Details

Autor(en) / Beteiligte

• Yadav, Anil Kumar
• Kartikeyan, M
• Raman, Rohan Kumar
• Das, Basant Kumar
• Jha, Dharm Nath
• Sahu, Sanjeev Kumar

Titel

Analysis of Variance (ANOVA) and Design of Experiments

Ist Teil von

• Concept Building in Fisheries Data Analysis, 2022, p.119-136

Ort / Verlag

Singapore: Springer

Erscheinungsjahr

2022

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Many experiments in fisheries science involve more than two treatment groups. We must not use t-test to compare more than two groups because multiple t-tests performed on the same data set increase likelihood of falsely reporting a significant difference. For testing the significance of means of several independent groups of observations, a powerful parametric statistical approach is analysis of variance (ANOVA). It was developed by one of the founders of modern statistical theory, Sir Ronald Fisher, in the 1920s. It assesses potential differences in a continuous-level (interval/ratio) dependent variable by a categorical-level (nominal/ordinal) independent variable having two or more categories. For example, an ANOVA can examine potential differences in fish yield of beels by stocking density or macrophyte infestation (low vs. moderate vs. high). The two main aims of classical ANOVA are (1) to examine the relative contribution of different sources of variation (factors or combination of factors, i.e. predictor variables) to the total amount of variability in the response variable and (2) to test the null hypothesis that population groups or treatment means are equal. In this chapter, assumptions of ANOVA, one-way ANOVA, two-way ANOVA, post hoc tests, repeated measures ANOVA and design of experiments with examples on inland fisheries will be discussed. The computations are involved in partitioning of total amount of variability in response variable into explained (treatments or factors or combination of factors) and unexplained variability (residual). Excel/SPSS has been demonstrated to carrying out ANOVA.