Заметки по R: Иерархический мультиномиальный логит
24.05.2016
Загружаем нужные библиотеки:
library("knitr")
library("dplyr") # стратегия Разделяй - Властвуй - Соединяй
library("reshape2") # melt - cast
library("ggplot2") # графики
library("MCMCpack")
library("haven")
library("bayesm")
library("stringr")help("rhierMnlRwMixture")Стащено из http://www.r-bloggers.com/lets-do-some-more-hierarchical-bayes-choice-modeling-in-r/: Оценивается мультиномиальный логит:
Стащено из http://www.r-bloggers.com/lets-do-some-more-hierarchical-bayes-choice-modeling-in-r/:
Читаем файл
df <- read_spss("~/Downloads/conjoint_1.sav")Посмотрим на данные:
glimpse(df)## Observations: 296
## Variables: 254
## $ id (dbl) 93, 105, 124, 127, 141, 158, 161, 169, 1...
## $ version (dbl) 40, 72, 97, 32, 99, 62, 97, 30, 75, 31, ...
## $ T1_C1_Minutes (dbl) 4, 1, 4, 3, 4, 6, 4, 6, 3, 3, 4, 7, 5, 3...
## $ T1_C1_Gigabytes (dbl) 1, 7, 4, 1, 10, 3, 4, 5, 9, 6, 9, 8, 3, ...
## $ T1_C1_Price (dbl) 4, 5, 3, 4, 5, 5, 3, 2, 5, 4, 5, 2, 2, 4...
## $ T1_C1_Host_provider (dbl) 4, 3, 1, 3, 3, 4, 1, 4, 3, 1, 2, 1, 4, 3...
## $ T1_C1_Personalization (dbl) 1, 1, 1, 2, 2, 1, 1, 1, 1, 2, 1, 2, 2, 2...
## $ T1_C1_Payment (dbl) 2, 2, 1, 2, 2, 1, 1, 1, 2, 2, 2, 1, 1, 2...
## $ T1_C1_Quantity_sim (dbl) 2, 2, 1, 2, 2, 3, 1, 3, 2, 1, 3, 1, 2, 3...
## $ T1_C2_Minutes (dbl) 3, 4, 5, 6, 1, 1, 5, 2, 7, 2, 7, 3, 6, 4...
## $ T1_C2_Gigabytes (dbl) 5, 2, 3, 8, 3, 9, 3, 6, 2, 9, 8, 7, 2, 7...
## $ T1_C2_Price (dbl) 5, 2, 5, 2, 3, 4, 5, 5, 3, 5, 4, 3, 5, 3...
## $ T1_C2_Host_provider (dbl) 3, 3, 4, 2, 2, 2, 4, 1, 1, 4, 3, 2, 2, 1...
## $ T1_C2_Personalization (dbl) 1, 1, 2, 1, 1, 2, 2, 2, 1, 1, 1, 2, 1, 1...
## $ T1_C2_Payment (dbl) 2, 2, 2, 1, 2, 2, 2, 2, 2, 1, 2, 1, 2, 1...
## $ T1_C2_Quantity_sim (dbl) 1, 3, 2, 2, 3, 2, 2, 2, 3, 2, 2, 2, 2, 2...
## $ T1_C3_Minutes (dbl) 7, 2, 6, 4, 6, 7, 6, 1, 1, 7, 1, 5, 4, 7...
## $ T1_C3_Gigabytes (dbl) 2, 9, 6, 9, 6, 8, 6, 9, 7, 10, 4, 9, 5, ...
## $ T1_C3_Price (dbl) 2, 1, 4, 5, 2, 3, 4, 1, 4, 2, 2, 1, 1, 5...
## $ T1_C3_Host_provider (dbl) 1, 1, 2, 2, 4, 3, 2, 2, 2, 4, 4, 3, 1, 1...
## $ T1_C3_Personalization (dbl) 2, 1, 1, 1, 2, 2, 1, 2, 1, 2, 2, 1, 2, 1...
## $ T1_C3_Payment (dbl) 1, 2, 1, 1, 1, 2, 1, 2, 1, 2, 1, 2, 2, 1...
## $ T1_C3_Quantity_sim (dbl) 3, 1, 1, 3, 1, 1, 1, 1, 3, 1, 1, 2, 3, 3...
## $ T1_C4_Minutes (dbl) 2, 7, 3, 7, 3, 3, 3, 4, 5, 5, 5, 2, 7, 2...
## $ T1_C4_Gigabytes (dbl) 8, 5, 7, 6, 8, 7, 7, 10, 4, 8, 10, 3, 8,...
## $ T1_C4_Price (dbl) 1, 4, 1, 3, 1, 2, 1, 3, 2, 1, 3, 4, 3, 2...
## $ T1_C4_Host_provider (dbl) 1, 2, 3, 1, 3, 1, 3, 3, 2, 3, 1, 4, 3, 4...
## $ T1_C4_Personalization (dbl) 2, 2, 2, 2, 1, 1, 2, 1, 2, 1, 2, 1, 1, 1...
## $ T1_C4_Payment (dbl) 1, 1, 1, 2, 2, 1, 1, 1, 1, 1, 1, 2, 1, 1...
## $ T1_C4_Quantity_sim (dbl) 3, 2, 2, 1, 2, 2, 2, 1, 2, 2, 3, 3, 1, 1...
## $ T1_C5_Minutes (dbl) 1, 3, 1, 2, 5, 5, 1, 5, 2, 1, 3, 4, 3, 6...
## $ T1_C5_Gigabytes (dbl) 3, 8, 1, 3, 2, 1, 1, 1, 6, 5, 2, 5, 10, ...
## $ T1_C5_Price (dbl) 3, 3, 2, 1, 4, 1, 2, 4, 1, 3, 1, 5, 4, 1...
## $ T1_C5_Host_provider (dbl) 2, 4, 1, 4, 1, 2, 1, 2, 4, 2, 4, 3, 4, 2...
