estimRoundingError

Estimate rounding error based on given sample of metric values
The idea is to check at which level of rounding the sample values do not change.

Fit parametric models for time-to-event data that show an initial
'incubation period', i.e., a variable delay phase where the hazard is zero. The
delayed Weibull distribution serves as foundational data model. The
specific method of 'MPSE' (maximum product of spacings estimation) and MLE-based methods are used for parameter
estimation. Bootstrap confidence intervals for parameters and significance
tests in a two group setting are provided.

Matthias Kuhn

incubate

Parametric Time-to-Event Analysis with Variable Incubation
Phases

estimRoundingError function

<dl><dt>obs</dt>
<dd>numeric. Metric values from a sample to estimate the corresponding rounding error</dd>
<dt>roundDigits</dt>
<dd>integer. Which level of rounding to test? Negative numbers round to corresponding powers of 10</dd>
<dt>maxObs</dt>
<dd>integer. How many observations to consider at most? If the provided sample has more observations a sub-sample is used.</dd></dl>

Arguments

Estimate rounding error based on given sample of metric values
The idea is to check at which level of rounding the sample values do not change. — estimRoundingError

<dl>

<dt>obs</dt>
<dd>numeric. Metric values from a sample to estimate the corresponding rounding error</dd>


<dt>roundDigits</dt>
<dd>integer. Which level of rounding to test? Negative numbers round to corresponding powers of 10</dd>


<dt>maxObs</dt>
<dd>integer. How many observations to consider at most? If the provided sample has more observations a sub-sample is used.</dd>

</dl>

estimRoundingError: Estimate rounding error based on given sample of metric values The idea is to check at which level of rounding the sample values do not change.

Description

Usage

Value

Arguments