Last updated on 2024-12-18 19:49:13 CET.
| Flavor | Version | Tinstall | Tcheck | Ttotal | Status | Flags |
|---|---|---|---|---|---|---|
| r-devel-linux-x86_64-debian-clang | 0.12.1 | 95.37 | 275.49 | 370.86 | NOTE | |
| r-devel-linux-x86_64-debian-gcc | 0.12.1 | 63.94 | 184.24 | 248.18 | NOTE | |
| r-devel-linux-x86_64-fedora-clang | 0.12.1 | 639.38 | OK | |||
| r-devel-linux-x86_64-fedora-gcc | 0.12.1 | 684.81 | OK | |||
| r-devel-windows-x86_64 | 0.12.1 | 97.00 | 299.00 | 396.00 | NOTE | |
| r-patched-linux-x86_64 | 0.12.1 | 108.41 | 263.59 | 372.00 | OK | |
| r-release-linux-x86_64 | 0.12.1 | 98.78 | 263.17 | 361.95 | OK | |
| r-release-macos-arm64 | 0.12.1 | 183.00 | NOTE | |||
| r-release-macos-x86_64 | 0.12.1 | 460.00 | NOTE | |||
| r-release-windows-x86_64 | 0.12.1 | 97.00 | 296.00 | 393.00 | NOTE | |
| r-oldrel-macos-arm64 | 0.12.1 | 167.00 | NOTE | |||
| r-oldrel-macos-x86_64 | 0.12.1 | 296.00 | NOTE | |||
| r-oldrel-windows-x86_64 | 0.12.1 | 121.00 | 369.00 | 490.00 | ERROR |
Version: 0.12.1
Check: Rd cross-references
Result: NOTE
Found the following Rd file(s) with Rd \link{} targets missing package
anchors:
feNmlm.Rd: jacobian, genD
Please provide package anchors for all Rd \link{} targets not in the
package itself and the base packages.
Flavors: r-devel-linux-x86_64-debian-clang, r-devel-linux-x86_64-debian-gcc, r-devel-windows-x86_64
Version: 0.12.1
Check: installed package size
Result: NOTE
installed size is 11.8Mb
sub-directories of 1Mb or more:
R 2.0Mb
doc 3.6Mb
libs 5.0Mb
Flavors: r-release-macos-arm64, r-release-macos-x86_64, r-release-windows-x86_64, r-oldrel-macos-arm64, r-oldrel-macos-x86_64, r-oldrel-windows-x86_64
Version: 0.12.1
Check: tests
Result: ERROR
Running 'fixest_tests.R' [17s]
Running the tests in 'tests/fixest_tests.R' failed.
Complete output:
> #----------------------------------------------#
> # Author: Laurent Berge
> # Date creation: Fri Jul 10 09:03:06 2020
> # ~: package sniff tests
> #----------------------------------------------#
>
> # Not everything is currently covered, but I'll improve it over time
>
> # Some functions are not trivial to test properly though
>
> library(fixest)
>
> test = fixest:::test ; chunk = fixest:::chunk
> vcovClust = fixest:::vcovClust
> stvec = stringmagic::string_vec_alias()
>
> setFixest_notes(FALSE)
>
> if(fixest:::is_r_check()){
+ if(requireNamespace("data.table", quietly = TRUE)){
+ library(data.table)
+ data.table::setDTthreads(1)
+ }
+ setFixest_nthreads(1)
+ }
>
> ####
> #### ESTIMATIONS ####
> ####
>
> ####
> #### ... Main ####
> ####
>
>
> chunk("ESTIMATION")
ESTIMATION
>
> set.seed(0)
>
> base = iris
> names(base) = c("y", "x1", "x2", "x3", "species")
> base$fe_2 = rep(1:5, 30)
> base$fe_3 = sample(15, 150, TRUE)
> base$constant = 5
> base$y_int = as.integer(base$y)
> base$w = as.vector(unclass(base$species) - 0.95)
> base$offset_value = unclass(base$species) - 0.95
> base$y_01 = 1 * ((scale(base$x1) + rnorm(150)) > 0)
> # what follows to avoid removal of fixed-effects (logit is pain in the neck)
> base$y_01[1:5 + rep(c(0, 50, 100), each = 5)] = 1
> base$y_01[6:10 + rep(c(0, 50, 100), each = 5)] = 0
> # We enforce the removal of observations
> base$y_int_null = base$y_int
> base$y_int_null[base$fe_3 %in% 1:5] = 0
>
> for(model in c("ols", "pois", "logit", "negbin", "Gamma")){
+ cat("Model: ", format(model, width = 6), sep = "")
+ for(use_weights in c(FALSE, TRUE)){
+ my_weight = NULL
+ if(use_weights) my_weight = base$w
+
+ for(use_offset in c(FALSE, TRUE)){
+ my_offset = NULL
+ if(use_offset) my_offset = base$offset_value
+
+ for(id_fe in 0:9){
+
+ cat(".")
