Employment, wages, capital, and output for companies based in the UK

Description

Unbalanced panel dataset of 140 firms from different sectors located in the UK which were observed over the years 1976 until 1984. The dataset contains the variables firm, year, sector, employment, wages, capital, and output and was used in Arellano and Bond (1991) which also provides more details on the different variables.

Usage

data(ABdata)

Format

A dataset with 1031 rows and 7 variables containing:

firm

firm identifier

year

year

sector

sector

emp

number of firm employees in the UK

wage

real wage

capital

gross capital stock

output

industry output

References

Arellano M, Bond S (1991). “Some Tests of Specification for Panel Data: Monte Carlo Evidence and an Application to Employment Equations.” The Review of Economic Studies, 58(2), 277–297. doi:10.2307/2297968.

Examples

## Not run: 
  data(ABdata, package = "pdynmc")
  n <- ABdata$emp
  w <- ABdata$wage
  \donttest{plot(y = n, x = w)}

## End(Not run)

First Difference Least Squares (FDLS) Estimator of Han and Phillips (2010).

Description

FDLS computes closed form estimator for lag parameter of linear dynamic panel data model based on first difference least squares (FDLS) estimator.

Usage

FDLS(dat, varname.i, varname.t, varname.y)

Arguments

Details

The function estimates a linear dynamic panel data model of the form

y_{i,t} = y_{i,t-1} \rho_1 + a_i + \varepsilon_{i,t}

where y_{i,t-1} is the lagged dependent variable, \rho_1 is the lag parameter, a_i is an unobserved individual specific effect, and \varepsilon_{i,t} is an idiosyncratic remainder component. The model structure accounts for unobserved individual specific heterogeneity and dynamics. Note that more general lag structures and further covariates are beyond the scope of the current implementation in pdynmc.

More details on the FDLS estimator and its properties are provided in Han and Phillips (2010).

Value

An object of class 'numeric' that contains the coefficient estimate for the lag parameter according to the two roots of the quadratic equation.

Author(s)

Joachim Schnurbus, Markus Fritsch

References

Han C, Phillips PCB (2010). “GMM Estimation For Dynamic Panels With Fixed Effects And Strong Instruments At Unity.” Econometric Theory, 26(1), 119–151. doi:10.1017/S026646660909063X.

Examples

## Load data
data(cigDemand, package = "pdynmc")
dat <- cigDemand

## Code example
m1 <- FDLS(dat = dat, varname.i = "state", varname.t = "year", varname.y = "packpc")

Nonlinear Instrumental Variables Estimator - T-Version (NLIV).

Description

NLIV Computes closed form solution for lag parameter of linear dynamic panel data model based on instrumental variables (IV) estimator employing nonlinear moment conditions.

Usage

NLIV(dat, varname.i, varname.t, varname.y)

Arguments

Details

The function estimates a linear dynamic panel data model of the form

y_{i,t} = y_{i,t-1} \rho_1 + a_i + \varepsilon_{i,t}

where y_{i,t-1} is the lagged dependent variable, \rho_1 is the lag parameter, a_i is an unobserved individual specific effect, and \varepsilon_{i,t} is an idiosyncratic remainder component. The model structure accounts for unobserved individual specific heterogeneity and dynamics. Note that more general lag structures and further covariates are beyond the scope of the current implementation in pdynmc.

The nonlinear IV estimator employs the original version of the nonlinear moment conditions of Ahn and Schmidt (1995). More details on the implementation and the properties of the estimator are provided in Fritsch et al. (2024).

Value

An object of class 'numeric' that contains the coefficient estimate for the lag parameter according to the two roots of the quadratic equation.

Author(s)

Joachim Schnurbus, Markus Fritsch

References

Ahn SC, Schmidt P (1995). “Efficient estimation of models for dynamic panel data.” Journal of Econometrics, 68(1), 5–27. doi:10.1016/0304-4076(94)01641-C.

