computePopulationT: Computes population counts at time instants t >t0.

In bogdanoancea/inference: R package for computing the number of individuals in the target population conditioned on the number of individuals detected by the MNO and auxiliary information.

Description

Computes the distribution of the population counts for all times instants t > t0. For details of the theoretical background behind this distribution an interested reader can consult the description of the methodological framework https://webgate.ec.europa.eu/fpfis/mwikis/essnetbigdata/images/f/fb/WPI_Deliverable_I3_A_proposed_production_framework_with_mobile_network_data_2020_05_31_draft.pdf.

Usage

computePopulationT(
  nt0,
  nnetODFileName,
  zip = TRUE,
  rndVal = FALSE,
  ciprob = NULL,
  method = "ETI"
)

Arguments

nt0	The population at t0.
nnetODFileName	the name of the file where the population moving from one region to another is stored. This is an output of the aggregation package.
zip	If TRUE the file where where the population moving from one region to another is stored is a zipped csv file, otherwise it is simple csv file.
rndVal	Controls if the random values generated for each t >t0 are returned or not in the result of this function. If TRUE, the random values generated according to the corresponding distribution are returned in the results, if FALSE only the summary statistics for each t>t0 and region are returned.
ciprob	Value of probability of the CI (between 0 and 1) to be estimated. If NULL the default value is 0.89.
method	The method to compute credible intervals. It could have 2 values, 'ETI' or 'HDI'. The default value is 'ETI.

Value

A list with one element for each time instant (including t0). Each element of the list is also a list with one or two elements, depending on the value of the rndVal parameter. If rndVal is TRUE there are two elements in the list corresponding to time instant t. The first one is a data.table object with some descriptive statistics for the population count at time t, containing the following columns:region, Mean, Mode, Median, Min, Max, Q1, Q3, IQR, SD, CV, CI_LOW, CI_HIGH. The second one is a data.table object with the random values for population count generated for each region, with the following columns: region, iter, NPop. If rndVal is FALSE the list for time instant t contains only the first element previously mentioned. The name of the list element corresponding to time instant t is 't' and the name of the two list elements giving the descriptive statistics and random values for time t are 'stats' and 'rnd_values'.

References

https://github.com/MobilePhoneESSnetBigData

bogdanoancea/inference documentation built on Nov. 28, 2020, 9:20 p.m.