regdistdicho() R function from [distdichoR]

normal, skew-normal or gamma distributed data (via linear regression)

Provides adjusted distributional estimates for the comparison of proportions for a dichotomised dependent continuous variable derived from a linear regression of the continuous outcome on the grouping variable and other covariates as described in Sauzet et al. 2015.


regdistdicho(mod, group_var, cp = 0, tail = c("lower", "upper"),
  conf.level = 0.95, dist = c("normal", "sk_normal", "gamma"), alpha = 1)

Arguments

mod: A linear model of the form lm(lhs ~ rhs) where lhs is a numeric variable giving the data values and rhs is the grouping variable and other covariates.
group_var: A character string specifying the name of the grouping variable.
cp: A numeric value specifying the cut point under which the distributional proportions are computed.
tail: A character string specifying the tail of the distribution in which the proportions are computed, must be either 'lower' (default) or 'upper'.
conf.level: Confidence level of the interval.
dist: A character string specifying the distribution of the error variable in the linear regression, must be either 'normal' (default), 'sk_normal or 'gamma'.
alpha: A numeric value specifying further parameter of the skew normal / gamma distribution.

Returns

A list with class 'distdicho' containing the following components: - data.name: The names of the data.

arguments: A list with the specified arguments.
parameter: The marginal mean, standard error and number of observations for both groups.
prop: The estimated proportions below / above the cut point for both groups.
dist.estimates: The difference in proportions, risk ratio and odds ratio of the groups.
se: The estimated standard error of the difference in proportions, the risk ratio and the odds ratio.
ci: The confidence intervals of the difference in proportions, the risk ratio and the odds ratio.
method: A character string indicating the used method.

Details

regdistdicho returns the distributional estimates and their standard errors (see Sauzet et al. 2014 and Peacock et al. 2012) for a difference in proportions, risk ratio and odds ratio. It also provides the distributional confidence intervals for the statistics estimated. The estimation is based on the marginal means of a linear regression of the outcome on the grouping variable and other covariates.

Examples


## Proportions of low birth weight babies among smoking and non-smoking mothers
## (data from Peacock et al. 1995)
mod_smoke <- lm(birthwt ~ smoke + gest, data = bwsmoke)
regdistdicho(mod = mod_smoke, group_var = 'smoke', cp = 2500, tail = 'lower')

References

Peacock J.L., Sauzet O., Ewings S.M., Kerry S.M. Dichotomising continuous data while retaining statistical power using a distributional approach. 2012 Statist. Med; 26:3089-3103. Sauzet, O., Peacock, J. L. Estimating dichotomised outcomes in two groups with unequal variances: a distributional approach. 2014 Statist. Med; 33 4547-4559 ;DOI: 10.1002/sim.6255. Sauzet, O., Brekenkamp, J., Brenne, S. , Borde, T., David, M., Razum, O., Peacock, J.L. 2015. A distributional approach to obtain adjusted differences in population at risk with a comparison with other regressions methods using perinatal data. In preparation. Peacock, J.L., Bland, J.M., Anderson, H.R.: Preterm delivery: effects of socioeconomic factors, psychological stress, smoking, alcohol, and caffeine. BMJ 311(7004), 531-535 (1995).

regdistdicho function