USING RESIDUAL ANALYSIS TO VALIDATE WATERMELON (Citrullus lanatus) DATE OF PLANTING EXPERIMENT MODELS

This research was carried out at the Teaching and Research Farm of the Department of Crop Production and Landscape Management, Ebonyi State University, Abakaliki. The main purpose of this work is to apply the residual analysis to check the suitability of the series of similar experimental model to describe the effects of dates of planting on yield of watermelon with the view of predicting optimum planting date for the cultivation of watermelon.  Four experiments were laid out as series of similar experiments representing the four planting dates (April 4, April 18, May 2 and May 16, 2014). Each experiment consists of three varieties of watermelon (Sugarbaby, Kaolack and F1 Koloss) and three levels of poultry manure (0, 5 and 10kg/ha). The data were separately analyzed for yield for each planting date, where variances were homogenous (i.e. where the experiments showed no significant Bartlett’s test) and this permits the combined analysis of variance for each planting date. The normal probability plots using the residuals showed that it was reasonable to assume that the random errors for the residuals were drawn from approximately normal distributions. Also, the histogram was bell shaped showing that the functional part of the model was correctly specified. The coefficient of determination (R2) was 65.5%. Generally, the results showed that series of similar experiments methodology was able to model the changes associated with different dates of planting. The questions associated with model adequacy were discussed. We recommend F1 Koloss watermelon variety and 5kg/ha poultry manure with early planting which should begin immediately after the first rain provided it is sufficient for field preparations, especially ploughing and harrowing.