WI Final
Amra Fetahovic
2024-11-26
Napomena Ovaj dokument sadrzi slijedece: zakljucno sa 25.11.2024.
Ovaj wage model sadrzi samo one osobe koje su zaposlene, a dodacu i novu dummy varijablu full time dummy ili part time dummy.
Takodjer to je varijanta koju finalno uzimam. dakle bez varijanti. na kraju sam ove rezultate pomnozila sa udjelom stope zaposlenosti ali to mi je u excel sheety Monetary indexes for mapping.
library(haven)
library(dplyr)##
## Attaching package: 'dplyr'## The following objects are masked from 'package:stats':
##
## filter, lag## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, unionsetwd("C:/Users/Amra/Documents/HBS database inspecting")
HBS_2015_HH_short <- read_sav("~/HBS database inspecting/HBS_2015_HH - short.sav")
hbs_short <- HBS_2015_HH_short01 OZNACAVA DA SE RADI O PRVOM CLANU DOMACINSTVA KOJI JE PRIMAO ZARADE YN Oznacava DA-NE tj. odnosi se na da li su ili nisu primali naknade IN Mjesecni iznos odredjene naknade NM Broj mjeseci za koji je primljen taj iznos
Sabracu za svakog clana domacinstva koji su rekli da su primili neku od nakanda i vidjeti koliko mi to pokriva opstina
hbs_short$amr.NEWINCOM <- rowSums(hbs_short[,c("Q02_YN_01_S12","Q02_YN_02_S12","Q02_YN_03_S12","Q02_YN_04_S12","Q02_YN_05_S12","Q02_YN_06_S12", "Q02_YN_07_S12", "Q02_YN_08_S12", "Q02_YN_09_S12","Q02_YN_10_S12","Q02_YN_11_S12","Q02_YN_12_S12", "Q02_YN_13_S12")],na.rm = T)
table(hbs_short$amr.NEWINCOM)##
## 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
## 44 592 1583 1297 1598 900 697 500 231 134 63 39 11 7 1 3
## 18
## 2Prema ovoma samo u 44 domacinstava ni jedan clan ne dobiva nsita sto je navedeno u piatanjama QA01 - QA23.
Plan za dalje:
- Za svaku varijablu koja ima neki inkom izracunati mjesecne izdatke i za svakog clana. jer imaju i iznos a ima i koliko mjesecno je primao, tako da to treba mnoziti sa kolonom broj mjeseci pa dijeli sa brojem 12.
- Nakon toga cu da izracunam mjesecna primanja za svakog clana domacinstva
- Necu racunati allowance jer to nije zarada niti cu stavljati iznamljivanje zemlje, garaze i slicen rente jer i to mi nije zarada.
- Onda cu to sve sabrati i imacu mjesecnu zaradu po domacinstvu.
- Zadrzavam samo one koje su Active 1 i Active 2
- Formiram full time dummy
ZA PLATE UZIMAM SVAKOG CLANA PORODICE POSEBNO
- NECU BRISATI _S2, _S6, _S7, _S10, COICOP, jer cu mozda samo za ove likove racunati transport.
- Samo prvih osam clanova razmatram, jer npr za 9-og clana QA01_YN_09_S12 samo je jedan primio remitencices, 10 nije nisa,
- _S11 brisati to su penzije, QBizbaciti to su penzije, a ostaviti QA, to je income, izbaciti QC, QD,
library(dplyr)
hbs_wage <- hbs_short %>% dplyr::select(contains(c( "SifraDom","Entity","Canton","naziv_opcine","RurUrb","ncomp","finweight","Relat","Sex","Age", "Educ","Activ", "HH_Monthly", "QA", "_S2", "_S6", "_S7", "_S10", "COICOP")))#remove additional unnecessary variables
hbs_wage <- as.data.frame(hbs_wage)
hbs_wage <- hbs_wage %>% select(-c(M_Entity, M_Canton_Region, Relat_9, Relat_10, Relat_11, Relat_12, Relat_13, Sex_9, Sex_10, Sex_11, Sex_12, Sex_13, Age_9, Age_10, Age_11, Age_12, Age_13, Educ_9, Educ_10, Educ_11, Educ_12,Educ_13,Activ_9, Activ_10, Activ_11, Activ_12, Activ_13))#izbacumjem nepotrebne varijable iz Educ (Class, now, Level)
hbs_wage <- hbs_wage %>% select(!contains(c("Class","now","Level","QA16","QA17","QA18", "QA19", "QA20", "QA22", "QA21","_09_S12", "_10_S12")))FAZA 2
SADA PRVO FORMIRAM WAGE ZA SVAKOG CLANA DOMACINSTVA ZA INCOME
Mjesecno all wage for 1st household
library(haven)
hbs_wage$QA01_01_mj <- (hbs_wage$QA01_IN_01_S12*hbs_wage$QA01_NM_01_S12)/12
hbs_wage$QA02_01_mj <- (hbs_wage$QA02_IN_01_S12*hbs_wage$QA02_NM_01_S12)/12
hbs_wage$QA03_01_mj <- (hbs_wage$QA03_IN_01_S12*hbs_wage$QA03_NM_01_S12)/12
hbs_wage$QA04_01_mj <- (hbs_wage$QA04_IN_01_S12*hbs_wage$QA04_NM_01_S12)/12
hbs_wage$QA05_01_mj <- (hbs_wage$QA05_IN_01_S12*hbs_wage$QA05_NM_01_S12)/12
hbs_wage$QA06_01_mj <- (hbs_wage$QA06_IN_01_S12*hbs_wage$QA06_NM_01_S12)/12
hbs_wage$QA07_01_mj <- (hbs_wage$QA07_IN_01_S12*hbs_wage$QA07_NM_01_S12)/12
hbs_wage$QA08_01_mj <- (hbs_wage$QA08_IN_01_S12*hbs_wage$QA08_NM_01_S12)/12
hbs_wage$QA09_01_mj <- (hbs_wage$QA09_IN_01_S12*hbs_wage$QA09_NM_01_S12)/12
hbs_wage$QA10_01_mj <- (hbs_wage$QA10_IN_01_S12*hbs_wage$QA10_NM_01_S12)/12
hbs_wage$QA11_01_mj <- (hbs_wage$QA11_IN_01_S12*hbs_wage$QA11_NM_01_S12)/12
hbs_wage$QA12_01_mj <- (hbs_wage$QA12_IN_01_S12*hbs_wage$QA12_NM_01_S12)/12
hbs_wage$QA13_01_mj <- (hbs_wage$QA13_IN_01_S12*hbs_wage$QA13_NM_01_S12)/12
hbs_wage$QA14_01_mj <- (hbs_wage$QA14_IN_01_S12*hbs_wage$QA14_NM_01_S12)/12
hbs_wage$QA15_01_mj <- (hbs_wage$QA15_IN_01_S12*hbs_wage$QA15_NM_01_S12)/12
hbs_wage$QA23_01_mj <- (hbs_wage$QA23_IN_01_S12*hbs_wage$QA23_NM_01_S12)/12Mjesecno sva primanja za prvog householda
hbs_wage$QA_01_all_mj <- rowSums(hbs_wage[,c("QA01_01_mj","QA02_01_mj","QA03_01_mj","QA04_01_mj","QA05_01_mj","QA06_01_mj", "QA07_01_mj", "QA08_01_mj", "QA09_01_mj", "QA10_01_mj", "QA11_01_mj", "QA12_01_mj","QA13_01_mj", "QA14_01_mj", "QA15_01_mj", "QA23_01_mj")],na.rm = T)
summary(hbs_wage$QA_01_all_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 0.0 0.0 290.0 466.7 18350.0plot(density(hbs_wage$QA_01_all_mj))
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za prvog clana. Ovo je taj Ismirov mail od 3.januara tj. not all.