## $ T1_C5_Personalization (dbl) 2, 2, 1, 1, 2, 2, 1, 2, 2, 2, 1, 2, 2, 2...
## $ T1_C5_Payment (dbl) 1, 1, 2, 1, 1, 2, 2, 2, 1, 2, 2, 1, 1, 2...
## $ T1_C5_Quantity_sim (dbl) 2, 3, 3, 1, 3, 3, 3, 3, 1, 3, 1, 3, 3, 2...
## $ T1_select (dbl) 3, 3, 3, 2, 3, 4, 1, 4, 5, 4, 5, 3, 3, 3...
## $ T2_C1_Minutes (dbl) 2, 2, 7, 7, 7, 6, 7, 3, 4, 4, 2, 4, 7, 1...
## $ T2_C1_Gigabytes (dbl) 9, 9, 8, 6, 5, 3, 8, 5, 10, 3, 1, 6, 6, ...
## $ T2_C1_Price (dbl) 4, 3, 4, 4, 1, 4, 4, 5, 4, 3, 1, 2, 1, 4...
## $ T2_C1_Host_provider (dbl) 1, 2, 4, 2, 4, 1, 4, 3, 1, 3, 2, 2, 1, 3...
## $ T2_C1_Personalization (dbl) 1, 1, 2, 2, 2, 2, 2, 1, 2, 2, 2, 1, 1, 1...
## $ T2_C1_Payment (dbl) 2, 1, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1...
## $ T2_C1_Quantity_sim (dbl) 2, 2, 3, 3, 3, 3, 3, 1, 2, 2, 2, 3, 2, 1...
## $ T2_C2_Minutes (dbl) 4, 6, 2, 6, 1, 7, 2, 2, 1, 1, 7, 1, 6, 3...
## $ T2_C2_Gigabytes (dbl) 5, 4, 2, 9, 7, 1, 2, 6, 1, 1, 6, 2, 7, 9...
## $ T2_C2_Price (dbl) 1, 1, 5, 3, 2, 1, 5, 2, 3, 2, 3, 4, 3, 1...
## $ T2_C2_Host_provider (dbl) 4, 2, 3, 3, 3, 3, 3, 2, 3, 2, 4, 1, 3, 1...
## $ T2_C2_Personalization (dbl) 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 2...
## $ T2_C2_Payment (dbl) 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 2, 2, 2, 1...
## $ T2_C2_Quantity_sim (dbl) 1, 3, 1, 1, 1, 2, 1, 1, 1, 1, 2, 2, 3, 1...
## $ T2_C3_Minutes (dbl) 5, 4, 6, 3, 6, 1, 6, 5, 5, 6, 6, 6, 5, 5...
## $ T2_C3_Gigabytes (dbl) 7, 7, 9, 8, 4, 8, 9, 10, 3, 4, 9, 4, 4, ...
## $ T2_C3_Price (dbl) 2, 4, 3, 1, 3, 5, 3, 4, 1, 5, 2, 1, 5, 2...
## $ T2_C3_Host_provider (dbl) 2, 3, 4, 1, 1, 1, 4, 2, 1, 1, 3, 4, 4, 4...
## $ T2_C3_Personalization (dbl) 2, 2, 2, 1, 1, 1, 2, 1, 2, 1, 1, 2, 2, 2...
## $ T2_C3_Payment (dbl) 2, 2, 2, 2, 1, 2, 2, 1, 2, 1, 1, 1, 1, 2...
## $ T2_C3_Quantity_sim (dbl) 1, 1, 1, 2, 2, 1, 1, 2, 3, 3, 1, 1, 1, 2...
## $ T2_C4_Minutes (dbl) 6, 5, 3, 5, 2, 4, 3, 1, 2, 2, 1, 7, 2, 6...
## $ T2_C4_Gigabytes (dbl) 2, 6, 5, 10, 1, 6, 5, 7, 8, 7, 2, 1, 9, ...
## $ T2_C4_Price (dbl) 5, 2, 2, 5, 4, 3, 2, 3, 5, 4, 5, 3, 2, 5...
## $ T2_C4_Host_provider (dbl) 3, 1, 1, 3, 1, 4, 1, 4, 2, 1, 3, 3, 1, 2...
## $ T2_C4_Personalization (dbl) 1, 2, 1, 2, 1, 2, 1, 2, 2, 1, 2, 2, 2, 2...
## $ T2_C4_Payment (dbl) 1, 2, 1, 1, 1, 1, 1, 2, 2, 1, 1, 1, 1, 1...
## $ T2_C4_Quantity_sim (dbl) 3, 2, 3, 1, 2, 2, 3, 3, 1, 2, 3, 2, 2, 2...
## $ T2_C5_Minutes (dbl) 3, 7, 4, 1, 3, 2, 4, 7, 6, 3, 3, 3, 1, 2...
## $ T2_C5_Gigabytes (dbl) 8, 1, 10, 3, 9, 9, 10, 2, 5, 2, 4, 10, 1...
## $ T2_C5_Price (dbl) 3, 5, 1, 2, 5, 2, 1, 1, 2, 1, 4, 5, 4, 3...
## $ T2_C5_Host_provider (dbl) 3, 4, 2, 4, 2, 2, 2, 1, 4, 4, 1, 1, 2, 1...
## $ T2_C5_Personalization (dbl) 2, 1, 2, 1, 2, 1, 2, 2, 1, 2, 1, 1, 1, 1...
## $ T2_C5_Payment (dbl) 2, 1, 2, 2, 2, 2, 2, 1, 1, 2, 1, 2, 2, 2...
## $ T2_C5_Quantity_sim (dbl) 2, 1, 2, 3, 3, 1, 2, 3, 3, 3, 3, 1, 1, 3...
## $ T2_select (dbl) 3, 5, 5, 5, 1, 5, 4, 1, 1, 3, 1, 3, 1, 3...
## $ T3_C1_Minutes (dbl) 1, 1, 5, 2, 7, 1, 5, 1, 7, 4, 4, 6, 2, 5...
## $ T3_C1_Gigabytes (dbl) 6, 3, 9, 2, 9, 5, 9, 8, 9, 2, 10, 5, 3, ...
## $ T3_C1_Price (dbl) 3, 3, 1, 4, 3, 4, 1, 5, 2, 4, 2, 4, 1, 4...
