Загрузка пакетов
library(ggplot2)
## Warning: пакет 'ggplot2' был собран под R версии 4.2.3
library(lmtest)
## Загрузка требуемого пакета: zoo
##
## Присоединяю пакет: 'zoo'
## Следующие объекты скрыты от 'package:base':
##
## as.Date, as.Date.numeric
library(foreign)
library(xtable)
library(readr)
## Warning: пакет 'readr' был собран под R версии 4.2.3
library(margins)
## Warning: пакет 'margins' был собран под R версии 4.2.3
library(dplyr)
##
## Присоединяю пакет: 'dplyr'
## Следующие объекты скрыты от 'package:stats':
##
## filter, lag
## Следующие объекты скрыты от 'package:base':
##
## intersect, setdiff, setequal, union
library(car)
## Warning: пакет 'car' был собран под R версии 4.2.3
## Загрузка требуемого пакета: carData
##
## Присоединяю пакет: 'car'
## Следующий объект скрыт от 'package:dplyr':
##
## recode
library(stargazer)
##
## Please cite as:
## Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables.
## R package version 5.2.3. https://CRAN.R-project.org/package=stargazer
library(broom)
library(writexl)
## Warning: пакет 'writexl' был собран под R версии 4.2.3
library(tidyverse)
## Warning: пакет 'tidyverse' был собран под R версии 4.2.3
## Warning: пакет 'forcats' был собран под R версии 4.2.3
## Warning: пакет 'lubridate' был собран под R версии 4.2.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ lubridate 1.9.2 ✔ tibble 3.1.8
## ✔ purrr 1.0.1 ✔ tidyr 1.3.0
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ✖ car::recode() masks dplyr::recode()
## ✖ purrr::some() masks car::some()
## ℹ Use the ]8;;http://conflicted.r-lib.org/conflicted package]8;; to force all conflicts to become errors
library(readxl)
## Warning: пакет 'readxl' был собран под R версии 4.2.3
library(tidyr)
library(plm)
## Warning: пакет 'plm' был собран под R версии 4.2.3
##
## Присоединяю пакет: 'plm'
##
## Следующие объекты скрыты от 'package:dplyr':
##
## between, lag, lead
library(openxlsx)
## Warning: пакет 'openxlsx' был собран под R версии 4.2.3
library(tseries)
## Warning: пакет 'tseries' был собран под R версии 4.2.3
## Registered S3 method overwritten by 'quantmod':
## method from
## as.zoo.data.frame zoo
library(AER)
## Warning: пакет 'AER' был собран под R версии 4.2.3
## Загрузка требуемого пакета: sandwich
## Загрузка требуемого пакета: survival
Загрузка данных для 3 гипотезы
lavka3 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/lavka_10_hyp3_all.xlsx")
magnit3 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/magnit_10_3.xlsx")
pyat3 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/pyaterka_10_hyp3_all.xlsx")
perek3 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/perek_10_3.xlsx")
lenta3 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/lenta_10_3.xlsx")
lavka3 <- lavka3[!duplicated(lavka3), ]
magnit3 <- magnit3[!duplicated(magnit3), ]
pyat3 <- pyat3[!duplicated(pyat3), ]
perek3 <- perek3[!duplicated(perek3), ]
lenta3 <- lenta3[!duplicated(lenta3), ]
Загрузка данных для 4-5 гипотез
lavka4_5 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/lavka_hope2.xlsx")
magnit4_5 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/magnit_hope_cool.xlsx")
pyat4_5 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/5ka_hope.xlsx")
perek4_5 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/perek_merge_8.xlsx")
lenta4_5 <- read_excel("D:/Рабочий стол/4 курс/диплом/фин_данные/lenta_7.xlsx")
lavka4_5 <- lavka4_5[!duplicated(lavka4_5), ]
magnit4_5 <- magnit4_5[!duplicated(magnit4_5), ]
pyat4_5 <- pyat4_5[!duplicated(pyat4_5), ]
perek4_5 <- perek4_5[!duplicated(perek4_5), ]
lenta4_5 <- lenta4_5[!duplicated(lenta4_5), ]
Проверка 3 гипотезы (крайняя левая цифра)
Лавка
logit_3hyp_left_lavka <- glm(factor(left_number_changed) ~ factor(price_increase) + right_number_changed + middle_number_changed + left_number_prev_changed + factor(category), data = lavka3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_left_lavka <- coeftest(logit_3hyp_left_lavka)
sum_hyp3_left_lavka
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.047932 0.230971 -21.8552 < 2.2e-16
## factor(price_increase)1 0.021288 0.026396 0.8065 0.4199644
## right_number_changed 0.455485 0.026757 17.0228 < 2.2e-16
## middle_number_changed 3.764905 0.040666 92.5818 < 2.2e-16
## left_number_prev_changed 1.885508 0.037651 50.0779 < 2.2e-16
## factor(category)Бакалея -0.431453 0.230062 -1.8754 0.0607405
## factor(category)Безалкогольные напитки -1.220405 0.236511 -5.1600 2.469e-07
## factor(category)Бытовая химия 0.543776 0.232536 2.3385 0.0193634
## factor(category)Замороженные продукты 0.162502 0.231186 0.7029 0.4821128
## factor(category)Красота и здоровье 0.148844 0.231092 0.6441 0.5195158
## factor(category)Молоко и яйца -0.209904 0.232569 -0.9025 0.3667672
## factor(category)Мясо 0.348622 0.231060 1.5088 0.1313524
## factor(category)Овощи -0.707194 0.247588 -2.8563 0.0042857
## factor(category)Рыба 0.368550 0.235176 1.5671 0.1170857
## factor(category)Сладости к чаю -0.881714 0.233769 -3.7717 0.0001621
## factor(category)Фрукты и ягоды 0.127602 0.238573 0.5349 0.5927504
## factor(category)Хлебобулочные изделия -1.137561 0.327822 -3.4701 0.0005203
##
## (Intercept) ***
## factor(price_increase)1
## right_number_changed ***
## middle_number_changed ***
## left_number_prev_changed ***
## factor(category)Бакалея .
## factor(category)Безалкогольные напитки ***
## factor(category)Бытовая химия *
## factor(category)Замороженные продукты
## factor(category)Красота и здоровье
## factor(category)Молоко и яйца
## factor(category)Мясо
## factor(category)Овощи **
## factor(category)Рыба
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды
## factor(category)Хлебобулочные изделия ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_left_lavka)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.097099 1 1.047425
## right_number_changed 1.116182 1 1.056495
## middle_number_changed 1.222416 1 1.105629
## left_number_prev_changed 1.064564 1 1.031777
## factor(category) 1.038557 12 1.001578
#wooldridgeTest(logit_3hyp_left_lavka)
Магнит
logit_3hyp_left_magnit <- glm(factor(left_number_changed) ~ factor(price_increase) + right_number_changed + middle_number_changed + left_number_prev_changed + factor(category), data = magnit3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_left_magnit <- coeftest(logit_3hyp_left_magnit)
sum_hyp3_left_magnit
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.142967 0.028922 -143.2482 < 2.2e-16
## factor(price_increase)1 0.167040 0.021123 7.9079 2.618e-15
## right_number_changed -0.155095 0.022264 -6.9662 3.256e-12
## middle_number_changed 3.373087 0.027351 123.3270 < 2.2e-16
## left_number_prev_changed 1.497350 0.021741 68.8723 < 2.2e-16
## factor(category)Безалкогольные напитки -0.099053 0.044596 -2.2211 0.0263441
## factor(category)Бытовая химия -0.069375 0.045776 -1.5155 0.1296444
## factor(category)Замороженные продукты 0.226796 0.046519 4.8754 1.086e-06
## factor(category)Красота и здоровье 0.191326 0.037570 5.0925 3.534e-07
## factor(category)Молоко и яйца 0.119200 0.031983 3.7270 0.0001938
## factor(category)Мясо 0.363235 0.032362 11.2240 < 2.2e-16
## factor(category)Овощи -0.374095 0.063557 -5.8860 3.957e-09
## factor(category)Рыба 0.113545 0.044076 2.5761 0.0099915
## factor(category)Сладости к чаю -0.019976 0.035974 -0.5553 0.5787013
## factor(category)Фрукты и ягоды -0.523656 0.074003 -7.0762 1.482e-12
## factor(category)Хлебобулочные изделия 0.657383 0.103557 6.3481 2.181e-10
##
## (Intercept) ***
## factor(price_increase)1 ***
## right_number_changed ***
## middle_number_changed ***
## left_number_prev_changed ***
## factor(category)Безалкогольные напитки *
## factor(category)Бытовая химия
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца ***
## factor(category)Мясо ***
## factor(category)Овощи ***
## factor(category)Рыба **
## factor(category)Сладости к чаю
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_left_magnit)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.165338 1 1.079508
## right_number_changed 1.120772 1 1.058665
## middle_number_changed 1.307468 1 1.143446
## left_number_prev_changed 1.036554 1 1.018113
## factor(category) 1.035807 11 1.001600
Пятерочка
logit_3hyp_left_pyat <- glm(factor(left_number_changed) ~ factor(price_increase) + right_number_changed + middle_number_changed + left_number_prev_changed + factor(category), data = pyat3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_left_pyat <- coeftest(logit_3hyp_left_pyat)
sum_hyp3_left_pyat
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -3.738919 0.017534 -213.2396 < 2.2e-16
## factor(price_increase)1 0.419997 0.013500 31.1108 < 2.2e-16
## right_number_changed 0.512352 0.014321 35.7774 < 2.2e-16
## middle_number_changed 2.426753 0.016891 143.6743 < 2.2e-16
## left_number_prev_changed 1.717071 0.013378 128.3500 < 2.2e-16
## factor(category)Безалкогольные напитки 0.238230 0.022031 10.8135 < 2.2e-16
## factor(category)Бытовая химия -0.024154 0.038827 -0.6221 0.533872
## factor(category)Замороженные продукты -0.168580 0.035661 -4.7272 2.276e-06
## factor(category)Красота и здоровье -0.319778 0.025168 -12.7056 < 2.2e-16
## factor(category)Молоко и яйца 0.168304 0.019801 8.4997 < 2.2e-16
## factor(category)Мясо -0.676775 0.032919 -20.5589 < 2.2e-16
## factor(category)Овощи 0.726605 0.038469 18.8879 < 2.2e-16
## factor(category)Рыба -0.065726 0.041546 -1.5820 0.113651
## factor(category)Сладости к чаю 0.082187 0.018214 4.5124 6.410e-06
## factor(category)Фрукты и ягоды -0.146483 0.054712 -2.6774 0.007421
## factor(category)Хлебобулочные изделия -0.307066 0.054873 -5.5960 2.194e-08
##
## (Intercept) ***
## factor(price_increase)1 ***
## right_number_changed ***
## middle_number_changed ***
## left_number_prev_changed ***
## factor(category)Безалкогольные напитки ***
## factor(category)Бытовая химия
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца ***