Fritsch M, Pua AAY, Schnurbus J (2024). “Properties of an estimator for linear dynamic panel data models based on nonlinear moment conditions.” Working Paper.

Examples

## Load data
data(cigDemand, package = "pdynmc")
dat <- cigDemand

## Code example
m1 <- NLIV(dat = dat, varname.i = "state", varname.t = "year", varname.y = "packpc")

Nonlinear Instrumental Variables Estimator - t-Version (NLIV.alt).

Description

NLIV.alt Computes closed form solution for lag parameter of linear dynamic panel data model based on instrumental variables (IV) estimator employing alternative formulation of nonlinear moment conditions.

Usage

NLIV.alt(dat, varname.i, varname.t, varname.y)

Arguments

Details

The function estimates a linear dynamic panel data model of the form

y_{i,t} = y_{i,t-1} \rho_1 + a_i + \varepsilon_{i,t}

where y_{i,t-1} is the lagged dependent variable, \rho_1 is the lag parameter, a_i is an unobserved individual specific effect, and \varepsilon_{i,t} is an idiosyncratic remainder component. The model structure accounts for unobserved individual specific heterogeneity and dynamics. Note that more general lag structures and further covariates are beyond the scope of the current implementation in pdynmc.

The nonlinear IV estimator employs an alternative formulation of the nonlinear moment conditions of Ahn and Schmidt (1995). More details on the implementation and the properties of the estimator are provided in Fritsch et al. (2024).

Value

An object of class 'numeric' that contains the coefficient estimate for the lag parameter according to the two roots of the quadratic equation.

Author(s)

Joachim Schnurbus, Markus Fritsch

References

Ahn SC, Schmidt P (1995). “Efficient estimation of models for dynamic panel data.” Journal of Econometrics, 68(1), 5–27. doi:10.1016/0304-4076(94)01641-C.

Fritsch M, Pua AAY, Schnurbus J (2024). “Properties of an estimator for linear dynamic panel data models based on nonlinear moment conditions.” Working Paper.

Examples

## Load data
data(cigDemand, package = "pdynmc")
dat <- cigDemand

## Code example
m1 <- NLIV.alt(dat = dat, varname.i = "state", varname.t = "year", varname.y = "packpc")

Case and Variable Names of Fitted Model.

Description

case.names extracts variable names of cross-sectional and longitudinal identifiers of an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
case.names(object, ...)

Arguments

Value

A list containing tow character vectors with the variable names of the cross-sectional and the longitudinal identifiers from object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
case.names(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 case.names(m1)

Cigarette consumption in the US

Description

Balanced panel dataset on annual cigarette consumption in the US for the 48 continental states in the years 1985 until 1995. The dataset is available from Stock and Watson (2003) and used in Stock and Watson (2019) and Fritsch et al. (2024). Gratitude is owed to Jonathan Gruber of MIT for providing the data.

Usage

data(cigDemand)

Format

A dataset with 528 rows and 9 variables containing:

state

state

year

year

cpi

consumer price index (US)

pop

state population

packpc

number of cigarette packs sold per capita and year

income

state personal income (total, nominal)

tax

average federal, state, and local excise taxes on cigarettes for fiscal year in cents per pack

avgprs

average price during fiscal year in cents per pack (including sales taxes)

taxs

average excise tax for fiscal year in cents per pack (including sales taxes)

References

Fritsch M, Pua AAY, Schnurbus J (2024). “Teaching Advanced Topics in Econometrics using Introductory Textbooks: The Case of Dynamic Panel Data Methods.” Working Paper.

Stock JH, Watson MM (2019). Introduction to Econometrics, Fourth edition. Pearson.

Stock JH, Watson MW (2003). “cig_ ch10, cig85_95, Instructional Stata datasets for econometrics cig8595.” https://ideas.repec.org/p/boc/bocins/cig8595.html.

