Skip to contents

Produce lags or leads in the formulas of fixest estimations or when creating variables in a data.table::data.table. The data must be set as a panel beforehand (either with the function panel or with the argument panel.id in the estimation).

Usage

f(x, lead = 1, fill = NA)

d(x, lag = 1, fill = NA)

l(x, lag = 1, fill = NA)

Arguments

x

The variable.

lead

A vector of integers giving the number of leads. Negative values lead to lags. This argument can be a vector when using it in fixest estimations. When creating variables in a data.table::data.table, it must be of length one.

fill

A scalar, default is NA. How to fill the missing values due to the lag/lead? Note that in a fixest estimation, 'fill' must be numeric (not required when creating new variables).

lag

A vector of integers giving the number of lags. Negative values lead to leads. This argument can be a vector when using it in fixest estimations. When creating variables in a data.table::data.table, it must be of length one.

Value

These functions can only be used i) in a formula of a fixest estimation, or ii) when creating variables within a fixest_panel object (obtained with function panel) which is alaos a data.table::data.table.

Functions

  • f(): Forwards a variable (inverse of lagging) in a fixest estimation

  • d(): Creates differences (i.e. x - lag(x)) in a fixest estimation

See also

The function panel changes data.frames into a panel from which the functions l and f can be called. Otherwise you can set the panel 'live' during the estimation using the argument panel.id (see for example in the function feols).

Examples


data(base_did)

# Setting a data set as a panel...
pdat = panel(base_did, ~ id + period)

# ...then using the functions l and f
est1 = feols(y ~ l(x1, 0:1), pdat)
#> NOTE: 108 observations removed because of NA values (RHS: 108).
est2 = feols(f(y) ~ l(x1, -1:1), pdat)
#> NOTE: 216 observations removed because of NA values (LHS: 108, RHS: 216).
est3 = feols(l(y) ~ l(x1, 0:3), pdat)
#> NOTE: 324 observations removed because of NA values (LHS: 108, RHS: 324).
etable(est1, est2, est3, order = c("f", "^x"), drop = "Int")
#>                               est1               est2               est3
#> Dependent Var.:                  y             f(y,1)             l(y,1)
#>                                                                         
#> f(x1,1)                            0.9940*** (0.0542)                   
#> x1              0.9948*** (0.0487)    0.0081 (0.0592)   -0.0534 (0.0545)
#> Constant         2.235*** (0.2032)  2.464*** (0.2233)  2.196*** (0.2110)
#> l(x1,1)            0.0410 (0.0558)    0.0157 (0.0640) 0.9871*** (0.0551)
#> l(x1,2)                                                  0.0220 (0.0580)
#> l(x1,3)                                                  0.0102 (0.0639)
#> _______________ __________________ __________________ __________________
#> S.E.: Clustered             by: id             by: id             by: id
#> Observations                   972                864                756
#> R2                         0.26558            0.25697            0.25875
#> Adj. R2                    0.26406            0.25438            0.25480
#> ---
#> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

# or using the argument panel.id
feols(f(y) ~ l(x1, -1:1), base_did, panel.id = ~id + period)
#> NOTE: 216 observations removed because of NA values (LHS: 108, RHS: 216).
#> OLS estimation, Dep. Var.: f(y, 1)
#> Observations: 864 
#> Standard-errors: Clustered (id) 
#>             Estimate Std. Error   t value  Pr(>|t|)    
#> (Intercept) 2.464313   0.223277 11.037009 < 2.2e-16 ***
#> f(x1, 1)    0.994018   0.054216 18.334504 < 2.2e-16 ***
#> x1          0.008072   0.059247  0.136241   0.89189    
#> l(x1, 1)    0.015693   0.063958  0.245360   0.80665    
#> ---
#> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#> RMSE: 4.97418   Adj. R2: 0.254377
feols(d(y) ~ d(x1), base_did, panel.id = ~id + period)
#> NOTE: 108 observations removed because of NA values (LHS: 108, RHS: 108).
#> OLS estimation, Dep. Var.: d(y, 1)
#> Observations: 972 
#> Standard-errors: Clustered (id) 
#>             Estimate Std. Error  t value   Pr(>|t|)    
#> (Intercept) 0.510685   0.072720  7.02262 2.0948e-10 ***
#> d(x1, 1)    0.972664   0.053437 18.20224  < 2.2e-16 ***
#> ---
#> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
#> RMSE: 5.83885   Adj. R2: 0.329253

# l() and f() can also be used within a data.table:
if(require("data.table")){
  pdat_dt = panel(as.data.table(base_did), ~id+period)
  # Now since pdat_dt is also a data.table
  #   you can create lags/leads directly
  pdat_dt[, x1_l1 := l(x1)]
  pdat_dt[, x1_d1 := d(x1)]
  pdat_dt[, c("x1_l1_fill0", "y_f2") := .(l(x1, fill = 0), f(y, 2))]
}
#> Loading required package: data.table
#> [1] TRUE