## factor(category)Мясо ***
## factor(category)Овощи ***
## factor(category)Рыба
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды **
## factor(category)Хлебобулочные изделия ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_left_pyat)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.167206 1 1.080373
## right_number_changed 1.089913 1 1.043989
## middle_number_changed 1.270752 1 1.127276
## left_number_prev_changed 1.029292 1 1.014540
## factor(category) 1.027886 11 1.001251
Перекрёсток
logit_3hyp_perek <- glm(factor(left_number_changed) ~ factor(price_increase) + right_number_changed + middle_number_changed + left_number_prev_changed + factor(category), data = perek3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_left_perek <- coeftest(logit_3hyp_perek)
sum_hyp3_left_perek
##
## z test of coefficients:
##
## Estimate Std. Error z value
## (Intercept) -4.4906531 0.0147774 -303.8857
## factor(price_increase)1 0.0367260 0.0113198 3.2444
## right_number_changed 0.1987713 0.0158865 12.5119
## middle_number_changed 4.2769952 0.0145822 293.3031
## left_number_prev_changed 1.4462806 0.0129466 111.7110
## factor(category)Безалкогольные напитки 0.4426391 0.0188630 23.4660
## factor(category)Бытовая химия -0.5211403 0.0190388 -27.3726
## factor(category)Замороженные продукты -0.3671880 0.0306850 -11.9664
## factor(category)Красота и здоровье -0.6004851 0.0144798 -41.4705
## factor(category)Молоко и яйца 0.2498495 0.0203766 12.2616
## factor(category)Мясо -1.2708327 0.0363948 -34.9180
## factor(category)Овощи 0.0021369 0.0330071 0.0647
## factor(category)Рыба -0.3257050 0.0404392 -8.0542
## factor(category)Сладости к чаю 0.3622380 0.0182137 19.8883
## factor(category)Фрукты и ягоды -1.0709485 0.0650908 -16.4531
## factor(category)Хлебобулочные изделия 0.1500360 0.0487621 3.0769
## Pr(>|z|)
## (Intercept) < 2.2e-16 ***
## factor(price_increase)1 0.001177 **
## right_number_changed < 2.2e-16 ***
## middle_number_changed < 2.2e-16 ***
## left_number_prev_changed < 2.2e-16 ***
## factor(category)Безалкогольные напитки < 2.2e-16 ***
## factor(category)Бытовая химия < 2.2e-16 ***
## factor(category)Замороженные продукты < 2.2e-16 ***
## factor(category)Красота и здоровье < 2.2e-16 ***
## factor(category)Молоко и яйца < 2.2e-16 ***
## factor(category)Мясо < 2.2e-16 ***
## factor(category)Овощи 0.948380
## factor(category)Рыба 8.001e-16 ***
## factor(category)Сладости к чаю < 2.2e-16 ***
## factor(category)Фрукты и ягоды < 2.2e-16 ***
## factor(category)Хлебобулочные изделия 0.002092 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_perek)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.233521 1 1.110640
## right_number_changed 1.049410 1 1.024407
## middle_number_changed 1.326524 1 1.151748
## left_number_prev_changed 1.043498 1 1.021517
## factor(category) 1.063572 11 1.002805
Лента
logit_3hyp_lenta <- glm(factor(left_number_changed) ~ factor(price_increase) + right_number_changed + middle_number_changed + left_number_prev_changed + factor(category), data = lenta3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_left_lenta <- coeftest(logit_3hyp_lenta)
sum_hyp3_left_lenta
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -5.582190 0.046945 -118.9087 < 2.2e-16
## factor(price_increase)1 0.111729 0.024305 4.5969 4.289e-06
## right_number_changed 0.917578 0.045677 20.0882 < 2.2e-16
## middle_number_changed 3.648300 0.058870 61.9723 < 2.2e-16
## left_number_prev_changed 2.279453 0.028461 80.0906 < 2.2e-16
## factor(category)Безалкогольные напитки 0.116692 0.036201 3.2234 0.0012667
## factor(category)Бытовая химия -0.602595 0.081572 -7.3873 1.498e-13
## factor(category)Замороженные продукты -0.735204 0.085884 -8.5604 < 2.2e-16
## factor(category)Красота и здоровье -1.100087 0.038953 -28.2416 < 2.2e-16
## factor(category)Молоко и яйца 0.066386 0.043480 1.5268 0.1268071
## factor(category)Мясо -1.103424 0.055758 -19.7896 < 2.2e-16
## factor(category)Овощи 0.429394 0.092060 4.6643 3.097e-06
## factor(category)Рыба -0.220253 0.069866 -3.1525 0.0016187
## factor(category)Сладости к чаю -0.285651 0.037202 -7.6784 1.611e-14
## factor(category)Фрукты и ягоды -0.629980 0.113884 -5.5318 3.170e-08
## factor(category)Хлебобулочные изделия -0.496626 0.130062 -3.8184 0.0001343
##
## (Intercept) ***
## factor(price_increase)1 ***
## right_number_changed ***
## middle_number_changed ***
## left_number_prev_changed ***
## factor(category)Безалкогольные напитки **
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца
## factor(category)Мясо ***
## factor(category)Овощи ***
## factor(category)Рыба **
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_lenta)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.071228 1 1.035002
## right_number_changed 1.834383 1 1.354394
## middle_number_changed 1.891131 1 1.375184
## left_number_prev_changed 1.039966 1 1.019787
## factor(category) 1.030082 11 1.001348
Предельные эффекты (Гипотеза 3 - крайняя левая цифра)
eff_lavka_3left <- summary(margins(logit_3hyp_left_lavka, variables = "price_increase"))
eff_magnit_3left <- summary(margins(logit_3hyp_left_magnit, variables = "price_increase"))
eff_pyat_3left <- summary(margins(logit_3hyp_left_pyat, variables = "price_increase"))
eff_perek_3left <- summary(margins(logit_3hyp_perek, variables = "price_increase"))
eff_lenta_3left <- summary(margins(logit_3hyp_lenta, variables = "price_increase"))
eff_lavka_3left
## factor AME SE z p lower upper
## price_increase1 0.0010 0.0012 0.8053 0.4207 -0.0014 0.0034
eff_magnit_3left
## factor AME SE z p lower upper
## price_increase1 0.0143 0.0018 7.7854 0.0000 0.0107 0.0179
eff_pyat_3left
## factor AME SE z p lower upper
## price_increase1 0.0446 0.0015 29.9509 0.0000 0.0417 0.0476
eff_perek_3left
## factor AME SE z p lower upper
## price_increase1 0.0020 0.0006 3.2328 0.0012 0.0008 0.0032
eff_lenta_3left
## factor AME SE z p lower upper
## price_increase1 0.0054 0.0012 4.5755 0.0000 0.0031 0.0078
Загрузка результатов в эксель (Гипотеза №3 - крайняя левая
цифра)
hyp3left_lavka_tidy_result <- tidy(sum_hyp3_left_lavka)
hyp3left_magnit_tidy_result <- tidy(sum_hyp3_left_magnit)
hyp3left_pyat_tidy_result <- tidy(sum_hyp3_left_pyat)
hyp3left_perek_tidy_result <- tidy(sum_hyp3_left_perek)
hyp3left_lenta_tidy_result <- tidy(sum_hyp3_left_lenta)
write.xlsx(hyp3left_lavka_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3left_lavka_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3left_magnit_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3left_magnit_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3left_pyat_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3left_pyat_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3left_perek_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3left_perek_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3left_lenta_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3left_lenta_tidy_result.xlsx", rowNames = TRUE)
Проверка 3 гипотезы (серединная цифра)
Лавка
logit_3hyp_mid_lavka <- glm(factor(middle_number_changed) ~ factor(price_increase) + right_number_changed + left_number_changed + middle_number_prev_changed + factor(category), data = lavka3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_mid_lavka <- coeftest(logit_3hyp_mid_lavka)
sum_hyp3_mid_lavka
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.715353 0.162378 -16.7224 < 2.2e-16
## factor(price_increase)1 2.631342 0.021907 120.1153 < 2.2e-16
## right_number_changed 2.904615 0.026419 109.9445 < 2.2e-16
## left_number_changed 3.567410 0.039929 89.3443 < 2.2e-16
## middle_number_prev_changed -0.444278 0.022266 -19.9531 < 2.2e-16
## factor(category)Бакалея 0.435849 0.163079 2.6726 0.0075258
## factor(category)Безалкогольные напитки 0.368425 0.164706 2.2369 0.0252950
## factor(category)Бытовая химия 0.650910 0.166416 3.9113 9.178e-05
## factor(category)Замороженные продукты 0.386706 0.164252 2.3544 0.0185551
## factor(category)Красота и здоровье 0.632579 0.164183 3.8529 0.0001167
## factor(category)Молоко и яйца 0.162497 0.165118 0.9841 0.3250538
## factor(category)Мясо 0.570430 0.164668 3.4641 0.0005320
## factor(category)Овощи 0.831546 0.170510 4.8768 1.078e-06
## factor(category)Рыба 0.429518 0.168689 2.5462 0.0108897
## factor(category)Сладости к чаю 0.433249 0.164370 2.6358 0.0083934
## factor(category)Фрукты и ягоды 0.869565 0.169753 5.1225 3.015e-07
## factor(category)Хлебобулочные изделия -0.514510 0.199930 -2.5734 0.0100691
##
## (Intercept) ***
## factor(price_increase)1 ***
## right_number_changed ***
## left_number_changed ***
## middle_number_prev_changed ***
## factor(category)Бакалея **
## factor(category)Безалкогольные напитки *
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты *
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца
## factor(category)Мясо ***
## factor(category)Овощи ***
## factor(category)Рыба *
## factor(category)Сладости к чаю **
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_mid_lavka)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.022690 1 1.011281
## right_number_changed 1.019589 1 1.009747
## left_number_changed 1.024707 1 1.012278
## middle_number_prev_changed 1.018207 1 1.009062
## factor(category) 1.033248 12 1.001364
Магнит
logit_3hyp_mid_magnit <- glm(factor(middle_number_changed) ~ factor(price_increase) + right_number_changed + left_number_changed + middle_number_prev_changed + factor(category), data = magnit3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_mid_magnit <- coeftest(logit_3hyp_mid_magnit)
