plot.panelAR: Plot Panel Structure

In panelAR: Estimation of Linear AR(1) Panel Data Models with Cross-Sectional Heteroskedasticity and/or Correlation

Description

Plots grid of panels and times, colored to distinguish observed and missing data.

Usage

## S3 method for class 'panelAR'
plot(x,legend=TRUE,rot.axis=c(0,0),...)

Arguments

x	an object of class "panelAR".
legend	logical. If TRUE, legend is printed.
rot.axis	vector of degrees for rotation of axis labels. First element corresponds to time labels and second element corresponds to panel labels.
...	further arguments passed to or from other methods.

Author(s)

Konstantin Kashin [e-mail]

See Also

panelAR.

Examples

data(WhittenWilliams)
# expect warning urging to use 'complete.case=FALSE'
out <- panelAR(milex_gdp~lag_milex_gdp+GOV_rl+gthreat+GOV_min+GOV_npty+election_yr+
lag_real_GDP_gr+cinclag+lag_alliance+lag_cinc_ratio+lag_us_change_milex_gdp, 
data=WhittenWilliams, panelVar="ccode", timeVar="year", autoCorr="psar1", 
panelCorrMethod="pcse", complete.case=TRUE)

par(cex.axis=0.6)
plot(out, rot.axis=c(45,0))

Example output

The following units have non-consecutive observations. Use runs.analysis() on output for additional details: 235.
Warning message:
The number of time periods used for the calculation of correlated SEs / PCSEs (18) is less than half the average number of time periods per panel (40.84). Consider setting complete.case=FALSE. 

panelAR documentation built on May 1, 2019, 8:19 p.m.