Examples

## Not run: 
  data(cigDemand, package = "pdynmc")
  packs <- cigDemand$packpc
  tax <- cigDemand$tax
  \donttest{plot(y = packs, x = tax)}

## End(Not run)

Extract Coefficient Estimates of Fitted Model.

Description

coef.pdynmc extracts coefficient estimates of an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
coef(object, ...)

Arguments

Value

Extract coefficient estimates from object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
coef(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 coef(m1)

Show Basic Structure of Panel Dataset.

Description

data.info shows basic structure of a balanced/unbalanced panel dataset contained in a 'data.frame'.

Usage

data.info(object, i.name = NULL, t.name = NULL, ...)

Arguments

Value

Returns information if panel dataset contained in an object of class 'data.frame' is a balanced or unbalanced panel dataset.

Author(s)

Markus Fritsch, Joachim Schnurbus

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
data.info(dat, i.name = "firm", t.name = "year")

data.info(dat[dat$year %in% 1979:1981, ], i.name = "firm", t.name = "year")

Extract Coefficient Estimates of Time Dummies of Fitted Model.

Description

dummy.coef.pdynmc extracts coefficient estimates of time dummies of an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
dummy.coef(object, ...)

Arguments

Value

Extract coefficient estimates of time dummies from object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
dummy.coef(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 dummy.coef(m1)

Extract Fitted Values of Fitted Model.

Description

fitted.pdynmc extracts fitted values of an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
fitted(object, step = object$iter, na.rm = FALSE, ...)

Arguments

Value

Extract fitted values from object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
fitted(m1, na.rm = TRUE)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 fitted(m1, na.rm = TRUE)

Hansen J-Test.

Description

jtest.fct tests the validity of the overidentifying restrictions.

Usage

jtest.fct(object)

Arguments

Details

The null hypothesis is that the overidentifying restrictions are valid. The test statistic is computed as proposed by Hansen (1982). As noted by Bowsher (2002) and Windmeijer (2005) the test statistic is weakened by many instruments.

Value

An object of class 'htest' which contains the Hansen J-test statistic and corresponding p-value for the null hypothesis that the overidentifying restrictions are valid.

References

Bowsher CG (2002). “On testing overidentifying restrictions in dynamic panel data models.” Economics Letters, 77(2), 211–220. doi:10.1016/S0165-1765(02)00130-1.

Hansen LP (1982). “Large Sample Properties of Generalized Method of Moments Estimators.” Econometrica, 50(4), 1029–1054. doi:10.2307/1912775.

Windmeijer F (2005). “A finite sample correction for the variance of linear efficient two-step GMM estimators.” Journal of Econometrics, 126(1), 25–51. doi:10.1016/j.jeconom.2004.02.005.

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(140:0), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
jtest.fct(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 jtest.fct(m1)

Extract Instrument Matrix of Fitted Model.

Description

model.matrix.pdynmc extracts instrument matrix of an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
model.matrix(object, sparse = TRUE, ...)

Arguments

Value

Extracts instrument matrix from an object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
model.matrix(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 model.matrix(m1)

Arellano and Bond Serial Correlation Test.

Description

mtest.pdynmc Methods to test for serial correlation in the error terms for objects of class 'pdynmc'.

Usage

mtest.fct(object, order = 2, ...)

Arguments

Details

The null hypothesis is that there is no serial correlation of a particular order. The test statistic is computed as proposed by Arellano and Bond (1991) and Arellano (2003).

Value

An object of class 'htest' which contains the Arellano and Bond m test statistic and corresponding p-value for the null hypothesis that there is no serial correlation of the given order.

References

Arellano M (2003). Panel Data Econometrics. Oxford University Press. doi:10.1093/0199245282.001.0001.

Arellano M, Bond S (1991). “Some Tests of Specification for Panel Data: Monte Carlo Evidence and an Application to Employment Equations.” The Review of Economic Studies, 58(2), 277–297. doi:10.2307/2297968.

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(140:0), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
mtest.fct(m1, order = 2)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 mtest.fct(m1, order = 2)

Extract Instrument Count of Fitted Model.

