Estimations table (export the results of multiples estimations to a DF or to Latex)

Description

Aggregates the results of multiple estimations and displays them in the form of either a Latex table or a data.frame.

Usage

etable(
  ...,
  se = NULL,
  dof = NULL,
  cluster = NULL,
  stage = 2,
  agg = NULL,
  .vcov,
  .vcov_args = NULL,
  digits = 4,
  digits.stats = 5,
  tex,
  fitstat,
  title,
  coefstat = "se",
  ci = 0.95,
  sdBelow = NULL,
  keep,
  drop,
  order,
  dict,
  file,
  replace = FALSE,
  convergence,
  signifCode,
  label,
  float,
  subtitles = list("auto"),
  fixef_sizes = FALSE,
  fixef_sizes.simplify = TRUE,
  keepFactors = TRUE,
  family,
  powerBelow = -5,
  interaction.combine = " $\\times $ ",
  depvar = TRUE,
  style.tex = NULL,
  style.df = NULL,
  notes = NULL,
  group = NULL,
  extraline = NULL,
  fixef.group = NULL,
  placement = "htbp",
  drop.section = NULL,
  poly_dict = c("", " square", " cube"),
  postprocess.tex = NULL,
  postprocess.df = NULL,
  fit_format = "__var__",
  coef.just = NULL
)

setFixest_etable(
  digits = 4,
  digits.stats = 5,
  fitstat,
  coefstat = c("se", "tstat", "confint"),
  ci = 0.95,
  sdBelow = TRUE,
  keep,
  drop,
  order,
  dict,
  signifCode,
  float,
  fixef_sizes = FALSE,
  fixef_sizes.simplify = TRUE,
  family,
  powerBelow = -5,
  interaction.combine = " $\\times $ ",
  depvar,
  style.tex = NULL,
  style.df = NULL,
  notes = NULL,
  group = NULL,
  extraline = NULL,
  fixef.group = NULL,
  placement = "htbp",
  drop.section = NULL,
  postprocess.tex = NULL,
  postprocess.df = NULL,
  fit_format = "__var__",
  reset = FALSE
)

getFixest_etable()

esttable(
  ...,
  se = NULL,
  dof = NULL,
  cluster = NULL,
  stage = 2,
  agg = NULL,
  .vcov,
  .vcov_args = NULL,
  digits = 4,
  digits.stats = 5,
  fitstat,
  coefstat = "se",
  ci = 0.95,
  sdBelow = NULL,
  keep,
  drop,
  order,
  dict,
  file,
  replace = FALSE,
  convergence,
  signifCode,
  subtitles = list("auto"),
  fixef_sizes = FALSE,
  fixef_sizes.simplify = TRUE,
  keepFactors = TRUE,
  family,
  powerBelow = -5,
  interaction.combine = " $\\times $ ",
  depvar = TRUE,
  style.df = NULL,
  group = NULL,
  extraline = NULL,
  fixef.group = NULL,
  drop.section = NULL,
  poly_dict = c("", " square", " cube"),
  postprocess.df = NULL,
  fit_format = "__var__",
  coef.just = NULL
)

esttex(
  ...,
  se = NULL,
  dof = NULL,
  cluster = NULL,
  stage = 2,
  agg = NULL,
  .vcov,
  .vcov_args = NULL,
  digits = 4,
  digits.stats = 5,
  fitstat,
  title,
  coefstat = "se",
  ci = 0.95,
  sdBelow = NULL,
  keep,
  drop,
  order,
  dict,
  file,
  replace = FALSE,
  convergence,
  signifCode,
  label,
  float,
  subtitles = list("auto"),
  fixef_sizes = FALSE,
  fixef_sizes.simplify = TRUE,
  keepFactors = TRUE,
  family,
  powerBelow = -5,
  interaction.combine = " $\\times $ ",
  depvar = TRUE,
  style.tex = NULL,
  notes = NULL,
  group = NULL,
  extraline = NULL,
  fixef.group = NULL,
  placement = "htbp",
  drop.section = NULL,
  poly_dict = c("", " square", " cube"),
  postprocess.tex = NULL,
  fit_format = "__var__"
)

Arguments

Details

The function esttex is equivalent to the function etable with argument tex = TRUE.

The function esttable is equivalent to the function etable with argument tex = FALSE.

You can permanently change the way your table looks in Latex by using setFixest_etable. The following vignette gives an example as well as illustrates how to use the style and postprocessing functions: Exporting estimation tables.

When the argument postprocessing.tex is not missing, two additional tags will be included in the character vector returned by etable: "%start:tab\n" and "%end:tab\n". These can be used to identify the start and end of the tabular and are useful to insert code within the table environment.

