Help for package twangContinuous

Type:

Package

Date:

2021-02-15

Title:

Toolkit for Weighting and Analysis of Nonequivalent Groups - Continuous Exposures

Version:

1.0.0

Description:

Provides functions for propensity score estimation and weighting for continuous exposures as described in Zhu, Y., Coffman, D. L., & Ghosh, D. (2015). A boosting algorithm for estimating generalized propensity scores with continuous treatments. Journal of Causal Inference, 3(1), 25-40. <doi:10.1515/jci-2014-0022>.

License:

GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]

Encoding:

UTF-8

LazyData:

true

VignetteBuilder:

knitr

Imports:

Rcpp (≥ 0.12.19), lattice (≥ 0.20-35), gbm (≥ 2.1.3), survey, xtable

Suggests:

knitr, rmarkdown

RoxygenNote:

7.1.1

NeedsCompilation:

Packaged:

2021-02-24 16:38:26 UTC; tug76052

Author:

Donna Coffman

[aut, cre], Brian Vegetabile [ctb]

Maintainer:

Donna Coffman <donna.coffman@gmail.com>

Depends:

R (≥ 3.5.0)

Repository:

CRAN

Date/Publication:

2021-02-26 09:50:02 UTC

Compute the balance table.

Description

'bal.table' is a generic function for extracting balance tables from 'ps.cont' objects, one for an unweighted analysis and one for the weighted analysis.

Usage

bal.table(x, digits = 3, ...)

Arguments

x

A 'ps.cont' object

digits

Number of digits to round to. Default: 3

...

Additional arguments.

Value

Returns a data frame containing the balance information. * 'unw' The unweighted correlation between the exposure and each covariate. * 'wcor' The weighted correlation between the exposure and each covariate.

Examples

  ## Not run: bal.table(test.mod)

A synthetic data set that was derived from a large scale observational study on youth in substance use treatment.

Description

A subset of measures from the Global Appraisal of Individual Needs biopsychosocial assessment instrument (GAIN) (Dennis, Titus et al. 2003) from sites that administered two different types of substance use disorder treatments (treatment “A” and treatment “B”). The Center for Substance Abuse Treatment (CSAT) funded the sites that administered these two SUD treatments. This dataset consists of 4,000 adolescents, 2,000 in each treatment group. The dataset includes substance use and mental health variables.

Usage

data("dat")

Format

A data frame with 4000 observations on the following 29 variables.

treat: a factor with levels A B
tss_0: a numeric vector
tss_3: a numeric vector
tss_6: a numeric vector
sfs8p_0: a numeric vector
sfs8p_3: a numeric vector
sfs8p_6: a numeric vector
eps7p_0: a numeric vector
eps7p_3: a numeric vector
eps7p_6: a numeric vector
ias5p_0: a numeric vector
dss9_0: a numeric vector
mhtrt_0: a numeric vector
sati_0: a numeric vector
sp_sm_0: a numeric vector
sp_sm_3: a numeric vector
sp_sm_6: a numeric vector
gvs: a numeric vector
ers21_0: a numeric vector
nproc: a numeric vector
ada_0: a numeric vector
ada_3: a numeric vector
ada_6: a numeric vector
recov_0: a numeric vector
recov_3: a numeric vector
recov_6: a numeric vector
subsgrps_n: a numeric vector
sncnt: a numeric vector
engage: a numeric vector

