Releases: ncn-foreigners/nonprobsvy
Releases · ncn-foreigners/nonprobsvy
nonprobsvy version 0.1.0
Version of the package submitted to CRAN
nonprobsvy 0.1.0
- implemented population mean estimation using doubly robust, inverse probability weighting and mass imputation methods
- implemented inverse probability weighting models with Maximum Likelihood Estimation and Generalized Estimating Equations methods with
logit
,complementary log-log
andprobit
link functions. - implemented
generalized linear models
,nearest neighbours
andpredictive mean matching
methods for Mass Imputation - implemented
y
-yhat
andyhat
-yhat
predictive mean matching
- implemented bias correction estimators for doubly-robust approach
- implemented estimation methods when vector of population means/totals is available
- implemented variables selection with
SCAD
,LASSO
andMCP
penalization equations - implemented analytic and bootstrap (with parallel computation -
doParallel
package) variance for described estimators - added control parameters for models
- added S3 methods for object of
nonprob
class such asnobs
for samples sizepop.size
for population size estimationresiduals
for residuals of the inverse probability weighting modelcooks.distance
for identifying influential observations that have a significant impact on the parameter estimateshatvalues
for measuring the leverage of individual observationslogLik
for computing the log-likelihood of the model,AIC
(Akaike Information Criterion) for evaluating the model based on the trade-off between goodness of fit and complexity, helping in model selectionBIC
(Bayesian Information Criterion) for a similar purpose as AIC but with a stronger penalty for model complexityconfint
for calculating confidence intervals around parameter estimatesvcov
for obtaining the variance-covariance matrix of the parameter estimatesdeviance
for assessing the goodness of fit of the model
Unit tests
- added unit tests for IPW estimators
- added unit tests for MI estimators
- added unit tests for DR estimators
- added unit tests for variable selection models
- Multicore tests will only be performed after
TEST_NONPROBSVY_MULTICORE_DEVELOPER
is set to "true" via Sys.setenv
Github repository
- added automated R-cmd check
- added CRAN and codecov badges
Documentation
- added documentation for
nonprob
function - added documenation for
control
functions - added documentation for
link
functions
Full changelog: v0.1.0
Nonprobsvy
Nonprobsvy Inference With Nonprobability Samples
An R package for statistical inference with non-probability samples when auxiliary information
from external sources such as probability samples or population totals or means is available. Details can be found
in: Wu et al. (2020) doi:10.1080/01621459.2019.1677241, Kim et al. (2021) doi:10.1111/rssa.12696,