Value

If tex = TRUE, the lines composing the Latex table are returned invisibly while the table is directly prompted on the console.

If tex = FALSE, the data.frame is directly returned. If the argument file is not missing, the data.frame is printed and returned invisibly.

Functions

• esttable: Exports the results of multiple fixest estimations in a Latex table.

• esttex: Exports the results of multiple fixest estimations in a Latex table.

How does digits handle the number of decimals displayed?

The default display of decimals is the outcome of an algorithm. Let's take the example of digits = 3 which "kind of" requires 3 significant digits to be displayed.

For numbers greater than 1 (in absolute terms), their integral part is always displayed and the number of decimals shown is equal to digits minus the number of digits in the integral part. This means that 12.345 will be displayed as 12.3. If the number of decimals should be 0, then a single decimal is displayed to suggest that the number is not whole. This means that 1234.56 will be displayed as 1234.5. Note that if the number is whole, no decimals are shown.

For numbers lower than 1 (in absolute terms), the number of decimals displayed is equal to digits except if there are only 0s in which case the first significant digit is shown. This means that 0.01234 will be displayed as 0.012 (first rule), and that 0.000123 will be displayed as 0.0001 (second rule).

Arguments keep, drop and order

The arguments keep, drop and order use regular expressions. If you are not aware of regular expressions, I urge you to learn it, since it is an extremely powerful way to manipulate character strings (and it exists across most programming languages).

For example drop = "Wind" would drop any variable whose name contains "Wind". Note that variables such as "Temp:Wind" or "StrongWind" do contain "Wind", so would be dropped. To drop only the variable named "Wind", you need to use drop = "^Wind$" (with "^" meaning beginning, resp. "$" meaning end, of the string => this is the language of regular expressions).

Although you can combine several regular expressions in a single character string using pipes, drop also accepts a vector of regular expressions.

You can use the special character "!" (exclamation mark) to reverse the effect of the regular expression (this feature is specific to this function). For example drop = "!Wind" would drop any variable that does not contain "Wind".

You can use the special character "%" (percentage) to make reference to the original variable name instead of the aliased name. For example, you have a variable named "Month6", and use a dictionary dict = c(Month6="June"). Thus the variable will be displayed as "June". If you want to delete that variable, you can use either drop="June", or drop="%Month6" (which makes reference to its original name).

The argument order takes in a vector of regular expressions, the order will follow the elements of this vector. The vector gives a list of priorities, on the left the elements with highest priority. For example, order = c("Wind", "!Inter", "!Temp") would give highest priorities to the variables containing "Wind" (which would then appear first), second highest priority is the variables not containing "Inter", last, with lowest priority, the variables not containing "Temp". If you had the following variables: (Intercept), Temp:Wind, Wind, Temp you would end up with the following order: Wind, Temp:Wind, Temp, (Intercept).

The argument extraline

The argument extraline adds well... extra lines to the table. It accepts either a list, or a one-sided formula.

If a one-sided formula: then the elements in the formula must represent either extraline macros, either fit statistics (i.e. valid types of the function fitstat). One new line will be added for each element of the formula, they will be appended right after the coefficients. To register extraline macros, you must first register them in extraline_register.

If a list: then the elements must be either: a) a logical scalar, b) a vector of the same length as the number of models, c) a function to be applied to each model and which returns a scalar, or d) a one-sided formula of extraline macros (registered with extraline_register) or valid fitstat types.

When a list, the elements of type a), b) and c) must have a name! Example: extraline = list("Controls" = TRUE) is good, extraline = list(TRUE) is bad. The name for element of type d) is optional. Example: extraline = list("^^My F-stat" = ~f) will add the row named "My F-stat" on top of the coefficients (for the placement, see the dedicated section), while extraline = list(~f) will add the F-stat row with its default name ("F-test") at its default placement (below the coefficients).

You can combine elements in the list, so that the following extraline = list(~r2, "Controls" = TRUE), ~f+ivf is valid.

Controlling the placement of extra lines

The arguments group, extraline and fixef.group allow to add customized lines in the table. They can be defined via a list where the list name will be the row name. By default, the placement of the extra line is right after the coefficients (except for fixef.group, covered in the last paragraph). For instance, group = list("Controls" = "x[[:digit:]]") will create a line right after the coefficients telling which models contain the control variables.

But the placement can be customized. The previous example (of the controls) will be used for illustration (the mechanism for extraline and fixef.group is identical).

