Stata 15 help for mi impute monotone

[MI] mi impute monotone -- Impute missing values in monotone data

Syntax

Default specification of prediction equations, basic syntax

mi impute monotone (uvmethod) ivars [= indepvars] [if] [weight] [, impute_options options]

Default specification of prediction equations, full syntax

mi impute monotone lhs [= indepvars] [if] [weight] [, impute_options options]

Custom specification of prediction equations

mi impute monotone cmodels [if] [weight], custom [impute_options options]

where lhs is lhs_spec [lhs_spec [...]] and lhs_spec is

(uvmethod [if] [, uvspec_options]) ivars

cmodels is (cond_spec) [(cond_spec) [...]] and a conditional specification, cond_spec, is

uvmethod ivar [rhs_spec] [if] [, uvspec_options]

rhs_spec includes varlist and expressions of imputation variables bound in parentheses.

ivar(s) (or newivar if uvmethod is intreg) is the name(s) of the imputation variable(s).

uvspec_options are ascontinuous, noisily, and the method-specific options as described in the manual entry for each univariate imputation method.

uvmethod Description ------------------------------------------------------------------------- regress linear regression for a continuous variable; [MI] mi impute regress pmm predictive mean matching for a continuous variable; [MI] mi impute pmm truncreg truncated regression for a continuous variable with a restricted range; [MI] mi impute truncreg intreg interval regression for a continuous partially observed (censored) variable; [MI] mi impute intreg logit logistic regression for a binary variable; [MI] mi impute logit ologit ordered logistic regression for an ordinal variable; [MI] mi impute ologit mlogit multinomial logistic regression for a nominal variable; [MI] mi impute mlogit poisson Poisson regression for a count variable; [MI] mi impute poisson nbreg negative binomial regression for an overdispersed count variable; [MI] mi impute nbreg -------------------------------------------------------------------------

options Description ------------------------------------------------------------------------- Main * custom customize prediction equations of conditional specifications augment perform augmented regression in the presence of perfect prediction for all categorical imputation variables bootstrap estimate model parameters using sampling with replacement

Reporting dryrun show conditional specifications without imputing data verbose show conditional specifications and impute data; implied when custom prediction equations are not specified report show report about each conditional specification

Advanced nomonotonechk do not check whether variables follow a monotone-missing pattern ------------------------------------------------------------------------- * custom is required when specifying customized predictions equations. You must mi set your data before using mi impute monotone; see [MI] mi set. You must mi register ivars as imputed before using mi impute monotone; see [MI] mi set. indepvars and rhs_spec may contain factor variables; see fvvarlist. fweights, aweights (regress, pmm, truncreg, and intreg only), iweights, and pweights are allowed; see weight.

Menu

Statistics > Multiple imputation

Description

mi impute monotone fills in missing values in multiple variables by using a sequence of independent univariate conditional imputation methods. Variables to be imputed, ivars, must follow a monotone-missing pattern (see [MI] intro substantive). You can perform separate imputations on different subsets of the data by specifying the by() option. You can also account for frequency, analytic (with continuous variables only), importance, and sampling weights.

Options

+------+ ----+ Main +-------------------------------------------------------------

custom is required to build customized prediction equations within the univariate conditional specifications. Otherwise, the default specification of prediction equations is assumed.

add(), replace, rseed(), double, by(); see [MI] mi impute.

augment specifies that augmented regression be performed if perfect prediction is detected. By default, an error is issued when perfect prediction is detected. The idea behind the augmented-regression approach is to add a few observations with small weights to the data during estimation to avoid perfect prediction. See The issue of perfect prediction during imputation of categorical data under Remarks and examples in [MI] mi impute for more information. augment is not allowed with importance weights. This option is equivalent to specifying augment within univariate specifications of all categorical imputation methods.

bootstrap specifies that posterior estimates of model parameters be obtained using sampling with replacement; that is, posterior estimates are estimated from a bootstrap sample. The default is to sample the estimates from the posterior distribution of model parameters or from the large-sample normal approximation of the posterior distribution. This option is useful when asymptotic normality of parameter estimates is suspect. This option is equivalent to specifying bootstrap within all univariate specifications.

