These functions are used by nnc()
in the behaviorchange package to
compute the Numbers Needed for Change, but are also available for manual use.
convert.cer.to.d(
cer,
eer,
eventDesirable = TRUE,
eventIfHigher = TRUE,
dist = "norm",
distArgs = NULL,
distNS = "stats"
)convert.d.to.eer(
d,
cer,
eventDesirable = TRUE,
eventIfHigher = TRUE,
dist = "norm",
distArgs = list(),
distNS = "stats"
)
convert.d.to.nnc(d, cer, r = 1, eventDesirable = TRUE, eventIfHigher = TRUE)
convert.eer.to.d(
eer,
cer,
eventDesirable = TRUE,
eventIfHigher = TRUE,
dist = "norm",
distArgs = NULL,
distNS = "stats"
)
The converted value.
The Control Event Rate.
The Experimental Event Rate.
Whether an event is desirable or undesirable.
Whether scores above or below the threshold are considered 'an event'.
Used to specify the distribution to use to convert
between Cohen's d and the CER and EER. distArgs can be used to specify
additional arguments to the corresponding q
and p
functions, and
distNS to specify the namespace (i.e. package) from where to get the
distribution functions.
The value of Cohen's d.
The correlation between the determinant and behavior (for mediated Numbers Needed for Change).
Gjalt-Jorn Peters & Stefan Gruijters
Maintainer: Gjalt-Jorn Peters gjalt-jorn@userfriendlyscience.com
Gruijters, S. L., & Peters, G. Y. (2019). Gauging the impact of behavior change interventions: A tutorial on the Numbers Needed to Treat. PsyArXiv. tools:::Rd_expr_doi("10.31234/osf.io/2bau7")
nnc()
in the behaviorchange package.
convert.d.to.eer(d=.5, cer=.25);
convert.d.to.nnc(d=.5, cer=.25);
Run the code above in your browser using DataLab