The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
An all-in-one DAG-driven robustness check. Classify variables by causal role, compute the smallest and largest permissible back-door adjustment sets, and compare the significance of models.
See the Quick
Tour vignette for a 10 minute start-to-finish guide on how to use
DAGassist to identify causal roles, create reports, and
interpret the results.
See the Making
Reports vignette for details on producing publication-quality
DAGassist reports in LaTex, Word,
Excel, and plain text.
See the Parameter
Guide vignette for examples of how to get the most out of
DAGassist.
See the Supported
Models vignette for documentation on what engines
DAGassist supports.
You can install the development version of DAGassist from GitHub with:
install.packages("pak")
pak::pak("grahamgoff/DAGassist")Simply provide a dagitty() object and a regression call
and DAGassist will create a report classifying variables by causal role,
and compare the specified regression to minimal and canonical
models.
library(DAGassist)
DAGassist(dag = dag_model,
formula = feols(Y ~ X + M + C + Z + A + B, data = df))
#> DAGassist Report:
#>
#> Roles:
#> variable role X Y conf med col IO dMed dCol
#> X exposure x
#> Y outcome x x
#> Z confounder x
#> M mediator x
#> C collider x x x
#> A other
#> B other
#>
#> (!) Bad controls in your formula: {M, C}
#> Minimal controls 1: {Z}
#> Canonical controls: {A, B, Z}
#>
#> Formulas:
#> original: Y ~ X + M + C + Z + A + B
#>
#> Model comparison:
#>
#> +---+-----------+-----------+-----------+
#> | | Original | Minimal 1 | Canonical |
#> +===+===========+===========+===========+
#> | X | 0.452*** | 1.256*** | 1.256*** |
#> +---+-----------+-----------+-----------+
#> | | (0.032) | (0.027) | (0.026) |
#> +---+-----------+-----------+-----------+
#> | M | 0.514*** | | |
#> +---+-----------+-----------+-----------+
#> | | (0.021) | | |
#> +---+-----------+-----------+-----------+
#> | C | 0.343*** | | |
#> +---+-----------+-----------+-----------+
#> | | (0.019) | | |
#> +---+-----------+-----------+-----------+
#> | Z | 0.249*** | 0.311*** | 0.309*** |
#> +---+-----------+-----------+-----------+
#> | | (0.027) | (0.034) | (0.033) |
#> +---+-----------+-----------+-----------+
#> | A | 0.152*** | | 0.187*** |
#> +---+-----------+-----------+-----------+
#> | | (0.021) | | (0.026) |
#> +---+-----------+-----------+-----------+
#> | B | -0.069*** | | -0.057* |
#> +---+-----------+-----------+-----------+
#> | | (0.021) | | (0.026) |
#> +===+===========+===========+===========+
#> | + p < 0.1, * p < 0.05, ** p < 0.01, |
#> | *** p < 0.001 |
#> +===+===========+===========+===========+
# note: this example uses a test DAG and dataset, which was created
# silently to avoid confusion. These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.