Tipping point for a single unmeasured confounder (native tipr)

Native tipr::tip: an unmeasured confounder whose standardised mean difference between exposure groups is smd tips an observed ratio \(b\) (use the CI bound nearest the null) to 1 when its effect on the outcome is \(b^{1/smd}\) (Lin, Psaty & Kronmal 1998). Pairs with tipping_point_analysis, which targets missing-data sensitivity. Mirrors tipping_point_smd in the Python arm.

Usage

morie_sensitivity_tipping_point(estimate, smd = NULL, r2 = NULL, ...)

Arguments

estimate

Observed ratio (e.g. risk ratio).

smd

Standardised mean difference of the unmeasured confounder between exposure groups.

r2

Unsupported (the partial-R2 pathway is omitted_variable_bias); must be NULL.

...

Unused.

Value

A list of class morie_sensitivity_tipping_point with tipped_estimate (1) and confounder_outcome_effect.

References

D'Agostino McGowan, L. (2022). tipr: An R package for sensitivity analyses for unmeasured confounders. Journal of Open Source Software, 7(77), 4495.

Examples

str(morie_sensitivity_tipping_point(1.8, smd = 0.5), max.level = 1)
#> List of 7
#>  $ estimate                 : num 1.8
#>  $ smd                      : num 0.5
#>  $ r2                       : NULL
#>  $ tipped_estimate          : num 1
#>  $ confounder_outcome_effect: num 3.24
#>  $ method                   : chr "tip (native)"
#>  $ raw                      :List of 3
#>  - attr(*, "class")= chr [1:2] "morie_sensitivity_tipping_point" "list"