Stata 15 help for _coef_table

Title

[P] _coef_table -- Displaying estimation results

Syntax

_coef_table [, options display_options eform_option diparm_options ]

options Description ------------------------------------------------------------------------- level(#) set confidence level; default is level(95)

first show only the first equation neq(#) show only the first # equations plus finish table with a continuation line separator(#) add a separator line for every # ancillary parameters notest suppress tests for ancillary parameters coeftitle(title) use title for coefficients column ptitle(title) super title for p-value column cititle(title) super title for confidence interval columns offsetonly1 report offset only for the first equation

nocnsreport do not display constraints fullcnsreport display all constraints

bmatrix(matname) row vector of coefficient estimates vmatrix(matname) matrix of variance estimates cnsmatrix(matname) constraints matrix dfmatrix(matname) row vector of degrees of freedom eqmatrix(matname) row vector identifying equation groups

sort sort rows by coefficient values within equation

dfci report parameter degrees of freedom with confidence intervals dfpvalues report parameter degrees of freedom with a test against zero

coeflegend display legend instead of statistics -------------------------------------------------------------------------

Description

_coef_table is an enhanced version of ereturn display; see [P] ereturn

Options

level(#) supplies the significance level for the confidence intervals of the coefficients; see [R] level.

first requests that Stata display only the first equation and make it appear as if only one equation was estimated.

neq(#) requests that Stata display only the first # equations and make it appear as if only # equations were estimated.

plus places a + symbol at the position of the dividing line between variable names and results on the bottom separation line produced by estimates display. This is useful if you plan on adding more output to the table.

separator(#) places a horizontal separator line between every # ancillary parameters.

notest suppresses the test statistic and p-value for ancillary parameters.

coeftitle(title) specifies the title for the coefficient column of the table. This option is ignored if eform() is specified.

ptitle(title) specifies the super title for the p-value column of the table.

cititle(title) specifies the super title for the confidence interval columns of the table.

offsetonly1 requests that _coef_table only report the offset for the first equation.

nocnsreport suppresses the display of constraints above the coefficient table. This option is ignored if constraints were not used to fit the model.

fullcnsreport specifies that all constraints be reported above the coefficient table. This includes automatic constraints implied for the o. and b. variable operators. This option is ignored if constraints were not used to fit the model.

bmatrix(matname) specifies that the coefficients are in matname instead of in e(b).

vmatrix(matname) specifies that the VCE matrix is matname instead of e(V). This option requires the bmatrix() option.

cnsmatrix(matname) specifies that the constraint matrix is matname instead of e(Cns). This option requires the bmatrix() option.

dfmatrix(matname) specifies that the degrees-of-freedom values are in matname. For mi estimation results, this option overrides the multiple-imputation degrees-of-freedom stored in e(mi_df); otherwise, this option overrides the contents of scalar e(df_r).

eqmatrix(matname) specifies that equations are grouped according to the elements in matname. The grouped equations will be delimited by titles taken from the equations in the column stripe attached to matname.

sort specifies that the table be sorted within equation on the coefficient values.

dfci specifies that table report parameter degrees of freedom with confidence intervals. p-values and their test statistics are suppressed.

dfpvalues specifies that table report parameter degrees of freedom with p-values and their test statistics. Confidence intervals are suppressed.

coeflegend; see [R] estimation options.

display_options: noci, nopvalues, noomitted, vsquish, noemptycells, baselevels, allbaselevels, nofvlabel, fvwrap(#), fvwrapon(style), cformat(%fmt), pformat(%fmt), sformat(%fmt), and nolstretch; see [R] estimation options.

eform_option is identified in [R] eform_option. Also see Exponentiated form below.

diparm_options is one or more diparm(diparm_args) options, where diparm_args is either __sep__ or anything accepted by the _diparm command; see [P] _diparm.

Although diparm_options are allowed, we recommend that you identify the number of ancillary parameters by setting e(k_aux); see Ancillary parameters.

Remarks

Remarks are presented under the following headings:

Automatic behavior Ancillary parameters Exponentiated form

Automatic behavior

_coef_table uses the following scalars and macros from e():

Scalar Description --------------------------------------------------------------------- e(k_eq) number of equations in e(b) e(k_aux) number of ancillary parameters in e(b) e(k_extra) number of extra statistics stored in e(b) e(k_eform) number of equations allowed to be affected by an eform_option; by default, only the first equation is affected ---------------------------------------------------------------------

Macro Description --------------------------------------------------------------------- e(diparm#) arguments to be supplied to _diparm e(diparm_opt#) extra options to be added to the call to _diparm for the ancillary parameter stored in equation #, typically noprob ---------------------------------------------------------------------

Ancillary parameters

Although diparm_options are allowed, we recommend that you identify the number of ancillary parameters by setting e(k_aux); for example,

ereturn scalar k_aux = 2

identifies that there are two ancillary parameters. If you want to display a transform of one or more ancillary parameters, identify them by setting e(diparm#); for example,

ereturn local diparm1 lnsigma, exp label("sigma")

specifies the arguments to _diparm, just like diparm_options.

Exponentiated form

_coef_table will display the coefficient table in exponentiated form when supplied with an eform_option; see [R] eform_option.

Although the eform and eform(string) options are always allowed, the properties of the commands identified in e(cmd) and e(cmd2) will determine which other eform_option is allowed (where the property matches the option). Thus, in order for the or option to be allowed, e(cmd) must have the "or" property; see [P] program for information about setting the properties of programs.

e(k_eform) determines which equations are affected by an eform_option; by default, only the first equation is affected.

Stored results

_coef_table stores the following in r():

Scalars r(level) confidence level of confidence intervals

Macros r(label#) label on the #th coefficient, such as (base), (omitted), (empty), or (constrained) r(table) information from the coefficient table (see below)

r(table) contains the following information for each coefficient:

b coefficient value se standard error t/z test statistic for coefficient pvalue observed significance level for t/z ll lower limit of confidence interval ul upper limit of confidence interval df degrees of freedom associated with coefficient crit critical value associated with t/z eform indicator for exponentiated coefficients


© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index