demest-package: Bayesian demographic estimation and forecasting.

demest-packageR Documentation

Bayesian demographic estimation and forecasting.

Description

Estimation and forecasting of cross-classified counts, rates, means, and probabilities, using Bayesian hierarchical models.

Details

Counts of people and events can be organized into demographic accounts, so that, for instance, population at the end of a period equals population at the start of the period plus births minus deaths. Inference can be carried out simultaneously for all components in the account.

Missing data, noisy data, and multiple datasets are all accommodated.

The key functions:

estimateModel

Model a single demographic series, using a single accurate dataset.

estimateCounts

Model a single demographic series, using multiple noisy datasets.

estimateAccount

Model a demographic account, using multiple noisy datasets.

Forecasts based on the estimation results are constructed using functions predictModel, predictCounts, and predictAccount.

Package demest uses S4 classes. It builds on package dembase, which provides the basic data structures and methods for manipulating cross-classified data.


StatisticsNZ/demest documentation built on Nov. 2, 2023, 7:56 p.m.