Dick
The classical linear regression model assumptions 1. Linear functional form of the relationship 2. Identifiability of the model parameters 3. Expected value of the disturbance given observed information 4. Variances and covariances of the disturbances given observed information 5. Nature of the sample of data on the independent variables 6. Probability distribution of the stochastic part of the model
Upper range=Average X+ (95%)*standard error
Standard error= coefficient/t-statistic
Spurious regression:independent variables can appear to be more significant than they actually are if they have the same underlying trend as the dependent variable.
For example.In country with rampant inflation,almost any nominal variable will appear to be highly correlated with all other nominal variables.Nominal variables are adjusted for inflation, so ,every nominal variable will have a powerful inflationary component. This inflationary component will usually outweigh any real caual relationshop,causing nominal variables to appear to be correlated even if they aren’t.
Two or more variables that is not caused by a real underlying causal relationship. If you run a regression in which the dependent variable and one or more independent variables are spuriously correlated, the result is a spurious regression,and t-scores and overall fit are likely to be overstated and untrustworthy
Cointegration consists of matching the degree of nonstationarity of the variables in an equation in a way that makes the error term and residuals of the equation stationary and rids the equation of any spurious regression results. Even though individual variables might be nonstationary, it is possible for linear combination of nonstationary variables to be stationary.If a long-run equilibrium relationshop exists between a set of variables, those variable are said to be cointegreated
Example
Spot and future price,ratio of relative price and a exchange rate, and equity
Upper range=Average X+ (95%)*standard error
Standard error= coefficient/t-statistic
Spurious regression:independent variables can appear to be more significant than they actually are if they have the same underlying trend as the dependent variable.
For example.In country with rampant inflation,almost any nominal variable will appear to be highly correlated with all other nominal variables.Nominal variables are adjusted for inflation, so ,every nominal variable will have a powerful inflationary component. This inflationary component will usually outweigh any real caual relationshop,causing nominal variables to appear to be correlated even if they aren’t.
Two or more variables that is not caused by a real underlying causal relationship. If you run a regression in which the dependent variable and one or more independent variables are spuriously correlated, the result is a spurious regression,and t-scores and overall fit are likely to be overstated and untrustworthy
Cointegration consists of matching the degree of nonstationarity of the variables in an equation in a way that makes the error term and residuals of the equation stationary and rids the equation of any spurious regression results. Even though individual variables might be nonstationary, it is possible for linear combination of nonstationary variables to be stationary.If a long-run equilibrium relationshop exists between a set of variables, those variable are said to be cointegreated
Example
Spot and future price,ratio of relative price and a exchange rate, and equity