PanelWithin: within transformation. PanelResiduals: pooled,
within or unit-by-unit OLS residuals. PanelVarianceComponents:
quadratic-form (Wallace-Hussain or Amemiya) error-component variances for a
balanced panel. CrossSectionDependence: Pesaran CD, Breusch-Pagan LM,
scaled and bias-corrected scaled LM tests and mean (absolute) residual
correlations. UnobservedEffectsTest: Wooldridge's test for unobserved
effects. BaltagiLiTest: Baltagi-Li LM test for AR(1)/MA(1) errors in
the random-effects model (maximum likelihood by the Breusch iteration).
PanelSerialTest: Breusch-Godfrey/Wooldridge test on within
residuals. ConleyVcov: Conley spatial HAC covariance of OLS
coefficients (uniform or Bartlett kernel on haversine distances, or the
fixest approximations). Rows must be sorted by unit and time.
Identical to the Python arm morie.fn.paneldiag.
Usage
PanelWithin(x, unit)
PanelResiduals(y, X, unit, model = "pooling")
PanelVarianceComponents(resid, unit, df_correction = 0)
CrossSectionDependence(resid, unit, time, test = "cd", w = NULL)
UnobservedEffectsTest(resid, unit)
BaltagiLiTest(y, X, unit, alternative = "twosided")
PanelSerialTest(y, X, unit, order = NULL, type = "Chisq")
ConleyVcov(
X,
resid,
lat,
lon,
cutoff,
kernel = "uniform",
distance = "haversine",
intercept = TRUE,
adjust = TRUE
)Arguments
- x
Vector or matrix to demean.
- unit
Unit identifiers.
- y
Response vector.
- X
Regressor matrix (without intercept).
- model
"pooling","within"or"heterogeneous".- resid
Residual vector.
- df_correction
Degrees of freedom subtracted from
N(T-1).- time
Period identifiers.
- test
"cd","lm","sclm","bcsclm","rho"or"absrho".- w
Optional proximity matrix restricting the unit pairs.
- alternative
"twosided"or"onesided".- order
Serial-correlation order (default: shortest unit length).
- type
"Chisq"or"F".- lat, lon
Coordinates in decimal degrees.
- cutoff
Distance cutoff in km.
- kernel
"uniform"or"bartlett".- distance
"haversine","fixest_triangular"or"fixest_spherical".- intercept
Add an intercept column to
X.- adjust
Multiply by
n / (n - k).
References
Pesaran, M. H. (2004). General diagnostic tests for cross section dependence in panels. CESifo Working Paper 1229.
Baltagi, B. H. and Li, Q. (1995). Testing AR(1) against MA(1) disturbances in an error component model. Journal of Econometrics 68, 133-151.
Wooldridge, J. M. (2010). Econometric Analysis of Cross Section and Panel Data, 2nd edn. MIT Press.
Conley, T. G. (1999). GMM estimation with cross sectional dependence. Journal of Econometrics 92, 1-45.