+
+ tol = switch(model, "negbin" = 1e-2, "logit" = 3e-5, 1e-5)
+
+ # Setting up the formula to accommodate FEs
+ if(id_fe == 0){
+ fml_fixest = fml_stats = y ~ x1
+ } else if(id_fe == 1){
+ fml_fixest = y ~ x1 | species
+ fml_stats = y ~ x1 + factor(species)
+ } else if(id_fe == 2){
+ fml_fixest = y ~ x1 | species + fe_2
+ fml_stats = y ~ x1 + factor(species) + factor(fe_2)
+ } else if(id_fe == 3){
+ # varying slope
+ fml_fixest = y ~ x1 | species[[x2]]
+ fml_stats = y ~ x1 + x2:species
+ } else if(id_fe == 4){
+ # varying slope -- 1 VS, 1 FE
+ fml_fixest = y ~ x1 | species[[x2]] + fe_2
+ fml_stats = y ~ x1 + x2:species + factor(fe_2)
+ } else if(id_fe == 5){
+ # varying slope -- 2 VS
+ fml_fixest = y ~ x1 | species[x2]
+ fml_stats = y ~ x1 + x2:species + species
+ } else if(id_fe == 6){
+ # varying slope -- 2 VS bis
+ fml_fixest = y ~ x1 | species[[x2]] + fe_2[[x3]]
+ fml_stats = y ~ x1 + x2:species + x3:factor(fe_2)
+ } else if(id_fe == 7){
+ # Combined clusters
+ fml_fixest = y ~ x1 + x2 | species^fe_2
+ fml_stats = y ~ x1 + x2 + paste(species, fe_2)
+ } else if(id_fe == 8){
+ fml_fixest = y ~ x1 | species[x2] + fe_2[x3] + fe_3
+ fml_stats = y ~ x1 + species + i(species, x2) + factor(fe_2) + i(fe_2, x3) + factor(fe_3)
+ } else if(id_fe == 9){
+ fml_fixest = y ~ x1 | species + fe_2[x2,x3] + fe_3
+ fml_stats = y ~ x1 + species + factor(fe_2) + i(fe_2, x2) + i(fe_2, x3) + factor(fe_3)
+ }
+
+ # ad hoc modifications of the formula
+ if(model == "logit"){
+ fml_fixest = xpd(y_01 ~ ..rhs, ..rhs = fml_fixest[[3]])
+ fml_stats = xpd(y_01 ~ ..rhs, ..rhs = fml_stats[[3]])
+
+ # The estimations are OK, conv differences out of my control
+ if(id_fe %in% 8:9) tol = 0.5
+
+ } else if(model == "pois"){
+ fml_fixest = xpd(y_int_null ~ ..rhs, ..rhs = fml_fixest[[3]])
+ fml_stats = xpd(y_int_null ~ ..rhs, ..rhs = fml_stats[[3]])
+
+ } else if(model %in% c("negbin", "Gamma")){
+ fml_fixest = xpd(y_int ~ ..rhs, ..rhs = fml_fixest[[3]])
+ fml_stats = xpd(y_int ~ ..rhs, ..rhs = fml_stats[[3]])
+ }
+
+ adj = 1
+ if(model == "ols"){
+ res = feols(fml_fixest, base, weights = my_weight, offset = my_offset)
+ res_bis = lm(fml_stats, base, weights = my_weight, offset = my_offset)
+
+ } else if(model %in% c("pois", "logit", "Gamma")){
+ adj = 0
+ if(model == "Gamma" && use_offset) next
+
+ my_family = switch(model, pois = poisson(), logit = binomial(), Gamma = Gamma())
+
+ res = feglm(fml_fixest, base, family = my_family, weights = my_weight, offset = my_offset)
+
+ if(!is.null(res$obs_selection$obsRemoved)){
+ qui = res$obs_selection$obsRemoved
+
+ # I MUST do that.... => subset does not work...
