Control settings for the z-curve 2.0 density algorithm

Source: R/zcurve_density.R

All settings are passed to the density fitting algorithm. All unspecified settings are set to the default value. Setting model = "KD2" sets all settings to the default value irrespective of any other setting and fits z-curve as describe in Bartoš and Schimmack (2020) . In order to fit the z-curve 1.0 density algorithm, set model = "KD1" and go to control_density_v1

Arguments

version

Which version of z-curve should be fitted. Defaults to 2 = z-curve 2.0. Set to 1 in order to fit the original version of z-curve. For its settings page go to control_density_v1.

model

A type of model to be fitted, defaults to "KD2" (another possibility is "KD1" for the original z-curve 1.0, see control_density_v1 for its settings)

sig_level

An alpha level of the test statistics, defaults to .05

a

A beginning of fitting interval, defaults to qnorm(sig_level/2,lower.tail = F)

b

An end of fitting interval, defaults to 6

mu

Means of the components, defaults to seq(0,6,1)

sigma

A standard deviation of the components, "Don't touch this" \- Ulrich Schimmack, defaults to 1

theta_min

Lower limits for weights, defaults to rep(0,length(mu))

theta_max

Upper limits for weights, defaults to rep(1,length(mu))

max_iter

A maximum number of iterations for the nlminb optimization for fitting mixture model, defaults to 150

max_eval

A maximum number of evaluation for the nlminb optimization for fitting mixture model, defaults to 1000

criterion

A criterion to terminate nlminb optimization, defaults to 1e-03

bw

A bandwidth of the kernel density estimation, defaults to .10

aug

Augment truncated kernel density, defaults to TRUE

aug.bw

A bandwidth of the augmentation, defaults to .20

n.bars

A resolution of density function, defaults to 512

density_dbc

Use bckden to estimate a truncated kernel density, defaults to FALSE, in which case density is used

compute_FDR

Whether to compute FDR, leads to noticeable increase in computation, defaults to FALSE

criterion_FDR

A criterion for estimating the maximum FDR, defaults to .02

criterion_FDR_dbc

A criterion for estimating the maximum FDR using the bckden function, defaults to .01

precision_FDR

A maximum FDR precision, defaults to .05

References

Bartoš F, Schimmack U (2020). “Z-curve. 2.0: Estimating Replication Rates and Discovery Rates.” doi:10.31219/osf.io/wr93f , submitted for publication.

Examples

# to decrease the criterion and increase the number of iterations
ctrl <- list(
   max_iter  = 300,
   criterion = 1e-4
)
if (FALSE) zcurve(OSC.z, method = "density", control = ctrl)