| adedis |
adedis computes estimates of the slope coefficients
in a single index model. The coefficents of the
continuous variables are estimated by (an average of)
dwade (density-weighted average derivtive) estimates.
The coefficients of the disrete
explanatory variables are estimated by the method
proposed in Horowitz and Haerdle, JASA 1996.
|
| adeind |
indirect average derivative estimation using binning
|
| adeslp |
slope estimation of average derivatives
using binning
|
| andrews |
andrews calculates the semiparametric estimator proposed
by Andrews and Schafgans (1994) of the intercept coefficients of the outcome
equation in a sample selection model.
|
| dpls |
calculating latent variables, weights, loadings
and path coefficients with dynamic partial least
squares algorithm
|
| dwade |
dwade estimation of the density weighted average derivatives
|
| heckman |
2-step estimation of a regression equation in the
presence of self-selection. Selection rule is of the
probit type (hence, this is a Type 2 Tobit Model in
chapter 10 of Amemiya's Advanced Econometrics).
|
| hhmult |
hhmult calculates the H-H statistic to jointly test the specification
of the link functions of a polychotomous response model
(such as the conditional logit model or the multinomial
logit model)
|
| hhtest |
hhtest calculates the H-H statistic to test the specifi-
cation of the link function of a generalized linear
model (such as the logit or probit model), assuming
the index is correctly specified.
|
| lts |
Computes the least trimmed squares estimate for the
coefficients of a linear model.
|
| makedesign |
generates with help of userdialog design matrices
for the dpls macro (dynamic partial least
squares algorithm)
|
| metricsmain |
loads the quantlibs needed by the quantlets in the
metrics quantlib
|
| metricstest |
executes some tests for the macros defined
in metrics.lib Is invoked by vertest().
|
| ndw |
ndw is an auxiliary macro of adedis. It defines
the nadaraya watson estimate of the link as a function
of the (estimated) index of continuous explanatory
variables. In adedis the simpsonint routine is used to
integrate over this function.
|
| newadeslp |
slope estimation of average derivatives
|
| pancoint |
Computes FM-OLS estimates for cointegration equations
with homogenous cointegration parameters and heterogeneous
short-run dynamics and deterministics
|
| pandyn |
Estimaties dynamic panel data model with GMM
|
| pandyn2 |
2nd Step of the 2-stage dynamic GMM
|
| panfix |
Estimation of a static Fixed-Effects-Modell
|
| panhaus |
Hausman Test for a correlation between the
regressors and the individual effects
|
| panlag |
Computes the lag of the variable
|
| panrand |
Estimation of a static Random-Effects-Modell
|
| pansort |
|
| panstats |
Computes summary statistics of the variables
|
| pantime |
Subtracts the mean of period t
from the model variables.
Purpose: Accounting for fixed time effects
|
| panunit |
Computes unit root statistics for panel data
|
| powell |
powell calculates the semiparametric estimator proposed
by Powell (1987) of the slope coefficients of the outcome
equation in a sample selection model.
|
| redun |
calculating single redundance and redundance vector
for dpls macro as measure for goodness
|
| rqfit |
Performs quantile regression of y on x using the original simplex
approach of Barrodale-Roberts/Koenker-d'Orey.
|
| rrstest |
Computes the regression rankscore test of a linear
hypothesis based on the dual quantile regression process.
It tests the hypothesis that b1 = 0 in the quantile
regression model y = x0'b0 + x1'b1 + u.
Test statistic is asymptotically Chi-squared with rank(x1)
degrees of freedom.
|
| select |
select calculates semiparametric estimators of the
intercept and slope coefficients in the "outcome" or "level" equation
of a self-selection model. select is therefore the second stage
of the two-stage procedure used to estimate these models.
select does not estimate the coefficients of the "selection" or "decision"
equation but requires that the estimated first-step "index"
be given as an input. The procedure to estimate the slope coefficients
is desribed in Powell (1987). The procedure to estimate the intercept
coefficient is desribed in Andrews and Schafgans (1994).
select combines the powell and andrews macros of the metrics library.
|
| seq |
Estimates a simultaneous equations model by 3-stage least squares
|
| sir |
Calculates the effective dimension-reduction (edr)
directions by Sliced Inverse Regression (Li, 1991)
|
| sir1 |
This macro is the taylored Sliced Inverse Regression method
for the "sssm" macro.
Here, the macro "sir1" builds a special slice which contains
the cases such that y=0 (the value "0" for y symbolically
indicates a missing value). Then, nbslices (by default,
nbslices=5) other slices are made by splitting the range of
the non missing y's into slices of nearly equal weight (i.e.
such that they contain nearly the same number of cases).
The classical algorithm of S.I.R. is then used with this
special slicing.
|
| sir2 |
Calculates the effective dimension-reduction (edr)
directions by Sliced Inverse Regression II (Li, 1991)
|
| sssm |
computes the estimates of the slope vectors in the outcome
equation and in the selection equation for a
semiparametric sample selection model (SSSM).
This is a two-stages estimation method:
the first one is a taylored Sliced Inverse Regression (S.I.R.)
analysis,
and, in the second one, two Canonical analyses are conducted
in order to convert the estimated EDR directions into
estimates of the slopes.
The identifiability conditions have to be verified:
there exists a component of the explanatory variable X
which affects the selection and does not affect the
outcome, and there also exists another component of X
which affects the outcome and does not affect the selection.
If these identifiability conditions are not verified,
the program stops.
Moreover, the number of explanatory variables for the
selection (resp. outcome) equation must be greater
or equal than 2.
|
| sur |
Estimates a seemingly unrelated regression system by feasible generalized least squares
|
| tobit |
2-step estimation of a Tobit model
|
| trimper |
trims a given percentage of a (binned) data matrix
|
| wtsder |
computes the weights for derivative estimation for
the use with the quatric kernel
in the context of binning
|