+ base_tmp = base[qui, ]
+ base_tmp$my_offset = my_offset[qui]
+ base_tmp$my_weight = my_weight[qui]
+ res_bis = glm(fml_stats, base_tmp, family = my_family, weights = my_weight, offset = my_offset)
+ } else {
+ res_bis = glm(fml_stats, data = base, family = my_family, weights = my_weight, offset = my_offset)
+ }
+
+ } else if(model == "negbin"){
+ # no offset in glm.nb + no VS in fenegbin + no weights in fenegbin
+ if(use_weights || use_offset || id_fe > 2) next
+
+ res = fenegbin(fml_fixest, base, notes = FALSE)
+ res_bis = MASS::glm.nb(fml_stats, base)
+
+ }
+
+ test(coef(res)["x1"], coef(res_bis)["x1"], "~", tol)
+ test(se(res, se = "st", ssc = ssc(adj = adj))["x1"], se(res_bis)["x1"], "~", tol)
+ test(pvalue(res, se = "st", ssc = ssc(adj = adj))["x1"], pvalue(res_bis)["x1"], "~", tol*10**(model == "negbin"))
+ # cat("Model: ", model, ", FE: ", id_fe, ", weight: ", use_weights, ", offset: ", use_offset, "\n", sep="")
+
+ }
+ cat("|")
+ }
+ }
+ cat("\n")
+ }
Model: ols ..........|..........|..........|..........|
Model: pois ..........|..........|..........|..........|
Model: logit ..........|..........|..........|..........|
Model: negbin..........|..........|..........|..........|
Model: Gamma ..........|..........|..........|..........|
There were 36 warnings (use warnings() to see them)
>
> ####
> #### ... Corner cases ####
> ####
>
> chunk("Corner cases")
CORNER CASES
>
>
> # We test the absence of bugs
>
> base = iris
> names(base) = c("y", "x1", "x2", "x3", "fe1")
> base$fe2 = rep(1:5, 30)
> base$y[1:5] = NA
> base$x1[4:8] = NA
> base$x2[4:21] = NA
> base$x3[110:111] = NA
> base$fe1[110:118] = NA
> base$fe2[base$fe2 == 1] = 0
> base$fe3 = sample(letters[1:5], 150, TRUE)
> base$period = rep(1:50, 3)
> base$x_cst = 1
>
> res = feols(y ~ 1 | csw(fe1, fe1^fe2), base)
>
> res = feols(y ~ 1 + csw(x1, i(fe1)) | fe2, base)
>
> res = feols(y ~ csw(f(x1, 1:2), x2) | sw0(fe2, fe2^fe3), base, panel.id = ~ fe1 + period)
>
> res = feols(d(y) ~ -1 + d(x2), base, panel.id = ~ fe1 + period)
> test(length(coef(res)), 1)
>
> res = feols(c(y, x1) ~ 1 | fe1 | x2 ~ x3, base)
>
> res = feols(y ~ x1 | fe1[x2] + fe2[x2], base)
>
> #
> # NA models (ie all variables are collinear with the FEs)
> #
>
> # Should work when warn = FALSE or multiple est
> for(i in 1:2){
+ fun = switch(i, "1" = feols, "2" = feglm)
+
+ res = feols(y ~ x_cst | fe1, base, warn = FALSE)
+ res # => no error
+ etable(res) # => no error
+
+ # error when warn = TRUE
+ test(feols(y ~ x_cst | fe1, base), "err")
+
+ # multiple est => no error
+ res = feols(c(y, x1) ~ x_cst | fe1, base)
+ res # => no error
+ etable(res) # => no error
+ }
>
>
> # Removing the intercept!!!
