Abstract:
One of the major problems of multiple linear regression analysis is multicollinearity of
the independent variables. The existence of mult
icollineariity on climate variables such
as relative humidity, solar radiation, rainfall, sunshine and temperature on the response
of agricultural output may lead to inflation of standard error of the regression
coefficients or false non
-
significant p
-
valu
e. In this study, monthly data spanning from
1980
-
2012 obtained from the Nigeria Institute for Oil Palm Research (NIFOR) on
relative humidity, solar radiation, rainfall, sunshine, temperature and oil palm yield
were used to examine the probable effects of
climate conditions/climate change would
have on oil palm yield
.
The estimation of parameters of climatic variables in multiple
linear regression appears to have suffered severe distortions due to multicollinearity.
This research study resort to principal
component regression
, ridge regression
and
stepwise regression
to stabilized the parameter estimate
.
Ridge regression was used to
estimate the effect of c
limate conditions
on oil palm yield because it performed
better
than others due to
its lower measure o
f accuracy. It was observed that average relative
humidity and rainfall had positive significant effect while solar radiation, mean
sunshine hour and average air temperature had negative significant effect on oil palm
yield.
