Question

While the simple regression model which is based on a linear relation between Y and X, in large part because estimating the parameters of a linear model is relatively simple statistically; for those cases where Y and X are instead related in a curvilinear fashion, a simple transformation of the variables often makes it possible to model nonlinear relations within the framework of the linear regression model. Select one:

True

False

Answer 1

TRUE.

Regression analysis can be done more easily if all the variables in the model are linear However, this is not true in the real life. Most of the variables are related to each other in a non-linear way. For example, y variable is dependent on square of x or the log of x.

These models, however, are complex and simple linear regression would fail in making any conclusions. In fact, OLS method assumes linearity in the regression parameters.

If is possible to convert non-linear relations into linear through some non-linear transformations. We can take log or exponential of the original model to make it linear or the variables can be divided by variance or square roots to obtain linearity.