simulate_diffusion: A function to simulate a network-based diffusion proccess...

In ctross/STRAND: An R package for simulating and analyzing social network data in R and Stan

A function to simulate a network-based diffusion proccess using the STRAND framework

Description

This function allows users to simulate data using a NBDA model. The user must supply a list of STRAND data objects, a set of parameters, and a series of formulas following standard lm() style syntax.

Usage

simulate_diffusion(
  long_data,
  individual_focal_regression,
  social_focal_regression,
  social_target_regression,
  social_dyad_regression,
  individual_focal_parameters,
  social_focal_parameters,
  social_target_parameters,
  social_dyad_parameters,
  base_rates,
  ces_parameters = list(alpha = 0.95, sigma = 100, eta = 1)
)

Arguments

long_data	A list of data objects of class STRAND prepared using the make_strand_data() function. The data objects must include all covariates and trait diffusion data used in the formulas listed below.
individual_focal_regression	A formula for the effects of focal predictors on individual learning rate. This should be specified as in lm(), e.g.: ~ Age * Education.
social_focal_regression	A formula for the effects of focal predictors on social attention weights. This should be specified as in lm(), e.g.: ~ Age * Education.
social_target_regression	A formula for the effects of target predictors on social attention weights. This should be specified as in lm(), e.g.: ~ Age * Education.
social_dyad_regression	A formula for the predictors of dyadic relationships on social attention weights. This should be specified as in lm(), e.g.: ~ Kinship + Friendship.
individual_focal_parameters	A formula for the effects of focal predictors on individual learning rate. This should be specified as in lm(), e.g.: ~ Age * Education.
social_focal_parameters	A formula for the effects of focal predictors on social attention weights. This should be specified as in lm(), e.g.: ~ Age * Education.
social_target_parameters	A formula for the effects of target predictors on social attention weights. This should be specified as in lm(), e.g.: ~ Age * Education.
social_dyad_parameters	A formula for the predictors of dyadic relationships on social attention weights. This should be specified as in lm(), e.g.: ~ Kinship + Friendship.
base_rates	The intercept parameters for the individual and then social learing rates on logg-odds scale.
ces_parameters	A named list: alpha is the share of social influence owing to i to j ties (which implies 1-alpha is the share due to j to i ties), sigma is the elastisity of substitution, eta is returns to scale.

Value

A STRAND model object containing the data used, and the Stan results.

Examples

## Not run: 
fit = fit_NBDA_model(long_data=model_dat,
                     individual_focal_regression = ~ Age * NoFood,
                     social_block_regression = ~ Ethnicity,
                     social_focal_regression = ~ Age * NoFood,
                     social_target_regression = ~ Age * NoFood,
                     social_dyad_regression = ~ Relatedness + Friends * SameSex,
                     mode="mcmc",
                     stan_mcmc_parameters = list(seed = 1, chains = 1, 
                       parallel_chains = 1, refresh = 1, 
                       iter_warmup = 100, iter_sampling = 100,
                       max_treedepth = NULL, adapt_delta = NULL)
                      )

## End(Not run)

ctross/STRAND documentation built on April 17, 2025, 3:53 a.m.