## $ T3_C1_Host_provider (dbl) 2, 1, 1, 3, 4, 3, 1, 3, 1, 2, 1, 3, 2, 2...
## $ T3_C1_Personalization (dbl) 1, 2, 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1...
## $ T3_C1_Payment (dbl) 1, 2, 1, 2, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2...
## $ T3_C1_Quantity_sim (dbl) 1, 3, 1, 3, 2, 2, 1, 3, 1, 1, 2, 1, 1, 3...
## $ T3_C2_Minutes (dbl) 5, 6, 7, 7, 6, 5, 7, 3, 6, 2, 2, 5, 4, 1...
## $ T3_C2_Gigabytes (dbl) 4, 5, 8, 1, 5, 2, 8, 1, 2, 8, 3, 7, 4, 8...
## $ T3_C2_Price (dbl) 5, 5, 5, 1, 4, 5, 5, 2, 1, 3, 1, 2, 3, 1...
## $ T3_C2_Host_provider (dbl) 4, 4, 2, 4, 2, 2, 2, 4, 2, 1, 4, 1, 4, 4...
## $ T3_C2_Personalization (dbl) 1, 2, 1, 2, 2, 2, 1, 2, 1, 2, 2, 2, 1, 2...
## $ T3_C2_Payment (dbl) 1, 2, 2, 1, 1, 1, 2, 1, 2, 2, 1, 2, 2, 1...
## $ T3_C2_Quantity_sim (dbl) 2, 1, 2, 1, 2, 2, 2, 2, 2, 3, 1, 2, 2, 2...
## $ T3_C3_Minutes (dbl) 6, 2, 2, 4, 5, 2, 2, 4, 3, 7, 6, 7, 3, 4...
## $ T3_C3_Gigabytes (dbl) 3, 2, 1, 4, 3, 10, 1, 4, 1, 4, 7, 9, 7, ...
## $ T3_C3_Price (dbl) 4, 1, 3, 3, 5, 1, 3, 1, 3, 5, 4, 5, 4, 3...
## $ T3_C3_Host_provider (dbl) 3, 1, 3, 4, 1, 4, 3, 2, 3, 3, 2, 1, 1, 1...
## $ T3_C3_Personalization (dbl) 2, 2, 2, 2, 1, 2, 2, 1, 2, 1, 1, 2, 2, 2...
## $ T3_C3_Payment (dbl) 2, 2, 1, 1, 2, 1, 1, 2, 2, 2, 2, 1, 1, 1...
## $ T3_C3_Quantity_sim (dbl) 3, 2, 3, 2, 1, 1, 3, 2, 2, 3, 1, 3, 3, 3...
## $ T3_C4_Minutes (dbl) 7, 3, 4, 1, 2, 3, 4, 7, 4, 6, 1, 1, 1, 3...
## $ T3_C4_Gigabytes (dbl) 10, 10, 6, 5, 2, 4, 6, 9, 8, 7, 5, 10, 9...
## $ T3_C4_Price (dbl) 1, 2, 2, 2, 1, 3, 2, 4, 5, 2, 5, 3, 5, 2...
## $ T3_C4_Host_provider (dbl) 1, 3, 3, 1, 2, 1, 3, 3, 4, 4, 2, 4, 3, 4...
## $ T3_C4_Personalization (dbl) 2, 1, 2, 2, 1, 1, 2, 1, 1, 2, 1, 1, 1, 1...
## $ T3_C4_Payment (dbl) 2, 1, 1, 1, 2, 2, 1, 2, 1, 1, 2, 1, 1, 2...
## $ T3_C4_Quantity_sim (dbl) 1, 2, 2, 3, 1, 1, 2, 3, 3, 2, 2, 3, 3, 2...
## $ T3_C5_Minutes (dbl) 3, 5, 1, 5, 4, 4, 1, 6, 1, 5, 5, 2, 5, 7...
## $ T3_C5_Gigabytes (dbl) 1, 8, 4, 7, 8, 7, 4, 3, 10, 5, 8, 2, 5, ...
## $ T3_C5_Price (dbl) 2, 4, 4, 5, 2, 2, 4, 3, 4, 1, 3, 1, 2, 5...
## $ T3_C5_Host_provider (dbl) 2, 2, 4, 2, 3, 3, 4, 1, 4, 1, 3, 2, 2, 3...
## $ T3_C5_Personalization (dbl) 1, 1, 1, 1, 2, 1, 1, 2, 2, 1, 1, 1, 1, 1...
## $ T3_C5_Payment (dbl) 1, 1, 2, 2, 1, 2, 2, 1, 2, 2, 2, 1, 1, 2...
## $ T3_C5_Quantity_sim (dbl) 3, 3, 3, 1, 3, 3, 3, 1, 1, 1, 3, 2, 1, 1...
## $ T3_select (dbl) 4, 5, 2, 4, 1, 5, 2, 2, 1, 5, 2, 5, 5, 1...
## $ T4_C1_Minutes (dbl) 2, 5, 7, 4, 7, 5, 7, 3, 5, 7, 4, 6, 4, 6...
## $ T4_C1_Gigabytes (dbl) 6, 10, 2, 9, 7, 6, 2, 3, 6, 1, 4, 1, 8, ...
## $ T4_C1_Price (dbl) 4, 1, 3, 1, 5, 5, 3, 2, 4, 5, 3, 5, 2, 3...
## $ T4_C1_Host_provider (dbl) 4, 4, 1, 3, 1, 3, 1, 3, 3, 1, 2, 4, 2, 4...
## $ T4_C1_Personalization (dbl) 2, 2, 1, 2, 1, 1, 1, 2, 1, 2, 1, 1, 2, 2...
## $ T4_C1_Payment (dbl) 1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 1, 2, 2, 2...
## $ T4_C1_Quantity_sim (dbl) 1, 1, 2, 3, 3, 3, 2, 3, 1, 1, 2, 2, 1, 1...
## $ T4_C2_Minutes (dbl) 6, 3, 6, 3, 5, 2, 6, 7, 6, 1, 3, 3, 2, 4...
## $ T4_C2_Gigabytes (dbl) 5, 5, 3, 1, 4, 1, 3, 7, 4, 10, 6, 4, 6, ...
