Factor analysis was carried out on the data set (10 variables) to compare the

compositional patterns between the water samples analyzed and to identify the
related factors that influence each of them. Four factors were extracted
explaining more than 53 % of the total variance in the water quality data set.
Eigenvalues were taken as criterion for the extraction of the principal components
required for explaining the source of variances in the data set.

The Scree plot, as Scree plot

shown in Figure , has
2.5 100
worked out to clarify
the method of
2 80
extraction of
Cumulative variability (%)

different factors.
The factor analysis 1.5 60
Eigenvalue

was actually
performed on the 1 40
correlation matrix
between different 0.5 20
parameters
followed by Varimax 0 0
rotation and the F1 F2 F3 F4 F5 F6 F7
same has been used axis
to examine their
inter relationship. The parameter loadings for the four identified factors from the
factor analysis of the data are given in Table . The factor 1 accounts for 22.63 % of
the total variance. It is positively correlated (loading > 0.70) with pH, Salinity,
dissolved oxygen, silicate and COD . Factor 2, on the other hand, explains 15.88%
of the total variance and is negatively loaded with DO, Turbidity and Nitrate. The
third factor represents 8.01% of the total variance related to Salinity & Nitrate
(positively correlated the fourth factor represents negative correlation with
Phosphate, COD & BOD. Factor loading plot (Figure 4) after varimax rotation
revealed that the Salinity, COD and BOD a concentration are showing positive
loading whereas turbidity, Phosphate and nitrate concentration showing negative
loading.

Factor loadings (axes F1 and F2: 38.51 %)

0.4 COD
BOD Salinity
0.2

0
F2 (15.88 %)

-0.2 Phosphate Temparature

Silicate
pH

-0.4
Turbidity

-0.6
DO

-0.8
Nitrate

-1
-1 -0.8 -0.6 -0.4 -0.2 0 0.2 0.4 0.6 0.8
F1 (22.63 %)