The row names accept 2 special characters at the very start. The first governs the placement of the new line within the section: it can be equal to "^", meaning first line, or "_", meaning last line. The second character tells in which section the line should appear: it can be equal to "^", "-", or "_", meaning respectively the coefficients, the fixed-effects and the statistics section (which typically appear at the top, mid and bottom of the table).

Let's have some examples. Using the previous example, writing "^_Controls" would place the new line in at the top of the statistics section. Writing "_-Controls" places it as the last row of the fixed-effects section; "^^Controls" at the top row of the coefficients section; etc...

On top of that there are shortcuts to avoid writing the two special characters. If only one special character is found, it is assumed to reflect the section, unless it corresponds to the default section, a case where the character then reflects the position within the section. An example will make it clear. Writing "^Controls" would place the line at the top of the coefficients section (since the default placement would have been this section). "_Controls" would place it at the bottom of the statistics section.

The placement in fixef.group is defined similarly, only the default placement is different. Its default placement is at the top of the fixed-effects section. This means that the only difference with group and extraline is when a single special character is used. Here using, e.g., "^My FEs" would place the row at the bottom of the coefficients section, since "^" would refer to the section (and not the row within the section).

Author(s)

Laurent Berge

See Also

See also the main estimation functions femlm, feols or feglm. Use summary.fixest to see the results with the appropriate standard-errors, fixef.fixest to extract the fixed-effects coefficients.

Examples

aq = airquality

est1 = feols(Ozone ~ i(Month) / Wind + Temp, data = aq)
est2 = feols(Ozone ~ i(Month, Wind) + Temp | Month, data = aq)

# Displaying the two results in a single table
etable(est1, est2)

# keep/drop: keeping only interactions
etable(est1, est2, keep = " x ")
# or using drop  (see regexp help):
etable(est1, est2, drop = "^(Month|Temp|\\()")

# keep/drop: dropping interactions
etable(est1, est2, drop = " x ")
# or using keep ("!" reverses the effect):
etable(est1, est2, keep = "! x ")

# order: Wind variable first, intercept last (note the "!" to reverse the effect)
etable(est1, est2, order = c("Wind", "!Inter"))
# Month, then interactions, then the rest
etable(est1, est2, order = c("^Month", " x "))

#
# dict
#

# You can rename variables with dict = c(var1 = alias1, var2 = alias2, etc)
# You can also rename values taken by factors.
# Here's a full example:
dict = c(Temp = "Temperature", "Month::5"="May", "6"="Jun")
etable(est1, est2, dict = dict)
# Note the difference of treatment between Jun and May

# Assume the following dictionary:
dict = c("Month::5"="May", "Month::6"="Jun", "Month::7"="Jul",
         "Month::8"="Aug", "Month::9"="Sep")

# We would like to keep only the Months, but now the names are all changed...
# How to do?
# We can use the special character '%' to make reference to the original names.

etable(est1, est2, dict = dict, keep = "%Month")

#
# signifCode
#

etable(est1, est2, signifCode = c(" A"=0.01, " B"=0.05, " C"=0.1, " D"=0.15, " F"=1))

#
# Using the argument style to customize Latex exports
#

# If you don't like the default layout of the table, no worries!
# You can modify many parameters with the argument style

# To drop the headers before each section, use:
# Note that a space adds an extra line
style_noHeaders = style.tex(var.title = "", fixef.title = "", stats.title = " ")
etable(est1, est2, dict = dict, tex = TRUE, style.tex = style_noHeaders)

# To change the lines of the table + dropping the table footer
style_lines = style.tex(line.top = "\\toprule", line.bottom = "\\bottomrule",
                    tablefoot = FALSE)
etable(est1, est2, dict = dict, tex = TRUE, style.tex = style_lines)

# Or you have the predefined type "aer"
etable(est1, est2, dict = dict, tex = TRUE, style.tex = style.tex("aer"))

#
# Group and extraline
#

# Sometimes it's useful to group control variables into a single line
# You can achieve that with the group argument

setFixest_fml(..ctrl = ~ poly(Wind, 2) + poly(Temp, 2))
est_c0 = feols(Ozone ~ Solar.R, data = aq)
est_c1 = feols(Ozone ~ Solar.R + ..ctrl, data = aq)
est_c2 = feols(Ozone ~ Solar.R + Solar.R^2 + ..ctrl, data = aq)

etable(est_c0, est_c1, est_c2, group = list(Controls = "poly"))

# 'group' here does the same as drop = "poly", but adds an extra line
# with TRUE/FALSE where the variables were found

# 'extraline' adds an extra line, where you can add the value for each model
est_all  = feols(Ozone ~ Solar.R + Temp + Wind, data = aq)
est_sub1 = feols(Ozone ~ Solar.R + Temp + Wind, data = aq[aq$Month %in% 5:6, ])
est_sub2 = feols(Ozone ~ Solar.R + Temp + Wind, data = aq[aq$Month %in% 7:8, ])
est_sub3 = feols(Ozone ~ Solar.R + Temp + Wind, data = aq[aq$Month == 9, ])

etable(est_all, est_sub1, est_sub2, est_sub3,
       extraline = list("Sub-sample" = c("All", "May-June", "Jul.-Aug.", "Sept.")))