## $ T4_C2_Price (dbl) 5, 2, 1, 5, 1, 3, 1, 1, 3, 3, 1, 1, 1, 1...
## $ T4_C2_Host_provider (dbl) 2, 1, 3, 4, 4, 2, 3, 2, 2, 3, 3, 2, 4, 3...
## $ T4_C2_Personalization (dbl) 2, 1, 2, 1, 2, 1, 2, 1, 2, 1, 1, 1, 1, 1...
## $ T4_C2_Payment (dbl) 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 2, 1, 2...
## $ T4_C2_Quantity_sim (dbl) 2, 3, 3, 2, 1, 3, 3, 1, 3, 2, 3, 3, 3, 2...
## $ T4_C3_Minutes (dbl) 1, 1, 2, 5, 1, 6, 2, 5, 2, 4, 5, 1, 7, 2...
## $ T4_C3_Gigabytes (dbl) 10, 4, 7, 3, 10, 5, 7, 1, 7, 6, 5, 6, 1,...
## $ T4_C3_Price (dbl) 1, 4, 4, 3, 2, 1, 4, 3, 2, 1, 4, 3, 3, 4...
## $ T4_C3_Host_provider (dbl) 3, 3, 2, 2, 3, 4, 2, 1, 4, 4, 1, 2, 3, 1...
## $ T4_C3_Personalization (dbl) 1, 2, 1, 2, 1, 1, 1, 1, 2, 1, 2, 1, 2, 1...
## $ T4_C3_Payment (dbl) 2, 1, 2, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 1...
## $ T4_C3_Quantity_sim (dbl) 3, 1, 1, 2, 2, 1, 1, 2, 2, 3, 1, 1, 3, 2...
## $ T4_C4_Minutes (dbl) 5, 6, 1, 1, 2, 7, 1, 2, 7, 5, 7, 4, 3, 1...
## $ T4_C4_Gigabytes (dbl) 4, 1, 10, 8, 1, 10, 10, 9, 5, 9, 1, 3, 2...
## $ T4_C4_Price (dbl) 2, 3, 5, 4, 3, 2, 5, 4, 1, 2, 2, 2, 5, 5...
## $ T4_C4_Host_provider (dbl) 1, 4, 4, 1, 2, 4, 4, 4, 2, 3, 4, 1, 1, 2...
## $ T4_C4_Personalization (dbl) 2, 1, 2, 1, 2, 2, 2, 2, 1, 2, 1, 2, 1, 2...
## $ T4_C4_Payment (dbl) 2, 2, 1, 1, 1, 2, 1, 1, 1, 2, 1, 1, 1, 2...
## $ T4_C4_Quantity_sim (dbl) 3, 3, 3, 1, 3, 2, 3, 1, 3, 2, 2, 1, 2, 1...
## $ T4_C5_Minutes (dbl) 4, 4, 5, 6, 3, 4, 5, 4, 3, 3, 6, 2, 6, 7...
## $ T4_C5_Gigabytes (dbl) 9, 8, 5, 6, 6, 9, 5, 5, 3, 3, 3, 8, 10, ...
## $ T4_C5_Price (dbl) 3, 5, 2, 2, 4, 4, 2, 5, 5, 4, 5, 4, 4, 2...
## $ T4_C5_Host_provider (dbl) 1, 2, 2, 4, 4, 1, 2, 1, 1, 2, 4, 3, 3, 3...
## $ T4_C5_Personalization (dbl) 1, 2, 1, 2, 1, 2, 1, 2, 1, 1, 2, 2, 2, 1...
## $ T4_C5_Payment (dbl) 1, 2, 2, 2, 2, 1, 2, 1, 1, 1, 2, 1, 2, 1...
## $ T4_C5_Quantity_sim (dbl) 1, 2, 2, 1, 1, 1, 2, 2, 2, 1, 3, 3, 2, 3...
## $ T4_select (dbl) 4, 1, 3, 1, 5, 5, 5, 5, 3, 4, 3, 4, 1, 5...
## $ T5_C1_Minutes (dbl) 7, 5, 5, 6, 5, 3, 5, 2, 2, 5, 2, 3, 4, 1...
## $ T5_C1_Gigabytes (dbl) 2, 3, 9, 5, 6, 8, 9, 10, 7, 9, 2, 9, 2, ...
## $ T5_C1_Price (dbl) 1, 5, 5, 2, 5, 2, 5, 1, 3, 5, 3, 2, 1, 5...
## $ T5_C1_Host_provider (dbl) 3, 3, 2, 3, 3, 2, 2, 3, 1, 1, 3, 3, 3, 3...
## $ T5_C1_Personalization (dbl) 1, 1, 1, 1, 1, 2, 1, 2, 1, 2, 2, 2, 2, 2...
## $ T5_C1_Payment (dbl) 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 1, 1...
## $ T5_C1_Quantity_sim (dbl) 2, 3, 3, 2, 3, 3, 3, 3, 2, 3, 1, 2, 1, 2...
## $ T5_C2_Minutes (dbl) 6, 7, 1, 3, 6, 1, 1, 4, 1, 2, 3, 5, 6, 7...
## $ T5_C2_Gigabytes (dbl) 8, 6, 6, 7, 4, 2, 6, 8, 1, 6, 7, 2, 6, 5...
## $ T5_C2_Price (dbl) 2, 3, 3, 5, 2, 3, 3, 5, 1, 2, 2, 5, 3, 4...
## $ T5_C2_Host_provider (dbl) 2, 2, 2, 1, 2, 1, 2, 4, 4, 3, 2, 4, 2, 2...
## $ T5_C2_Personalization (dbl) 1, 1, 2, 2, 2, 1, 2, 1, 1, 1, 2, 1, 2, 2...
## $ T5_C2_Payment (dbl) 1, 2, 1, 2, 2, 2, 1, 2, 2, 2, 2, 1, 1, 1...
## $ T5_C2_Quantity_sim (dbl) 1, 1, 2, 3, 3, 3, 2, 1, 3, 1, 3, 1, 2, 3...
## $ T5_C3_Minutes (dbl) 4, 2, 3, 7, 3, 4, 3, 7, 7, 4, 4, 1, 1, 5...
## $ T5_C3_Gigabytes (dbl) 3, 7, 10, 10, 9, 3, 10, 6, 3, 1, 9, 3, 1...