hbs_wage$QAnotall_01_mj <- rowSums(hbs_wage[,c("QA01_01_mj","QA02_01_mj","QA07_01_mj", "QA08_01_mj", "QA09_01_mj", "QA14_01_mj", "QA15_01_mj")],na.rm = T)
summary(hbs_wage$QAnotall_01_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 0.0 0.0 244.1 369.2 18350.0plot(density(hbs_wage$QAnotall_01_mj))
mjesecno all wage for 2nd household
Mjesecno sva primanja za drugog householda
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za drugog clana
hbs_wage$QAnotall_02_mj <- rowSums(hbs_wage[,c("QA01_02_mj","QA02_02_mj","QA07_02_mj", "QA08_02_mj", "QA09_02_mj", "QA14_02_mj", "QA15_02_mj")],na.rm = T)
summary(hbs_wage$QAnotall_02_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 0.0 0.0 127.5 0.0 12833.3plot(density(hbs_wage$QAnotall_02_mj))
mjesecno all wage for 3nd household
Mjesecno sva primanja za treci householda
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za treceg clana
hbs_wage$QAnotall_03_mj <- rowSums(hbs_wage[,c("QA01_03_mj","QA02_03_mj","QA07_03_mj", "QA08_03_mj", "QA09_03_mj", "QA14_03_mj", "QA15_03_mj")],na.rm = T)
summary(hbs_wage$QAnotall_03_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 67.53 0.00 12000.00plot(density(hbs_wage$QAnotall_03_mj))
mjesecno all wage for 4th household
Mjesecno sva primanja za cetvrta householda
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za cetvrtog clana
hbs_wage$QAnotall_04_mj <- rowSums(hbs_wage[,c("QA01_04_mj","QA02_04_mj","QA07_04_mj", "QA08_04_mj", "QA09_04_mj", "QA14_04_mj", "QA15_04_mj")],na.rm = T)
hbs_wage$QAnotall_04_mj <- as.numeric(hbs_wage$QAnotall_04_mj)
summary(hbs_wage$QAnotall_04_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 18.41 0.00 2750.00str(hbs_wage$QAnotall_04_mj)## num [1:7702] 0 0 0 0 0 0 0 0 0 0 ...plot(density(hbs_wage$QAnotall_04_mj))
mjesecno all wage for 5th household
Mjesecno sva primanja za petog householda
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za petog clana
hbs_wage$QAnotall_05_mj <- rowSums(hbs_wage[,c("QA01_05_mj","QA02_05_mj","QA07_05_mj", "QA08_05_mj", "QA09_05_mj", "QA14_05_mj", "QA15_05_mj")],na.rm = T)
hbs_wage$QAnotall_05_mj <- as.numeric(hbs_wage$QAnotall_05_mj)
summary(hbs_wage$QAnotall_05_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 4.682 0.000 1500.000str(hbs_wage$QAnotall_05_mj)## num [1:7702] 0 0 0 0 0 0 0 0 0 0 ...plot(density(hbs_wage$QAnotall_05_mj))
mjesecno all wage for 6th household
Mjesecno sva primanja za sesti householda
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za sestog clana
hbs_wage$QAnotall_06_mj <- rowSums(hbs_wage[,c("QA01_06_mj","QA02_06_mj","QA07_06_mj", "QA08_06_mj", "QA09_06_mj", "QA14_06_mj", "QA15_06_mj")],na.rm = T)
hbs_wage$QAnotall_06_mj <- as.numeric(hbs_wage$QAnotall_06_mj)
summary(hbs_wage$QAnotall_06_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 1.657 0.000 1200.000str(hbs_wage$QAnotall_06_mj)## num [1:7702] 0 0 0 0 0 0 0 0 0 0 ...plot(density(hbs_wage$QAnotall_06_mj))
mjesecno all wage for 7th household
Mjesecno sva primanja za sedmog householda
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za petog clana
hbs_wage$QAnotall_07_mj <- rowSums(hbs_wage[,c("QA01_07_mj","QA02_07_mj","QA07_07_mj", "QA08_07_mj", "QA09_07_mj", "QA14_07_mj", "QA15_07_mj")],na.rm = T)
hbs_wage$QAnotall_07_mj <- as.numeric(hbs_wage$QAnotall_07_mj)
summary(hbs_wage$QAnotall_07_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0000 0.0000 0.0000 0.4068 0.0000 1200.0000str(hbs_wage$QAnotall_07_mj)## num [1:7702] 0 0 0 0 0 0 0 0 0 0 ...plot(density(hbs_wage$QAnotall_07_mj))
mjesecno all wage for 8th household
Mjesecno sva primanja za osmog householda
Mjesecno samo QA01_, QA02, QA_07, QA_08, QA_09, QA14, QA15 za osmog clana
hbs_wage$QAnotall_08_mj <- rowSums(hbs_wage[,c("QA01_08_mj","QA02_08_mj","QA07_08_mj", "QA08_08_mj", "QA09_08_mj", "QA14_08_mj", "QA15_08_mj")],na.rm = T)
hbs_wage$QAnotall_08_mj <- as.numeric(hbs_wage$QAnotall_08_mj)
summary(hbs_wage$QAnotall_08_mj)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00000 0.00000 0.00000 0.02597 0.00000 200.00000str(hbs_wage$QAnotall_08_mj)## num [1:7702] 0 0 0 0 0 0 0 0 0 0 ...plot(density(hbs_wage$QAnotall_08_mj))
Samo topli obrok i prevoz za sve
Ovo racunam da vidim da li i u kojoj mjeri razlikuju prevoz i topli obrok
NOVI FRAME SAMO SA _mj VARIJABLAMA I SOCIO-EK
hbs_wage.NEW <- hbs_wage %>% select(contains(c("SifraDom", "Entity", "naziv_Opcine", "Relat", "Age", "Activ", "Educ","Rur","Sex", "all_mj","notall_","QA07_0","QA08_0")))#all_mj dodajem radi ukupnih prihoda po clanu a Q07_i Q08_ radi toplog obr i prevoza po svakom clanu; notall_mj su mjesecni incomi od rada po osnovu zaposlenosti, rada u bih ali strani poslodavac, usluge(npr.pravnici),poljoprivreda, topli obrok prevoz i smjestaj
names(hbs_wage.NEW)## [1] "SifraDom" "Entity" "naziv_Opcine" "Relat_1"