Description

ninst is a generic function fo extracting the instrument count of an object.

Usage

ninst(object, ...)

Arguments

Value

Extracts instrument count from an object.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
ninst(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 ninst(m1)

Extract Instrument Count of Fitted Model.

Description

ninst.pdynmc extracts instrument count of an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
ninst(object, ...)

Arguments

Value

Extracts instrument count from an object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
ninst(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 ninst(m1)

Extract Number of Observations of Fitted Model.

Description

nobs.pdynmc extracts number of observations in cross-section dimension and longitudinal dimension of an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
nobs(object, ...)

Arguments

Value

Extracts number of observations in cross-section dimension and longitudinal dimension of an object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
nobs(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 nobs(m1)

Extract Input Parameters of Numeric Optimization of Fitted Model.

Description

optimIn is a generic function for extracting input parameters of numeric optimization for an object.

Usage

optimIn(object, ...)

Arguments

Value

optimIn extracts input parameters used in numeric optimization from object.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
optimIn(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "BFGS")
 optimIn(m1)

Extract Input Parameters of Numeric Optimization of Fitted Model.

Description

optimIn.pdynmc extracts input parameters of numeric optimization for an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
optimIn(object, step = object$iter, ...)

Arguments

Value

Extracts input parameters of numeric optimization from object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
optimIn(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "BFGS")
 optimIn(m1)

Plot Empirical Density of a Column of a Panel Dataset over Time.

Description

pDensTime.plot Plot the empirical density of a column of an object of class 'data.frame' containing a panel dataset across time periods/aggregates of time periods.

Usage

pDensTime.plot(
  object,
  var.name,
  i.name,
  t.name,
  aggregate.t = NULL,
  plot.quantiles = TRUE,
  plot.mean_ci = TRUE,
  plot.extrema = TRUE,
  col.set = c("gray", "navy", "darkorange1", "red"),
  ...
)

Arguments

Value

Returns a plot that visualizes the empirical density for a column of a panel dataset contained in an object of class 'data.frame'. The variable of interest is plotted on the ordinate, the longitudinal dimension on the abscissa. For each time period or aggregate of time periods, one empirical density is computed and plotted. Corresponding summary statistics on empirical quantiles and the sample size per longitudinal dimension are included in the plot.

Author(s)

Markus Fritsch, Joachim Schnurbus

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])

## Minimal set of arguments
pDensTime.plot(object = ABdata, var.name = "emp", i.name = "firm", t.name = "year")

## All arguments explicitly stated
pDensTime.plot(object	= ABdata, var.name	= "emp", i.name	= "firm", t.name	= "year",
 aggregate.t	= NULL,	plot.quantiles	= TRUE, plot.mean_ci	= TRUE, plot.extrema	= TRUE,
 col.set		= c("gray", "navy", "darkorange1", "red"))

## Aggregation over time periods (3 time periods per group)
pDensTime.plot(object = ABdata, var.name = "emp", i.name = "firm", t.name = "year",
 aggregate.t = 3)

## Employ alternative colouring scheme
pDensTime.plot(object = ABdata, var.name = "emp", i.name = "firm", t.name = "year",
 col.set		= c("pink", "blue", "purple", "black"))

## Plot only density, mean, and asymptotic confidence interval
pDensTime.plot(object = ABdata, var.name = "emp", i.name = "firm", t.name = "year",
 plot.quantiles	= FALSE, plot.extrema	= FALSE)

pdynmc: A package for moment conditions based estimation of linear dynamic panel data models

Description

The pdynmc package provides four categories of functions that are available to the user: A function for model fitting, functions for visualizing estimation results and panel data structures, functions for specification testing, and functions that extract and summarize particular information from fitted model objects.

Generalized Method of Moments (GMM) Estimation of Linear Dynamic Panel Data Models.