>
> res = feols(y ~ -1 + x1 + i(fe1), base)
> test("(Intercept)" %in% names(res$coefficients), FALSE)
>
> res = feols(y ~ -1 + x1 + factor(fe1), base)
> test("(Intercept)" %in% names(res$coefficients), FALSE)
>
> res = feols(y ~ -1 + x1 + i(fe1) + i(fe2), base)
> test("(Intercept)" %in% names(res$coefficients), FALSE)
> test(is.null(res$collin.var), TRUE)
>
>
> # IV + interacted FEs
> res = feols(y ~ x1 | fe1^fe2 | x2 ~ x3, base)
>
> # IVs no exo var
> res = feols(y ~ 0 | x2 ~ x3, base)
> # Same in stepwise
> res = feols(y ~ 0 | sw0(fe1) | x2 ~ x3, base)
>
> # IVs + lags
> res = feols(y ~ x1 | fe1^fe2 | l(x2, -1:1) ~ l(x3, -1:1), base, panel.id = ~ fe1 + period)
>
> # functions in interactions
> res = feols(y ~ x1 | factor(fe1)^factor(fe2), base)
> res = feols(y ~ x1 | round(x2^2), base)
> test(feols(y ~ x1 | factor(fe1^fe2), base), "err")
>
> res = feols(y ~ x1 | bin(x2, "bin::1")^fe1 + fe1^fe2, base)
>
> # 1 obs (after FE removal) estimation
> base_1obs = data.frame(y = c(1, 0), fe = c(1, 2), x = c(1, 0))
> test(fepois(y ~ x | fe, base_1obs), "err")
> # no error
> res = fepois(y ~ 1 | fe, base_1obs)
>
> # warning when demeaning algo reaches max iterations
> data(trade)
> test(feols(Euros ~ log(dist_km) | Destination + Origin + Product,
+ trade, fixef.iter = 1), "warn")
>
>
> ####
> #### ... Fit methods ####
> ####
>
> chunk("Fit methods")
FIT METHODS
>
> base = iris
> names(base) = c("y", "x1", "x2", "x3", "species")
> base$y_int = as.integer(base$y)
> base$y_log = sample(c(TRUE, FALSE), 150, TRUE)
>
> res = feglm.fit(base$y, base[, 2:4])
> res_bis = feglm(y ~ -1 + x1 + x2 + x3, base)
> test(coef(res), coef(res_bis))
>
> res = feglm.fit(base$y_int, base[, 2:4])
> res_bis = feglm(y_int ~ -1 + x1 + x2 + x3, base)
> test(coef(res), coef(res_bis))
>
> res = feglm.fit(base$y_log, base[, 2:4])
> res_bis = feglm(y_log ~ -1 + x1 + x2 + x3, base)
> test(coef(res), coef(res_bis))
>
>
>
> res = feglm.fit(base$y, base[, 2:4], family = "poisson")
> res_bis = feglm(y ~ -1 + x1 + x2 + x3, base, family = "poisson")
> test(coef(res), coef(res_bis))
>
> res = feglm.fit(base$y_int, base[, 2:4], family = "poisson")
> res_bis = feglm(y_int ~ -1 + x1 + x2 + x3, base, family = "poisson")
> test(coef(res), coef(res_bis))
>
> res = feglm.fit(base$y_log, base[, 2:4], family = "poisson")
> res_bis = feglm(y_log ~ -1 + x1 + x2 + x3, base, family = "poisson")
> test(coef(res), coef(res_bis))
>
> ####
> #### global variables ####
> ####
>
> chunk("globals")
GLOBALS
>
> est_reg = function(df, yvar, xvar, refgrp) {
+ feols(.[yvar] ~ i(.[xvar], ref = refgrp), data = df)
+ }
>
> (est = est_reg(iris, "Sepal.Length", "Species", ref = "setosa"))
OLS estimation, Dep. Var.: Sepal.Length
Observations: 150
Standard-errors: IID
Estimate Std. Error t value Pr(>|t|)
(Intercept) 5.006 0.072802 68.76164 < 2.2e-16 ***
Species::versicolor 0.930 0.102958 9.03282 8.7702e-16 ***
Species::virginica 1.582 0.102958 15.36551 < 2.2e-16 ***
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
RMSE: 0.509616 Adj. R2: 0.613518
>
> # checking when it should not work
> base = setNames(iris, c("y", "x1", "x2", "x3", "species"))
>
> z = base$x1
> test(feols(y ~ z, base), "err")
>
>
>
> ####
> #### ... Collinearity ####
> ####
>
> chunk("COLLINEARITY")
COLLINEARITY
>
> base = iris
> names(base) = c("y", "x1", "x2", "x3", "species")
> base$constant = 5
> base$y_int = as.integer(base$y)
> base$w = as.vector(unclass(base$species) - 0.95)
>
> for(useWeights in c(FALSE, TRUE)){
+ for(model in c("ols", "pois")){
+ for(use_fe in c(FALSE, TRUE)){
+ cat(".")
