Theses

Browse

Browsing Theses by Subject "Agricultural Statistics"

Now showing 1 - 3 of 3
  • Thumbnail Image
    ThesisItemOpen Access
    Balanced n-ary designs with equal or unequal block size & equal or unequal replications
    (Department of Statistics, College of Veterinary,Mannuthy, 1981) Sujatha, K S; KAU; Surendran, P U
    Tocher (1952) introduced n-ary designs as generalization of balanced incomplete block designs. But the properties of the parameters of the design have not been discussed so far. We have shown that some important properties of the balanced incomplete block binary design are also true in the case of balanced n-ary symmetrical proper equireplicate designs. That is if h =∑jnij2 , λ=∑jnijnpj; in a proper equireplicate balanced design then (i) h > λ (ii) b ≥ v (iii) rk = h+(v-1) λ Among the methods block section, block intersection, complementation and inversion considered by us for the construction of designs the method of complementation is only found fruitful for the construction of proper equireplicate balanced designs. There are situations like comparison of new varieties of seeds of which are in short supply where equal replication of treatments is not possible. There may also be contexts in which the available few animals cannot be used completely for the experiment using conventional designs. For such circumstances we have proposed a systematic method of construction of balanced n-ary designs with equal or unequal replications and equal or unequal block sizes. The method of Kronecker product has been formally introduced to the literature for the construction of proper equireplicate balanced n-ary designs and the methods is contained in the following results. If N1 and N2 are two BIB designs with parameters v, b1, r1, k1, λ1 and v, b2, r2, k2, λ2 respectively, for positive integral values of a1 and a2, a1E(1,b2)xN1+a2N2xE(1,b1) is in general a proper equireplicate n-ary design provided a1+a2+1= n. If N1 and N2 are two balanced proper equireplicate n1-ary and n2-ary designs in v treatments with b1,b2 blocks respectively, for positive integers a1 and a2, a1E(1,b2)xN1+a2N2xE(1, b1)is a n-ary balanced equireplicate proper design with b1b2 blocks where n=a1 (n1-1)+a2(n2-1)+1.
  • Thumbnail Image
    ThesisItemOpen Access
    Price forecast models for coconut and coconut oil
    (College of Horticulture, Vellanikkara, 2016) Indraji, K N; KAU; Laly, John C
    The study on “Price forecast models for coconut and coconut oil” was conducted to estimate seasonal variations in prices of coconut oil, copra and coconut, to evaluate different time series forecast models for prices of coconut oil, copra and coconut and to suggest suitable forecast models for Alappuzha, Kochi and Kozhikode markets. Time series data on monthly average prices of coconut oil and copra for Alappuzha, Kochi and Kozhikode markets from January 1990 to December 2015 and for coconut price at Alappuzha market from January 1998 to December 2015 were collected from Coconut Development Board (CDB), Kochi formed the database.Analysis of price pattern revealed that wide fluctuation exists in the prices of coconut oil and copra at Alappuzha, Kochi and Kozhikode markets and price of coconut at Alappuzha market. For coconut oil and copra price, the coefficient of variation was around 50 per cent indicating the instability in prices and a coefficient of variation of 37 per cent for coconut price showed that variability in price is lower than that of coconut oil and copra. Seasonal indices for the 12 months from January to December showed that December is the peak price month for coconut oil at Alappuzha and Kozhikode markets, whereas it is in January at Kochi. Lowest price is observed in May at Alappuzha and Kozhikode market, whereas, at Kochi it is in July. In all the three markets, September – February is the buoyant phase and price depression is during March - August. For copra, peak price is in December at Alappuzha and Kochi markets, whereas, it is in November at Kozhikode. Trough price for copra is in May in all the three markets. October to February is favourable for copra price in all the three markets, whereas, depressed phase is from March to September. For coconut, peak price at Alappuzha market is in December and the buoyant phase is from November to February. April is the low price month with depressed phase from March to October. During the summer months from March to May, harvest the coconuts as tender and increase the production of neera. Also, during March- September, where the price of coconut oil and copra is low, steps are to be taken to convert coconut into other value added products like desiccated coconut powder, virgin coconut oil, activated carbon etc. and to identify regular markets in major cities of India as also outside India. Different forecast models were fitted viz., Auto regressive Integrated Moving Average (ARIMA), Artificial Neural Network (ANN) and exponential smoothing models (single, double, Holt-Winters’ additive and multiplicative) were fitted and compared for prices of coconut, coconut oil and copra in different market. Holt-Winters’ Multiplicative Seasonal (HWMS) model is the appropriate forecast model for price of coconut oil at Alappuzha and Kochi markets. At Kozhikode market, SARIMA(1,1,1)(1,0,1)12 and HWMS can be used. HWMS model is selected as the suitable forecast model for copra at all markets. ARIMA (0,1,1) model is suitable for forecasting price of coconut at Alappuzha market
  • Thumbnail Image
    ThesisItemOpen Access
    Yield prediction in cocoa (Theobrama cacao L)
    (College of Horticulture, Vellanikkara, 2009) Jayasree, K; KAU; Laly, john C
    The present investigation, “Yield prediction in Cocoa (Theobroma cacao L.)” was undertaken to determine the age at yield stabilization, to identify the optimum range for growth characters and early yield and to identify yield prediction models, if any, based on the growth characters and early yield of cocoa. For this purpose, the data were collected from a progeny trial of the Cadbury-KAU Co-operative Cocoa Research Project, Vellanikkara, pertaining to Forastero variety of cocoa, planted in 1989 under the shade of rubber. Individual plant data on girth (13 years), height (three years), spread (one year) and pod yield (12 years) of 660 plants were analyzed. Graphical method, correlation and regression analyses, analysis of variance, frequency distribution and 95% confidence interval were used. From graphical analyses, it was found that stabilized yield for the plant was obtained from sixth year after planting. Correlation studies established that girth is an important determining factor of yield potential of cocoa. Height in the early years has significant association with girth and yield of the plant. HD2 in the initial year of planting has clear influence on the yield of the plant upto age at yield stabilization. HD2 in the first and second year after planting have clear influence on the yield after stabilization year. Precocity has significant influence on total yield. No model could be obtained for predicting total yield of cocoa based on growth characters with reasonable predictability. There exists optimum for girth at different stages of plant growth and was derived from planting to 12 years after planting, for maximizing yield. The optimum ranges for seedling height and precocity, optimum combination of girth and height of seedlings and optimum combination of initial girth, initial height and precocity was derived, for maximizing yield.