sum_hyp3_mid_magnit
##
## z test of coefficients:
##
## Estimate Std. Error z value
## (Intercept) -2.5278065 0.0203899 -123.9732
## factor(price_increase)1 2.6891227 0.0233281 115.2738
## right_number_changed 2.9763073 0.0292951 101.5974
## left_number_changed 3.1256855 0.0267987 116.6357
## middle_number_prev_changed 0.6183136 0.0184732 33.4708
## factor(category)Безалкогольные напитки -0.0058367 0.0404812 -0.1442
## factor(category)Бытовая химия 0.2332047 0.0410444 5.6818
## factor(category)Замороженные продукты -0.0807808 0.0441672 -1.8290
## factor(category)Красота и здоровье -0.2017380 0.0342163 -5.8960
## factor(category)Молоко и яйца 0.0531395 0.0300134 1.7705
## factor(category)Мясо 0.2117381 0.0321771 6.5804
## factor(category)Овощи 0.4517849 0.0591672 7.6357
## factor(category)Рыба 0.1884017 0.0403722 4.6666
## factor(category)Сладости к чаю -0.1914036 0.0326346 -5.8650
## factor(category)Фрукты и ягоды 0.3687480 0.0757045 4.8709
## factor(category)Хлебобулочные изделия -0.6218828 0.1132280 -5.4923
## Pr(>|z|)
## (Intercept) < 2.2e-16 ***
## factor(price_increase)1 < 2.2e-16 ***
## right_number_changed < 2.2e-16 ***
## left_number_changed < 2.2e-16 ***
## middle_number_prev_changed < 2.2e-16 ***
## factor(category)Безалкогольные напитки 0.88536
## factor(category)Бытовая химия 1.333e-08 ***
## factor(category)Замороженные продукты 0.06740 .
## factor(category)Красота и здоровье 3.725e-09 ***
## factor(category)Молоко и яйца 0.07664 .
## factor(category)Мясо 4.692e-11 ***
## factor(category)Овощи 2.245e-14 ***
## factor(category)Рыба 3.062e-06 ***
## factor(category)Сладости к чаю 4.490e-09 ***
## factor(category)Фрукты и ягоды 1.111e-06 ***
## factor(category)Хлебобулочные изделия 3.967e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_mid_magnit)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.018839 1 1.009376
## right_number_changed 1.020611 1 1.010253
## left_number_changed 1.020580 1 1.010238
## middle_number_prev_changed 1.009068 1 1.004524
## factor(category) 1.027055 11 1.001214
Пятерочка
logit_3hyp_mid_pyat <- glm(factor(middle_number_changed) ~ factor(price_increase) + right_number_changed + left_number_changed + middle_number_prev_changed + factor(category), data = pyat3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_mid_pyat <- coeftest(logit_3hyp_mid_pyat)
sum_hyp3_mid_pyat
##
## z test of coefficients:
##
## Estimate Std. Error z value
## (Intercept) -2.20640602 0.01274567 -173.1103
## factor(price_increase)1 3.09192584 0.01748940 176.7886
## right_number_changed 2.20489154 0.01998622 110.3206
## left_number_changed 2.17361017 0.01714520 126.7766
## middle_number_prev_changed 1.22665093 0.01159985 105.7471
## factor(category)Безалкогольные напитки -0.31856091 0.02212854 -14.3959
## factor(category)Бытовая химия 0.08947884 0.03417232 2.6185
## factor(category)Замороженные продукты 0.15524502 0.03219741 4.8217
## factor(category)Красота и здоровье 0.15957221 0.02072771 7.6985
## factor(category)Молоко и яйца -0.12579870 0.01952728 -6.4422
## factor(category)Мясо 0.44810291 0.02509508 17.8562
## factor(category)Овощи -0.24469497 0.04365088 -5.6057
## factor(category)Рыба 0.08929652 0.03578267 2.4955
## factor(category)Сладости к чаю 0.00023529 0.01733247 0.0136
## factor(category)Фрукты и ягоды 0.69035944 0.05597714 12.3329
## factor(category)Хлебобулочные изделия -0.21693428 0.04584993 -4.7314
## Pr(>|z|)
## (Intercept) < 2.2e-16 ***
## factor(price_increase)1 < 2.2e-16 ***
## right_number_changed < 2.2e-16 ***
## left_number_changed < 2.2e-16 ***
## middle_number_prev_changed < 2.2e-16 ***
## factor(category)Безалкогольные напитки < 2.2e-16 ***
## factor(category)Бытовая химия 0.008833 **
## factor(category)Замороженные продукты 1.424e-06 ***
## factor(category)Красота и здоровье 1.377e-14 ***
## factor(category)Молоко и яйца 1.178e-10 ***
## factor(category)Мясо < 2.2e-16 ***
## factor(category)Овощи 2.074e-08 ***
## factor(category)Рыба 0.012577 *
## factor(category)Сладости к чаю 0.989169
## factor(category)Фрукты и ягоды < 2.2e-16 ***
## factor(category)Хлебобулочные изделия 2.230e-06 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_mid_pyat)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.006672 1 1.003330
## right_number_changed 1.012754 1 1.006357
## left_number_changed 1.017603 1 1.008763
## middle_number_prev_changed 1.009453 1 1.004715
## factor(category) 1.028331 11 1.001271
Перекресток
logit_3hyp_mid_perek <- glm(factor(middle_number_changed) ~ factor(price_increase) + right_number_changed + left_number_changed + middle_number_prev_changed + factor(category), data = perek3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_mid_perek <- coeftest(logit_3hyp_mid_perek)
sum_hyp3_mid_perek
##
## z test of coefficients:
##
## Estimate Std. Error z value
## (Intercept) -3.24964613 0.01127589 -288.1942
## factor(price_increase)1 4.55232808 0.01516765 300.1341
## right_number_changed 3.46630719 0.02771766 125.0577
## left_number_changed 4.14366568 0.01460246 283.7649
## middle_number_prev_changed 0.61019553 0.01102731 55.3349
## factor(category)Безалкогольные напитки -0.22428365 0.02041080 -10.9885
## factor(category)Бытовая химия 0.57246310 0.01761450 32.4995
## factor(category)Замороженные продукты 0.01925524 0.02933608 0.6564
## factor(category)Красота и здоровье 0.52482025 0.01392917 37.6778
## factor(category)Молоко и яйца -0.25875082 0.02227682 -11.6152
## factor(category)Мясо 0.41916273 0.02724800 15.3832
## factor(category)Овощи -0.03241040 0.03400126 -0.9532
## factor(category)Рыба 0.15010563 0.03893527 3.8553
## factor(category)Сладости к чаю 0.00016075 0.01927952 0.0083
## factor(category)Фрукты и ягоды 0.99617949 0.05052622 19.7161
## factor(category)Хлебобулочные изделия -0.09037909 0.05081620 -1.7785
## Pr(>|z|)
## (Intercept) < 2.2e-16 ***
## factor(price_increase)1 < 2.2e-16 ***
## right_number_changed < 2.2e-16 ***
## left_number_changed < 2.2e-16 ***
## middle_number_prev_changed < 2.2e-16 ***
## factor(category)Безалкогольные напитки < 2.2e-16 ***
## factor(category)Бытовая химия < 2.2e-16 ***
## factor(category)Замороженные продукты 0.5115881
## factor(category)Красота и здоровье < 2.2e-16 ***
## factor(category)Молоко и яйца < 2.2e-16 ***
## factor(category)Мясо < 2.2e-16 ***
## factor(category)Овощи 0.3404828
## factor(category)Рыба 0.0001156 ***
## factor(category)Сладости к чаю 0.9933476
## factor(category)Фрукты и ягоды < 2.2e-16 ***
## factor(category)Хлебобулочные изделия 0.0753138 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_mid_perek)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.032928 1 1.016331
## right_number_changed 1.010755 1 1.005363
## left_number_changed 1.077714 1 1.038130
## middle_number_prev_changed 1.009598 1 1.004787
## factor(category) 1.064344 11 1.002839
Лента
logit_3hyp_mid_lenta <- glm(factor(middle_number_changed) ~ factor(price_increase) + right_number_changed + left_number_changed + middle_number_prev_changed + factor(category), data = lenta3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_mid_lenta <- coeftest(logit_3hyp_mid_lenta)
sum_hyp3_mid_lenta
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.293470 0.037011 -116.0048 < 2.2e-16
## factor(price_increase)1 2.995203 0.049847 60.0883 < 2.2e-16
## right_number_changed 5.537303 0.032213 171.8958 < 2.2e-16
## left_number_changed 2.674840 0.063726 41.9744 < 2.2e-16
## middle_number_prev_changed 1.157126 0.030526 37.9064 < 2.2e-16
## factor(category)Безалкогольные напитки 0.020354 0.048043 0.4237 0.6718040
## factor(category)Бытовая химия -0.042474 0.093272 -0.4554 0.6488345
## factor(category)Замороженные продукты 0.374426 0.094660 3.9555 7.638e-05
## factor(category)Красота и здоровье 0.866777 0.045385 19.0983 < 2.2e-16
## factor(category)Молоко и яйца -0.327165 0.066022 -4.9554 7.218e-07
## factor(category)Мясо 0.531185 0.058810 9.0322 < 2.2e-16
## factor(category)Овощи -0.270070 0.152795 -1.7675 0.0771398
## factor(category)Рыба 0.317114 0.093888 3.3776 0.0007313
## factor(category)Сладости к чаю 0.146658 0.050044 2.9306 0.0033831
## factor(category)Фрукты и ягоды 1.154245 0.166352 6.9386 3.961e-12
## factor(category)Хлебобулочные изделия 0.191710 0.141024 1.3594 0.1740153
##
## (Intercept) ***
## factor(price_increase)1 ***
## right_number_changed ***
## left_number_changed ***
## middle_number_prev_changed ***
## factor(category)Безалкогольные напитки
## factor(category)Бытовая химия
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца ***
## factor(category)Мясо ***
## factor(category)Овощи .
## factor(category)Рыба ***
## factor(category)Сладости к чаю **
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_mid_lenta)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.035054 1 1.017376
## right_number_changed 1.073891 1 1.036287
## left_number_changed 1.039420 1 1.019519
## middle_number_prev_changed 1.048105 1 1.023770
## factor(category) 1.094306 11 1.004105
Предельные эффекты (Гипотеза 3 - серединные цифры)
eff_lavka_3middle <- summary(margins(logit_3hyp_mid_lavka, variables = "price_increase"))
eff_magnit_3middle <- summary(margins(logit_3hyp_mid_magnit, variables = "price_increase"))
eff_pyat_3middle <- summary(margins(logit_3hyp_mid_pyat, variables = "price_increase"))
eff_perek_3middle <- summary(margins(logit_3hyp_mid_perek, variables = "price_increase"))
eff_lenta_3middle <- summary(margins(logit_3hyp_mid_lenta, variables = "price_increase"))
eff_lavka_3middle
## factor AME SE z p lower upper
## price_increase1 0.4407 0.0043 103.3654 0.0000 0.4323 0.4491
eff_magnit_3middle
## factor AME SE z p lower upper
## price_increase1 0.4298 0.0041 104.1544 0.0000 0.4217 0.4379
eff_pyat_3middle
## factor AME SE z p lower upper
## price_increase1 0.5145 0.0023 221.8735 0.0000 0.5099 0.5190
eff_perek_3middle
## factor AME SE z p lower upper
## price_increase1 0.7014 0.0018 389.4809 0.0000 0.6979 0.7049
eff_lenta_3middle
## factor AME SE z p lower upper
## price_increase1 0.2287 0.0071 32.4211 0.0000 0.2149 0.2426
Загрузка результатов в эксель (Гипотеза №3 - серединные цифры)
hyp3middle_lavka_tidy_result <- tidy(sum_hyp3_mid_lavka)
hyp3middle_magnit_tidy_result <- tidy(sum_hyp3_mid_magnit)
hyp3middle_pyat_tidy_result <- tidy(sum_hyp3_mid_pyat)
hyp3middle_perek_tidy_result <- tidy(sum_hyp3_mid_perek)
hyp3middle_lenta_tidy_result <- tidy(sum_hyp3_mid_lenta)
write.xlsx(hyp3middle_lavka_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3middle_lavka_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3middle_magnit_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3middle_magnit_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3middle_pyat_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3middle_pyat_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3middle_perek_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3middle_perek_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3middle_lenta_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3middle_lenta_tidy_result.xlsx", rowNames = TRUE)
Проверка 3 гипотезы (крайняя правая цифра)
Лавка
logit_3hyp_right_lavka <- glm(factor(right_number_changed) ~ factor(price_increase) + left_number_changed + middle_number_changed + right_number_prev_changed + factor(category), data = lavka3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_right_lavka <- coeftest(logit_3hyp_right_lavka)
sum_hyp3_right_lavka
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.099635 0.193202 -21.2194 < 2.2e-16