## [5] "Relat_2" "Relat_3" "Relat_4" "Relat_5"
## [9] "Relat_6" "Relat_7" "Relat_8" "Age_1"
## [13] "Age_2" "Age_3" "Age_4" "Age_5"
## [17] "Age_6" "Age_7" "Age_8" "Activ_1"
## [21] "Activ_2" "Activ_3" "Activ_4" "Activ_5"
## [25] "Activ_6" "Activ_7" "Activ_8" "Educ_1"
## [29] "Educ_2" "Educ_3" "Educ_4" "Educ_5"
## [33] "Educ_6" "Educ_7" "Educ_8" "RurUrb"
## [37] "Sex_1" "Sex_2" "Sex_3" "Sex_4"
## [41] "Sex_5" "Sex_6" "Sex_7" "Sex_8"
## [45] "QA_01_all_mj" "QA_02_all_mj" "QA_03_all_mj" "QA_04_all_mj"
## [49] "QA_05_all_mj" "QA_06_all_mj" "QA_07_all_mj" "QA_08_all_mj"
## [53] "QAnotall_01_mj" "QAnotall_02_mj" "QAnotall_03_mj" "QAnotall_04_mj"
## [57] "QAnotall_05_mj" "QAnotall_06_mj" "QAnotall_07_mj" "QAnotall_08_mj"
## [61] "QA07_01_mj" "QA07_02_mj" "QA07_03_mj" "QA07_04_mj"
## [65] "QA07_05_mj" "QA07_06_mj" "QA07_07_mj" "QA07_08_mj"
## [69] "QA08_01_mj" "QA08_02_mj" "QA08_03_mj" "QA08_04_mj"
## [73] "QA08_05_mj" "QA08_06_mj" "QA08_07_mj" "QA08_08_mj"FAZA 3- FROM WIDE TO LONG
to summarize specific variables - code
library(tidyr)
hbs_wage.NEW.long <- hbs_wage.NEW %>% pivot_longer(cols = c(starts_with("Age"), starts_with("Relat"), starts_with("Activ"),starts_with("Educ"),starts_with ("Sex") ,contains("_mj")),names_to = c(".value", "Relat"), names_pattern = "(\\w+).*?(\\d)")dim(hbs_wage.NEW.long)## [1] 61616 14names(hbs_wage.NEW.long) #QA07_0 je topli obrok za svakog clana QA_0 je ukupni wage za svakog clana i QA08_0 je prevoz za svakog clana QAnotall wage ali redukovani## [1] "SifraDom" "Entity" "naziv_Opcine" "RurUrb" "Relat"
## [6] "Age_" "Relat_" "Activ_" "Educ_" "Sex_"
## [11] "QA_0" "QAnotall_0" "QA07_0" "QA08_0"prvo izbaci godine NA i sve ispod 15 godina i preko 80
hbs_wage.NEW.long.1 <- hbs_wage.NEW.long %>% dplyr::filter(14 < Age_ & Age_<80)
dim(hbs_wage.NEW.long.1)## [1] 18548 14names(hbs_wage.NEW.long.1)## [1] "SifraDom" "Entity" "naziv_Opcine" "RurUrb" "Relat"
## [6] "Age_" "Relat_" "Activ_" "Educ_" "Sex_"
## [11] "QA_0" "QAnotall_0" "QA07_0" "QA08_0"#18548 obseryvacijahead(hbs_wage.NEW.long.1)## # A tibble: 6 × 14
## SifraDom Entity naziv_Opcine RurUrb Relat Age_ Relat_ Activ_ Educ_ Sex_
## <dbl> <dbl> <chr> <dbl+lbl> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 2258 1 B.Grahovo 1 [Urban] 1 75 1 8 5 1
## 2 2258 1 B.Grahovo 1 [Urban] 2 79 2 8 5 2
## 3 2258 1 B.Grahovo 1 [Urban] 3 47 3 4 5 1
## 4 2273 1 B.Grahovo 1 [Urban] 2 54 3 4 5 1
## 5 2299 1 B.Grahovo 1 [Urban] 1 71 1 8 5 1
## 6 2299 1 B.Grahovo 1 [Urban] 2 64 2 5 4 2
## # ℹ 4 more variables: QA_0 <dbl>, QAnotall_0 <dbl>, QA07_0 <dbl>, QA08_0 <dbl>#QA_O je wage tj.sva posmatrana primanja
table (hbs_wage.NEW.long.1$Activ_) #koji su employed 6429##
## 1 2 3 4 5 6 7 8 9
## 5676 753 1189 1600 3729 1918 433 3066 184tapply(hbs_wage.NEW.long.1$QA_0, hbs_wage.NEW.long.1$Activ_, summary)## $`1`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 250.0 600.0 656.7 920.0 18350.0
##
## $`2`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 50.0 175.0 250.9 333.3 3000.0
##
## $`3`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 69.44 25.00 2193.33
##
## $`4`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 0.0 0.0 10.3 0.0 1000.0
##
## $`5`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 11.33 0.00 3000.00
##
## $`6`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 2.678 0.000 1200.000
##
## $`7`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 1.447 0.000 266.667
##
## $`8`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 13.36 0.00 3333.33
##
## $`9`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 59.46 0.00 1500.00tapply(hbs_wage.NEW.long.1$QAnotall_0, hbs_wage.NEW.long.1$Activ_, summary)## $`1`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 50.0 520.0 580.6 850.0 18350.0
##
## $`2`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.0 0.0 100.0 192.8 285.0 3000.0
##
## $`3`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 41.38 0.00 2193.33
##
## $`4`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 5.628 0.000 1000.000
##
## $`5`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 8.912 0.000 1800.000
##
## $`6`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 1.521 0.000 1200.000
##
## $`7`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.000 0.000 0.000 1.186 0.000 266.667
##
## $`8`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 10.35 0.00 3333.33
##
## $`9`
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.00 0.00 0.00 28.38 0.00 1500.00# Zadrzi samo Activ_==1 i/ili ==2 tj. samo one koji su zaposleni
hbs_wage.NEW.long.1 <- hbs_wage.NEW.long.1 %>% dplyr::filter(Activ_==1 | Activ_==2)
table (hbs_wage.NEW.long.1$Activ_)##
## 1 2
## 5676 753dim(hbs_wage.NEW.long.1) #dakle 6429 je ili bilo puno zaposleno ili pola radnog vremena## [1] 6429 14table (hbs_wage.NEW.long.1$QA_0>0)##
## FALSE TRUE
## 1185 5244#od svih koji su radili 5244 ih je koji su imali prihode vece od 0
table (hbs_wage.NEW.long.1$QAnotall_0 >0)##
## FALSE TRUE
## 1650 4779#od svih koji su radili 4779 ih je koji su imali prihode vece od 0#FAZA 4 SREDI QA_0 ### Remove zeros .2
hbs_wage.NEW.long.2 <- hbs_wage.NEW.long.1 %>% dplyr::filter(QA_0>0)
