Great online book from Harvard edx course on genomics/data science http://genomicsclass.github.io/book/
Great explanation on Sampling , shuffling and bootstraping
For easy, quick and very good notes on applied linear regression, look here:
When you are trying to fit a regression o logistic regression model you have to decide the number of parameters to use in your model. Usually you start with a few of them and add new parameters, or you start with all of them and remove parameters. In any case you decide between succesive models which are a kind of russian dolls in respect to the parameters used(nested parameters models).
In these cases, there are two different approaches to decide which model is better:
- Logistic regression, or models solved using Maximul Likelihood Estimates: In these cases you use one the likelihood ratio, Wald, or Lagrange multiplier (score) tests.
- Ordinary regression (OLS): You use Anova, partial-F tests.
En este articulo se presenta muy claramente la diferencia entre: series temporales, datos de corte transversal y datos panel.
Great list of graduate level science courses (free video courses)
The subjects are:
- 2014/15 « High Energy Physics
- 2014/15 « Mathematics
- 2014/15 « Condensed Matter Phys
- 2014/15 « Earth System Physics
- 2014/15 joint courses
Interesting monograph on dynamic linear models in R:
- Kalman filtering
- AR, VAR
If you need to do time series regression with specified lags you can use this package
to specify the lags you use the lag operator syntax: L(x)
Look at this video from udacity ….it is great: