*4.3.2 Multiple sample comparison on the west to east direction profiles*

Consequent upon the results of the above t-test in Section 4.3, the six profile sections were further subjected to a robust multiple comparison statistical test. This procedure compares the data in 12 columns of the dataset file. It constructs various statistical tests—F-test, analysis of variance (ANOVA), multiple range tests and variance check (**Tables 3**–**6**) to compare the significant changes along each of the profile lines. ANOVA test was used in order to examine and analyse the variance between and within the different profile lines.

The F-test in the ANOVA table (**Table 3**) tests whether there are any significant differences among the means. The ANOVA table decomposes the variance of the data into two components: a between-group component and a within-group component. The F-ratio that in this case equals to 11.08 is a ratio of the between-group estimate to the within-group estimate. Since the p-value of the F-test is less than


#### **Table 3.** *ANOVA table for multiple sample comparison.*


*Morphodynamics in a Tropical Shallow Lagoon: Observation and Inferences of Change DOI: http://dx.doi.org/10.5772/intechopen.90189*

confirmed by visual observation during data collection, as serious local dredging was going on in the area by those who are constructing near the lagoon bank.

In testing the hypothesis, a t-test was conducted to compare the mean values of depths of the two sample data (2008 and 2014 data). The result of the test, that is, the calculated t-test, is in **Table 2**. The tabulated values of t-statistics, p-value and confidence interval were calculated for each of the profiles established on the coverage area of the lagoon at 95% confidence level, which is the probability of

The six profiles considered along with the direction west to east have different calculated t-values (measure the size of the difference relative to the variation in sample data) and p-values (calculated probability) even though they were all computed with the same confidence interval, and this may be evident that the changes along each profile section are not the same. Only profile line A-A<sup>0</sup> has a p-value that is less than 0.05; hence, the null hypothesis is rejected meaning that there is significant variation in the depth range of the 2008 data and that of 2014. The remaining five profiles have p-value greater than 0.05; it implies that there is no significant difference on the changes along each of the profile line, and there could be changes inherent in the profiles that needed a further test to discover it. Hence, the null hypothesis is rejected for profile A-A<sup>0</sup> and conversely accepted for the five profile

. The implication is that there was significant change along

) and it is different from the rest of the profiles B to F.

Consequent upon the results of the above t-test in Section 4.3, the six profile sections were further subjected to a robust multiple comparison statistical test. This procedure compares the data in 12 columns of the dataset file. It constructs various statistical tests—F-test, analysis of variance (ANOVA), multiple range tests and variance check (**Tables 3**–**6**) to compare the significant changes along each of the profile lines. ANOVA test was used in order to examine and analyse the variance

The F-test in the ANOVA table (**Table 3**) tests whether there are any significant differences among the means. The ANOVA table decomposes the variance of the data into two components: a between-group component and a within-group component. The F-ratio that in this case equals to 11.08 is a ratio of the between-group estimate to the within-group estimate. Since the p-value of the F-test is less than

**Source Sum of squares Df Mean square F-Ratio P-Value** Between groups 215.41 11 19.5828 **11.08 0.0000\***

*4.3.2 Multiple sample comparison on the west to east direction profiles*

between and within the different profile lines.

Total (Corr.) 763.222 321

*\*denotes a statistically significant difference.*

*ANOVA table for multiple sample comparison.*

**Table 3.**

**92**

Within groups 547.811 310 1.76713

**4.3 Statistical comparison of profiles**

*Lagoon Environments Around the World - A Scientific Perspective*

making a correct assertion.

*4.3.1 Decision on the hypothesis*

lines from B-B<sup>0</sup> to F-F<sup>0</sup>

this profile (A-A<sup>0</sup>