summary(hbs_wage.NEW.long.2$QA_0)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 0.083 400.000 630.000 746.782 977.000 18350.000BRISATI PERCENTILE .2 (all income)
dim(hbs_wage.NEW.long.2)#imam samo 5135 varijabli## [1] 5135 14 hbs_wage.NEW.long.2 %>%
select(naziv_Opcine) %>%
group_by(naziv_Opcine) %>%
summarise (
n = n()
)%>%
arrange (desc(n))%>%
print(n=137) #izlistalo 29 opstina koje imaju manje od 10 obs## # A tibble: 130 × 2
## naziv_Opcine n
## <chr> <int>
## 1 Brcko 307
## 2 Bijeljina 234
## 3 Banja Luka 227
## 4 N.G.Sarajevo 213
## 5 Grad Mostar 188
## 6 Zenica 173
## 7 Travnik 136
## 8 Tuzla 100
## 9 Bihac 93
## 10 Bugojno 91
## 11 Sanski Most 87
## 12 Prijedor 84
## 13 Samac 84
## 14 Vitez 80
## 15 N.Travnik 79
## 16 Doboj 78
## 17 Tesanj 74
## 18 Zavidovici 71
## 19 Cazin 70
## 20 Konjic 69
## 21 C.Sarajevo 67
## 22 Zvornik 66
## 23 Zivinice 65
## 24 N.Sarajevo 64
## 25 V.Kladusa 62
## 26 Modrica 60
## 27 Novi Grad 60
## 28 Visoko 60
## 29 S.Brijeg 59
## 30 Ilidza 58
## 31 Prnjavor 53
## 32 D.Vakuf 52
## 33 S.G.Sarajevo 51
## 34 Gradacac 50
## 35 Gracanica 48
## 36 Teslic 47
## 37 Lopare 46
## 38 Laktasi 45
## 39 Maglaj 45
## 40 Derventa 42
## 41 G.Vakuf 42
## 42 Gorazde 40
## 43 Kakanj 40
## 44 Trebinje 40
## 45 Ljubuski 39
## 46 Lukavac 39
## 47 Kalesija 38
## 48 Kiseljak 38
## 49 Livno 36
## 50 B.Krupa 35
## 51 Brod 33
## 52 Busovaca 33
## 53 Grude 32
## 54 Orasje 32
## 55 Foca - RS 31
## 56 Citluk 29
## 57 Capljina 28
## 58 Gacko 28
## 59 Banovici 26
## 60 Vogosca 26
## 61 Ugljevik 25
## 62 Pale 24
## 63 Kresevo 23
## 64 Rudo 22
## 65 Gradiska 21
## 66 Jajce 21
## 67 Posusje 21
## 68 Rogatica 21
## 69 Drvar 20
## 70 Ilijas 19
## 71 Srbac 19
## 72 I.Ilidza 18
## 73 Kljuc 18
## 74 Ribnik 18
## 75 Tomislavgrad 18
## 76 Vlasenica 18
## 77 Breza 17
## 78 Prozor 17
## 79 Stolac 17
## 80 Visegrad 17
## 81 Cajnice 16
## 82 Kupres 16
## 83 N.Gorazde 16
## 84 K.Dubica 15
## 85 Kladanj 15
## 86 Fojnica 14
## 87 Bileca 13
## 88 Bratunac 13
## 89 Buzim 13
## 90 Glamoc 13
## 91 Kotor Varos 13
## 92 B.Petrovac 12
## 93 Knezevo 12
## 94 Nevesinje 12
## 95 Sokolac 12
## 96 Zepce 12
## 97 Celinac 11
## 98 Doboj-Jug 11
## 99 Mrkonjic 11
## 100 Srebrenica 11
## 101 Srebrenik 11
## 102 Doboj-Istok 9
## 103 Hadzici 9
## 104 Milici 8
## 105 Odzak 8
## 106 Teocak 8
## 107 B.Grahovo 7
## 108 Han Pijesak 7
## 109 Kostajnica 7
## 110 Pelagicevo 7
## 111 Celic 6
## 112 D-Samac 6
## 113 Olovo 6
## 114 Vares 6
## 115 Vukosavlje 6
## 116 Ostra Luka 5
## 117 Usora 5
## 118 Jablanica 4
## 119 Petrovo 4
## 120 Sekovici 4
## 121 Trnovo 4
## 122 Berkovici 3
## 123 Donji Zabar 3
## 124 Kalinovik 3
## 125 Sapna 3
## 126 Sipovo 3
## 127 Osmaci 2
## 128 Krupa na Uni 1
## 129 Neum 1
## 130 Ravno 1#FAZA 4a SREDI QAnotall_0 ### Remove zeros .2a
hbs_wage.NEW.long.2a <- hbs_wage.NEW.long.1 %>% dplyr::filter(QAnotall_0>0)
summary(hbs_wage.NEW.long.2a$QAnotall_0)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 4.0 400.0 616.7 719.9 950.0 18350.0BRISATI PERCENTILE .2A NOT ALL INCOME
dim(hbs_wage.NEW.long.2a)#imam samo 4654 varijabli## [1] 4654 14hbs_wage.NEW.long.2a %>%
select(naziv_Opcine) %>%
group_by(naziv_Opcine) %>%
summarise (
n = n()
)%>%
arrange (desc(n))%>%
print(n=137) #izlistalo 30 opstina koje imaju manje od 10 obs## # A tibble: 130 × 2
## naziv_Opcine n
## <chr> <int>
## 1 Brcko 267
## 2 Banja Luka 218
## 3 Bijeljina 213
## 4 N.G.Sarajevo 201
## 5 Grad Mostar 176
## 6 Zenica 163
## 7 Travnik 130
## 8 Bihac 87
## 9 Tuzla 82
## 10 Prijedor 81
## 11 Samac 80
## 12 N.Travnik 78
## 13 Sanski Most 76
## 14 Vitez 76
## 15 Doboj 75
## 16 Bugojno 73
## 17 Cazin 68
## 18 Konjic 64
## 19 Zvornik 63
## 20 Visoko 58
## 21 C.Sarajevo 57
## 22 N.Sarajevo 56
## 23 S.Brijeg 56
## 24 Tesanj 56
## 25 Modrica 55
## 26 Novi Grad 55
## 27 Zavidovici 54
## 28 Zivinice 51
## 29 Ilidza 50
## 30 S.G.Sarajevo 50
## 31 Gradacac 45
## 32 Laktasi 45
## 33 Prnjavor 45
## 34 V.Kladusa 44
## 35 D.Vakuf 43
## 36 Lopare 43
## 37 Gracanica 42
## 38 Trebinje 40
## 39 Kakanj 39
## 40 Gorazde 38
## 41 Teslic 38
## 42 Derventa 37
## 43 Kiseljak 35
## 44 G.Vakuf 34
## 45 B.Krupa 33
## 46 Livno 33
## 47 Ljubuski 32
## 48 Lukavac 32
## 49 Busovaca 31
## 50 Foca - RS 31
## 51 Grude 31
## 52 Maglaj 29
## 53 Orasje 29
## 54 Citluk 28
## 55 Brod 27
## 56 Capljina 27
## 57 Gacko 27
## 58 Banovici 25
## 59 Kalesija 25
## 60 Ugljevik 25
## 61 Vogosca 25
## 62 Pale 24
## 63 Kresevo 23
## 64 Gradiska 21
## 65 Drvar 20
## 66 Rogatica 20
## 67 Jajce 19
## 68 Posusje 19
## 69 Srbac 18
## 70 Vlasenica 18
## 71 Breza 17
## 72 I.Ilidza 17
## 73 Ribnik 17
## 74 Rudo 17
## 75 Ilijas 16
## 76 Kljuc 16
## 77 Kupres 16
## 78 Stolac 16
## 79 Cajnice 15
## 80 Visegrad 15
## 81 Fojnica 14
## 82 K.Dubica 14
## 83 Bileca 13
## 84 Bratunac 13
## 85 Buzim 13
## 86 Glamoc 13
## 87 Kladanj 13
## 88 Kotor Varos 13
## 89 Prozor 13
## 90 Knezevo 12
## 91 Nevesinje 12
## 92 Sokolac 12
## 93 Tomislavgrad 12
## 94 B.Petrovac 11