## $ T5_C3_Price (dbl) 5, 4, 4, 3, 1, 1, 4, 4, 4, 3, 4, 4, 5, 2...
## $ T5_C3_Host_provider (dbl) 4, 1, 3, 2, 4, 3, 3, 2, 2, 4, 2, 3, 4, 2...
## $ T5_C3_Personalization (dbl) 2, 2, 1, 1, 1, 1, 1, 2, 2, 1, 2, 1, 1, 2...
## $ T5_C3_Payment (dbl) 2, 1, 2, 1, 1, 2, 2, 1, 1, 2, 2, 1, 2, 1...
## $ T5_C3_Quantity_sim (dbl) 3, 2, 1, 1, 2, 2, 1, 2, 2, 1, 2, 2, 1, 1...
## $ T5_C4_Minutes (dbl) 2, 4, 7, 2, 7, 6, 7, 5, 4, 6, 5, 2, 5, 4...
## $ T5_C4_Gigabytes (dbl) 1, 9, 1, 4, 2, 4, 1, 4, 5, 10, 10, 10, 3...
## $ T5_C4_Price (dbl) 4, 2, 2, 4, 4, 4, 2, 2, 2, 4, 5, 3, 4, 3...
## $ T5_C4_Host_provider (dbl) 4, 1, 1, 3, 3, 2, 1, 1, 3, 2, 4, 2, 1, 4...
## $ T5_C4_Personalization (dbl) 1, 1, 2, 1, 2, 2, 2, 1, 1, 1, 1, 2, 1, 1...
## $ T5_C4_Payment (dbl) 1, 2, 1, 1, 1, 1, 1, 2, 2, 2, 1, 2, 2, 2...
## $ T5_C4_Quantity_sim (dbl) 3, 1, 1, 2, 1, 2, 1, 1, 3, 3, 1, 1, 3, 1...
## $ T5_C5_Minutes (dbl) 1, 3, 4, 5, 4, 7, 4, 6, 6, 1, 1, 6, 7, 6...
## $ T5_C5_Gigabytes (dbl) 7, 2, 2, 2, 10, 7, 2, 2, 2, 4, 8, 1, 9, ...
## $ T5_C5_Price (dbl) 3, 1, 1, 1, 3, 5, 1, 3, 5, 1, 1, 1, 2, 1...
## $ T5_C5_Host_provider (dbl) 1, 4, 4, 4, 1, 4, 4, 4, 1, 4, 1, 1, 4, 1...
## $ T5_C5_Personalization (dbl) 2, 2, 1, 2, 2, 2, 1, 1, 2, 2, 1, 1, 2, 1...
## $ T5_C5_Payment (dbl) 2, 1, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 2, 2...
## $ T5_C5_Quantity_sim (dbl) 2, 3, 3, 3, 1, 1, 3, 3, 1, 2, 2, 3, 3, 3...
## $ T5_select (dbl) 2, 4, 1, 5, 5, 3, 5, 3, 1, 4, 1, 5, 1, 5...
## $ T6_C1_Minutes (dbl) 1, 1, 3, 4, 6, 5, 3, 1, 5, 3, 6, 1, 3, 7...
## $ T6_C1_Gigabytes (dbl) 4, 8, 8, 2, 1, 3, 8, 6, 9, 2, 6, 4, 4, 2...
## $ T6_C1_Price (dbl) 2, 1, 4, 2, 5, 4, 4, 1, 4, 3, 4, 2, 2, 3...
## $ T6_C1_Host_provider (dbl) 4, 3, 1, 1, 1, 2, 1, 1, 4, 2, 2, 2, 2, 2...
## $ T6_C1_Personalization (dbl) 2, 1, 2, 2, 1, 1, 2, 1, 1, 2, 2, 1, 1, 2...
## $ T6_C1_Payment (dbl) 1, 1, 2, 1, 2, 2, 2, 1, 1, 1, 1, 1, 1, 2...
## $ T6_C1_Quantity_sim (dbl) 1, 2, 3, 1, 1, 1, 3, 3, 2, 2, 2, 3, 3, 2...
## $ T6_C2_Minutes (dbl) 5, 3, 5, 7, 5, 4, 5, 3, 2, 4, 3, 3, 1, 2...
## $ T6_C2_Gigabytes (dbl) 8, 1, 4, 8, 7, 2, 4, 9, 10, 3, 1, 7, 1, ...
## $ T6_C2_Price (dbl) 1, 3, 2, 5, 4, 2, 2, 3, 3, 5, 5, 5, 1, 5...
## $ T6_C2_Host_provider (dbl) 1, 3, 3, 3, 2, 4, 3, 3, 2, 1, 1, 4, 1, 3...
## $ T6_C2_Personalization (dbl) 1, 2, 2, 2, 2, 1, 2, 1, 1, 1, 1, 2, 2, 2...
## $ T6_C2_Payment (dbl) 2, 2, 2, 2, 1, 1, 2, 1, 1, 2, 2, 2, 2, 2...
## $ T6_C2_Quantity_sim (dbl) 3, 1, 2, 2, 2, 3, 2, 1, 1, 2, 1, 1, 2, 3...
## $ T6_C3_Minutes (dbl) 4, 5, 2, 1, 1, 3, 2, 7, 6, 5, 7, 7, 2, 4...
## $ T6_C3_Gigabytes (dbl) 6, 9, 7, 1, 5, 9, 7, 5, 4, 8, 9, 8, 5, 1...
## $ T6_C3_Price (dbl) 3, 4, 1, 1, 3, 5, 1, 5, 1, 2, 1, 3, 4, 4...
## $ T6_C3_Host_provider (dbl) 3, 4, 4, 2, 4, 3, 4, 2, 3, 2, 3, 3, 3, 2...
## $ T6_C3_Personalization (dbl) 2, 2, 1, 1, 1, 2, 1, 2, 2, 2, 2, 1, 1, 1...
## $ T6_C3_Payment (dbl) 1, 2, 1, 2, 2, 2, 1, 2, 2, 1, 1, 1, 1, 1...
## $ T6_C3_Quantity_sim (dbl) 2, 2, 2, 2, 3, 2, 2, 2, 2, 3, 3, 1, 1, 1...
## $ T6_C4_Minutes (dbl) 7, 7, 7, 6, 2, 2, 7, 2, 4, 7, 2, 5, 6, 5...
## $ T6_C4_Gigabytes (dbl) 1, 4, 3, 4, 3, 6, 3, 10, 6, 5, 4, 6, 7, ...