+
+ my_weight = NULL
+ if(useWeights) my_weight = base$w
+
+ adj = 1
+ if(model == "ols"){
+ if(!use_fe){
+ res = feols(y ~ x1 + constant, base, weights = my_weight)
+ res_bis = lm(y ~ x1 + constant, base, weights = my_weight)
+ } else {
+ res = feols(y ~ x1 + constant | species, base, weights = my_weight)
+ res_bis = lm(y ~ x1 + constant + species, base, weights = my_weight)
+ }
+ } else {
+ if(!use_fe){
+ res = fepois(y_int ~ x1 + constant, base, weights = my_weight)
+ res_bis = glm(y_int ~ x1 + constant, base, weights = my_weight, family = poisson)
+ } else {
+ res = fepois(y_int ~ x1 + constant | species, base, weights = my_weight)
+ res_bis = glm(y_int ~ x1 + constant + species, base, weights = my_weight, family = poisson)
+ }
+ adj = 0
+ }
+
+ test(coef(res)["x1"], coef(res_bis)["x1"], "~")
+ test(se(res, se = "st", ssc = ssc(adj=adj))["x1"], se(res_bis)["x1"], "~")
+ # cat("Weight: ", useWeights, ", model: ", model, ", FE: ", use_fe, "\n", sep="")
+
+ }
+ }
+ }
........> cat("\n")
>
>
> ####
> #### ... Non linear tests ####
> ####
>
> chunk("NON LINEAR")
NON LINEAR
>
> base = iris
> names(base) = c("y", "x1", "x2", "x3", "species")
>
> tab = c("versicolor" = 5, "setosa" = 0, "virginica" = -5)
>
> fun_nl = function(a, b, spec){
+ res = as.numeric(tab[spec])
+ a*res + b*res^2
+ }
>
> est_nl = feNmlm(y ~ x1, base, NL.fml = ~fun_nl(a, b, species), NL.start = 1, family = "gaussian")
>
> base$var_spec = as.numeric(tab[base$species])
>
> est_lin = feols(y ~ x1 + var_spec + I(var_spec^2), base)
>
> test(coef(est_nl), coef(est_lin)[c(3, 4, 1, 2)], "~")
>
> ####
> #### ... Lagging ####
> ####
>
> # Different types of lag
> # 1) check no error in wide variety of situations
> # 2) check consistency
>
> chunk("LAGGING")
LAGGING
>
> data(base_did)
> base = base_did
>
> n = nrow(base)
>
> set.seed(0)
> base$y_na = base$y ; base$y_na[sample(n, 50)] = NA
> base$period_txt = letters[base$period]
> ten_dates = c("1960-01-15", "1960-01-16", "1960-03-31", "1960-04-05", "1960-05-12", "1960-05-25", "1960-06-20", "1960-07-30", "1965-01-02", "2002-12-05")
> base$period_date = as.Date(ten_dates, "%Y-%m-%d")[base$period]
> base$y_0 = base$y**2 ; base$y_0[base$id == 1] = 0
>
> # We compute the lags "by hand"
> base = base[order(base$id, base$period), ]
> base$x1_lag = c(NA, base$x1[-n]) ; base$x1_lag[base$period == 1] = NA
> base$x1_lead = c(base$x1[-1], NA) ; base$x1_lead[base$period == 10] = NA
> base$x1_diff = base$x1 - base$x1_lag
>
> # we create holes
> base$period_bis = base$period ; base$period_bis[base$period_bis == 5] = 50
> base$x1_lag_hole = base$x1_lag ; base$x1_lag_hole[base$period %in% c(5, 6)] = NA
> base$x1_lead_hole = base$x1_lead ; base$x1_lead_hole[base$period %in% c(4, 5)] = NA
>
> # we reshuffle the base
> base = base[sample(n), ]
>
> #
> # Checks consistency
> #
>
> cat("consistentcy...")
