12.1 The Nature of Autocorrelation 1. Definition (1) CLRM assumption: No autocorrelation exist in dishurbances ui; E(iμi)=0 Autocorrelation means: E(μiμ)≠0 (2) Autocorrelation is usually associated with time series data, but it can also occur in cross-sectional data, which is called spatial correlation

The models we discussed are models that are linear in parameters; variables Y and Xs do not necessarily have to be linear The price elasticity of demand~the log-linear models The rate of growth~semilog model Functional forms of regression models which are linear in parameters, but not necessarily linear in variables:

Definition (1) Econometrics: economic measurement. (2) Econometrics: the social science in which the tools of economic theory, mathematics, and statistical inference are applied to the analysis of economic phenomena. (3) Econometrics: the result of a certain outlook on the role of economics, consists of the application of mathematical statistics to economic data to lend

The Normal Distribution: the distribution of a continuous r.v. whose value depends on a number of factors, yet no single factor dominates the other. 1. Properties of the normal distribution: 1)The normal distribution curve is symmetrical around its mean valueu. 2)The PDF of the distribution is the highest at its mean value but tails off at its extremities

Redefining variables Changing the scale of the y variable will lead to a corresponding change in the scale of the coefficients and standard errors. so no change in the significance or interpretation Changing the scale of one x variable will lead to a change in the scale of that coefficient and standard error, so no change in the significance or interpretation Economics 20- Prof anderson

Dummy variables a dummy variable is a variable that takes on the value l or o Examples: male(= 1 if are male, O otherwise), south(=l if in the south, 0 otherwise), etc dummy variables are also called binar variables. for obvious reasons Economics 20- Prof anderson

What is Heteroskedasticity Recall the assumption of homoskedastic implied that conditional on the explanator variables the variance of the unobserved error u was constant If this is not true that is if the variance of u is different for different values of thex's. then the errors are heteroskedastic

Time series vs Cross sectional e Time series data has a temporal ordering unlike cross-section data Will need to alter some of our assumptions to take into account that we no longer have a random sample of individuals Instead. we have one realization of a stochastic(i.e. random) process Economics 20- Prof anderson

Testing for AR(IS eria Correlation Want to be able to test for whether the errors are serially correlated or not Want to test the null thatp=0 in u,=pu, 1 +et=2.. where u is the model error

Fixed Effects estimation When there is an observed fixed effect. an alternative to first differences is fixed effects estimation Consider the average over time of y Bx1+…+Bxik+a1+l The average of a, will be ai so if you subtract the mean. a will be differenced out just as when doing first differences Economics 20- Prof anderson