Details

tss_0: Traumatic Stress Scale - Baseline
tss_3: Traumatic Stress Scale - 3 months
tss_6: Traumatic Stress Scale - 6 months
sfs8p_0: Substance Frequency Scale - Baseline
sfs8p_3: Substance Frequency Scale - 3 months
sfs8p_6: Substance Frequency Scale - 6 months
eps7p_0: Emotional Problems Scale - Baseline
eps7p_3: Emotional Problems Scale - 3 months
eps7p_6: Emotional Problems Scale - 6 months
ias5p_0: Illegal Activities Scale - baseline
dss9_0: depressive symptom scale - baseline
mhtrt_0: mental health treatment in the past 90 days - baseline
sati_0: substance abuse treatment index - baseline
sp_sm_0: substance problem scale (past month) - baseline
sp_sm_3: substance problem scale (past month) - 3 months
sp_sm_6: substance problem scale (past month) - 6 months
gvs: General Victimization Scale
ers21_0: Environmental Risk Scale - baseline
ada_0: adjusted days abstinent (any in past 90) - baseline
ada_3: adjusted days abstinent (any in past 90) - 3 months
ada_6: adjusted days abstinent (any in past 90) - 6 months
recov_0: in recovery - baseline
recov_3: in recovery - 3 months
recov_6: in recovery - 6 months
subsgrps_n: primarily opioid using youth vs alcohol/marijuana using youth vs other

Source

Diamond, G., Godley, S. H., Liddle, H. A., Sampl, S., Webb, C., Tims, F. M., & Meyers, R. (2002). Five outpatient treatment models for adolescent marijuana use: a description of the Cannabis Youth Treatment Interventions. Addiction, 97, 70-83.

References

Examples

data(dat)
## maybe str(dat) ; plot(dat) ...

Extract propensity score weights

Description

Extracts propensity score weights from a ps.cont object.

Usage

get.weights(ps1, stop.method = "wcor", withSampW = TRUE)

Arguments

ps1

a ps.cont object

stop.method

indicates which set of weights to retrieve from the ps.cont object

withSampW

Returns weights with sample weights multiplied in, if they were provided in the original ps.cont call.

Value

a vector of weights

Author(s)

Donna L. Coffman

Plot the 'ps.cont' object.

Description

This function produces a collection of diagnostic plots for 'ps.cont' objects.

Usage

## S3 method for class 'ps.cont'
plot(x, plots = "optimize", subset = NULL, ...)

Arguments

x

'ps.cont' object

plots

An indicator of which type of plot is desired. The options are * '"optimize"' A plot of the balance criteria as a function of the GBM iteration. * '"es"' Plots of the standardized effect size of the pre-treatment variables before and after weighting

subset

Used to restrict which of the 'stop.method's will be used in the figure.

...

Additional arguments.

Value

Returns diagnostic plots for 'ps.cont' objects.

Examples

   ## Not run: plot(test.mod)

Gradient boosted propensity score estimation for continuous exposures

Description

'ps.cont' calculates propensity scores using gradient boosted regression and provides diagnostics of the resulting propensity scores.

Usage

ps.cont(
  formula,
  data,
  n.trees = 10000,
  interaction.depth = 3,
  shrinkage = 0.01,
  bag.fraction = 1,
  sampw = NULL,
  print.level = 2,
  verbose = FALSE,
  stop.method = "wcor",
  treat.as.cont = FALSE,
  ...
)

Arguments

formula

An object of class [formula]: a symbolic description of the propensity score model to be fit with the treatment variable on the left side of the formula and the potential confounding variables on the right side.

data

A dataset that includes the treatment as well as the potential confounding variables.

n.trees

Number of gbm iterations passed on to [gbm]. Default: 10000.

interaction.depth

A positive integer denoting the tree depth used in gradient boosting. Default: 3.

shrinkage

A numeric value between 0 and 1 denoting the learning rate. See [gbm] for more details. Default: 0.01.

bag.fraction

A numeric value between 0 and 1 denoting the fraction of the observations randomly selected in each iteration of the gradient boosting algorithm to propose the next tree. See [gbm] for more details. Default: 1.0.

sampw

Optional sampling weights.

print.level

The amount of detail to print to the screen. Default: 2.

verbose

If 'TRUE', lots of information will be printed to monitor the the progress of the fitting. Default: 'FALSE'.

stop.method

A method or methods of measuring and summarizing balance across pretreatment variables. Current options are 'wcor', the weighted Pearson correlation, summarized by using the mean across the pretreatment variables. Default: 'wcor'.

treat.as.cont

Used as a check on whether the exposure has greater than five levels. If it does not and treat.as.cont=FALSE, an error will be produced. Default: FALSE

...