Description

pdynmc fits a linear dynamic panel data model based on moment conditions with the Generalized Method of Moments (GMM).

Usage

pdynmc(
  dat = NULL,
  varname.i = NULL,
  varname.t = NULL,
  use.mc.diff = NULL,
  use.mc.lev = NULL,
  use.mc.nonlin = NULL,
  use.mc.nonlinAS = NULL,
  inst.collapse = FALSE,
  inst.stata = FALSE,
  include.y,
  varname.y = NULL,
  lagTerms.y = NULL,
  maxLags.y = NULL,
  include.x = FALSE,
  varname.reg.end = NULL,
  lagTerms.reg.end = NULL,
  maxLags.reg.end = NULL,
  varname.reg.pre = NULL,
  lagTerms.reg.pre = NULL,
  maxLags.reg.pre = NULL,
  varname.reg.ex = NULL,
  lagTerms.reg.ex = NULL,
  maxLags.reg.ex = NULL,
  inst.reg.ex.expand = TRUE,
  include.x.instr = FALSE,
  varname.reg.instr = NULL,
  include.x.toInstr = FALSE,
  varname.reg.toInstr = NULL,
  fur.con = FALSE,
  fur.con.diff = NULL,
  fur.con.lev = NULL,
  varname.reg.fur = NULL,
  lagTerms.reg.fur = NULL,
  include.dum = FALSE,
  dum.diff = NULL,
  dum.lev = NULL,
  varname.dum = NULL,
  col_tol = 0.65,
  w.mat = "iid.err",
  w.mat.stata = FALSE,
  std.err = "corrected",
  estimation = "iterative",
  max.iter = 100,
  iter.tol = 0.01,
  inst.thresh = NULL,
  opt.meth = "BFGS",
  hessian = FALSE,
  optCtrl = list(kkt = FALSE, kkttol = .Machine$double.eps^(1/3), kkt2tol =
    .Machine$double.eps^(1/3), starttests = TRUE, dowarn = TRUE, badval = (0.25) *
    .Machine$double.xmax, usenumDeriv = FALSE, reltol = 1e-12, maxit = 200, trace = TRUE,
    follow.on = FALSE, save.failures = TRUE, maximize = FALSE, factr = 1e+07, pgtol = 0,
    all.methods = FALSE),
  custom.start.val = FALSE,
  start.val = NULL,
  start.val.lo = -1,
  start.val.up = 1,
  seed.input = 42
)

Arguments

Details

The function estimates a linear dynamic panel data model of the form

y_{i,t} = y_{i,t-1} \rho_1 + \boldsymbol{x}_{i,t}' \boldsymbol{\beta} + a_i + \varepsilon_{i,t}

where y_{i,t-1} is the lagged dependent variable, \rho_1 is the lag parameter, \boldsymbol{x}_{i,t} are further covariates, \boldsymbol{\beta} are the corresponding parameters, a_i is an unobserved individual specific effect, and \varepsilon_{i,t} is an idiosyncratic remainder component. The model structure accounts for unobserved individual specific heterogeneity and dynamics. Note that the specification given above is simplified for illustratory purposes and more general lag structures are allowed in pdynmc.

Estimation of the model parameters in pdynmc is based on moment conditions with the generalized method of moments (GMM). Linear dynamic panel data models The moment conditions employed in estimation can be linear and nonlinear in parameters and estimation is carried out iteratively. In case only linear moment conditions are used in estimation, closed form solutions can be for computing parameter estimates – while when nonlinear moment conditions are employed, parameter estimation relies on numerical optimization of the objective function.

'pdynmc' provides an implementation of some of the functionality available in the Stata library xtdpdgmm Kripfganz (2019) and allows for '"onestep"', '"twostep"', and '"iterative"' GMM estimation based on the moment conditions of Holtz-Eakin et al. (1988), Arellano and Bover (1995), and Ahn and Schmidt (1995). Standard error corrections according to Windmeijer (2005) and Hwang et al. (2021) are available. For further details, please see Fritsch et al. (2021).