consistentcy...>
> test(lag(x1 ~ id + period, data = base), base$x1_lag)
> test(lag(x1 ~ id + period, -1, data = base), base$x1_lead)
>
> test(lag(x1 ~ id + period_bis, data = base), base$x1_lag_hole)
> test(lag(x1 ~ id + period_bis, -1, data = base), base$x1_lead_hole)
>
> test(lag(x1 ~ id + period_txt, data = base), base$x1_lag)
> test(lag(x1 ~ id + period_txt, -1, data = base), base$x1_lead)
>
> test(lag(x1 ~ id + period_date, data = base), base$x1_lag)
> test(lag(x1 ~ id + period_date, -1, data = base), base$x1_lead)
>
> cat("done.\nEstimations...")
done.
Estimations...>
> #
> # Estimations
> #
>
> # Poisson
>
> for(depvar in c("y", "y_na", "y_0")){
+ for(p in c("period", "period_txt", "period_date")){
+
+ base$per = base[[p]]
+
+ cat(".")
+
+ base$y_dep = base[[depvar]]
+ pdat = panel(base, ~ id + period)
+
+ if(depvar == "y_0"){
+ estfun = fepois
+ } else {
+ estfun = feols
+ }
+
+ est_raw = estfun(y_dep ~ x1 + x1_lag + x1_lead, base)
+ est = estfun(y_dep ~ x1 + l(x1) + f(x1), base, panel.id = "id,per")
+ est_pdat = estfun(y_dep ~ x1 + l(x1, 1) + f(x1, 1), pdat)
+ test(coef(est_raw), coef(est))
+ test(coef(est_raw), coef(est_pdat))
+
+ # Now diff
+ est_raw = estfun(y_dep ~ x1 + x1_diff, base)
+ est = estfun(y_dep ~ x1 + d(x1), base, panel.id = "id,per")
+ est_pdat = estfun(y_dep ~ x1 + d(x1, 1), pdat)
+ test(coef(est_raw), coef(est))
+ test(coef(est_raw), coef(est_pdat))
+
+ # Now we just check that calls to l/f works without checking coefs
+
+ est = estfun(y_dep ~ x1 + l(x1) + f(x1), base, panel.id = "id,per")
+ est = estfun(y_dep ~ l(x1, -1:1) + f(x1, 2), base, panel.id = c("id", "per"))
+ est = estfun(y_dep ~ l(x1, -1:1, fill = 1), base, panel.id = ~ id + per)
+ if(depvar == "y") test(est$nobs, n)
+ est = estfun(f(y_dep) ~ f(x1, -1:1), base, panel.id = ~ id + per)
+ }
+ }
.........>
> cat("done.\n\n")
done.
>
> #
> # Data table
> #
>
> cat("data.table...")
data.table...> # We just check there is no bug (consistency should be OK)
>
> library(data.table)
>
> base_dt = data.table(id = c("A", "A", "B", "B"),
+ time = c(1, 2, 1, 3),
+ x = c(5, 6, 7, 8))
>
> base_dt = panel(base_dt, ~id + time)
>
> base_dt[, x_l := l(x)]
> test(base_dt$x_l, c(NA, 5, NA, NA))
>
> lag_creator = function(dt) {
+ dt2 = panel(dt, ~id + time)
+ dt2[, x_l := l(x)]
+ return(dt2)
+ }
>
> base_bis = lag_creator(base_dt)
>
> base_bis[, x_d := d(x)]
>
> cat("done.\n\n")
done.