Additional arguments that are passed to ps function.

Value

Returns an object of class 'ps.cont', a list containing

* 'gbm.obj' The returned [gbm] object.

* 'treat' The treatment variable.

* 'desc' A list containing balance tables for each method selected in 'stop.methods'. Includes a component for the unweighted analysis names “unw”. Each 'desc' component includes a list with the following components

- 'ess' The effective sample size.

- 'n' The number of subjects.

- 'max.wcor' The largest weighted correlation across the covariates.

- 'mean.wcor' The average weighted correlation across the covariates.

- 'rms.wcor' The root mean square of the absolute weighted correlations across the covariates.

- 'bal.tab' a (potentially large) table summarizing the quality of the weights for balancing the distribution of the pretreatment covariates. This table is best extracted using the [bal.table] method. See the help for [bal.table] for details.

- 'n.trees' The estimated optimal number of [gbm] iterations to optimize the loss function.

* 'ps.den' Denominator values for the propensity score weights.

* 'ps.num' Numerator values for the propensity score weights.

* 'w' The propensity score weights. If sampling weights are given then these are incorporated into these weights.

* 'datestamp' Records the date of the analysis.

* 'parameters' Saves the 'ps.cont' call.

* 'alerts' Text containing any warnings accumulated during the estimation.

* 'iters' A sequence of iterations used in the GBM fits used by 'plot' function.

* 'balance' The balance measures for the pretreatment covariates used in plotting.

* 'sampw' The sampling weights as specified in the 'sampw' argument.

* 'preds' Predicted values based on the propensity score model.

* 'covariates' Data frame containing the covariates used in the propensity score model.

* 'n.trees' Maximum number of trees considered in GBM fit.

* 'data' Data as specified in the 'data' argument.

References

Zhu, Y., Coffman, D. L., & Ghosh, D. (2015). A boosting algorithm for estimating generalized propensity scores with continuous treatments. *Journal of Causal Inference*, 3(1), 25-40. doi: 10.1515/jci-2014-0022

Examples

  ## Not run: test.mod <- ps.cont(tss_0 ~ sfs8p_0 + sati_0 + sp_sm_0
          + recov_0 + subsgrps_n + treat, data=dat
## End(Not run)

Displays a useful description of a 'ps.cont' object.

Description

Computes a short summary table describing the size of the dataset and the quality of the propensity score weights about a stored 'ps.cont' object.

Usage

## S3 method for class 'ps.cont'
summary(object, ...)

Arguments

object

A 'ps.cont' object

...

Additional arguments.

Value

*'n' The number of subjects. *'ess' The effective sample size. *'max.wcor' The largest weighted correlation across the covariates. *'mean.wcor' The average weighted correlation across the covariates. *'rms.wcor' The root mean square of the absolute weighted correlations across the covariates. *'iter' The estimated optimal number of [gbm] iterations to optimize the loss function.

Examples

   ## Not run: summary(test.mod)

Compute the balance table.

Description

Usage

Arguments

Value

See Also

Examples

A synthetic data set that was derived from a large scale observational study on youth in substance use treatment.

Description

Usage

Format

Details

Source

References

Examples

Extract propensity score weights

Description

Usage

Arguments

Value

Author(s)

See Also

Plot the 'ps.cont' object.

Description

Usage

Arguments

Value

See Also

Examples

Gradient boosted propensity score estimation for continuous exposures

Description

Usage

Arguments

Value

References

See Also

Examples

Displays a useful description of a 'ps.cont' object.

Description

Usage

Arguments

Value

See Also

Examples