## $ T6_C4_Price (dbl) 5, 2, 3, 4, 2, 1, 3, 2, 5, 4, 2, 4, 5, 1...
## $ T6_C4_Host_provider (dbl) 3, 2, 2, 1, 3, 1, 2, 2, 3, 4, 1, 4, 4, 4...
## $ T6_C4_Personalization (dbl) 1, 2, 1, 1, 2, 2, 1, 1, 2, 1, 1, 2, 2, 1...
## $ T6_C4_Payment (dbl) 2, 2, 1, 2, 1, 1, 1, 2, 2, 2, 2, 2, 2, 1...
## $ T6_C4_Quantity_sim (dbl) 1, 3, 1, 3, 1, 3, 1, 3, 1, 3, 1, 3, 1, 2...
## $ T6_C5_Minutes (dbl) 3, 6, 6, 2, 4, 6, 6, 6, 3, 6, 4, 4, 4, 3...
## $ T6_C5_Gigabytes (dbl) 10, 2, 5, 7, 8, 1, 5, 8, 8, 7, 10, 5, 8,...
## $ T6_C5_Price (dbl) 4, 5, 5, 3, 1, 3, 5, 4, 2, 1, 3, 1, 3, 2...
## $ T6_C5_Host_provider (dbl) 2, 1, 3, 4, 1, 4, 3, 4, 1, 3, 4, 1, 3, 1...
## $ T6_C5_Personalization (dbl) 2, 1, 2, 1, 1, 2, 2, 2, 2, 2, 1, 2, 1, 2...
## $ T6_C5_Payment (dbl) 1, 1, 2, 1, 2, 2, 2, 2, 2, 1, 2, 2, 1, 2...
## $ T6_C5_Quantity_sim (dbl) 2, 1, 1, 3, 2, 2, 1, 2, 3, 1, 3, 2, 2, 1...
## $ T6_select (dbl) 2, 4, 4, 5, 5, 4, 3, 5, 1, 5, 2, 5, 1, 4...
## $ T7_C1_Minutes (dbl) 2, 4, 6, 5, 1, 1, 6, 3, 5, 2, 6, 5, 2, 3...
## $ T7_C1_Gigabytes (dbl) 2, 6, 4, 10, 2, 7, 4, 7, 5, 7, 3, 10, 10...
## $ T7_C1_Price (dbl) 3, 1, 4, 2, 1, 1, 4, 1, 5, 5, 1, 1, 2, 5...
## $ T7_C1_Host_provider (dbl) 2, 2, 3, 4, 1, 2, 3, 2, 3, 2, 2, 4, 1, 4...
## $ T7_C1_Personalization (dbl) 1, 1, 1, 1, 2, 1, 1, 1, 2, 2, 1, 2, 2, 1...
## $ T7_C1_Payment (dbl) 2, 1, 1, 2, 2, 1, 1, 2, 1, 2, 2, 1, 1, 1...
## $ T7_C1_Quantity_sim (dbl) 3, 3, 3, 3, 1, 1, 3, 2, 2, 3, 1, 2, 2, 2...
## $ T7_C2_Minutes (dbl) 5, 6, 1, 1, 3, 2, 1, 5, 1, 7, 1, 4, 1, 6...
## $ T7_C2_Gigabytes (dbl) 3, 10, 9, 9, 1, 10, 9, 4, 3, 2, 5, 8, 3,...
## $ T7_C2_Price (dbl) 1, 3, 5, 4, 3, 2, 5, 3, 3, 2, 3, 4, 3, 2...
## $ T7_C2_Host_provider (dbl) 3, 3, 1, 1, 3, 3, 1, 4, 1, 1, 3, 2, 2, 3...
## $ T7_C2_Personalization (dbl) 2, 2, 1, 2, 1, 1, 1, 2, 1, 1, 2, 1, 2, 1...
## $ T7_C2_Payment (dbl) 1, 2, 2, 1, 1, 1, 2, 1, 2, 1, 1, 1, 1, 1...
## $ T7_C2_Quantity_sim (dbl) 1, 2, 2, 2, 3, 2, 2, 1, 3, 2, 1, 2, 3, 3...
## $ T7_C3_Minutes (dbl) 7, 7, 2, 3, 4, 5, 2, 4, 4, 3, 2, 6, 7, 5...
## $ T7_C3_Gigabytes (dbl) 5, 3, 2, 3, 3, 4, 2, 1, 7, 5, 2, 4, 7, 3...
## $ T7_C3_Price (dbl) 5, 4, 2, 3, 4, 3, 2, 2, 1, 3, 4, 3, 4, 4...
## $ T7_C3_Host_provider (dbl) 1, 1, 2, 2, 2, 3, 2, 1, 1, 3, 4, 1, 4, 3...
## $ T7_C3_Personalization (dbl) 2, 1, 2, 2, 1, 2, 2, 2, 2, 1, 1, 2, 1, 1...
## $ T7_C3_Payment (dbl) 1, 1, 2, 1, 1, 2, 2, 1, 1, 1, 2, 2, 1, 1...
## $ T7_C3_Quantity_sim (dbl) 3, 1, 3, 3, 3, 3, 3, 3, 1, 3, 2, 3, 2, 1...
## $ T7_C4_Minutes (dbl) 3, 2, 4, 4, 2, 7, 4, 1, 7, 1, 7, 2, 3, 2...
## $ T7_C4_Gigabytes (dbl) 7, 5, 6, 6, 7, 8, 6, 2, 6, 4, 7, 1, 8, 6...
## $ T7_C4_Price (dbl) 4, 5, 1, 1, 5, 4, 1, 4, 2, 4, 5, 2, 1, 1...
## $ T7_C4_Host_provider (dbl) 2, 2, 1, 3, 4, 4, 1, 3, 2, 4, 1, 2, 1, 1...
## $ T7_C4_Personalization (dbl) 1, 1, 1, 1, 2, 2, 1, 1, 1, 2, 2, 2, 1, 2...
## $ T7_C4_Payment (dbl) 2, 1, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 2, 2...
## $ T7_C4_Quantity_sim (dbl) 1, 2, 1, 1, 2, 1, 1, 2, 1, 1, 3, 3, 1, 1...
## $ T7_C5_Minutes (dbl) 6, 1, 3, 2, 7, 3, 3, 6, 3, 6, 5, 7, 5, 1...
## $ T7_C5_Gigabytes (dbl) 9, 7, 5, 5, 10, 5, 5, 3, 1, 10, 8, 3, 6,...
