cases
Valid Missing Total
N Percent N Percent N Percent
$MultRespSmoke a
62 100.0% 0 0.0% 62 100.0%
a. Dichotomy group tabulated at value 1.

Table 3.2: $MultRespSmoke Frequencies

Responses
N Percent Percent of Cases
Why do you smoke?a StressBuster 38 40.9% 61.3%
Networking 24 25.8% 38.7%
OutOfAddiction 29 31.2% 46.8%
PeerPressure 2 2.2% 3.2%
Total 93 100.0% 150.0%
a. Dichotomy group tabulated at value 1.

Interpretation: Table 3.2 shows that 61.3 percent of the 62 respondents cited stress relief
as a cause for smoking, 38.7% cited networking as a reason, 46.8% cited addiction, and 3.2
percent (least) cited peer pressure as a reason for smoking.

QUESTION 4

Table 4.1: Electronic Payment Systems - Representative Data

(Updated as on March 06, 2018)
Volume in
million
IMPS
RTGS NEFT CTS*
*
Data for the
period volu volu volu volu
me Forecast MS me Forecast me Forecast MS me Forecast
sales E sales MSE sales E sales MSE
164. 118.
Jan-17 9.3 #N/A 2 #N/A 5 #N/A 62.4 #N/A
148. 255. 100. 324
Feb-17 9.1 9.3 0.1 2 164.2 4 4 118.5 .5 59.7 62.4 7.15
11. 186. 1030 119. 133 43.5
Mar-17 12.5 9.194713 2 7 154.5984 .7 2 107.6462 .6 67.4 60.81721 0
143. 942. 373
Apr-17 9.5 11.20073 2.7 2 173.8614 0 95.3 114.5815 .4 65.1 64.77457 0.09
155. 34.
May-17 10.4 10.20614 0.1 8 155.4462 0.1 97.1 102.9875 9 66.7 64.95851 3.09
152. 57.
Jun-17 9.8 10.34225 0.3 3 155.6707 11.1 91.9 99.44105 6 65.8 66.01337 0.03
148.
Jul-17 9.4 10.03388 0.4 1 153.6734 30.6 92.2 94.88901 7.2 69.1 65.91132 9.99
151. 61.6
Aug-17 9.5 9.641562 0.0 6 150.3526 1.6 92.1 93.27599 1.5 75.7 67.80757 6
157. 106.
Sep-17 9.6 9.530196 0.0 7 151.1044 43.1 92.2 92.54087 0.1 82.9 72.51904 74
158. 88.4
Oct-17 10.0 9.575703 0.2 8 155.0443 14.0 94.4 92.30969 4.5 88.1 78.7179 4
162. 26.3
Nov-17 10.8 9.829937 1.0 0 157.2859 21.9 96.3 93.58488 7.4 89.5 84.36049 1
169. 111.
Dec-17 10.9 10.42711 0.2 0 160.0953 80.2 94.6 95.21247 0.4 98.0 87.43789 68
170. 33.4
Jan-18 11.2 10.70664 0.2 2 165.468 22.5 96.7 94.82921 3.5 99.6 93.77848 0
165. 17.
Feb-18 10.6 10.97798 0.1 6 168.3156 7.4 91.8 95.95856 1 99.2 97.24619 4.00
189. 74. 38.1
Mar-18 10.76731 1.3 166.6787 3 93.47598 3 98.44566 6
Interpretation: Exponential smoothing is the time series model that was used to forecast
the data for March 2018. Because there is no evident pattern in the data to anticipate future
data, the exponential smoothing method is the best option. RTGS has the least amount of
inaccuracy, which is 1.3, based on a 6 0 percent weightage (Refer Table 4).