The following options appear on a Specification dialog that appears when you click on the Create ... button of the Main tab.

uvspec_options are options specified within each univariate imputation method, uvmethod. uvspec_options include ascontinuous, noisily, and the method-specific options as described in the manual entry for each univariate imputation method.

ascontinuous specifies that categorical imputation variables corresponding to the current uvmethod be included as continuous in all prediction equations. This option is only allowed when uvmethod is logit, ologit, or mlogit.

noisily specifies that the output from the current univariate model fit to the observed data be displayed.

+-----------+ ----+ Reporting +--------------------------------------------------------

dots, noisily, nolegend; see [MI] mi impute. noisily specifies that the output from all univariate conditional models fit to the observed data be displayed. nolegend suppresses all imputation table legends which include a legend with the titles of the univariate imputation methods used, a legend about conditional imputation when conditional() is used within univariate specifications, and group legends when by() is specified.

dryrun specifies to show the conditional specifications that would be used to impute each variable without actually imputing data. This option is recommended for checking specifications of conditional models prior to imputation.

verbose specifies to show conditional specifications and impute data. verbose is implied when custom prediction equations are not specified.

report specifies to show a report about each univariate conditional specification. This option, in a combination with dryrun, is recommended for checking specifications of conditional models prior to imputation.

+----------+ ----+ Advanced +---------------------------------------------------------

force; see [MI] mi impute.

nomonotonechk specifies not to check that imputation variables follow a monotone-missing pattern. This option may be used to avoid potentially time-consuming checks. The monotonicity check may be time consuming when a large number of variables is being imputed. If you use nomonotonechk with a custom specification, make sure that you list the univariate conditional specifications in the order of monotonicity or you might obtain incorrect results.

The following option is available with mi impute but is not shown in the dialog box:

noupdate; see [MI] noupdate option.

Examples: Default prediction equations

Setup . webuse mheart5s0

Describe mi data . mi describe

Examine missing-data patterns . mi misstable nested

Impute bmi and age via linear regression . mi impute monotone (regress) bmi age = attack smokes hsgrad female, add(10)

Impute bmi using linear regression, age using predictive mean matching . mi impute monotone (regress) bmi (pmm, knn(5)) age = attack smokes hsgrad female, replace

Examples: Custom prediction equations

Setup . webuse mheart6s0, clear

Describe mi data . mi describe

Examine missing-data patterns . mi misstable nested

Specify custom equations for each of hightar, bmi, and age; include bmi squared in equation for age . mi impute monotone /// (logit hightar attack hsgrad female if smokes) /// (pmm bmi hightar attack smokes hsgrad female, knn(5)) /// (regress age bmi (bmi^2) hightar attack smokes hsgrad female), custom add(10)

Examples: Imputing on subsamples

Setup . webuse mheart5s0, clear

Impute bmi and age using predictive mean matching separately for males and females . mi impute monotone (pmm, knn(5)) bmi age = attack smokes hsgrad, add(10) by(female)

Examples: Conditional imputation

Setup . webuse mheart7s0, clear

Describe mi data . mi describe

Impute bmi and age using predictive mean matching, and smokes and hightar using logistic regression; impute hightar using only observations for which smokes==1 . mi impute monotone /// (pmm, knn(5)) bmi /// (pmm, knn(5)) age /// (logit, cond(if smokes==1)) hightar /// (logit) smokes = attack hsgrad female, add(10)

Stored results

mi impute monotone stores the following in r():

Scalars r(M) total number of imputations r(M_add) number of added imputations r(M_update) number of updated imputations r(k_ivars) number of imputed variables r(N_g) number of imputed groups (1 if by() is not specified)

Macros r(method) name of imputation method (monotone) r(ivars) names of imputation variables r(rngstate) random-number state used r(uvmethods) names of univariate conditional imputation methods r(by) names of variables specified within by()

Matrices r(N) number of observations in imputation sample in each group (per variable) r(N_complete) number of complete observations in imputation sample in each group (per variable) r(N_incomplete) number of incomplete observations in imputation sample in each group (per variable) r(N_imputed) number of imputed observations in imputation sample in each group (per variable)


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