Value

An object of class 'pdynmc' with the following elements:

It has 'case.names', 'coef', 'dum.coef', 'fitted', 'model.matrix', 'ninst', 'nobs', 'optimIn', 'plot', 'print','residuals', 'summary', 'variable.names', 'vcov', and 'wmat' methods.

Author(s)

Markus Fritsch

References

Ahn SC, Schmidt P (1995). “Efficient estimation of models for dynamic panel data.” Journal of Econometrics, 68(1), 5–27. doi:10.1016/0304-4076(94)01641-C.

Arellano M, Bover O (1995). “Another look at the instrumental variable estimation of error-components models.” Journal of Econometrics, 68(1), 29–51. doi:10.1016/0304-4076(94)01642-D.

Fritsch M, Pua AAY, Schnurbus J (2021). “pdynmc: A Package for Estimating Linear Dynamic Panel Data Models Based on Nonlinear Moment Conditions.” The R Journal, 13(1), 218–231. doi:10.32614/RJ-2021-035.

Holtz-Eakin D, Newey WK, Rosen HS (1988). “Estimating Vector Autoregressions with Panel Data.” Econometrica, 56(6), 1371–1395. doi:10.2307/1913103.

Hwang J, Kang B, Lee S (2021). “A doubly corrected robust variance estimator for linear GMM.” Journal of Econometrics, forthcoming. doi:10.1016/j.jeconom.2020.09.010.

Kripfganz S (2019). “XTDPDGMM: Stata module to perform generalized method of moments estimation of linear dynamic panel data models.” https://econpapers.repec.org/RePEc:boc:bocode:s458395.

Roodman D (2009). “A Note on the Theme of Too Many Instruments.” Oxford Bulletin of Economics and Statistics, 71(1), 135–158. doi:10.1111/j.1468-0084.2008.00542.x.

Roodman D (2018). “xtabond2: Stata module to extend xtabond dynamic panel data estimator.” https://econpapers.repec.org/software/bocbocode/s435901.htm.

Windmeijer F (2005). “A finite sample correction for the variance of linear efficient two-step GMM estimators.” Journal of Econometrics, 126(1), 25–51. doi:10.1016/j.jeconom.2004.02.005.

See Also

wald.fct for Wald tests, jtest.fct for the Hansen J test, and mtest.fct for serial correlation tests. optimx for details on alternative routines and options for numerical optimization

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
         use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
         include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
         fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
         varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
         include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
         w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
         opt.meth = "none")
summary(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Arellano and Bond (1991) estimation in Table 4, column (a1)
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
         use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
         include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
         fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
         varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
         include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
         w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
         opt.meth = "none")
 summary(m1)

## Arellano and Bond (1991) estimation in Table 4, column (a2)
 m2 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
         use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
         include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
         fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
         varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
         include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
         w.mat = "iid.err", std.err = "corrected", estimation = "twostep",
         opt.meth = "none")
 summary(m2)

## Arellano and Bond (1991) twostep estimation extended by nonlinear moment
## conditions
 m3 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
         use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = TRUE,
         include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
         fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
         varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
         include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
         w.mat = "iid.err", std.err = "corrected", estimation = "twostep",
         opt.meth = "BFGS")
 summary(m3)

## Arellano and Bond (1991) iterative estimation extended by nonlinear moment
## conditions
 m4 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
         use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = TRUE,
         include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
         fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
         varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
         include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
         w.mat = "iid.err", std.err = "corrected", estimation = "iterative",
         max.iter = 4, opt.meth = "BFGS")
 summary(m4)

## Arellano and Bond (1991) twostep estimation extended by linear moment
## conditions from equations in levels
 m5 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
         use.mc.diff = TRUE, use.mc.lev = TRUE, use.mc.nonlin = FALSE,
         include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
         fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
         varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
         include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
         w.mat = "iid.err", std.err = "corrected", estimation = "twostep",
         opt.meth = "none")
 summary(m5)

Plot Coefficient Estimates and Corresponding Ranges of Fitted Model.

