R/calculate_laspeyres.R

In REPS: Hedonic and Multilateral Index Methods for Real Estate Price Statistics

# This is the first main function (calculate laspeyres)

#' Calculate direct index according to the Laspeyres hedonic double imputation method
#'
#' By the parameters 'dependent_variable', 'continue_variable' and 'categorical_variables' as regression model is compiled.
#' With the model, a direct series of index figures is estimated by use of hedonic regression.
#'
#' N.B.: the independent variables must be entered transformed (and ready) in the parameters.
#' Hence, not: log(floor_area), but transform the variable in advance and then provide log_floor_area.
#' This does not count for the dependent variable. This should be entered untransformed/
#'
#' Within the data, it is not necessary to filter the data on relevant variables or complete records.
#' This is taken care of in the function.
#'
#' @author Farley Ishaak 
#'
#' @param dataset table with data (does not need to be a selection of relevant variables)
#' @param period_variable variable in the table with periods
#' @param dependent_variable usually the sale price
#' @param numerical_variables vector with quality determining numeric variables (no dummies)
#' @param categorical_variables vector with quality determining categorical variables (also dummies)
#' @param reference_period period or group of periods that will be set to 100 (numeric/string)
#' @param number_of_observations number of observations per period (default = TRUE)
#' @param imputation display the underlying average imputation values? (default = FALSE)
#' @importFrom stats na.omit
#' @importFrom stats lm
#' @importFrom stats predict
#' @importFrom stats runif
#' @return
#' table with index, imputation averages, number of observations and confidence intervals per period
#' @keywords internal
calculate_laspeyres <- function(dataset
                                , period_variable
                                , dependent_variable
                                , numerical_variables
                                , categorical_variables
                                , reference_period = NULL
                                , number_of_observations = FALSE
                                , imputation = FALSE) {
  
 
  
  independent_variables <- c(numerical_variables, categorical_variables)
  
  
  # Rename period_variable and transform to character
  names(dataset)[names(dataset) == period_variable] <- "period_var_temp"
  dataset[["period_var_temp"]] <- as.character(dataset[["period_var_temp"]])
  for (var in categorical_variables) dataset[[var]] <- as.factor(dataset[[var]])
  
  

  # Create list of periods
  period_list <- sort(unique(dataset$period_var_temp), decreasing = FALSE)
  
  # Calculate laspeyres imputations and numbers
  tbl_average_imputation <-
    calculate_hedonic_imputation(dataset_temp = dataset
                                 , period_temp = "period_var_temp"
                                 , dependent_variable_temp = dependent_variable
                                 , independent_variables_temp = independent_variables
                                 , number_of_observations_temp = number_of_observations
                                 , period_list_temp = period_list)
  
  
  # Calculate index
  Index <- calculate_index(tbl_average_imputation$period, tbl_average_imputation$average_imputation, reference_period = reference_period)
  
  # Create table
  laspeyres <- data.frame(period = tbl_average_imputation$period)
  
  if (number_of_observations == TRUE) {
    laspeyres$number_of_observations <- tbl_average_imputation$number_of_observations
  }
  if (imputation == TRUE) {
    laspeyres$Imputation <- tbl_average_imputation$average_imputation
  }
  
  laspeyres$Index <- Index
  
 
  
  return(laspeyres)
  
}