qgcomp.noboot: Quantile g-computation for continuous, binary, and count outcomes under linearity/additivity

Description

This function estimates a linear dose-response parameter representing a one quantile increase in a set of exposures of interest. This function is limited to linear and additive effects of individual components of the exposure. This model estimates the parameters of a marginal structural model (MSM) based on g-computation with quantized exposures. Note: this function is valid only under linear and additive effects of individual components of the exposure, but when these hold the model can be fit with very little computational burden.

Usage

qgcomp.noboot(
  f,
  data,
  expnms = NULL,
  q = 4,
  breaks = NULL,
  id = NULL,
  weights,
  alpha = 0.05,
  bayes = FALSE,
  ...
)

Arguments

R style formula

data

data frame

expnms

character vector of exposures of interest

NULL or number of quantiles used to create quantile indicator variables representing the exposure variables. If NULL, then gcomp proceeds with un-transformed version of exposures in the input datasets (useful if data are already transformed, or for performing standard g-computation)

breaks

(optional) NULL, or a list of (equal length) numeric vectors that characterize the minimum value of each category for which to break up the variables named in expnms. This is an alternative to using 'q' to define cutpoints.

(optional) NULL, or variable name indexing individual units of observation (only needed if analyzing data with multiple observations per id/cluster). Note that qgcomp.noboot will not produce cluster-appropriate standard errors (this parameter is essentially ignored in qgcomp.noboot). Qgcomp.boot can be used for this, which will use bootstrap sampling of clusters/individuals to estimate cluster-appropriate standard errors via bootstrapping.

weights

"case weights" - passed to the "weight" argument of glm or bayesglm

alpha

alpha level for confidence limit calculation

bayes

use underlying Bayesian model (arm package defaults). Results in penalized parameter estimation that can help with very highly correlated exposures. Note: this does not lead to fully Bayesian inference in general, so results should be interpreted as frequentist.

...

arguments to glm (e.g. family)

Value

a qgcompfit object, which contains information about the effect measure of interest (psi) and associated variance (var.psi), as well as information on the model fit (fit) and information on the weights/standardized coefficients in the positive (pos.weights) and negative (neg.weights) directions.

Details

For continuous outcomes, under a linear model with no interaction terms, this is equivalent to g-computation of the effect of increasing every exposure by 1 quantile. For binary/count outcomes outcomes, this yields a conditional log odds/rate ratio(s) representing the change in the expected conditional odds/rate (conditional on covariates) from increasing every exposure by 1 quantile. In general, the latter quantity is not equivalent to g-computation estimates. Hypothesis test statistics and confidence intervals are based on using the delta estimate variance of a linear combination of random variables.

Examples

Run this code

# NOT RUN {
set.seed(50)
# linear model
dat <- data.frame(y=runif(50), x1=runif(50), x2=runif(50), z=runif(50))
qgcomp.noboot(f=y ~ z + x1 + x2, expnms = c('x1', 'x2'), data=dat, q=2, family=gaussian())
# logistic model
dat2 <- data.frame(y=rbinom(50, 1,0.5), x1=runif(50), x2=runif(50), z=runif(50))
qgcomp.noboot(f=y ~ z + x1 + x2, expnms = c('x1', 'x2'), data=dat2, q=2, family=binomial())
# poisson model
dat3 <- data.frame(y=rpois(50, .5), x1=runif(50), x2=runif(50), z=runif(50))
qgcomp.noboot(f=y ~ z + x1 + x2, expnms = c('x1', 'x2'), data=dat3, q=2, family=poisson())
# weighted model
N=5000
dat4 <- data.frame(y=runif(N), x1=runif(N), x2=runif(N), z=runif(N))
dat4$w=runif(N)*2
qdata = quantize(dat4, expnms = c("x1", "x2"))$data
(qgcfit <- qgcomp.noboot(f=y ~ z + x1 + x2, expnms = c('x1', 'x2'), data=dat4, q=4, 
                         family=gaussian(), weights=w))
qgcfit$fit
glm(y ~ z + x1 + x2, data = qdata, weights=w)
# }