Application Of Multivariate Technique Of The Analysis Of Statistical Data

ABSTRACT

The main aim of this work or study is to obtain a measure of overall degree of relationship of the yield of cassava and the weather variables namely rainfall, temperature and relative humidity; and construct a model which can be used to predict values of yield of cassava. Secondary data was collected from the office of "Agriculture Development Programme" (ADP) Owerri in Imo State on the effects of rainfall, temperature and relative humidity on the yield of cassava from 1991 to 1999. The matrix approach on multiple regressions is used to analyze the data and a model was set up based on the result. A model 9 = 38.70382072 — 0.01191460491Xi — 0.5206003789X2 —0.0995887962X3, was set up that could be used to predict the yield of cassava base on the annual rainfall (Xi), temperature (X2) and relative humidity (X3) of the area. The model show that the combination of rainfall, temperature and relative humidity have effect in the yield of cassava. Attempt was made to measure the degree of relationship between the variables (correlation theory).