## $ T7_C5_Price (dbl) 2, 2, 3, 5, 2, 5, 3, 5, 4, 1, 2, 5, 5, 3...
## $ T7_C5_Host_provider (dbl) 4, 4, 4, 2, 2, 1, 4, 3, 4, 1, 3, 3, 3, 2...
## $ T7_C5_Personalization (dbl) 1, 2, 2, 2, 1, 1, 2, 2, 2, 2, 2, 1, 2, 2...
## $ T7_C5_Payment (dbl) 2, 2, 1, 1, 1, 1, 1, 1, 1, 2, 1, 2, 2, 2...
## $ T7_C5_Quantity_sim (dbl) 2, 3, 1, 1, 2, 2, 1, 1, 3, 2, 2, 1, 3, 3...
## $ T7_select (dbl) 5, 1, 3, 1, 5, 2, 3, 4, 3, 5, 2, 1, 4, 2...Исходим из предположения, что каждому индивиду предлагалось одно и то же количество карточек. Также предполагаем, что на каждой карточке было одно и то же количество альтернатив.
Разрезаем исходную матрицу на две, \(y\) и \(X\):
n_persons <- nrow(df)
n_cards <- 7
n_alternatives <- 5
person_ids <- df$id
df_X <- dplyr::select(df, -ends_with("select"))
df_y <- dplyr::select(df, ends_with("select"))
head(df_y)## Source: local data frame [6 x 7]
##
## T1_select T2_select T3_select T4_select T5_select T6_select T7_select
## (dbl) (dbl) (dbl) (dbl) (dbl) (dbl) (dbl)
## 1 3 3 4 4 2 2 5
## 2 3 5 5 1 4 4 1
## 3 3 5 2 3 1 4 3
## 4 2 5 4 1 5 5 1
## 5 3 1 1 5 5 5 5
## 6 4 5 5 5 3 4 2Превращаем матрицу \(X\) из широкой в длинную:
df_X_melted <- melt(df_X, id.vars = c("id", "version"))
head(df_X_melted)## id version variable value
## 1 93 40 T1_C1_Minutes 4
## 2 105 72 T1_C1_Minutes 1
## 3 124 97 T1_C1_Minutes 4
## 4 127 32 T1_C1_Minutes 3
## 5 141 99 T1_C1_Minutes 4
## 6 158 62 T1_C1_Minutes 6Разбиваем название переменной на три составляющих:
df_X_sep <- tidyr::separate(df_X_melted, variable, into = c("card", "alternative", "variable"), sep = "_")## Warning: Too many values at 20720 locations: 889, 890, 891, 892, 893, 894,
## 895, 896, 897, 898, 899, 900, 901, 902, 903, 904, 905, 906, 907, 908, ...# warning возникает из за разбивки "T1_C4_Host_provider". "provider" теряется
# пока забьём
head(df_X_sep)## id version card alternative variable value
## 1 93 40 T1 C1 Minutes 4
## 2 105 72 T1 C1 Minutes 1
## 3 124 97 T1 C1 Minutes 4
## 4 127 32 T1 C1 Minutes 3
## 5 141 99 T1 C1 Minutes 4
## 6 158 62 T1 C1 Minutes 6Переделываем табличку с данными в список:
# list lgtdata should contain for each person:
# y numeric vector (n_card x 1)
# X numeric matrix (n_card * n_alternatives) x (n_variables):
# card alternative var1 var2
# 1 1 xx zz
# 1 2 xx zz
# 2 1 xx zz
# 2 2 xx zz
choice_data <- list()
for (person_no in 1:n_persons) {
person_id <- person_ids[person_no]
person_y <- unlist(df_y[person_no, ])
names(person_y) <- NULL
# unlist нужен чтобы превратить tbl_df размера (1 x n_cards) в простой вектор
person_X_melted <- df_X_sep %>% dplyr::filter(id == person_id) %>%
dplyr::select(-id, -version)
person_X_df <- dcast(person_X_melted, card + alternative ~ variable,
value.var = "value")
person_X <- dplyr::select(person_X_df, -card, -alternative) %>% as.matrix()
choice_data[[person_no]] <- list(y = person_y, X = person_X)
}Структура матриц \(y\) и \(X\) для последнего индивида. Для наглядности в матрице \(X\) сохранены номера карточек и альтернатив:
head(person_y)## [1] 4 2 4 4 2 2head(person_X_df)## card alternative Gigabytes Host Minutes Payment Personalization Price