## factor(price_increase)1 0.715918 0.022356 32.0232 < 2.2e-16
## left_number_changed 0.417119 0.026551 15.7103 < 2.2e-16
## middle_number_changed 3.092846 0.026798 115.4126 < 2.2e-16
## right_number_prev_changed 1.248147 0.029336 42.5466 < 2.2e-16
## factor(category)Бакалея 0.183949 0.193288 0.9517 0.34126
## factor(category)Безалкогольные напитки 0.124546 0.195332 0.6376 0.52373
## factor(category)Бытовая химия -0.309892 0.197317 -1.5705 0.11629
## factor(category)Замороженные продукты -0.124472 0.194919 -0.6386 0.52309
## factor(category)Красота и здоровье -0.330574 0.195058 -1.6947 0.09012
## factor(category)Молоко и яйца 0.442879 0.195006 2.2711 0.02314
## factor(category)Мясо 0.091662 0.194856 0.4704 0.63806
## factor(category)Овощи -0.469922 0.205786 -2.2835 0.02240
## factor(category)Рыба 0.014634 0.199225 0.0735 0.94145
## factor(category)Сладости к чаю 0.268021 0.194747 1.3763 0.16874
## factor(category)Фрукты и ягоды -0.803699 0.205965 -3.9021 9.536e-05
## factor(category)Хлебобулочные изделия 0.322757 0.227703 1.4174 0.15635
##
## (Intercept) ***
## factor(price_increase)1 ***
## left_number_changed ***
## middle_number_changed ***
## right_number_prev_changed ***
## factor(category)Бакалея
## factor(category)Безалкогольные напитки
## factor(category)Бытовая химия
## factor(category)Замороженные продукты
## factor(category)Красота и здоровье .
## factor(category)Молоко и яйца *
## factor(category)Мясо
## factor(category)Овощи *
## factor(category)Рыба
## factor(category)Сладости к чаю
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_right_lavka)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.161200 1 1.077590
## left_number_changed 1.127150 1 1.061673
## middle_number_changed 1.319515 1 1.148701
## right_number_prev_changed 1.067191 1 1.033049
## factor(category) 1.061870 12 1.002504
Магнит
logit_3hyp_right_magnit <- glm(factor(right_number_changed) ~ factor(price_increase) + left_number_changed + middle_number_changed + right_number_prev_changed + factor(category), data = magnit3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_right_magnit <- coeftest(logit_3hyp_right_magnit)
sum_hyp3_right_magnit
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.202194 0.030202 -139.1365 < 2.2e-16
## factor(price_increase)1 0.293051 0.021503 13.6284 < 2.2e-16
## left_number_changed -0.209834 0.022157 -9.4704 < 2.2e-16
## middle_number_changed 3.238479 0.029277 110.6159 < 2.2e-16
## right_number_prev_changed 1.365872 0.022463 60.8066 < 2.2e-16
## factor(category)Безалкогольные напитки -0.097694 0.045414 -2.1512 0.0314622
## factor(category)Бытовая химия -0.199953 0.048095 -4.1574 3.218e-05
## factor(category)Замороженные продукты 0.073410 0.048612 1.5101 0.1310115
## factor(category)Красота и здоровье -0.359964 0.042929 -8.3851 < 2.2e-16
## factor(category)Молоко и яйца 0.105181 0.032658 3.2207 0.0012790
## factor(category)Мясо 0.251952 0.033219 7.5845 3.338e-14
## factor(category)Овощи 0.255893 0.059075 4.3317 1.480e-05
## factor(category)Рыба -0.199113 0.047652 -4.1784 2.935e-05
## factor(category)Сладости к чаю 0.156794 0.035847 4.3740 1.220e-05
## factor(category)Фрукты и ягоды 0.986763 0.066574 14.8221 < 2.2e-16
## factor(category)Хлебобулочные изделия 0.413906 0.109050 3.7955 0.0001473
##
## (Intercept) ***
## factor(price_increase)1 ***
## left_number_changed ***
## middle_number_changed ***
## right_number_prev_changed ***
## factor(category)Безалкогольные напитки *
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца **
## factor(category)Мясо ***
## factor(category)Овощи ***
## factor(category)Рыба ***
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_right_magnit)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.151362 1 1.073015
## left_number_changed 1.124755 1 1.060545
## middle_number_changed 1.289656 1 1.135630
## right_number_prev_changed 1.023604 1 1.011733
## factor(category) 1.029153 11 1.001307
Пятерочка
logit_3hyp_right_pyat <- glm(factor(right_number_changed) ~ factor(price_increase) + left_number_changed + middle_number_changed + right_number_prev_changed + factor(category), data = pyat3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_right_pyat <- coeftest(logit_3hyp_right_pyat)
sum_hyp3_right_pyat
##
## z test of coefficients:
##
## Estimate Std. Error z value
## (Intercept) -4.2098015 0.0207465 -202.9160
## factor(price_increase)1 0.4570737 0.0147448 30.9990
## left_number_changed 0.5293241 0.0148219 35.7123
## middle_number_changed 2.4851445 0.0199554 124.5352
## right_number_prev_changed 2.2434771 0.0152813 146.8124
## factor(category)Безалкогольные напитки 0.2681808 0.0237813 11.2770
## factor(category)Бытовая химия -0.5522076 0.0489045 -11.2916
## factor(category)Замороженные продукты -0.1399609 0.0389563 -3.5928
## factor(category)Красота и здоровье -0.5326342 0.0296202 -17.9821
## factor(category)Молоко и яйца 0.1681656 0.0214846 7.8273
## factor(category)Мясо -0.5192385 0.0353564 -14.6858
## factor(category)Овощи -0.0850265 0.0447622 -1.8995
## factor(category)Рыба -0.7748227 0.0562255 -13.7806
## factor(category)Сладости к чаю 0.0045721 0.0200930 0.2275
## factor(category)Фрукты и ягоды -0.3301636 0.0617853 -5.3437
## factor(category)Хлебобулочные изделия 0.0523114 0.0561621 0.9314
## Pr(>|z|)
## (Intercept) < 2.2e-16 ***
## factor(price_increase)1 < 2.2e-16 ***
## left_number_changed < 2.2e-16 ***
## middle_number_changed < 2.2e-16 ***
## right_number_prev_changed < 2.2e-16 ***
## factor(category)Безалкогольные напитки < 2.2e-16 ***
## factor(category)Бытовая химия < 2.2e-16 ***
## factor(category)Замороженные продукты 0.0003272 ***
## factor(category)Красота и здоровье < 2.2e-16 ***
## factor(category)Молоко и яйца 4.986e-15 ***
## factor(category)Мясо < 2.2e-16 ***
## factor(category)Овощи 0.0574968 .
## factor(category)Рыба < 2.2e-16 ***
## factor(category)Сладости к чаю 0.8199979
## factor(category)Фрукты и ягоды 9.105e-08 ***
## factor(category)Хлебобулочные изделия 0.3516280
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_right_pyat)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.145729 1 1.070387
## left_number_changed 1.099218 1 1.048436
## middle_number_changed 1.245938 1 1.116216
## right_number_prev_changed 1.047709 1 1.023576
## factor(category) 1.027100 11 1.001216
Перекресток
logit_3hyp_right_perek <- glm(factor(right_number_changed) ~ factor(price_increase) + left_number_changed + middle_number_changed + right_number_prev_changed + factor(category), data = perek3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_right_perek <- coeftest(logit_3hyp_right_perek)
sum_hyp3_right_perek
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -6.047466 0.026691 -226.5733 < 2.2e-16
## factor(price_increase)1 0.050294 0.015790 3.1852 0.001447
## left_number_changed 0.211174 0.015996 13.2019 < 2.2e-16
## middle_number_changed 3.767627 0.026400 142.7117 < 2.2e-16
## right_number_prev_changed 1.953040 0.018111 107.8354 < 2.2e-16
## factor(category)Безалкогольные напитки 0.084753 0.029011 2.9214 0.003485
## factor(category)Бытовая химия -0.470894 0.032507 -14.4858 < 2.2e-16
## factor(category)Замороженные продукты -0.140454 0.048499 -2.8960 0.003779
## factor(category)Красота и здоровье 0.534951 0.020000 26.7472 < 2.2e-16
## factor(category)Молоко и яйца 0.388798 0.028900 13.4531 < 2.2e-16
## factor(category)Мясо 0.095023 0.044590 2.1310 0.033087
## factor(category)Овощи -0.570238 0.062617 -9.1067 < 2.2e-16
## factor(category)Рыба -0.612688 0.076936 -7.9636 1.671e-15
## factor(category)Сладости к чаю -0.358927 0.030878 -11.6239 < 2.2e-16
## factor(category)Фрукты и ягоды -1.244050 0.134254 -9.2664 < 2.2e-16
## factor(category)Хлебобулочные изделия -0.754543 0.103057 -7.3216 2.451e-13
##
## (Intercept) ***
## factor(price_increase)1 **
## left_number_changed ***
## middle_number_changed ***
## right_number_prev_changed ***
## factor(category)Безалкогольные напитки **
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты **
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца ***
## factor(category)Мясо *
## factor(category)Овощи ***
## factor(category)Рыба ***
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_right_perek)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.138699 1 1.067099
## left_number_changed 1.157267 1 1.075763
## middle_number_changed 1.264508 1 1.124504
## right_number_prev_changed 1.014473 1 1.007211
## factor(category) 1.052174 11 1.002314
Лента
logit_3hyp_right_lenta <- glm(factor(right_number_changed) ~ factor(price_increase) + left_number_changed + middle_number_changed + right_number_prev_changed + factor(category), data = lenta3, family = binomial(link = "logit"), x = TRUE)
sum_hyp3_right_lenta <- coeftest(logit_3hyp_right_lenta)
sum_hyp3_right_lenta
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -4.442709 0.036654 -121.2063 < 2.2e-16
## factor(price_increase)1 1.037541 0.035608 29.1376 < 2.2e-16
## left_number_changed 0.687217 0.041917 16.3945 < 2.2e-16
## middle_number_changed 5.679678 0.032743 173.4637 < 2.2e-16
## right_number_prev_changed 1.269343 0.029560 42.9417 < 2.2e-16
## factor(category)Безалкогольные напитки -0.534268 0.044626 -11.9720 < 2.2e-16
## factor(category)Бытовая химия -0.036978 0.086851 -0.4258 0.670283
## factor(category)Замороженные продукты -0.132471 0.091087 -1.4543 0.145853
## factor(category)Красота и здоровье -0.102175 0.043133 -2.3688 0.017846
## factor(category)Молоко и яйца 0.352685 0.060573 5.8225 5.798e-09
## factor(category)Мясо -0.164073 0.056913 -2.8829 0.003941
## factor(category)Овощи -0.071223 0.134477 -0.5296 0.596370
## factor(category)Рыба -0.181204 0.088606 -2.0451 0.040850
## factor(category)Сладости к чаю 0.073440 0.046869 1.5669 0.117130
## factor(category)Фрукты и ягоды -0.351958 0.153275 -2.2962 0.021662
## factor(category)Хлебобулочные изделия -0.236705 0.134805 -1.7559 0.079103
##
## (Intercept) ***
## factor(price_increase)1 ***
## left_number_changed ***
## middle_number_changed ***
## right_number_prev_changed ***
## factor(category)Безалкогольные напитки ***
## factor(category)Бытовая химия
## factor(category)Замороженные продукты
## factor(category)Красота и здоровье *
## factor(category)Молоко и яйца ***
## factor(category)Мясо **
## factor(category)Овощи
## factor(category)Рыба *
## factor(category)Сладости к чаю
## factor(category)Фрукты и ягоды *
## factor(category)Хлебобулочные изделия .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_3hyp_right_lenta)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.101943 1 1.049735
## left_number_changed 1.098399 1 1.048045
## middle_number_changed 1.250510 1 1.118262
## right_number_prev_changed 1.057445 1 1.028321
## factor(category) 1.074242 11 1.003261
Предельные эффекты (Гипотеза 3 - крайняя правая цифра)
eff_lavka_3right <- summary(margins(logit_3hyp_right_lavka, variables = "price_increase"))
eff_magnit_3right <- summary(margins(logit_3hyp_right_magnit, variables = "price_increase"))
eff_pyat_3right <- summary(margins(logit_3hyp_right_pyat, variables = "price_increase"))
eff_perek_3right <- summary(margins(logit_3hyp_right_perek, variables = "price_increase"))
eff_lenta_3right <- summary(margins(logit_3hyp_right_lenta, variables = "price_increase"))
eff_lavka_3right
## factor AME SE z p lower upper
## price_increase1 0.0551 0.0019 29.1579 0.0000 0.0514 0.0588
eff_magnit_3right
## factor AME SE z p lower upper
## price_increase1 0.0239 0.0018 13.2802 0.0000 0.0204 0.0274
eff_pyat_3right
## factor AME SE z p lower upper
## price_increase1 0.0391 0.0013 30.1166 0.0000 0.0365 0.0416
eff_perek_3right
## factor AME SE z p lower upper
## price_increase1 0.0013 0.0004 3.1806 0.0015 0.0005 0.0021
eff_lenta_3right
## factor AME SE z p lower upper
## price_increase1 0.0424 0.0018 23.7102 0.0000 0.0389 0.0459
Загрузка результатов в эксель (Гипотеза №3 - крайняя правая
цифра)
hyp3right_lavka_tidy_result <- tidy(sum_hyp3_right_lavka)
hyp3right_magnit_tidy_result <- tidy(sum_hyp3_right_magnit)
hyp3right_pyat_tidy_result <- tidy(sum_hyp3_right_pyat)
hyp3right_perek_tidy_result <- tidy(sum_hyp3_right_perek)
hyp3right_lenta_tidy_result <- tidy(sum_hyp3_right_lenta)
write.xlsx(hyp3right_lavka_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3right_lavka_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3right_magnit_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3right_magnit_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3right_pyat_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3right_pyat_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3right_perek_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3right_perek_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp3right_lenta_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp3right_lenta_tidy_result.xlsx", rowNames = TRUE)
Проверка 4 гипотезы
Лавка
logit_4_lavka <- glm(factor(end_nine) ~ factor(price_increase) + factor(prev_price_nine) + factor(category) + factor(holiday), data = lavka4_5, family = binomial(link = "logit"), x = TRUE)
sum_hyp4_lavka <- coeftest(logit_4_lavka)
sum_hyp4_lavka
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -1.201320 0.013886 -86.5121 < 2.2e-16
## factor(price_increase)1 0.817519 0.017570 46.5304 < 2.2e-16
## factor(prev_price_nine)1 3.708490 0.012912 287.2157 < 2.2e-16
## factor(category)Безалкогольные напитки -0.043559 0.020728 -2.1014 0.035605
## factor(category)Бытовая химия 0.468264 0.039058 11.9889 < 2.2e-16
## factor(category)Замороженные продукты 0.462064 0.023895 19.3376 < 2.2e-16
## factor(category)Красота и здоровье 0.481464 0.027276 17.6513 < 2.2e-16
## factor(category)Молоко и яйца -0.318524 0.019251 -16.5463 < 2.2e-16
## factor(category)Мясо 0.353126 0.029732 11.8769 < 2.2e-16
## factor(category)Овощи 0.513351 0.046013 11.1565 < 2.2e-16
## factor(category)Рыба 0.403641 0.042718 9.4489 < 2.2e-16
## factor(category)Сладости к чаю -0.086434 0.019996 -4.3226 1.542e-05
## factor(category)Фрукты и ягоды 1.018268 0.056797 17.9283 < 2.2e-16
## factor(category)Хлебобулочные изделия -0.146179 0.040659 -3.5953 0.000324
## factor(holiday)1 -0.302905 0.012361 -24.5047 < 2.2e-16
##
## (Intercept) ***
## factor(price_increase)1 ***
## factor(prev_price_nine)1 ***
## factor(category)Безалкогольные напитки *
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца ***
## factor(category)Мясо ***
## factor(category)Овощи ***
## factor(category)Рыба ***
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия ***
## factor(holiday)1 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_4_lavka)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.049379 1 1.024392
## factor(prev_price_nine) 1.048295 1 1.023863
## factor(category) 1.006365 11 1.000288
## factor(holiday) 1.004514 1 1.002255
#wooldridgeTest(logit_4_lavka)
eff_lavka_23 <- summary(margins(logit_4_lavka, variables = "price_increase"))
eff_lavka_23
## factor AME SE z p lower upper
## price_increase1 0.0905 0.0019 47.0202 0.0000 0.0868 0.0943
Магнит
logit_4_magnit <- glm(factor(end_nine) ~ factor(price_increase) + factor(prev_price_nine) + factor(category) + factor(holiday), data = magnit4_5, family = binomial(link = "logit"), x = TRUE)
sum_hyp4_magnit <- coeftest(logit_4_magnit)
sum_hyp4_magnit
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -2.556963 0.019705 -129.7638 < 2.2e-16
## factor(price_increase)1 -0.795696 0.032240 -24.6807 < 2.2e-16
## factor(prev_price_nine)1 6.824022 0.040721 167.5802 < 2.2e-16
## factor(category)Безалкогольные напитки 0.031742 0.037622 0.8437 0.398842
## factor(category)Бытовая химия 0.342192 0.046051 7.4308 1.079e-13
## factor(category)Замороженные продукты 0.130184 0.048290 2.6959 0.007020
## factor(category)Красота и здоровье 0.650219 0.031352 20.7395 < 2.2e-16
## factor(category)Молоко и яйца -0.092938 0.030388 -3.0583 0.002226
## factor(category)Мясо -0.228652 0.042588 -5.3689 7.920e-08
## factor(category)Овощи -0.438511 0.075425 -5.8138 6.106e-09
## factor(category)Рыба -0.104085 0.051553 -2.0190 0.043489
## factor(category)Сладости к чаю -0.461928 0.033778 -13.6753 < 2.2e-16
## factor(category)Фрукты и ягоды -0.596941 0.112280 -5.3166 1.058e-07
## factor(category)Хлебобулочные изделия -0.467061 0.077000 -6.0657 1.314e-09
## factor(holiday)1 0.078257 0.020058 3.9015 9.561e-05
##
## (Intercept) ***
## factor(price_increase)1 ***
## factor(prev_price_nine)1 ***
## factor(category)Безалкогольные напитки
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты **
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца **
## factor(category)Мясо ***
## factor(category)Овощи ***
## factor(category)Рыба *
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия ***
## factor(holiday)1 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_4_magnit)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.045730 1 1.022609
## factor(prev_price_nine) 1.049971 1 1.024681
## factor(category) 1.015299 11 1.000690
## factor(holiday) 1.003272 1 1.001635
eff_magnit_23 <- summary(margins(logit_4_magnit, variables = "price_increase"))
eff_magnit_23
## factor AME SE z p lower upper
## price_increase1 -0.0341 0.0011 -30.3625 0.0000 -0.0363 -0.0319
Пятерочка
logit_4_pyat <- glm(factor(end_nine) ~ factor(price_increase) + factor(prev_price_nine) + factor(category) + factor(holiday), data = pyat4_5, family = binomial(link = "logit"), x = TRUE)
sum_hyp4_pyat <- coeftest(logit_4_pyat)
sum_hyp4_pyat
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 1.700246 0.032468 52.3667 < 2.2e-16
## factor(price_increase)1 -1.170435 0.034412 -34.0121 < 2.2e-16
## factor(prev_price_nine)1 3.254159 0.032553 99.9638 < 2.2e-16
## factor(category)Безалкогольные напитки 0.137635 0.054039 2.5470 0.0108663
## factor(category)Бытовая химия 0.843607 0.124045 6.8008 1.041e-11
## factor(category)Замороженные продукты 0.339212 0.092093 3.6834 0.0002302
## factor(category)Красота и здоровье 1.295264 0.091945 14.0874 < 2.2e-16
## factor(category)Молоко и яйца 1.371420 0.080327 17.0730 < 2.2e-16
## factor(category)Мясо 0.085829 0.068963 1.2446 0.2132926
## factor(category)Овощи -0.557632 0.075279 -7.4075 1.287e-13
## factor(category)Рыба 0.484872 0.115483 4.1986 2.685e-05
## factor(category)Сладости к чаю -0.347909 0.038585 -9.0168 < 2.2e-16
## factor(category)Фрукты и ягоды -0.965238 0.085742 -11.2575 < 2.2e-16
## factor(category)Хлебобулочные изделия 0.277140 0.125628 2.2060 0.0273808
## factor(holiday)1 -0.100943 0.033291 -3.0321 0.0024286
##
## (Intercept) ***
## factor(price_increase)1 ***
## factor(prev_price_nine)1 ***
## factor(category)Безалкогольные напитки *
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца ***
## factor(category)Мясо
## factor(category)Овощи ***
## factor(category)Рыба ***
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия *
## factor(holiday)1 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_4_pyat)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.155780 1 1.075072
## factor(prev_price_nine) 1.164076 1 1.078923
## factor(category) 1.010609 11 1.000480
## factor(holiday) 1.018992 1 1.009451
eff_pyat_23 <- summary(margins(logit_4_pyat, variables = "price_increase"))
eff_pyat_23
## factor AME SE z p lower upper
## price_increase1 -0.0256 0.0009 -28.1722 0.0000 -0.0274 -0.0238
Перекресток
logit_4_perek <- glm(factor(end_nine) ~ factor(price_increase) + factor(prev_price_nine) + factor(category) + factor(holiday), data = perek4_5, family = binomial(link = "logit"), x = TRUE)
sum_hyp4_perek <- coeftest(logit_4_perek)
sum_hyp4_perek
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) -0.7672979 0.0108832 -70.5027 < 2.2e-16
## factor(price_increase)1 0.7388353 0.0146867 50.3065 < 2.2e-16
## factor(prev_price_nine)1 4.3587926 0.0094694 460.3037 < 2.2e-16
## factor(category)Бытовая химия -0.5272840 0.0168213 -31.3463 < 2.2e-16
## factor(category)Замороженные продукты -0.3000229 0.0254511 -11.7882 < 2.2e-16
## factor(category)Красота и здоровье -0.8049997 0.0126959 -63.4064 < 2.2e-16
## factor(category)Молоко и яйца -0.1274374 0.0192306 -6.6268 3.431e-11
## factor(category)Мясо -0.3291527 0.0255891 -12.8630 < 2.2e-16
## factor(category)Напитки -0.1436856 0.0175420 -8.1910 2.592e-16
## factor(category)Овощи 0.6576353 0.0383083 17.1669 < 2.2e-16
## factor(category)Рыба 0.4154371 0.0437649 9.4925 < 2.2e-16
## factor(category)Сладости к чаю 0.3186283 0.0195582 16.2913 < 2.2e-16
## factor(category)Фрукты и ягоды 0.5845151 0.0661593 8.8350 < 2.2e-16
## factor(category)Хлебобулочные изделия 0.0844473 0.0469648 1.7981 0.07216
## factor(holiday)1 -0.1316515 0.0094274 -13.9648 < 2.2e-16
##
## (Intercept) ***
## factor(price_increase)1 ***
## factor(prev_price_nine)1 ***
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье ***
## factor(category)Молоко и яйца ***
## factor(category)Мясо ***
## factor(category)Напитки ***
## factor(category)Овощи ***
## factor(category)Рыба ***
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды ***
## factor(category)Хлебобулочные изделия .
## factor(holiday)1 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_4_perek)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.025793 1 1.012815
## factor(prev_price_nine) 1.027958 1 1.013883
## factor(category) 1.011096 11 1.000502
## factor(holiday) 1.009540 1 1.004759
eff_perek_23 <- summary(margins(logit_4_perek, variables = "price_increase"))
eff_perek_23
## factor AME SE z p lower upper
## price_increase1 0.0471 0.0009 51.5590 0.0000 0.0453 0.0489
Лента
logit_4_lenta <- glm(factor(end_nine) ~ factor(price_increase) + factor(prev_price_nine) + factor(category) + factor(holiday), data = lenta4_5, family = binomial(link = "logit"), x = TRUE)
sum_hyp4_lenta <- coeftest(logit_4_lenta)
sum_hyp4_lenta
##
## z test of coefficients:
##
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 5.463783 0.207839 26.2885 < 2.2e-16
## factor(price_increase)1 -1.255611 0.128306 -9.7861 < 2.2e-16
## factor(prev_price_nine)1 3.447048 0.094657 36.4162 < 2.2e-16
## factor(category)Безалкогольные напитки -2.924571 0.211592 -13.8218 < 2.2e-16
## factor(category)Бытовая химия -3.073687 0.237674 -12.9324 < 2.2e-16
## factor(category)Замороженные продукты -1.478494 0.378479 -3.9064 9.368e-05
## factor(category)Красота и здоровье 1.176715 0.540488 2.1771 0.029471
## factor(category)Молоко и яйца -0.784831 0.323992 -2.4224 0.015419
## factor(category)Мясо -2.418213 0.230888 -10.4735 < 2.2e-16
## factor(category)Овощи -0.270779 0.738085 -0.3669 0.713718
## factor(category)Рыба -1.200786 0.393481 -3.0517 0.002275
## factor(category)Сладости к чаю -1.211955 0.259140 -4.6768 2.913e-06
## factor(category)Фрукты и ягоды 11.313314 193.188123 0.0586 0.953302
## factor(category)Хлебобулочные изделия 0.093965 1.022401 0.0919 0.926773
## factor(holiday)1 -0.635402 0.092459 -6.8723 6.318e-12
##
## (Intercept) ***
## factor(price_increase)1 ***
## factor(prev_price_nine)1 ***
## factor(category)Безалкогольные напитки ***
## factor(category)Бытовая химия ***
## factor(category)Замороженные продукты ***
## factor(category)Красота и здоровье *
## factor(category)Молоко и яйца *
## factor(category)Мясо ***
## factor(category)Овощи
## factor(category)Рыба **
## factor(category)Сладости к чаю ***
## factor(category)Фрукты и ягоды
## factor(category)Хлебобулочные изделия
## factor(holiday)1 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
vif(logit_4_lenta)
## GVIF Df GVIF^(1/(2*Df))
## factor(price_increase) 1.165487 1 1.079577
## factor(prev_price_nine) 1.242388 1 1.114625
## factor(category) 1.030268 11 1.001356
## factor(holiday) 1.125752 1 1.061014
eff_lenta_23 <- summary(margins(logit_4_lenta, variables = "price_increase"))
eff_lenta_23
## factor AME SE z p lower upper
## price_increase1 -0.0083 0.0012 -6.6289 0.0000 -0.0107 -0.0058
Загрузка результатов в эксель (Гипотеза №4)
hyp4_lavka_tidy_result <- tidy(sum_hyp4_lavka)
hyp4_magnit_tidy_result <- tidy(sum_hyp4_magnit)
hyp4_pyat_tidy_result <- tidy(sum_hyp4_pyat)
hyp4_perek_tidy_result <- tidy(sum_hyp4_perek)
hyp4_lenta_tidy_result <- tidy(sum_hyp4_lenta)
write.xlsx(hyp4_lavka_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp4_lavka_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp4_magnit_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp4_magnit_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp4_pyat_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp4_pyat_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp4_perek_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp4_perek_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp4_lenta_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp4_lenta_tidy_result.xlsx", rowNames = TRUE)
Проверка 5 гипотезы
Лавка
hyp5_lavka_fixed <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "within", data = lavka4_5)
sum_hyp5_lavka_fixed <- summary(hyp5_lavka_fixed)
sum_hyp5_lavka_fixed
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = lavka4_5, model = "within", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 17862, T = 1-168, N = 242430
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -3.36587764 -0.00094538 0.01374656 0.03669215 45.93561014
##
## Coefficients:
## Estimate Std. Error
## factor(prev_price_nine)1 -1.5664e-02 1.3162e-03
## factor(price_increase)1 3.2391e-01 2.0893e-03
## factor(category)Безалкогольные напитки 3.1686e-04 2.2376e-01
## factor(category)Бытовая химия -4.1157e-02 2.3371e-01
## factor(category)Замороженные продукты -6.2183e-02 1.6915e-01
## factor(category)Молоко и яйца 3.3173e-02 2.3921e-01
## factor(category)Мясо -7.7356e-02 3.5881e-01
## factor(category)Сладости к чаю 5.3335e-02 2.4981e-01
## fx -3.7205e-04 4.6974e-05
## factor(holiday)1 -1.4238e-04 9.6873e-04
## factor(prev_price_nine)1:factor(price_increase)1 -3.3266e-02 2.8684e-03
## t-value Pr(>|t|)
## factor(prev_price_nine)1 -11.9009 < 2.2e-16 ***
## factor(price_increase)1 155.0340 < 2.2e-16 ***
## factor(category)Безалкогольные напитки 0.0014 0.9989
## factor(category)Бытовая химия -0.1761 0.8602
## factor(category)Замороженные продукты -0.3676 0.7131
## factor(category)Молоко и яйца 0.1387 0.8897
## factor(category)Мясо -0.2156 0.8293
## factor(category)Сладости к чаю 0.2135 0.8309
## fx -7.9204 2.379e-15 ***
## factor(holiday)1 -0.1470 0.8832
## factor(prev_price_nine)1:factor(price_increase)1 -11.5975 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 13605
## Residual Sum of Squares: 11243
## R-Squared: 0.17361
## Adj. R-Squared: 0.10783
## F-statistic: 4288.53 on 11 and 224557 DF, p-value: < 2.22e-16
hyp5_lavka_random <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "random", data = lavka4_5)
sum_hyp5_lavka_random <- summary(hyp5_lavka_random)
sum_hyp5_lavka_random
## Oneway (individual) effect Random Effect Model
## (Swamy-Arora's transformation)
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = lavka4_5, model = "random", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 17862, T = 1-168, N = 242430
##
## Effects:
## var std.dev share
## idiosyncratic 0.050067 0.223757 0.962
## individual 0.001973 0.044417 0.038
## theta:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.01914 0.19721 0.34067 0.29969 0.39950 0.63774
##
## Residuals:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## -2.104 0.009 0.019 0.000 0.027 47.138
##
## Coefficients:
## Estimate Std. Error
## (Intercept) 1.0583e-02 3.3492e-03
## factor(prev_price_nine)1 -1.3208e-02 1.1087e-03
## factor(price_increase)1 3.2217e-01 1.9948e-03
## factor(category)Безалкогольные напитки 1.3313e-03 2.1900e-03
## factor(category)Бытовая химия -1.2923e-03 3.7763e-03
## factor(category)Замороженные продукты 6.7743e-03 2.3296e-03
## factor(category)Красота и здоровье 4.5708e-03 2.6827e-03
## factor(category)Молоко и яйца 4.2777e-04 2.0550e-03
## factor(category)Мясо -3.9846e-03 2.9531e-03
## factor(category)Овощи 1.2567e-04 4.4375e-03
## factor(category)Рыба -2.6256e-03 4.2117e-03
## factor(category)Сладости к чаю 6.2234e-04 2.1100e-03
## factor(category)Фрукты и ягоды -4.4181e-03 4.8194e-03
## factor(category)Хлебобулочные изделия 8.0291e-03 4.2326e-03
## fx -3.4113e-04 4.0961e-05
## factor(holiday)1 -2.5920e-04 9.2606e-04
## factor(prev_price_nine)1:factor(price_increase)1 -3.6083e-02 2.7430e-03
## z-value Pr(>|z|)
## (Intercept) 3.1598 0.001579 **
## factor(prev_price_nine)1 -11.9133 < 2.2e-16 ***
## factor(price_increase)1 161.5103 < 2.2e-16 ***
## factor(category)Безалкогольные напитки 0.6079 0.543252
## factor(category)Бытовая химия -0.3422 0.732189
## factor(category)Замороженные продукты 2.9080 0.003638 **
## factor(category)Красота и здоровье 1.7038 0.088412 .
## factor(category)Молоко и яйца 0.2082 0.835103
## factor(category)Мясо -1.3493 0.177241
## factor(category)Овощи 0.0283 0.977407
## factor(category)Рыба -0.6234 0.533024
## factor(category)Сладости к чаю 0.2949 0.768037
## factor(category)Фрукты и ягоды -0.9167 0.359290
## factor(category)Хлебобулочные изделия 1.8970 0.057831 .
## fx -8.3281 < 2.2e-16 ***
## factor(holiday)1 -0.2799 0.779558
## factor(prev_price_nine)1:factor(price_increase)1 -13.1544 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 14062
## Residual Sum of Squares: 11657
## R-Squared: 0.17103
## Adj. R-Squared: 0.17097
## Chisq: 50129.6 on 16 DF, p-value: < 2.22e-16
#Hausman test
lavka_hausman <- phtest(hyp5_lavka_fixed, hyp5_lavka_random)
lavka_hausman
##
## Hausman Test
##
## data: price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) * ...
## chisq = 91.285, df = 11, p-value = 9.332e-15
## alternative hypothesis: one model is inconsistent
#выбираем модель fixed effects
Магнит
hyp5_magnit_fixed <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "within", data = magnit4_5)
sum_hyp5_magnit_fixed <- summary(hyp5_magnit_fixed)
sum_hyp5_magnit_fixed
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = magnit4_5, model = "within", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 22701, T = 1-77, N = 209219
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -2.252927 -0.010849 0.024254 0.053116 5.340226
##
## Coefficients:
## Estimate Std. Error
## factor(prev_price_nine)1 -1.2809e-03 1.2222e-03
## factor(price_increase)1 3.6966e-01 1.0764e-03
## factor(category)Безалкогольные напитки 1.3259e-03 1.8163e-01
## factor(category)Замороженные продукты -1.1621e-02 1.2953e-01
## factor(category)Красота и здоровье 2.0782e-03 1.6990e-01
## factor(category)Молоко и яйца 4.1433e-02 1.6214e-01
## factor(category)Овощи 3.4269e-02 6.1664e-02
## factor(category)Рыба 3.4711e-02 3.4199e-02
## factor(category)Сладости к чаю -3.5863e-03 4.9518e-02
## factor(category)Хлебобулочные изделия 1.8298e-02 9.6675e-02
## fx 4.2254e-05 5.0706e-05
## factor(holiday)1 -4.0530e-03 7.6885e-04
## factor(prev_price_nine)1:factor(price_increase)1 -4.6915e-02 2.3720e-03
## t-value Pr(>|t|)
## factor(prev_price_nine)1 -1.0481 0.2946
## factor(price_increase)1 343.4356 < 2.2e-16 ***
## factor(category)Безалкогольные напитки 0.0073 0.9942
## factor(category)Замороженные продукты -0.0897 0.9285
## factor(category)Красота и здоровье 0.0122 0.9902
## factor(category)Молоко и яйца 0.2555 0.7983
## factor(category)Овощи 0.5557 0.5784
## factor(category)Рыба 1.0150 0.3101
## factor(category)Сладости к чаю -0.0724 0.9423
## factor(category)Хлебобулочные изделия 0.1893 0.8499
## fx 0.8333 0.4047
## factor(holiday)1 -5.2715 1.355e-07 ***
## factor(prev_price_nine)1:factor(price_increase)1 -19.7788 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 8083
## Residual Sum of Squares: 4614.6
## R-Squared: 0.4291
## Adj. R-Squared: 0.35957
## F-statistic: 10783.1 on 13 and 186505 DF, p-value: < 2.22e-16
hyp5_magnit_random <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "random", data = magnit4_5)
sum_hyp5_magnit_random <- summary(hyp5_magnit_random)
sum_hyp5_magnit_random
## Oneway (individual) effect Random Effect Model
## (Swamy-Arora's transformation)
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = magnit4_5, model = "random", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 22701, T = 1-77, N = 209219
##
## Effects:
## var std.dev share
## idiosyncratic 0.02474 0.15730 1
## individual 0.00000 0.00000 0
## theta:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0 0 0 0 0 0
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -0.8233286 -0.0042497 0.0361838 0.0436521 5.6314155
##
## Coefficients:
## Estimate Std. Error
## (Intercept) -5.6947e-02 2.2345e-03
## factor(prev_price_nine)1 1.1877e-03 9.6360e-04
## factor(price_increase)1 3.5363e-01 1.0109e-03
## factor(category)Безалкогольные напитки -3.4823e-03 1.3489e-03
## factor(category)Бытовая химия -5.0810e-03 1.8331e-03
## factor(category)Замороженные продукты 5.3404e-03 1.7746e-03
## factor(category)Красота и здоровье 1.1991e-02 1.3364e-03
## factor(category)Молоко и яйца -1.1547e-02 1.0603e-03
## factor(category)Мясо 6.3971e-04 1.4094e-03
## factor(category)Овощи -2.9203e-02 2.3119e-03
## factor(category)Рыба -3.6446e-04 1.7609e-03
## factor(category)Сладости к чаю 4.3304e-03 1.0860e-03
## factor(category)Фрукты и ягоды -5.7617e-02 3.1883e-03
## factor(category)Хлебобулочные изделия 9.3704e-03 2.3970e-03
## fx 2.7496e-04 3.0288e-05
## factor(holiday)1 -6.0404e-03 7.1459e-04
## factor(prev_price_nine)1:factor(price_increase)1 -4.6772e-02 2.2376e-03
## z-value Pr(>|z|)
## (Intercept) -25.4849 < 2.2e-16 ***
## factor(prev_price_nine)1 1.2326 0.217735
## factor(price_increase)1 349.8134 < 2.2e-16 ***
## factor(category)Безалкогольные напитки -2.5816 0.009834 **
## factor(category)Бытовая химия -2.7719 0.005573 **
## factor(category)Замороженные продукты 3.0094 0.002618 **
## factor(category)Красота и здоровье 8.9726 < 2.2e-16 ***
## factor(category)Молоко и яйца -10.8908 < 2.2e-16 ***
## factor(category)Мясо 0.4539 0.649919
## factor(category)Овощи -12.6312 < 2.2e-16 ***
## factor(category)Рыба -0.2070 0.836032
## factor(category)Сладости к чаю 3.9877 6.672e-05 ***
## factor(category)Фрукты и ягоды -18.0711 < 2.2e-16 ***
## factor(category)Хлебобулочные изделия 3.9093 9.257e-05 ***
## fx 9.0782 < 2.2e-16 ***
## factor(holiday)1 -8.4529 < 2.2e-16 ***
## factor(prev_price_nine)1:factor(price_increase)1 -20.9032 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 8464.2
## Residual Sum of Squares: 4977.9
## R-Squared: 0.41189
## Adj. R-Squared: 0.41185
## Chisq: 146518 on 16 DF, p-value: < 2.22e-16
#Hausman test
magnit_hausman <- phtest(hyp5_magnit_fixed, hyp5_magnit_random)
magnit_hausman
##
## Hausman Test
##
## data: price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) * ...
## chisq = 2254.3, df = 13, p-value < 2.2e-16
## alternative hypothesis: one model is inconsistent
#выбираем модель fixed effects
Пятерочка
hyp5_pyat_fixed <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "within", data = pyat4_5)
sum_hyp5_pyat_fixed <- summary(hyp5_pyat_fixed)
sum_hyp5_pyat_fixed
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = pyat4_5, model = "within", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 11741, T = 1-114, N = 255887
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -1.748482 -0.037232 0.012593 0.038706 11.515762
##
## Coefficients:
## Estimate Std. Error
## factor(prev_price_nine)1 -1.2642e-02 1.3912e-03
## factor(price_increase)1 5.5513e-01 4.2931e-03
## factor(category)Безалкогольные напитки 1.5368e-02 2.2472e-02
## factor(category)Бытовая химия -4.4539e-02 3.7835e-02
## factor(category)Замороженные продукты -3.0061e-02 1.5155e-02
## factor(category)Красота и здоровье -3.0772e-03 3.3025e-02
## factor(category)Молоко и яйца -9.4360e-03 8.2398e-03
## factor(category)Мясо 3.1567e-02 1.8089e-02
## factor(category)Овощи 4.2307e-02 1.7980e-02
## factor(category)Рыба 1.5175e-02 8.3271e-03
## factor(category)Сладости к чаю -1.1868e-02 6.7668e-03
## factor(category)Фрукты и ягоды 1.5583e-02 3.0797e-02
## factor(category)Хлебобулочные изделия 1.2424e-02 1.2226e-02
## fx 1.6227e-05 3.3871e-05
## factor(holiday)1 -9.8224e-04 6.5271e-04
## factor(prev_price_nine)1:factor(price_increase)1 -3.4844e-01 4.3530e-03
## t-value Pr(>|t|)
## factor(prev_price_nine)1 -9.0875 < 2e-16 ***
## factor(price_increase)1 129.3071 < 2e-16 ***
## factor(category)Безалкогольные напитки 0.6839 0.49406
## factor(category)Бытовая химия -1.1772 0.23911
## factor(category)Замороженные продукты -1.9835 0.04731 *
## factor(category)Красота и здоровье -0.0932 0.92576
## factor(category)Молоко и яйца -1.1452 0.25213
## factor(category)Мясо 1.7451 0.08097 .
## factor(category)Овощи 2.3531 0.01862 *
## factor(category)Рыба 1.8223 0.06840 .
## factor(category)Сладости к чаю -1.7538 0.07946 .
## factor(category)Фрукты и ягоды 0.5060 0.61287
## factor(category)Хлебобулочные изделия 1.0162 0.30954
## fx 0.4791 0.63188
## factor(holiday)1 -1.5049 0.13236
## factor(prev_price_nine)1:factor(price_increase)1 -80.0472 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 7405.4
## Residual Sum of Squares: 5389.3
## R-Squared: 0.27224
## Adj. R-Squared: 0.23719
## F-statistic: 5707.73 on 16 and 244130 DF, p-value: < 2.22e-16
hyp5_pyat_random <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "random", data = pyat4_5)
sum_hyp5_pyat_random <- summary(hyp5_pyat_random)
sum_hyp5_pyat_random
## Oneway (individual) effect Random Effect Model
## (Swamy-Arora's transformation)
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = pyat4_5, model = "random", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 11741, T = 1-114, N = 255887
##
## Effects:
## var std.dev share
## idiosyncratic 0.02208 0.14858 1
## individual 0.00000 0.00000 0
## theta:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0 0 0 0 0 0
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -0.811454 -0.045417 0.027367 0.035659 12.138814
##
## Coefficients:
## Estimate Std. Error
## (Intercept) -4.4537e-03 2.4545e-03
## factor(prev_price_nine)1 -1.6599e-02 1.2660e-03
## factor(price_increase)1 5.4315e-01 4.0672e-03
## factor(category)Безалкогольные напитки 4.9283e-03 1.0624e-03
## factor(category)Бытовая химия 1.3925e-02 1.7760e-03
## factor(category)Замороженные продукты 1.1405e-03 1.6840e-03
## factor(category)Красота и здоровье 8.7821e-03 1.0913e-03
## factor(category)Молоко и яйца -3.5472e-03 9.7813e-04
## factor(category)Мясо 4.9016e-04 1.3853e-03
## factor(category)Овощи -5.2256e-03 2.0915e-03
## factor(category)Рыба 5.4229e-03 1.8573e-03
## factor(category)Сладости к чаю 7.1403e-03 8.8160e-04
## factor(category)Фрукты и ягоды -5.5530e-03 2.9633e-03
## factor(category)Хлебобулочные изделия 9.4488e-03 2.2150e-03
## fx -2.3811e-04 2.8074e-05
## factor(holiday)1 2.7849e-03 6.3257e-04
## factor(prev_price_nine)1:factor(price_increase)1 -3.5043e-01 4.1297e-03
## z-value Pr(>|z|)
## (Intercept) -1.8145 0.0695961 .
## factor(prev_price_nine)1 -13.1117 < 2.2e-16 ***
## factor(price_increase)1 133.5446 < 2.2e-16 ***
## factor(category)Безалкогольные напитки 4.6390 3.501e-06 ***
## factor(category)Бытовая химия 7.8404 4.491e-15 ***
## factor(category)Замороженные продукты 0.6772 0.4982492
## factor(category)Красота и здоровье 8.0471 8.480e-16 ***
## factor(category)Молоко и яйца -3.6265 0.0002873 ***
## factor(category)Мясо 0.3538 0.7234626
## factor(category)Овощи -2.4985 0.0124706 *
## factor(category)Рыба 2.9198 0.0035023 **
## factor(category)Сладости к чаю 8.0993 5.528e-16 ***
## factor(category)Фрукты и ягоды -1.8739 0.0609429 .
## factor(category)Хлебобулочные изделия 4.2658 1.992e-05 ***
## fx -8.4815 < 2.2e-16 ***
## factor(holiday)1 4.4025 1.070e-05 ***
## factor(prev_price_nine)1:factor(price_increase)1 -84.8561 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 7657.4
## Residual Sum of Squares: 5664.7
## R-Squared: 0.26023
## Adj. R-Squared: 0.26019
## Chisq: 90009.4 on 16 DF, p-value: < 2.22e-16
#Hausman test
pyat_hausman <- phtest(hyp5_pyat_fixed, hyp5_pyat_random)
