report.etable

report.etable(
    models,
    type='gt',
    signif_code=None,
    coef_fmt='b \n (se)',
    custom_stats=None,
    custom_model_stats=None,
    keep=None,
    drop=None,
    exact_match=False,
    labels=None,
    cat_template=None,
    show_fe=True,
    show_se_type=True,
    felabels=None,
    notes='',
    model_heads=None,
    head_order='dh',
    file_name=None,
    **kwargs,
)

Generate a table summarizing the results of multiple regression models. It supports various output formats including html (via great tables), markdown, and LaTeX.

Parameters

Name	Type	Description	Default
models	A supported model object (Feols, Fepois, Feiv, FixestMulti) or a list of	Feols, Fepois & Feiv models. The models to be summarized in the table.	required
type	str	Type of output. Either “df” for pandas DataFrame, “md” for markdown, “gt” for great_tables, or “tex” for LaTeX table. Default is “gt”.	`'gt'`
signif_code	list	Significance levels for the stars. Default is None, which sets [0.001, 0.01, 0.05]. If None, no stars are printed.	`None`
coef_fmt	str	The format of the coefficient (b), standard error (se), t-stats (t), and p-value (p). Default is `"b \n (se)"`. Spaces , parentheses `()`, brackets `[]`, newlines `\n` are supported.	`'b \n (se)'`
custom_stats	Optional[dict]	A dictionary of custom statistics that can be used in the coef_fmt string to be displayed in the coefficuent cells analogously to “b”, “se” etc. The keys are the names of the custom statistics, and the values are lists of lists, where each inner list contains the custom statistic values for all coefficients each model. Note that “b”, “se”, “t”, or “p” are reserved and cannot be used as keys.	`None`
custom_model_stats	Optional[dict]	A dictionary of custom model statistics or model information displayed in a new line in the bottom panel of the table. The keys are the names of the statistics (i.e. entry in the first column) and the values are a lists of the same length as the number of models. Default is None.	`None`
keep	Optional[Union[list, str]]	The pattern for retaining coefficient names. You can pass a string (one pattern) or a list (multiple patterns). Default is keeping all coefficients. You should use regular expressions to select coefficients. “age”, # would keep all coefficients containing age r”^tr”, # would keep all coefficients starting with tr r”\d$“, # would keep all coefficients ending with number Output will be in the order of the patterns.	`None`
drop	Optional[Union[list, str]]	The pattern for excluding coefficient names. You can pass a string (one pattern) or a list (multiple patterns). Syntax is the same as for `keep`. Default is keeping all coefficients. Parameter `keep` and `drop` can be used simultaneously.	`None`
exact_match	Optional[bool]	Whether to use exact match for `keep` and `drop`. Default is False. If True, the pattern will be matched exactly to the coefficient name instead of using regular expressions.	`False`
labels	Optional[dict]	A dictionary to relabel the variables. The keys in this dictionary are the original variable names, which correspond to the names stored in the `_coefnames` attribute of the model. The values in the dictionary are the new names you want to assign to these variables. Note that interaction terms will also be relabeled using the labels of the individual variables. The command is applied after the `keep` and `drop` commands.	`None`
cat_template	Optional[str]	Template to relabel categorical variables. None by default, which applies no relabeling. Other options include combinations of “{variable}” and “{value}”, e.g. “{variable}::{value}” to mimic fixest encoding. But “{variable}–{value}” or “{variable}{value}” or just “{value}” are also possible.	`None`
show_fe	Optional[bool]	Whether to show the rows with fixed effects markers. Default is True.	`True`
show_se_type	Optional[bool]	Whether to show the rows with standard error type. Default is True.	`True`
felabels	Optional[dict]	A dictionary to relabel the fixed effects. Only needed if you want to relabel the FE lines with a different label than the one specied for the respective variable in the labels dictionary. The command is applied after the `keep` and `drop` commands.	`None`
digits		The number of digits to round to.	required
thousands_sep		The thousands separator. Default is False.	required
scientific_notation		Whether to use scientific notation. Default is True.	required
scientific_notation_threshold		The threshold for using scientific notation. Default is 10_000.	required
notes	str	Custom table notes. Default shows the significance levels and the format of the coefficient cell.	`''`
model_heads	Optional[list]	Add custom headlines to models when output as df or latex. Length of list must correspond to number of models. Default is None.	`None`
head_order	Optional[str]	String to determine the display of the table header when output as df or latex. Allowed values are “dh”, “hd”, “d”, “h”, or ““. When head_order is”dh”, the dependent variable is displayed first, followed by the custom model_heads (provided the user has specified them). With “hd” it is the other way around. When head_order is “d”, only the dependent variable and model numbers are displayed and with “” only the model numbers. Default is “dh”.	`'dh'`
file_name	Optional[str]	The name/path of the file to save the LaTeX table to. Default is None.	`None`

Returns

Name	Type	Description
	pandas.DataFrame	A styled DataFrame with the coefficients and standard errors of the models. When output is “tex”, the LaTeX code is returned as a string.

Examples

For more examples, take a look at the regression tables and summary statistics vignette.

import pyfixest as pf

# load data
df = pf.get_data()
fit1 = pf.feols("Y~X1 + X2 | f1", df)
fit2 = pf.feols("Y~X1 + X2 | f1 + f2", df)

pf.etable([fit1, fit2])

	Y
	(1)	(2)
coef
X1	-0.950*** (0.067)	-0.924*** (0.062)
X2	-0.174*** (0.018)	-0.174*** (0.015)
fe
f2	-	x
f1	x	x
stats
Observations	997	997
S.E. type	by: f1	by: f1
R²	0.489	0.659
R² Within	0.239	0.303
Significance levels: * p < 0.05, p < 0.01, * p < 0.001. Format of coefficient cell: Coefficient (Std. Error)