Package 'surveynnet'

Title: Neural Network for Complex Survey Data
Description: The surveynnet package extends the functionality of nnet (Venables and Ripley, 2002), which already supports survey weights, by enabling it to handle clustered and stratified data. It achieves this by incorporating design effects through the use of effective sample sizes in the calculations, performed by the package described in Valliant et al. (2023), by following the methods outlined by Chen and Rust (2017) and Valliant et al. (2018).
Authors: Aaron Cohen [aut, cre] , Raul Cruz-Cano [aut]
Maintainer: Aaron Cohen <[email protected]>
License: MIT + file LICENSE
Version: 1.0.0
Built: 2024-12-10 05:49:16 UTC
Source: https://github.com/237triangle/surveynnet

Help Index

Simple body fat example data

Description

Simple body fat example data

Usage

body_fat

Format

body_fat

A data frame with 12 rows and 9 columns:

Subject

Subject ID

group

group

Weight_kg

weight

Height_cm

height

Age

age

pct_body_fat

percent body fat

survey_wt

survey weight

stratum

stratum

cluster

cluster

Nhanes example

Description

Nhanes example

Usage

nhanes.demo

Format

nhanes.demo

A data frame with 6230 rows and 9 columns:

SEQN

Respondent sequence number

SDMVPSU

Masked variance pseudo-PSU

SDMVSTRA

Masked variance pseudo-stratum

WTMEC2YR

Full sample 2 year MEC exam weight

BMXHT

Standing height (cm)

BMXWT

Weight (kg)

BMXBMI

Body maxx index (kg/m**2)

BPXSY1

Systolic blood pressure

BPXDI1

Diastolic blood pressure

Predict response from fitted nnet, using new data

Description

Predict response from fitted nnet, using new data

Usage

## S3 method for class 'surveynnet'
predict(object, newdat, ...)

Arguments

object

The surveynnet object (returned by surveynnet())
newdat

The matrix or data frame of test examples. Must be of the same structure as the data matrix used to fit the surveynnet object.
...

arguments passed to or from other methods

Value

The matrix/vector of values returned by the trained network. Note: it is possible to pass type = "raw" or type = "class" as appropriate. See predict.nnet() for more details.

Examples

# From the example in `surveynnet` help file:
y <- body_fat$pct_body_fat
x <- body_fat[,c("Weight_kg", "Height_cm", "Age")]
weight <- body_fat$survey_wt
strat <- body_fat$stratum
clust <- body_fat$cluster
y[strat==1] <- y[strat==1] + 30*0.00015*rnorm(sum(strat==1))
y[strat==2] <- y[strat==2] + 30*0.15*rnorm(sum(strat==2))
myout <- surveynnet(x,y,weight = weight, strat = strat, clust=clust)
newdat <-  2*x+rnorm(dim(x)[1])
predict(myout, newdat = newdat)

Neural Net for Complex Survey Data

Description

The surveynnet package extends the functionality of nnet (Venables and Ripley, 2002), which already supports survey weights, by enabling it to handle clustered and stratified data. It achieves this by incorporating design effects through the use of effective sample sizes in the calculations, performed by the package described in Valliant et al. (2023), by following the methods outlined by Chen and Rust (2017) and Valliant et al. (2018).

Usage

surveynnet(x, y, weight, strat, clust, comp_cases = F, ...)

Arguments

x

Matrix or data frame of predictors. Must not contain any missing values.
y

Vector of targets / response values. Must not contain any missing values.
weight

The weights for each sample.
strat

The stratum for each sample.
clust

The cluster for each sample.
comp_cases

If TRUE, filter out missing values from x, y, weight, strat, and clust. Default FALSE. Note that in either case, the dimensions of all data mentioned above must agree.
...

Additional arguments to be passed into PracTools::deffCR or nnet::nnet. See documentation of those packages and functions for more details. Note that for the neural net (nnet), the default here is set to 3 layers ("size" parameter) and maximum iterations ("maxit" parameter) is set to 2000.

Value

A list containing two objects:

  • A dataframe with the fitted values of the neural nets, using: no weights ("fitted"), the user-inputted weights ("fitted_weighted"), and the new method that adjusts the weights by using a design effect incorporating cluster and strata ("fitted_deff").

  • The fitted neural network object (from nnet), using the novel design-effect based weights; this can be used to predict the outcomes for new observations.

References

  • Venables WN, Ripley BD (2002). Modern Applied Statistics with S, Fourth edition. Springer, New York. ISBN 0-387-95457-0, https://www.stats.ox.ac.uk/pub/MASS4/.

  • Chen, S., and K. F. Rust. 2017."An Extension of Kish’s Formula for Design Effects to Two- and Three-Stage Designs with Stratification.”, Journal of Survey Statistics and Methodology,5 (2): 111–30.

  • Valliant, R., J. A. Dever, and F. Kreuter. 2018. Practical Tools for Designing and Weighting Survey Samples .2nd ed. New York: Springer-Verlag.

  • Valliant, R., J. A. Dever, and F. Kreuter. 2023. PracTools: Tools for Designing and Weighting Survey Samples, Version 1.4 . https://CRAN.R-project.org/package=PracTools

Examples

# short example with body fat dataset
y <- body_fat$pct_body_fat
x <- body_fat[,c("Weight_kg", "Height_cm", "Age")]
weight <- body_fat$survey_wt
strat <- body_fat$stratum
clust <- body_fat$cluster
y[strat==1] <- y[strat==1] + 30*0.00015*rnorm(sum(strat==1))
y[strat==2] <- y[strat==2] + 30*0.15*rnorm(sum(strat==2))
myout <- surveynnet(x,y,weight = weight, strat = strat, clust=clust)
myout

# NHANES example
# Predicting Diastolic BP from BMI, Systolic BP and Height
# PLEASE NOTE: for this example, pass "nest=TRUE" into the
# "..." parameters of the main function `surveynnet`

x <- nhanes.demo[,c("BMXBMI", "BPXSY1", "BMXHT")]
weight <- nhanes.demo$WTMEC2YR
strat <- nhanes.demo$SDMVSTRA
clust <- nhanes.demo$SDMVPSU
y <- nhanes.demo$BPXDI1
myout <- surveynnet(x,y,weight = weight, strat = strat, clust=clust, nest=TRUE)
head(myout$results, 15)