pyat_hausman
##
## Hausman Test
##
## data: price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) * ...
## chisq = 4045.8, df = 16, p-value < 2.2e-16
## alternative hypothesis: one model is inconsistent
#выбираем модель fixed effects
Перекресток
hyp5_perek_fixed <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "within", data = perek4_5)
sum_hyp5_perek_fixed <- summary(hyp5_perek_fixed)
sum_hyp5_perek_fixed
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = perek4_5, model = "within", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 26455, T = 1-50, N = 714677
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -1.2058297 0.0017583 0.0158811 0.0293943 7.4384072
##
## Coefficients:
## Estimate Std. Error
## factor(prev_price_nine)1 -0.01396482 0.00045564
## factor(price_increase)1 0.28334812 0.00093597
## fx 0.00068857 0.00010139
## factor(holiday)1 -0.00931409 0.00027778
## factor(prev_price_nine)1:factor(price_increase)1 -0.01062365 0.00105212
## t-value Pr(>|t|)
## factor(prev_price_nine)1 -30.6486 < 2.2e-16 ***
## factor(price_increase)1 302.7329 < 2.2e-16 ***
## fx 6.7914 1.112e-11 ***
## factor(holiday)1 -33.5305 < 2.2e-16 ***
## factor(prev_price_nine)1:factor(price_increase)1 -10.0974 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 14103
## Residual Sum of Squares: 8777.7
## R-Squared: 0.37762
## Adj. R-Squared: 0.35369
## F-statistic: 83513.2 on 5 and 688217 DF, p-value: < 2.22e-16
hyp5_perek_random <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "random", data = perek4_5)
sum_hyp5_perek_random <- summary(hyp5_perek_random)
sum_hyp5_perek_random
## Oneway (individual) effect Random Effect Model
## (Swamy-Arora's transformation)
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = perek4_5, model = "random", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 26455, T = 1-50, N = 714677
##
## Effects:
## var std.dev share
## idiosyncratic 0.01275 0.11293 1
## individual 0.00000 0.00000 0
## theta:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0 0 0 0 0 0
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -0.870886 0.013606 0.019427 0.024853 7.777108
##
## Coefficients:
## Estimate Std. Error
## (Intercept) -5.8448e-02 7.1842e-03
## factor(prev_price_nine)1 -8.6183e-03 3.6396e-04
## factor(price_increase)1 2.7768e-01 8.9909e-04
## factor(category)Бытовая химия -7.0969e-03 4.9951e-04
## factor(category)Замороженные продукты -2.4879e-03 7.5293e-04
## factor(category)Красота и здоровье -8.5687e-03 3.8254e-04
## factor(category)Молоко и яйца -8.2036e-03 5.4514e-04
## factor(category)Мясо -5.2096e-03 7.6117e-04
## factor(category)Напитки 1.2361e-03 4.9676e-04
## factor(category)Овощи -6.9804e-03 8.7412e-04
## factor(category)Рыба -6.0274e-03 1.0351e-03
## factor(category)Сладости к чаю 2.0123e-03 4.9514e-04
## factor(category)Фрукты и ягоды -1.4534e-02 1.6818e-03
## factor(category)Хлебобулочные изделия -4.3553e-03 1.2519e-03
## fx 7.0013e-04 9.7323e-05
## factor(holiday)1 -9.6019e-03 2.7242e-04
## factor(prev_price_nine)1:factor(price_increase)1 -1.4079e-02 1.0108e-03
## z-value Pr(>|z|)
## (Intercept) -8.1357 4.097e-16 ***
## factor(prev_price_nine)1 -23.6790 < 2.2e-16 ***
## factor(price_increase)1 308.8463 < 2.2e-16 ***
## factor(category)Бытовая химия -14.2078 < 2.2e-16 ***
## factor(category)Замороженные продукты -3.3043 0.0009521 ***
## factor(category)Красота и здоровье -22.3996 < 2.2e-16 ***
## factor(category)Молоко и яйца -15.0486 < 2.2e-16 ***
## factor(category)Мясо -6.8442 7.689e-12 ***
## factor(category)Напитки 2.4883 0.0128366 *
## factor(category)Овощи -7.9856 1.398e-15 ***
## factor(category)Рыба -5.8229 5.782e-09 ***
## factor(category)Сладости к чаю 4.0640 4.823e-05 ***
## factor(category)Фрукты и ягоды -8.6421 < 2.2e-16 ***
## factor(category)Хлебобулочные изделия -3.4791 0.0005031 ***
## fx 7.1938 6.300e-13 ***
## factor(holiday)1 -35.2473 < 2.2e-16 ***
## factor(prev_price_nine)1:factor(price_increase)1 -13.9286 < 2.2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 14331
## Residual Sum of Squares: 9020.8
## R-Squared: 0.37054
## Adj. R-Squared: 0.37053
## Chisq: 420695 on 16 DF, p-value: < 2.22e-16
#Hausman test
perek_hausman <- phtest(hyp5_perek_fixed, hyp5_perek_random)
perek_hausman
##
## Hausman Test
##
## data: price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) * ...
## chisq = 6302.3, df = 5, p-value < 2.2e-16
## alternative hypothesis: one model is inconsistent
#выбираем модель fixed effects
Лента
hyp5_lenta_fixed <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "within", data = lenta4_5)
sum_hyp5_lenta_fixed <- summary(hyp5_lenta_fixed)
sum_hyp5_lenta_fixed
## Oneway (individual) effect Within Model
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = lenta4_5, model = "within", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 12529, T = 1-38, N = 150303
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -1.3930891 -0.0013924 0.0017770 0.0194558 3.5257018
##
## Coefficients:
## Estimate Std. Error
## factor(prev_price_nine)1 -0.01466418 0.00067917
## factor(price_increase)1 0.09630249 0.00551368
## factor(category)Овощи -0.00836206 0.03828832
## fx 0.00042771 0.00012095
## factor(holiday)1 -0.00180926 0.00033687
## factor(prev_price_nine)1:factor(price_increase)1 0.03463101 0.00553238
## t-value Pr(>|t|)
## factor(prev_price_nine)1 -21.5915 < 2.2e-16 ***
## factor(price_increase)1 17.4661 < 2.2e-16 ***
## factor(category)Овощи -0.2184 0.8271200
## fx 3.5361 0.0004062 ***
## factor(holiday)1 -5.3708 7.850e-08 ***
## factor(prev_price_nine)1:factor(price_increase)1 6.2597 3.869e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 760.92
## Residual Sum of Squares: 498.93
## R-Squared: 0.34431
## Adj. R-Squared: 0.28465
## F-statistic: 12057.1 on 6 and 137768 DF, p-value: < 2.22e-16
hyp5_lenta_random <- plm(price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine)*factor(price_increase) + factor(category) + fx + factor(holiday), index = c("Наименование", "Дата"), model = "random", data = lenta4_5)
sum_hyp5_lenta_random <- summary(hyp5_lenta_random)
sum_hyp5_lenta_random
## Oneway (individual) effect Random Effect Model
## (Swamy-Arora's transformation)
##
## Call:
## plm(formula = price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) *
## factor(price_increase) + factor(category) + fx + factor(holiday),
## data = lenta4_5, model = "random", index = c("Наименование",
## "Дата"))
##
## Unbalanced Panel: n = 12529, T = 1-38, N = 150303
##
## Effects:
## var std.dev share
## idiosyncratic 0.003622 0.060179 1
## individual 0.000000 0.000000 0
## theta:
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0 0 0 0 0 0
##
## Residuals:
## Min. 1st Qu. Median 3rd Qu. Max.
## -0.80045699 -0.00013071 0.00998133 0.01676122 3.97300257
##
## Coefficients:
## Estimate Std. Error
## (Intercept) -0.02690506 0.00883401
## factor(prev_price_nine)1 -0.01413501 0.00061695
## factor(price_increase)1 0.07907542 0.00513314
## factor(category)Безалкогольные напитки 0.00739130 0.00045094
## factor(category)Бытовая химия 0.00556569 0.00090440
## factor(category)Замороженные продукты 0.00254629 0.00102020
## factor(category)Красота и здоровье -0.00673269 0.00052650
## factor(category)Молоко и яйца -0.00600959 0.00068656
## factor(category)Мясо -0.00059869 0.00065787
## factor(category)Овощи 0.00745390 0.00146822
## factor(category)Рыба -0.00128337 0.00105000
## factor(category)Сладости к чаю -0.00023732 0.00053707
## factor(category)Фрукты и ягоды 0.00592505 0.00197659
## factor(category)Хлебобулочные изделия 0.00188668 0.00147886
## fx 0.00034032 0.00011680
## factor(holiday)1 -0.00108471 0.00033370
## factor(prev_price_nine)1:factor(price_increase)1 0.03613893 0.00515305
## z-value Pr(>|z|)
## (Intercept) -3.0456 0.002322 **
## factor(prev_price_nine)1 -22.9113 < 2.2e-16 ***
## factor(price_increase)1 15.4049 < 2.2e-16 ***
## factor(category)Безалкогольные напитки 16.3909 < 2.2e-16 ***
## factor(category)Бытовая химия 6.1540 7.553e-10 ***
## factor(category)Замороженные продукты 2.4959 0.012564 *
## factor(category)Красота и здоровье -12.7877 < 2.2e-16 ***
## factor(category)Молоко и яйца -8.7532 < 2.2e-16 ***
## factor(category)Мясо -0.9100 0.362798
## factor(category)Овощи 5.0768 3.838e-07 ***
## factor(category)Рыба -1.2223 0.221607
## factor(category)Сладости к чаю -0.4419 0.658573
## factor(category)Фрукты и ягоды 2.9976 0.002721 **
## factor(category)Хлебобулочные изделия 1.2758 0.202040
## fx 2.9137 0.003572 **
## factor(holiday)1 -3.2505 0.001152 **
## factor(prev_price_nine)1:factor(price_increase)1 7.0131 2.331e-12 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Total Sum of Squares: 788.26
## Residual Sum of Squares: 550.15
## R-Squared: 0.30207
## Adj. R-Squared: 0.30199
## Chisq: 65044.3 on 16 DF, p-value: < 2.22e-16
#Hausman test
lenta_hausman <- phtest(hyp5_lenta_fixed, hyp5_lenta_random)
lenta_hausman
##
## Hausman Test
##
## data: price_change_pct ~ factor(prev_price_nine) + factor(prev_price_nine) * ...
## chisq = 7675.3, df = 6, p-value < 2.2e-16
## alternative hypothesis: one model is inconsistent
#выбираем модель fixed effects
Загрузка результатов в эксель (Гипотеза №5)
hyp5_lavka_tidy_result <- tidy(coeftest(hyp5_lavka_fixed))
hyp5_magnit_tidy_result <- tidy(coeftest(hyp5_magnit_fixed))
hyp5_pyat_tidy_result <- tidy(coeftest(hyp5_pyat_fixed))
hyp5_perek_tidy_result <- tidy(coeftest(hyp5_perek_fixed))
hyp5_lenta_tidy_result <- tidy(coeftest(hyp5_lenta_fixed))
write.xlsx(hyp5_lavka_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp5_lavka_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp5_magnit_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp5_magnit_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp5_pyat_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp5_pyat_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp5_perek_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp5_perek_tidy_result.xlsx", rowNames = TRUE)
write.xlsx(hyp5_lenta_tidy_result, "D:/Рабочий стол/4 курс/диплом/R/hyp5_lenta_tidy_result.xlsx", rowNames = TRUE)