>
> #
> # Panel
> #
>
> # We ensure we get the right SEs whether we use the panel() or the panel.id method
> data(base_did)
>
> # Setting a data set as a panel...
> pdat = panel(base_did, ~id+period)
> pdat$fe = sample(15, nrow(pdat), replace = TRUE)
>
> base_panel = unpanel(pdat)
>
> est_pdat = feols(y ~ x1 | fe, pdat)
> est_panel = feols(y ~ x1 | fe, base_panel, panel.id = ~id+period)
>
> test(attr(vcov(est_pdat, attr = TRUE), "type"),
+ attr(vcov(est_panel, attr = TRUE), "type"))
>
> ####
> #### ... subset ####
> ####
>
> chunk("SUBSET")
SUBSET
>
> set.seed(5)
> base = iris
> names(base) = c("y", "x1", "x2", "x3", "species")
> base$fe_bis = sample(letters, 150, TRUE)
> base$x4 = rnorm(150)
> base$x1[sample(150, 5)] = NA
>
> fml = y ~ x1 + x2
>
> # Errors
> test(feols(fml, base, subset = ~species), "err")
> test(feols(fml, base, subset = -1:15), "err")
> test(feols(fml, base, subset = integer(0)), "err")
> test(feols(fml, base, subset = c(TRUE, TRUE, FALSE)), "err")
>
> # Valid use
> for(id_fun in 1:6){
+ estfun = switch(as.character(id_fun),
+ "1" = feols,
+ "2" = feglm,
+ "3" = fepois,
+ "4" = femlm,
+ "5" = fenegbin,
+ "6" = feNmlm)
+
+ for(id_fe in 1:5){
+
+ cat(".")
+
+ fml = switch(as.character(id_fe),
+ "1" = y ~ x1 + x2,
+ "2" = y ~ x1 + x2 | species,
+ "3" = y ~ x1 + x2 | fe_bis,
+ "4" = y ~ x1 + x2 + i(fe_bis),
+ "5" = y ~ x1 + x2 | fe_bis[x3])
+
+ if(id_fe == 5 && id_fun %in% 4:6) next
+
+ if(id_fun == 6){
+ res_sub_a = estfun(fml, base, subset = ~species == "setosa", NL.fml = ~ a*x4, NL.start = 0)
+ res_sub_b = estfun(fml, base, subset = base$species == "setosa", NL.fml = ~ a*x4, NL.start = 0)
+ res_sub_c = estfun(fml, base, subset = which(base$species == "setosa"), NL.fml = ~ a*x4, NL.start = 0)
+ res = estfun(fml, base[base$species == "setosa", ], NL.fml = ~ a*x4, NL.start = 0)
+ } else {
+ res_sub_a = estfun(fml, base, subset = ~species == "setosa")
+ res_sub_b = estfun(fml, base, subset = base$species == "setosa")
+ res_sub_c = estfun(fml, base, subset = which(base$species == "setosa"))
+ res = estfun(fml, base[base$species == "setosa", ])
+ }
+
+ test(coef(res_sub_a), coef(res))
+ test(coef(res_sub_b), coef(res))
+ test(coef(res_sub_c), coef(res))
+ test(se(res_sub_c, cluster = "fe_bis"), se(res, cluster = "fe_bis"))
+ }
+ cat("|")
+ }
.....|.....|.....|.....|.....|.....|> cat("\n")
>
>
> ####
> #### ... split ####
> ####
>
> chunk("split")
SPLIT
>
> base = setNames(iris, c("y", "x1", "x2", "x3", "species"))
>
> # simple: formula
> est = feols(y ~ x.[1:3], base, split = ~species %keep% "@^v")
> test(length(est), 2)
>
> est = feols(y ~ x.[1:3], base, fsplit = ~species %keep% c("set", "vers"))
> test(length(est), 3)
>
> est = feols(y ~ x.[1:3], base, split = ~species %drop% "set")
> test(length(est), 2)
>
> # simple: vector
> est = feols(y ~ x.[1:3], base, split = base$species %keep% "@^v")
> test(length(est), 2)
>