## 95 Celinac 11
## 96 Srebrenik 11
## 97 Doboj-Jug 10
## 98 Mrkonjic 10
## 99 N.Gorazde 10
## 100 Srebrenica 10
## 101 Doboj-Istok 9
## 102 Hadzici 9
## 103 B.Grahovo 7
## 104 Han Pijesak 7
## 105 Kostajnica 7
## 106 Milici 7
## 107 Odzak 7
## 108 Teocak 7
## 109 Zepce 7
## 110 Celic 6
## 111 D-Samac 6
## 112 Pelagicevo 6
## 113 Vares 6
## 114 Vukosavlje 6
## 115 Olovo 5
## 116 Ostra Luka 5
## 117 Sekovici 4
## 118 Trnovo 4
## 119 Usora 4
## 120 Berkovici 3
## 121 Donji Zabar 3
## 122 Jablanica 3
## 123 Kalinovik 3
## 124 Petrovo 3
## 125 Sipovo 3
## 126 Osmaci 2
## 127 Krupa na Uni 1
## 128 Neum 1
## 129 Ravno 1
## 130 Sapna 1unique(hbs_wage$naziv_Opcine) #137 opcina## [1] "B.Grahovo" "B.Krupa" "B.Petrovac" "Banovici" "Banja Luka"
## [6] "Berkovici" "Bihac" "Bijeljina" "Bileca" "Bratunac"
## [11] "Brcko" "Breza" "Brod" "Bugojno" "Busovaca"
## [16] "Buzim" "C.Sarajevo" "Cajnice" "Capljina" "Cazin"
## [21] "Celic" "Celinac" "Citluk" "D-Samac" "D.Vakuf"
## [26] "Derventa" "Doboj" "Doboj-Istok" "Doboj-Jug" "Dobretici"
## [31] "Donji Zabar" "Drvar" "Foca" "Foca - RS" "Fojnica"
## [36] "G.Vakuf" "Gacko" "Glamoc" "Gorazde" "Gracanica"
## [41] "Grad Mostar" "Gradacac" "Gradiska" "Grude" "Hadzici"
## [46] "Han Pijesak" "I.Ilidza" "I.N.Sarajevo" "I.Stari Grad" "Ilidza"
## [51] "Ilijas" "Jablanica" "Jajce" "Jezero" "K.Dubica"
## [56] "Kakanj" "Kalesija" "Kalinovik" "Kiseljak" "Kladanj"
## [61] "Kljuc" "Knezevo" "Konjic" "Kostajnica" "Kotor Varos"
## [66] "Kresevo" "Krupa na Uni" "Kupres" "Laktasi" "Livno"
## [71] "Lopare" "Lukavac" "Ljubinje" "Ljubuski" "Maglaj"
## [76] "Milici" "Modrica" "Mrkonjic" "N.G.Sarajevo" "N.Gorazde"
## [81] "N.Sarajevo" "N.Travnik" "Neum" "Nevesinje" "Novi Grad"
## [86] "Odzak" "Olovo" "Orasje" "Osmaci" "Ostra Luka"
## [91] "Pale" "Pale-FBiH" "Pelagicevo" "Petrovo" "Posusje"
## [96] "Prijedor" "Prnjavor" "Prozor" "Ravno" "Ribnik"
## [101] "Rogatica" "Rudo" "S.Brijeg" "S.G.Sarajevo" "Samac"
## [106] "Sanski Most" "Sapna" "Sekovici" "Sipovo" "Sokolac"
## [111] "Srbac" "Srebrenica" "Srebrenik" "Stolac" "Teocak"
## [116] "Tesanj" "Teslic" "Tomislavgrad" "Travnik" "Trebinje"
## [121] "Trnovo" "Tuzla" "Ugljevik" "Usora" "V.Kladusa"
## [126] "Vares" "Visegrad" "Visoko" "Vitez" "Vlasenica"
## [131] "Vogosca" "Vukosavlje" "Zavidovici" "Zenica" "Zepce"
## [136] "Zivinice" "Zvornik"unique(hbs_wage.NEW.long.2$naziv_Opcine) #130 ## [1] "B.Grahovo" "B.Krupa" "B.Petrovac" "Banovici" "Banja Luka"
## [6] "Berkovici" "Bihac" "Bijeljina" "Bileca" "Bratunac"
## [11] "Brcko" "Breza" "Brod" "Bugojno" "Busovaca"
## [16] "Buzim" "C.Sarajevo" "Cajnice" "Capljina" "Cazin"
## [21] "Celic" "Celinac" "Citluk" "D-Samac" "D.Vakuf"
## [26] "Derventa" "Doboj" "Doboj-Istok" "Doboj-Jug" "Donji Zabar"
## [31] "Drvar" "Foca - RS" "Fojnica" "G.Vakuf" "Gacko"
## [36] "Glamoc" "Gorazde" "Gracanica" "Grad Mostar" "Gradacac"
## [41] "Gradiska" "Grude" "Hadzici" "Han Pijesak" "I.Ilidza"
## [46] "Ilidza" "Ilijas" "Jablanica" "Jajce" "K.Dubica"
## [51] "Kakanj" "Kalesija" "Kalinovik" "Kiseljak" "Kladanj"
## [56] "Kljuc" "Knezevo" "Konjic" "Kostajnica" "Kotor Varos"
## [61] "Kresevo" "Krupa na Uni" "Kupres" "Laktasi" "Livno"
## [66] "Lopare" "Lukavac" "Ljubuski" "Maglaj" "Milici"
## [71] "Modrica" "Mrkonjic" "N.G.Sarajevo" "N.Gorazde" "N.Sarajevo"
## [76] "N.Travnik" "Neum" "Nevesinje" "Novi Grad" "Odzak"
## [81] "Olovo" "Orasje" "Osmaci" "Ostra Luka" "Pale"
## [86] "Pelagicevo" "Petrovo" "Posusje" "Prijedor" "Prnjavor"
## [91] "Prozor" "Ravno" "Ribnik" "Rogatica" "Rudo"
## [96] "S.Brijeg" "S.G.Sarajevo" "Samac" "Sanski Most" "Sapna"
## [101] "Sekovici" "Sipovo" "Sokolac" "Srbac" "Srebrenica"
## [106] "Srebrenik" "Stolac" "Teocak" "Tesanj" "Teslic"
## [111] "Tomislavgrad" "Travnik" "Trebinje" "Trnovo" "Tuzla"
## [116] "Ugljevik" "Usora" "V.Kladusa" "Vares" "Visegrad"
## [121] "Visoko" "Vitez" "Vlasenica" "Vogosca" "Vukosavlje"
## [126] "Zavidovici" "Zenica" "Zepce" "Zivinice" "Zvornik"unique(hbs_wage.NEW.long.2a$naziv_Opcine) #131## [1] "B.Grahovo" "B.Krupa" "B.Petrovac" "Banovici" "Banja Luka"
## [6] "Berkovici" "Bihac" "Bijeljina" "Bileca" "Bratunac"
## [11] "Brcko" "Breza" "Brod" "Bugojno" "Busovaca"
## [16] "Buzim" "C.Sarajevo" "Cajnice" "Capljina" "Cazin"
## [21] "Celic" "Celinac" "Citluk" "D-Samac" "D.Vakuf"
## [26] "Derventa" "Doboj" "Doboj-Istok" "Doboj-Jug" "Donji Zabar"
## [31] "Drvar" "Foca - RS" "Fojnica" "G.Vakuf" "Gacko"
## [36] "Glamoc" "Gorazde" "Gracanica" "Grad Mostar" "Gradacac"
## [41] "Gradiska" "Grude" "Hadzici" "Han Pijesak" "I.Ilidza"
## [46] "Ilidza" "Ilijas" "Jablanica" "Jajce" "K.Dubica"
## [51] "Kakanj" "Kalesija" "Kalinovik" "Kiseljak" "Kladanj"
## [56] "Kljuc" "Knezevo" "Konjic" "Kostajnica" "Kotor Varos"
## [61] "Kresevo" "Krupa na Uni" "Kupres" "Laktasi" "Livno"
## [66] "Lopare" "Lukavac" "Ljubuski" "Maglaj" "Milici"
## [71] "Modrica" "Mrkonjic" "N.G.Sarajevo" "N.Gorazde" "N.Sarajevo"
## [76] "N.Travnik" "Neum" "Nevesinje" "Novi Grad" "Odzak"
