- The odd moment of a standard normal random variable are all zero.

OLS

* The R^{2}

* ESS, error sum of squares/ explained sum of squares

* TSS, total sum of squares

* SSR, sum of squared residuals

* TSS=ESS+SSR

* SER, standard error of the regression

- probability density function
- cumulative distribution function
- conditional distribution
- t-test
- F-test
- Chi-square test
- conditional heterosketicity (prof. ucsd)
- i.i.d., independent identical distribution
- moment
- bayesian
- correlation only tell linear correlation, useless for non-linear relation between 2 variables.
- variance of sample mean $var(\bar{Y})=\frac{\sigma^2}{n}$, $\overline{Y}$is sample mean, n is sample size.

Sep10

Sep. 15

- weak law of large numbers
- OLS

Sep. 22

- Measures of fit

The regression R^{2}

The standard error of regression

Sep. 28

Check P76, 3.4, standard error of Y bar is not the same as standard deviation of Y bar.

- The least square assumption

After class Oct. 21

Central limit theorem wikipedia

Law of large numbers wikipedia

Law of large number and central limit theorem only say relation of mean and expectation. Not imply other statistics moment.

Consistency is for any moment.

Law of large number is necessary but not sufficient condition of central limit theorem. LLN only tells the limit, but no distribution of the mean, as n converges to infinite. CLT tell the information of the distribution.