Description

plot.pdynmc Plot methods for objects of class 'pdynmc'. The available plot options visualize: Fitted values versus residuals, coefficient ranges across GMM iterations, coefficient paths and objective function values across GMM iterations as proposed by Hansen and Lee (2021).

Usage

## S3 method for class 'pdynmc'
plot(
  x,
  type = "fire",
  include.dum = FALSE,
  include.fur.con = FALSE,
  col.coefRange = 1,
  col.coefInitial = "darkgrey",
  col.coefEst = "royalblue",
  omit1step = FALSE,
  boxplot.coef = FALSE,
  co = NULL,
  add.se.approx = NULL,
  conf.lev = 0.95,
  ...
)

Arguments

Value

Plot fitted values against residuals ('type = fire') or coefficient estimates and coefficient estimate ranges ('type = coef.range') for object of class 'pdynmc'. The latter plot requires twostep or iterative GMM estimates.

Author(s)

Markus Fritsch and Joachim Schnurbus

References

Hansen BE, Lee S (2021). “Inference for Iterated GMM Under Misspecification.” Econometrica, 89(3), 1419–1447. doi:10.3982/ECTA16274.

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "twostep",
    opt.meth = "none")
plot(m1)
plot(m1, type = "coef.range")
plot(m1, type = "coef.path")


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "iterative",
    opt.meth = "none")
 plot(m1)
 plot(m1, type = "coef.range")
 plot(m1, type = "coef.path")

Print Fitted Model Object.

Description

print.pdynmc prints objects of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
print(x, digits = max(3, getOption("digits") - 3), ...)

Arguments

Value

Print objects of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
m1


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 m1

Print Summary of Fitted Model Object.

Description

print.summary.pdynmc prints the summary for objects of class 'pdynmc'.

Usage

## S3 method for class 'summary.pdynmc'
print(
  x,
  digits = max(3, getOption("digits") - 3),
  signif.stars = getOption("show.signif.stars"),
  ...
)

Arguments

Value

Print information on objects of class 'summary.pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
summary(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 summary(m1)

Extract Residuals of Fitted Model.

Description

residuals.pdynmc extracts residuals from an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
residuals(object, step = object$iter, na.rm = FALSE, ...)

Arguments

Value

Extract residuals from object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
residuals(m1, na.rm = TRUE)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 residuals(m1, na.rm = TRUE)

Sargan test.

Description

sargan.fct tests the validity of the overidentifying restrictions.

Usage

sargan.fct(object)

Arguments

Details

The null hypothesis is that the overidentifying restrictions are valid. The test statistic is computed as proposed by Sargan (1958). As noted by Bowsher (2002) and Windmeijer (2005), the test statistic is weakened by many instruments and inconsistent in the presence of heteroscedasticity according to Roodman (2009a).

Value

An object of class 'htest' which contains the Sargan test statistic and corresponding p-value for the null hypothesis that the overidentifying restrictions are valid.

References

Bowsher CG (2002). “On testing overidentifying restrictions in dynamic panel data models.” Economics Letters, 77(2), 211–220. doi:10.1016/S0165-1765(02)00130-1.

Roodman D (2009a). “How to do xtabond2: An Introduction to Difference and System GMM in Stata.” Stata Journal, 9(1), 86–136. https://www.stata-journal.com/article.html?article=st0159.

Sargan JD (1958). “The Estimation of Economic Relationships Using Instrumental Variables.” Econometrica, 26(3), 393–415. doi:10.2307/1907619.

Windmeijer F (2005). “A finite sample correction for the variance of linear efficient two-step GMM estimators.” Journal of Econometrics, 126(1), 25–51. doi:10.1016/j.jeconom.2004.02.005.

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(140:0), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
sargan.fct(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 sargan.fct(m1)

Plot on Structure of Unbalanced Panel Dataset.

