Question

I would like to ask if you know any R packages with data to do linear econometric model (least squares method). I must have 5-7 variables (some of them can occur insignificant later). I should check heteroscedascity, autocorelation, catalysis etc. Mayby you can recommend me data from other source f.e. other math program data package?

Answer 1

A cool package on CRAN: http://cran.r-project.org/web/packages/HistData/index.html

The `HistData’ package provides a
collection of small data sets that are
interesting and important in the
history of statistics and data
visualization. The goal of the package
is to make these available, both for
instructional use and for historical
research. Some of these present
interesting challenges for graphics or
analysis in R.

[Insert apologies for shameless self-promotion here] You could also use the WDI package to download data from the World Bank’s World Development indicators. For instance, here’s a least squares regression of GDP per capita on trade as a % of GDP and the density of a country’s road network.

library(WDI)
ind <- c('NY.GDP.PCAP.CD', 'NE.TRD.GNFS.ZS', 'IS.ROD.DNST.K2')
dat <- WDI(country='all', start=2002, end=2002, indicator=ind)
names(dat) <- c('country', 'iso2c', 'year', 'gdp.per.cap', 'trade.to.gdp', 'roads')
mod <- lm(gdp.per.cap ~ trade.to.gdp + roads, dat)
summary(mod)

You can search for new data with keywords:

WDIsearch('forest')

http://cran.r-project.org/web/packages/WDI/index.html