## [81] "Olovo" "Orasje" "Osmaci" "Ostra Luka" "Pale"
## [86] "Pelagicevo" "Petrovo" "Posusje" "Prijedor" "Prnjavor"
## [91] "Prozor" "Ravno" "Ribnik" "Rogatica" "Rudo"
## [96] "S.Brijeg" "S.G.Sarajevo" "Samac" "Sanski Most" "Sapna"
## [101] "Sekovici" "Sipovo" "Sokolac" "Srbac" "Srebrenica"
## [106] "Srebrenik" "Stolac" "Teocak" "Tesanj" "Teslic"
## [111] "Tomislavgrad" "Travnik" "Trebinje" "Trnovo" "Tuzla"
## [116] "Ugljevik" "Usora" "V.Kladusa" "Vares" "Visegrad"
## [121] "Visoko" "Vitez" "Vlasenica" "Vogosca" "Vukosavlje"
## [126] "Zavidovici" "Zenica" "Zepce" "Zivinice" "Zvornik"#7 se ne nalaye u hbs_wage.NEW.long.2 jer vec su izbacene dakle 30+7 = 37 opstine manje#FAZA 5 BRISATI OPSTINE SA MANJE OD 10 OBZERVACIJA=hbs_wage.NEW.long.2
Delete low frequency obs (<10) ne mozemo ih stavljati u model - all income
freq.less.10 <- hbs_wage.NEW.long.2 %>%
dplyr::select(naziv_Opcine) %>%
group_by(naziv_Opcine) %>%
summarise (
n = n()
)%>% dplyr::filter (n<10)
hbs_wage.NEW.long.3<- hbs_wage.NEW.long.2[!hbs_wage.NEW.long.2$naziv_Opcine %in% freq.less.10$naziv_Opcine,]
dim(hbs_wage.NEW.long.3)## [1] 4989 14#4989 obzervacijaProvjeri da li su izbrisane sve ispod 10
hbs_wage.NEW.long.3 %>%
select(naziv_Opcine) %>%
group_by(naziv_Opcine) %>%
summarise (
n = n()
)%>%
arrange ((n))%>%
print(n=10) #sve su izbrisane## # A tibble: 101 × 2
## naziv_Opcine n
## <chr> <int>
## 1 Celinac 11
## 2 Doboj-Jug 11
## 3 Mrkonjic 11
## 4 Srebrenica 11
## 5 Srebrenik 11
## 6 B.Petrovac 12
## 7 Knezevo 12
## 8 Nevesinje 12
## 9 Sokolac 12
## 10 Zepce 12
## # ℹ 91 more rowsunique(hbs_wage.NEW.long.3$naziv_Opcine)## [1] "B.Krupa" "B.Petrovac" "Banovici" "Banja Luka" "Bihac"
## [6] "Bijeljina" "Bileca" "Bratunac" "Brcko" "Breza"
## [11] "Brod" "Bugojno" "Busovaca" "Buzim" "C.Sarajevo"
## [16] "Cajnice" "Capljina" "Cazin" "Celinac" "Citluk"
## [21] "D.Vakuf" "Derventa" "Doboj" "Doboj-Jug" "Drvar"
## [26] "Foca - RS" "Fojnica" "G.Vakuf" "Gacko" "Glamoc"
## [31] "Gorazde" "Gracanica" "Grad Mostar" "Gradacac" "Gradiska"
## [36] "Grude" "I.Ilidza" "Ilidza" "Ilijas" "Jajce"
## [41] "K.Dubica" "Kakanj" "Kalesija" "Kiseljak" "Kladanj"
## [46] "Kljuc" "Knezevo" "Konjic" "Kotor Varos" "Kresevo"
## [51] "Kupres" "Laktasi" "Livno" "Lopare" "Lukavac"
## [56] "Ljubuski" "Maglaj" "Modrica" "Mrkonjic" "N.G.Sarajevo"
## [61] "N.Gorazde" "N.Sarajevo" "N.Travnik" "Nevesinje" "Novi Grad"
## [66] "Orasje" "Pale" "Posusje" "Prijedor" "Prnjavor"
## [71] "Prozor" "Ribnik" "Rogatica" "Rudo" "S.Brijeg"
## [76] "S.G.Sarajevo" "Samac" "Sanski Most" "Sokolac" "Srbac"
## [81] "Srebrenica" "Srebrenik" "Stolac" "Tesanj" "Teslic"
## [86] "Tomislavgrad" "Travnik" "Trebinje" "Tuzla" "Ugljevik"
## [91] "V.Kladusa" "Visegrad" "Visoko" "Vitez" "Vlasenica"
## [96] "Vogosca" "Zavidovici" "Zenica" "Zepce" "Zivinice"
## [101] "Zvornik"#101 opcina od ukupno 137 koje su u HBS, dakle u wage- imam manje 36 opstina#FAZA 5 BRISATI OPSTINE SA MANJE OD 10 OBZERVACIJA=hbs_wage.NEW.long.2a - not all income
Delete low frequency obs (<10) ne mozemo ih stavljati u model
Provjeri da li su izbrisane sve ispod 10
hbs_wage.NEW.long.3a %>%
select(naziv_Opcine) %>%
group_by(naziv_Opcine) %>%
summarise (
n = n()
)%>%
arrange ((n))%>%
print(n=10) #sve su izbrisane## # A tibble: 100 × 2
## naziv_Opcine n
## <chr> <int>
## 1 Doboj-Jug 10
## 2 Mrkonjic 10
## 3 N.Gorazde 10
## 4 Srebrenica 10
## 5 B.Petrovac 11
## 6 Celinac 11
## 7 Srebrenik 11
## 8 Knezevo 12
## 9 Nevesinje 12
## 10 Sokolac 12
## # ℹ 90 more rowsunique(hbs_wage.NEW.long.3a$naziv_Opcine)## [1] "B.Krupa" "B.Petrovac" "Banovici" "Banja Luka" "Bihac"
## [6] "Bijeljina" "Bileca" "Bratunac" "Brcko" "Breza"
## [11] "Brod" "Bugojno" "Busovaca" "Buzim" "C.Sarajevo"
## [16] "Cajnice" "Capljina" "Cazin" "Celinac" "Citluk"
## [21] "D.Vakuf" "Derventa" "Doboj" "Doboj-Jug" "Drvar"
## [26] "Foca - RS" "Fojnica" "G.Vakuf" "Gacko" "Glamoc"
## [31] "Gorazde" "Gracanica" "Grad Mostar" "Gradacac" "Gradiska"
## [36] "Grude" "I.Ilidza" "Ilidza" "Ilijas" "Jajce"
## [41] "K.Dubica" "Kakanj" "Kalesija" "Kiseljak" "Kladanj"
## [46] "Kljuc" "Knezevo" "Konjic" "Kotor Varos" "Kresevo"
## [51] "Kupres" "Laktasi" "Livno" "Lopare" "Lukavac"
## [56] "Ljubuski" "Maglaj" "Modrica" "Mrkonjic" "N.G.Sarajevo"
## [61] "N.Gorazde" "N.Sarajevo" "N.Travnik" "Nevesinje" "Novi Grad"
## [66] "Orasje" "Pale" "Posusje" "Prijedor" "Prnjavor"
## [71] "Prozor" "Ribnik" "Rogatica" "Rudo" "S.Brijeg"
## [76] "S.G.Sarajevo" "Samac" "Sanski Most" "Sokolac" "Srbac"
## [81] "Srebrenica" "Srebrenik" "Stolac" "Tesanj" "Teslic"
## [86] "Tomislavgrad" "Travnik" "Trebinje" "Tuzla" "Ugljevik"
## [91] "V.Kladusa" "Visegrad" "Visoko" "Vitez" "Vlasenica"
## [96] "Vogosca" "Zavidovici" "Zenica" "Zivinice" "Zvornik"#100 opcina od ukupno 137 koje su u HBS, dakle u wage- imam manje 37 opstinaFAZA 6 ISPITAJ VARIJABLE
Rename varijables - all income
library(dplyr)
WI.df <- hbs_wage.NEW.long.3
names(WI.df)## [1] "SifraDom" "Entity" "naziv_Opcine" "RurUrb" "Relat"