# You can monitor the placement of the new lines with two special characters
# at the beginning of the row name.
# 1) "^" or "_" which mean first or last line of the section
# 2) "^", "-" or "_" which mean the coefficients, the fixed-effects or the
# statistics section.
#
# Ex: starting with "^_" will place the line at the top of the stat. section
#     starting with "_-" will place the line at the bottom of the FEs section
#     etc.
#
# You can use a single character which will represent the section, unless
# it's

# Examples
etable(est_c0, est_c1, est_c2, group = list("_Controls" = "poly"))
etable(est_all, est_sub1, est_sub2, est_sub3,
       extraline = list("^Sub-sample" = c("All", "May-June", "Jul.-Aug.", "Sept.")))
# Note that since the default placement is the coefficients section,
# a single "^" then refers to the position within the section. We end
# up at the top of the coefficients section.

#
# fixef.group
#

# You can group the fixed-effects line with fixef.group

est_0fe = feols(Ozone ~ Solar.R + Temp + Wind, aq)
est_1fe = feols(Ozone ~ Solar.R + Temp + Wind | Month, aq)
est_2fe = feols(Ozone ~ Solar.R + Temp + Wind | Month + Day, aq)

# A) automatic way => simply use fixef.group = TRUE

etable(est_0fe, est_2fe, fixef.group = TRUE)

# Note that when grouping would lead to inconsistencies across models,
# it is avoided

etable(est_0fe, est_1fe, est_2fe, fixef.group = TRUE)

# B) customized way => use a list

etable(est_0fe, est_2fe, fixef.group = list("Dates" = "Month|Day"))

# Note that when a user grouping would lead to inconsistencies,
# the term partial replaces yes/no and the fixed-effects are not removed.

etable(est_0fe, est_1fe, est_2fe, fixef.group = list("Dates" = "Month|Day"))

# Using customized placement => as with 'group' and 'extraline',
# the user can control the placement of the new line.
# See the previous 'group' examples and the dedicated section in the help.

# On top of the coefficients:
etable(est_0fe, est_2fe, fixef.group = list("^^Dates" = "Month|Day"))

# Last line of the statistics
etable(est_0fe, est_2fe, fixef.group = list("_Dates" = "Month|Day"))



#
# Using custom functions to compute the standard errors
#

# You can customize the way you compute the SEs with the argument .vcov
# Let's use some covariances from the sandwich package

etable(est_c0, est_c1, est_c2, .vcov = sandwich::vcovHC)

# To add extra arguments to vcovHC, you need to use .vcov_args
etable(est_c0, est_c1, est_c2, .vcov = sandwich::vcovHC, .vcov_args = list(type = "HC0"))


#
# Customize which fit statistic to display
#

# You can change the fit statistics with the argument fitstat
# and you can rename them with the dictionnary
etable(est1, est2, fitstat = ~ r2 + n + G)

# If you use a formula, '.' means the default:
etable(est1, est2, fitstat = ~ ll + .)


#
# Computing a different SE for each model
#

est = feols(Ozone ~ Solar.R + Wind + Temp, data = aq)

#
# Method 1: use summary

s1 = summary(est, "standard")
s2 = summary(est, cluster = ~ Month)
s3 = summary(est, cluster = ~ Day)
s4 = summary(est, cluster = ~ Day + Month)

etable(list(s1, s2, s3, s4))

#
# Method 2: using a list in the argument 'cluster'

est_bis = feols(Ozone ~ Solar.R + Wind + Temp | Month, data = aq)
etable(list(est, est_bis), cluster = list("standard", ~ Month))

#
# Method 3: Using rep()

etable(rep(est, cluster = list("standard", ~ Month)))

# When using rep on 2 or more objects, you need to embed them in .l()
etable(rep(.l(est, est_bis), cluster = list("standard", ~ Month, ~ Day)))

# Using each to order differently
etable(rep(.l(est, est_bis), each = 3, cluster = list("standard", ~ Month, ~ Day)))