Learn R Programming

TSEwgt (version 0.1.0)

Total Survey Error Under Multiple, Different Weighting Schemes

Description

Calculates total survey error (TSE) for a survey under multiple, different weighting schemes, using both scale-dependent and scale-independent metrics. Package works directly from the data set, with no hand calculations required: just upload a properly structured data set (see TESTWGT and its documentation), properly input column names (see functions documentation), and run your functions. For more on TSE, see: Weisberg, Herbert (2005, ISBN:0-226-89128-3); Biemer, Paul (2010) ; Biemer, Paul et.al. (2017, ISBN:9781119041672); etc.

Copy Link

Version

Install

install.packages('TSEwgt')

Monthly Downloads

128

Version

0.1.0

License

GPL (>= 2)

Maintainer

Joshua Miller

Last Published

July 2nd, 2019

Functions in TSEwgt (0.1.0)

FULLSDw

Full scale-dependent statistics
TESTWGT

A data set created by merging 1) "actual" data from a "gold standard" survey (A1, A2), and 2) data from another survey (Q1, Q2), including weights columns for that data (W1, W2). A1/Q1 and A2/Q2 are responses to the same two questions, asked to the same 10 respondents (ID), along the same 1-99 response scale.
AVERMSEw

Average root mean squared error (aRMSE)
FULLSIw

Full scale-independent statistics
AVEMSLEw

Average mean squared logarithmic error (aMSLE)
AVESMAPEw

Average symmetric mean absolute percentage error (aSMAPE)
AVEMAPEw

Average mean absolute percentage error (aMAPE)
AVERSEw

Average relative squared error (aRSE)
AVEMAEw

Average mean absolute error (aMAE)
AVERAEw

Average relative absolute error (aRAE)
AVEMSEw

Average mean squared error (aMSE) with bias-variance decomposition
AVERMSLEw

Average root mean squared logarithmic error (aRMSLE)
AVERRSEw

Average root relative squared error (aRRSE)