## [6] "Age_" "Relat_" "Activ_" "Educ_" "Sex_"
## [11] "QA_0" "QAnotall_0" "QA07_0" "QA08_0"WI.df <- rename(WI.df, c(wages = QA_0, Age = Age_, Active = Activ_, Educ = Educ_, Munic = naziv_Opcine))rename not all income
library(dplyr)
WI.dfa <- hbs_wage.NEW.long.3a
names(WI.dfa)## [1] "SifraDom" "Entity" "naziv_Opcine" "RurUrb" "Relat"
## [6] "Age_" "Relat_" "Activ_" "Educ_" "Sex_"
## [11] "QA_0" "QAnotall_0" "QA07_0" "QA08_0"WI.dfa <- rename(WI.dfa, c(wages = QAnotall_0, Age = Age_, Active = Activ_, Educ = Educ_, Munic = naziv_Opcine))Active
Status tekuce zaposlenosti: 1. puno radno vrijeme 2. pola radnog vremena Od 3-9 je izbaceno 3. nezaposlen 4 - trazi prvo zaposlenje 5 - domacica 6 - student 7 - nesposoban za rad 8 - penzioner 9 - ostalo #### Educ
Steceno obrazovanje: 1 - bez skole; 2- nepotpuna osnovna 8.g.skola 3 - nepotpuna osnovna 9.g. skola; 4-osnovna skola, 5-srednja skola, 6-specijalizacia poslije s.s; 7 - Visa skola; 8 - Fakultet; 9 - Master; 10 - Doktorat
sredi Educ varijablu u notall income
WI.dfa <- WI.dfa %>% mutate(Full.time = case_when(Active == 1 ~"full time", Active == 2 ~"part time"),
Educ.1 = case_when(Educ %in% c(1,2,3) ~ "no elementary", Educ == 4 ~ "elementary", Educ %in% c(5,6) ~ "high schl", Educ %in% c(7,8,9,10) ~ "faculty"),
Educ.2 = case_when(Educ == 1 ~ "no education",
Educ %in% c(2,3) ~ "no elementary",
Educ == 4 ~ "elementary",
Educ %in% c(5,6) ~ "high schl",
Educ %in% c(7) ~ "college",
Educ %in% c(8,9,10) ~ "university")) #Relevel Educ.2
WI.dfa$Educ.2 <- forcats::fct_relevel (WI.dfa$Educ.2, "no education","no elementary", "elementary", "high schl","college", "university")
prop.table(table(WI.dfa$Educ.2))##
## no education no elementary elementary high schl college
## 0.007093771 0.011305697 0.124584349 0.667922855 0.037463977
## university
## 0.151629350Check if it is ok
Active
dim (WI.dfa)## [1] 4511 17unique(WI.dfa$Munic)## [1] "B.Krupa" "B.Petrovac" "Banovici" "Banja Luka" "Bihac"
## [6] "Bijeljina" "Bileca" "Bratunac" "Brcko" "Breza"
## [11] "Brod" "Bugojno" "Busovaca" "Buzim" "C.Sarajevo"
## [16] "Cajnice" "Capljina" "Cazin" "Celinac" "Citluk"
## [21] "D.Vakuf" "Derventa" "Doboj" "Doboj-Jug" "Drvar"
## [26] "Foca - RS" "Fojnica" "G.Vakuf" "Gacko" "Glamoc"
## [31] "Gorazde" "Gracanica" "Grad Mostar" "Gradacac" "Gradiska"
## [36] "Grude" "I.Ilidza" "Ilidza" "Ilijas" "Jajce"
## [41] "K.Dubica" "Kakanj" "Kalesija" "Kiseljak" "Kladanj"
## [46] "Kljuc" "Knezevo" "Konjic" "Kotor Varos" "Kresevo"
## [51] "Kupres" "Laktasi" "Livno" "Lopare" "Lukavac"
## [56] "Ljubuski" "Maglaj" "Modrica" "Mrkonjic" "N.G.Sarajevo"
## [61] "N.Gorazde" "N.Sarajevo" "N.Travnik" "Nevesinje" "Novi Grad"
## [66] "Orasje" "Pale" "Posusje" "Prijedor" "Prnjavor"
## [71] "Prozor" "Ribnik" "Rogatica" "Rudo" "S.Brijeg"
## [76] "S.G.Sarajevo" "Samac" "Sanski Most" "Sokolac" "Srbac"
## [81] "Srebrenica" "Srebrenik" "Stolac" "Tesanj" "Teslic"
## [86] "Tomislavgrad" "Travnik" "Trebinje" "Tuzla" "Ugljevik"
## [91] "V.Kladusa" "Visegrad" "Visoko" "Vitez" "Vlasenica"
## [96] "Vogosca" "Zavidovici" "Zenica" "Zivinice" "Zvornik"table (WI.dfa$Full.time)##
## full time part time
## 4078 433round (prop.table(table(WI.dfa$Active))*100,1)##
## 1 2
## 90.4 9.6##Educ
table (WI.dfa$Educ)##
## 1 2 3 4 5 6 7 8 9 10
## 32 47 4 562 2989 24 169 608 69 7table (WI.dfa$Educ.1)##
## elementary faculty high schl no elementary
## 562 853 3013 83round (prop.table(table(WI.dfa$Educ.1))*100,2)##
## elementary faculty high schl no elementary
## 12.46 18.91 66.79 1.84Relevel
Full.time
library(forcats)
WI.dfa$Full.time <- fct_relevel (WI.dfa$Full.time, "full time", "part time")
table(WI.dfa$Full.time)##
## full time part time
## 4078 433str(WI.dfa$Full.time)## Factor w/ 2 levels "full time","part time": 1 1 1 1 1 1 1 1 1 1 ...Educ
Sada treba relevel varijablu da no elementary bude
referentna vrijednost
Sex - notall income
round (prop.table(table(WI.dfa$Sex_))*100,1)##
## 1 2
## 64.4 35.6#FAZA 7 BUILD UP A MODEL
Mincer earnings function log(wages)
#Isti model koji je winner kad uzmem sve opcije za Active
library(texreg)## Version: 1.39.4
## Date: 2024-07-23
## Author: Philip Leifeld (University of Manchester)
##
## Consider submitting praise using the praise or praise_interactive functions.
## Please cite the JSS article in your publications -- see citation("texreg").##
## Attaching package: 'texreg'## The following object is masked from 'package:tidyr':
##
## extract#not all income
WI.3a <- lm (log(wages)~ Age + as.numeric(Age^2)+ factor (Sex_) + Educ.1 + factor(Full.time) + factor (Munic) , data = WI.dfa) # No rur. urb THE WINNING MODEL
summary(WI.3a)#only 31 sign. municipal##
## Call:
## lm(formula = log(wages) ~ Age + as.numeric(Age^2) + factor(Sex_) +
## Educ.1 + factor(Full.time) + factor(Munic), data = WI.dfa)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.54025 -0.23473 0.06767 0.32865 2.32918
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.882e+00 1.385e-01 35.239 < 2e-16 ***