## 1 T1 C1 4 1 7 1 1 1
## 2 T1 C2 8 2 3 2 2 4
## 3 T1 C3 5 3 2 2 2 2
## 4 T1 C4 10 4 5 1 1 3
## 5 T1 C5 9 3 6 1 2 5
## 6 T2 C1 1 1 1 1 2 4
## Quantity
## 1 3
## 2 1
## 3 2
## 4 1
## 5 3
## 6 1Наконец оценим:
# ncomp - количество смешиваемых нормальных распределений (кластеров среди покупателей)
# p - число альтернатив (должно быть постоянно!)
mcmc_pars <- list(R = 2000, keep = 10)
# R - общее количество симуляций
# keep = 10, сохраняем каждую 10ую
out <- rhierMnlRwMixture(Data = list(p = 5, lgtdata = choice_data),
Prior = list(ncomp = 1), Mcmc = mcmc_pars)## Z not specified
## Table of Y values pooled over all units
## ypooled
## 1 2 3 4 5
## 446 442 396 399 389
##
## Starting MCMC Inference for Hierarchical Logit:
## Normal Mixture with 1 components for first stage prior
## 5 alternatives; 7 variables in X
## for 296 cross-sectional units
##
## Prior Parms:
## nu = 10
## V
## [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## [1,] 10 0 0 0 0 0 0
## [2,] 0 10 0 0 0 0 0
## [3,] 0 0 10 0 0 0 0
## [4,] 0 0 0 10 0 0 0
## [5,] 0 0 0 0 10 0 0
## [6,] 0 0 0 0 0 10 0
## [7,] 0 0 0 0 0 0 10
## mubar
## [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## [1,] 0 0 0 0 0 0 0
## Amu
## [,1]
## [1,] 0.01
## a
## [1] 5
##
## MCMC Parms:
## s= 0.9 w= 0.1 R= 2000 keep= 10 nprint= 100
##
## initializing Metropolis candidate densities for 296 units ...
## completed unit # 50
## completed unit # 100
## completed unit # 150
## completed unit # 200
## completed unit # 250
## MCMC Iteration (est time to end - min)
## 100 (0.0)
## 200 (0.0)
## 300 (0.0)
## 400 (0.1)
## 500 (0.1)
## 600 (0.0)
## 700 (0.0)
## 800 (0.0)
## 900 (0.0)
## 1000 (0.0)
## 1100 (0.0)
## 1200 (0.0)
## 1300 (0.0)
## 1400 (0.0)
## 1500 (0.0)
## 1600 (0.0)
## 1700 (0.0)
## 1800 (0.0)
## 1900 (0.0)
## 2000 (0.0)
## Total Time Elapsed: 0.05Логарифм правдоподобия???:
plot(out$loglike, type = "l")
График бет усреднённый по индивидам:
burnin <- 50
betas <- out$betadraw
# betas: [n_person x n_variables x chain_lenght]
chain_lenght <- dim(betas)[3]
betas <- betas[, , (burnin + 1):chain_lenght]
betas_mean <- t(apply(betas, c(2, 3), mean))
matplot(betas_mean, type = "l")
Значения бет, усреднённые по индивидам:
beta_estimate_df <- data.frame(varname = colnames(choice_data[[1]]$X),
beta_estimate = apply(betas, c(2), mean))
beta_estimate_df## varname beta_estimate
## 1 Gigabytes 0.22545999
## 2 Host -0.28636579
## 3 Minutes 0.47523959
## 4 Payment -0.09398692
## 5 Personalization -0.15583096
## 6 Price -0.58002422
## 7 Quantity 0.16617111Тестируем сходимость…
Сохраняем беты для индивидов:
personal_betas <- apply(betas, c(1, 2), mean)
colnames(personal_betas) <- colnames(choice_data[[1]]$X)
df_betas <- cbind(dplyr::select(df, id), personal_betas)
head(df_betas)## id Gigabytes Host Minutes Payment Personalization
## 1 93 0.3836733 -0.44900577 1.08770908 0.08221019 -0.08639441
## 2 105 0.2942580 -0.18267362 0.55542007 -0.18840870 -0.52459999
## 3 124 0.2966247 -0.50920370 0.38127583 -0.02868183 -0.42650785
## 4 127 0.3190092 0.35920652 -0.03169329 0.02036271 -0.07515843
## 5 141 0.4464321 0.09129706 0.65850741 0.20779608 -0.12979423
## 6 158 0.4189896 -0.80246568 0.12262250 -0.05548735 -0.62680929
## Price Quantity
## 1 -0.9217028 0.19978635
## 2 -0.6013333 -0.01531799
## 3 0.0763326 0.05577725
## 4 -1.0870413 1.09119671
## 5 -0.4980147 -0.49107021
## 6 -0.8038376 0.28709210write.csv(df_betas, file = "person_betas.csv", row.names = FALSE)Пример из хелпа