In: Economics
In terms of econometric perspective, what are the assumptions or elements that you need to consider in developing the model for estimation.
In Econometrics, the models are built keeping in mind certain points in order to generate the correct results for prediction. Below are some assumptions:
- If the researcher wants to apply Ordinary Least Squares techniques of estimation, then the researcher needs to use only the linear parameters in the model. Model would give incorrect results in non-linear parameters are used.
- Research has to assume upfront that the correlation between the independent variables and the error term is zero.
- It is also assumed that on an average, the sum of error term = 0
- There is no multicollinearity i.e.. the independent variables are not related to each other in some way
- there is no autocorrelation i.e. the correlation between error term and its past values are equal to zero
- There is Homoscedasticity: The variance of the error term is constant for all observations. A fluctuating variable would give misleading model results.