> est = feols(y ~ x.[1:3], base, split = base$species %keep% c("set", "vers"))
> test(length(est), 2)
>
> est = feols(y ~ x.[1:3], base, split = base$species %drop% "set")
> test(length(est), 2)
>
> # with bin
> est = feols(y ~ x.[1:2], base,
+ split = ~bin(x3, c("cut::5", "saint emilion", "pessac leognan",
+ "margaux", "saint julien", "entre deux mers")) %keep% c("saint e", "pe"))
> test(length(est), 2)
>
> est = feols(y ~ x.[1:2], base,
+ split = ~bin(x3, c("cut::5", "saint emilion", "pessac leognan", NA)) %drop% "@\\d")
> test(length(est), 2)
>
> # with argument
> est = feols(y ~ x.[1:3], base, split = ~species, split.keep = "@^v")
> test(length(est), 2)
>
> est = feols(y ~ x.[1:3], base, fsplit = ~species, split.keep = c("set", "vers"))
> test(length(est), 3)
>
> est = feols(y ~ x.[1:3], base, split = ~species, split.drop = "set")
> test(length(est), 2)
>
>
> ####
> #### ... Multiple estimations ####
> ####
>
> chunk("Multiple")
MULTIPLE
>
> set.seed(2)
> base = iris
> names(base) = c("y1", "x1", "x2", "x3", "species")
> base$y2 = 10 + rnorm(150) + 0.5 * base$x1
> base$x4 = rnorm(150) + 0.5 * base$y1
> base$fe2 = rep(letters[1:15], 10)
> base$fe2[50:51] = NA
> base$y2[base$fe2 == "a" & !is.na(base$fe2)] = 0
> base$x2[1:5] = NA
> base$x3[6] = NA
> base$x5 = rnorm(150)
> base$x6 = rnorm(150) + base$y1 * 0.25
> base$fe3 = rep(letters[1:10], 15)
>
>
> for(id_fun in 1:5){
+ estfun = switch(as.character(id_fun),
+ "1" = feols,
+ "2" = feglm,
+ "3" = fepois,
+ "4" = femlm,
+ "5" = feNmlm)
+
+ # Following weird bug ASAN on CRAN I cannot replicate, check 4/5 not performed on non Windows
+ if(Sys.info()["sysname"] != "Windows"){
+ if(id_fun %in% 4:5) next
+ }
+
+
+ est_multi = estfun(c(y1, y2) ~ x1 + sw(x2, x3), base, split = ~species)
+
+ k = 1
+ for(s in c("setosa", "versicolor", "virginica")){
+ for(lhs in c("y1", "y2")){
+ for(rhs in c("x2", "x3")){
+ res = estfun(.[lhs] ~ x1 + .[rhs], base[base$species == s, ], notes = FALSE)
+
+ test(coef(est_multi[[k]]), coef(res))
+ test(se(est_multi[[k]], cluster = "fe3"), se(res, cluster = "fe3"))
+ k = k + 1
+ }
+ }
+ }
+
+ cat("__")
+
+ est_multi = estfun(c(y1, y2) ~ x1 + csw0(x2, x3) + x4 | species + fe2, base, fsplit = ~species)
+ k = 1
+ all_rhs = c("", "x2", "x3")
+ for(s in c("all", "setosa", "versicolor", "virginica")){
+ for(lhs in c("y1", "y2")){
+ for(n_rhs in 1:3){
+ if(s == "all"){
+ res = estfun(xpd(..lhs ~ x1 + ..rhs + x4 | species + fe2, ..lhs = lhs, ..rhs = all_rhs[1:n_rhs]), base, notes = FALSE)
+ } else {
+ res = estfun(xpd(..lhs ~ x1 + ..rhs + x4 | species + fe2, ..lhs = lhs, ..rhs = all_rhs[1:n_rhs]), base[base$species == s, ], notes = FALSE)
+ }
+
+ vname = names(coef(res))
+ test(coef(est_multi[[k]])[vname], coef(res), "~" , 1e-6)
+ test(se(est_multi[[k]], cluster = "fe3")[vname], se(res, cluster = "fe3"), "~" , 1e-6)
+ k = k + 1
+ }
+ }
+ }
+
+ cat("|")
+ }
Flavor: r-oldrel-windows-x86_64