Description

strucUPD.plot Plot on cross-section and longtudinal structure of an object of class 'data.frame' containing an unbalanced panel dataset.

Usage

strucUPD.plot(
  object,
  i.name = NULL,
  t.name = NULL,
  col.range = c("gold", "darkblue"),
  plot.name = "Unbalanced panel structure",
  ...
)

Arguments

Value

Returns a plot for an unbalanced panel dataset contained in an object of class 'data.frame' that visualizes the structure of the data. Cross-section dimension is plotted on the ordinate, longitudinal dimension on the abscissa. Each cross-sectional observation is represented by a bar. Breaks in the bars represent missing longitudinal observations.

Author(s)

Markus Fritsch, Joachim Schnurbus

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])

## Code example
strucUPD.plot(dat, i.name = "firm", t.name = "year")

Summary for Fitted Model Object.

Description

summary.pdynmc generates the summary for objects of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
summary(object, ...)

Arguments

Value

Object of class 'summary.pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
summary(m1, na.rm = TRUE)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 summary(m1)

Extract Names of Explanatory Variables of Fitted Model.

Description

variable.names.pdynmc extracts explanatory variables from an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
variable.names(object, ...)

Arguments

Value

Extract explanatory variables from an object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
variable.names(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 variable.names(m1)

Extract Variance Covariance Matrix of Fitted Model.

Description

vcov.pdynmc extracts variance covariance matrix of the paramter estimates from an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
vcov(object, step = object$iter, ...)

Arguments

Value

Extract variance covariance matrix of the paramter estimates from an object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
vcov(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 vcov(m1)

Wald Test.

Description

wald.fct computes F test statistics and corresponding p-values for 'pdynmc' objects.

Usage

wald.fct(object, param)

Arguments

Details

The three available null hypothesis are: All time dummies are jointly zero, all slope coefficients are jointly zero, all times dummies and slope coefficients are jointly zero.

Value

An object of class 'htest' which contains the F test statistic and corresponding p-value for the tested null hypothesis.

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(140:0), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
wald.fct(param = "all", m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

## Further code example
 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 wald.fct(m1, param = "all")

Extract Weighting Matrix of Fitted Model.

Description

wmat is a generic function for extracting the weighting matrix of an object.

Usage

wmat(object, ...)

Arguments

Value

Extract weighting matrix from an object.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
wmat(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 wmat(m1)

Extract Weighting Matrix of Fitted Model.

Description

wmat.pdynmc extracts weighting matrix from an object of class 'pdynmc'.

Usage

## S3 method for class 'pdynmc'
wmat(object, step = object$iter, ...)

Arguments

Value

Extract weighting matrix from an object of class 'pdynmc'.

Author(s)

Markus Fritsch

See Also

pdynmc for fitting a linear dynamic panel data model.

Examples

## Load data
data(ABdata, package = "pdynmc")
dat <- ABdata
dat[,c(4:7)] <- log(dat[,c(4:7)])
dat <- dat[c(1:140), ]

## Code example
m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
wmat(m1)


## Load data
 data(ABdata, package = "pdynmc")
 dat <- ABdata
 dat[,c(4:7)] <- log(dat[,c(4:7)])

 m1 <- pdynmc(dat = dat, varname.i = "firm", varname.t = "year",
    use.mc.diff = TRUE, use.mc.lev = FALSE, use.mc.nonlin = FALSE,
    include.y = TRUE, varname.y = "emp", lagTerms.y = 2,
    fur.con = TRUE, fur.con.diff = TRUE, fur.con.lev = FALSE,
    varname.reg.fur = c("wage", "capital", "output"), lagTerms.reg.fur = c(1,2,2),
    include.dum = TRUE, dum.diff = TRUE, dum.lev = FALSE, varname.dum = "year",
    w.mat = "iid.err", std.err = "corrected", estimation = "onestep",
    opt.meth = "none")
 wmat(m1)