## Age 4.106e-02 4.939e-03 8.315 < 2e-16 ***
## as.numeric(Age^2) -3.956e-04 5.834e-05 -6.781 1.35e-11 ***
## factor(Sex_)2 -1.462e-01 1.734e-02 -8.431 < 2e-16 ***
## Educ.1elementary 1.655e-01 6.756e-02 2.450 0.014338 *
## Educ.1high schl 4.823e-01 6.571e-02 7.340 2.53e-13 ***
## Educ.1faculty 9.292e-01 6.791e-02 13.683 < 2e-16 ***
## factor(Full.time)part time -7.410e-01 3.014e-02 -24.587 < 2e-16 ***
## factor(Munic)B.Petrovac -1.828e-01 1.881e-01 -0.972 0.331014
## factor(Munic)Banovici 3.017e-01 1.435e-01 2.102 0.035622 *
## factor(Munic)Banja Luka 1.150e-01 1.018e-01 1.130 0.258490
## factor(Munic)Bihac -8.512e-02 1.110e-01 -0.767 0.443091
## factor(Munic)Bijeljina -1.147e-01 1.011e-01 -1.135 0.256639
## factor(Munic)Bileca 4.909e-02 1.771e-01 0.277 0.781594
## factor(Munic)Bratunac 3.501e-01 1.768e-01 1.981 0.047707 *
## factor(Munic)Brcko 1.161e-01 1.001e-01 1.160 0.246258
## factor(Munic)Breza 2.315e-01 1.615e-01 1.433 0.151933
## factor(Munic)Brod -2.568e-01 1.402e-01 -1.832 0.067015 .
## factor(Munic)Bugojno 3.926e-02 1.140e-01 0.344 0.730521
## factor(Munic)Busovaca 6.027e-02 1.354e-01 0.445 0.656223
## factor(Munic)Buzim -6.659e-01 1.767e-01 -3.768 0.000167 ***
## factor(Munic)C.Sarajevo 3.420e-01 1.193e-01 2.867 0.004157 **
## factor(Munic)Cajnice -1.785e-01 1.686e-01 -1.059 0.289878
## factor(Munic)Capljina 4.760e-01 1.400e-01 3.400 0.000679 ***
## factor(Munic)Cazin -1.264e-01 1.145e-01 -1.104 0.269596
## factor(Munic)Celinac -1.168e-01 1.880e-01 -0.621 0.534620
## factor(Munic)Citluk 2.928e-01 1.391e-01 2.105 0.035380 *
## factor(Munic)D.Vakuf -1.137e-01 1.259e-01 -0.904 0.366228
## factor(Munic)Derventa -4.717e-01 1.294e-01 -3.646 0.000270 ***
## factor(Munic)Doboj 1.505e-01 1.133e-01 1.328 0.184221
## factor(Munic)Doboj-Jug -1.087e-01 1.950e-01 -0.557 0.577387
## factor(Munic)Drvar 2.669e-02 1.535e-01 0.174 0.861975
## factor(Munic)Foca - RS -3.240e-02 1.355e-01 -0.239 0.811095
## factor(Munic)Fojnica 2.497e-01 1.723e-01 1.449 0.147484
## factor(Munic)G.Vakuf -1.004e-01 1.326e-01 -0.757 0.449049
## factor(Munic)Gacko 2.474e-01 1.404e-01 1.762 0.078135 .
## factor(Munic)Glamoc 2.371e-01 1.773e-01 1.337 0.181347
## factor(Munic)Gorazde 2.352e-01 1.289e-01 1.825 0.068039 .
## factor(Munic)Gracanica -1.288e-01 1.260e-01 -1.022 0.306996
## factor(Munic)Grad Mostar 3.323e-01 1.032e-01 3.219 0.001296 **
## factor(Munic)Gradacac 7.144e-02 1.237e-01 0.578 0.563598
## factor(Munic)Gradiska -4.956e-02 1.509e-01 -0.328 0.742638
## factor(Munic)Grude 4.016e-01 1.354e-01 2.965 0.003044 **
## factor(Munic)I.Ilidza -1.296e-02 1.615e-01 -0.080 0.936055
## factor(Munic)Ilidza 5.109e-01 1.214e-01 4.209 2.61e-05 ***
## factor(Munic)Ilijas 1.766e-01 1.646e-01 1.073 0.283470
## factor(Munic)Jajce 2.768e-01 1.556e-01 1.779 0.075271 .
## factor(Munic)K.Dubica -1.379e-01 1.723e-01 -0.801 0.423451
## factor(Munic)Kakanj 7.807e-02 1.280e-01 0.610 0.541813
## factor(Munic)Kalesija -1.259e-01 1.436e-01 -0.876 0.380820
## factor(Munic)Kiseljak 2.476e-01 1.314e-01 1.884 0.059658 .
## factor(Munic)Kladanj 1.331e-01 1.768e-01 0.753 0.451400
## factor(Munic)Kljuc -1.006e-02 1.646e-01 -0.061 0.951270
## factor(Munic)Knezevo -2.828e-02 1.821e-01 -0.155 0.876559
## factor(Munic)Konjic 2.337e-01 1.161e-01 2.012 0.044256 *
## factor(Munic)Kotor Varos 1.407e-01 1.768e-01 0.796 0.426000
## factor(Munic)Kresevo 3.693e-01 1.471e-01 2.511 0.012066 *
## factor(Munic)Kupres 2.037e-01 1.643e-01 1.240 0.215175
## factor(Munic)Laktasi 2.353e-02 1.241e-01 0.190 0.849623
## factor(Munic)Livno 4.060e-01 1.331e-01 3.050 0.002305 **
## factor(Munic)Lopare -1.237e-02 1.261e-01 -0.098 0.921844
## factor(Munic)Lukavac 1.165e-01 1.343e-01 0.867 0.385883
## factor(Munic)Ljubuski 4.160e-01 1.345e-01 3.093 0.001995 **
## factor(Munic)Maglaj 6.616e-02 1.378e-01 0.480 0.631132
## factor(Munic)Modrica -6.353e-02 1.195e-01 -0.532 0.595000
## factor(Munic)Mrkonjic 2.657e-01 1.952e-01 1.361 0.173453
## factor(Munic)N.G.Sarajevo 3.454e-01 1.022e-01 3.379 0.000735 ***
## factor(Munic)N.Gorazde -4.083e-01 1.950e-01 -2.094 0.036340 *
## factor(Munic)N.Sarajevo 4.299e-01 1.194e-01 3.600 0.000321 ***
## factor(Munic)N.Travnik -1.673e-01 1.125e-01 -1.487 0.137135
## factor(Munic)Nevesinje -3.494e-02 1.822e-01 -0.192 0.847908
## factor(Munic)Novi Grad -5.045e-02 1.193e-01 -0.423 0.672377
## factor(Munic)Orasje 3.446e-01 1.378e-01 2.501 0.012413 *
## factor(Munic)Pale 7.309e-02 1.452e-01 0.503 0.614781
## factor(Munic)Posusje 4.060e-01 1.558e-01 2.607 0.009176 **
## factor(Munic)Prijedor 1.439e-01 1.120e-01 1.285 0.198752
## factor(Munic)Prnjavor 1.964e-02 1.242e-01 0.158 0.874379
## factor(Munic)Prozor 2.234e-01 1.772e-01 1.261 0.207409
## factor(Munic)Ribnik -1.957e-02 1.614e-01 -0.121 0.903513
## factor(Munic)Rogatica 1.831e-01 1.536e-01 1.192 0.233289
## factor(Munic)Rudo -1.642e-01 1.615e-01 -1.017 0.309369
## factor(Munic)S.Brijeg 6.098e-01 1.190e-01 5.124 3.13e-07 ***
## factor(Munic)S.G.Sarajevo 3.636e-01 1.218e-01 2.986 0.002844 **
## factor(Munic)Samac 2.103e-02 1.124e-01 0.187 0.851528
## factor(Munic)Sanski Most -1.254e-02 1.129e-01 -0.111 0.911530
## factor(Munic)Sokolac -1.643e-01 1.824e-01 -0.901 0.367796
## factor(Munic)Srbac 5.756e-02 1.583e-01 0.363 0.716253
## factor(Munic)Srebrenica 3.278e-01 1.949e-01 1.681 0.092769 .
## factor(Munic)Srebrenik 1.607e-01 1.879e-01 0.856 0.392305
## factor(Munic)Stolac 3.132e-01 1.648e-01 1.901 0.057387 .
## factor(Munic)Tesanj 1.299e-03 1.188e-01 0.011 0.991277
## factor(Munic)Teslic -3.769e-02 1.288e-01 -0.293 0.769767
## factor(Munic)Tomislavgrad 1.667e-01 1.821e-01 0.916 0.359887
## factor(Munic)Travnik 3.328e-01 1.056e-01 3.152 0.001635 **
## factor(Munic)Trebinje 3.394e-02 1.274e-01 0.266 0.790013
## factor(Munic)Tuzla 1.673e-01 1.119e-01 1.495 0.134965
## factor(Munic)Ugljevik 1.734e-01 1.434e-01 1.209 0.226649
## factor(Munic)V.Kladusa -2.492e-01 1.243e-01 -2.005 0.045074 *
## factor(Munic)Visegrad -1.453e-01 1.685e-01 -0.862 0.388509
## factor(Munic)Visoko 1.286e-01 1.181e-01 1.089 0.276360
## factor(Munic)Vitez -6.815e-02 1.131e-01 -0.602 0.546978
## factor(Munic)Vlasenica 1.152e-01 1.583e-01 0.728 0.466599
## factor(Munic)Vogosca 1.412e-01 1.435e-01 0.983 0.325438
## factor(Munic)Zavidovici -4.154e-02 1.198e-01 -0.347 0.728695
## factor(Munic)Zenica 1.013e-01 1.038e-01 0.975 0.329371
## factor(Munic)Zivinice -5.412e-02 1.208e-01 -0.448 0.654192
## factor(Munic)Zvornik -3.265e-01 1.163e-01 -2.807 0.005018 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5385 on 4404 degrees of freedom
## Multiple R-squared: 0.4012, Adjusted R-squared: 0.3868
## F-statistic: 27.84 on 106 and 4404 DF, p-value: < 2.2e-16names(WI.dfa)## [1] "SifraDom" "Entity" "Munic" "RurUrb" "Relat" "Age"
## [7] "Relat_" "Active" "Educ" "Sex_" "QA_0" "wages"
## [13] "QA07_0" "QA08_0" "Full.time" "Educ.1" "Educ.2"summary (WI.dfa$Age)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 17.00 33.00 43.00 42.49 52.00 79.00sd (WI.dfa$Age)## [1] 11.56855summary (WI.dfa$wages)## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 52.5 400.0 630.0 701.0 940.0 2300.0sd (WI.dfa$wages)## [1] 406.2234statistics categorical
library(Hmisc)##
## Attaching package: 'Hmisc'## The following objects are masked from 'package:dplyr':
##
## src, summarize## The following objects are masked from 'package:base':
##
## format.pval, unitsdescribe (WI.dfa$Educ.1)## WI.dfa$Educ.1
## n missing distinct
## 4511 0 4
##
## Value no elementary elementary high schl faculty
## Frequency 83 562 3013 853
## Proportion 0.018 0.125 0.668 0.189describe (WI.dfa$Full.time)## WI.dfa$Full.time
## n missing distinct
## 4511 0 2
##
## Value full time part time
## Frequency 4078 433
## Proportion 0.904 0.096describe (WI.dfa$Sex_)## WI.dfa$Sex_
## n missing distinct Info Mean
## 4511 0 2 0.688 1.356
##
## Value 1 2
## Frequency 2905 1606
## Proportion 0.644 0.356library(fastDummies)
# Step 1: Create dummy variables for Educ.1
WI.dfa.1 <- WI.dfa %>%
mutate(Educ.1 = as.factor(Educ.1)) %>%
dummy_cols(select_columns = "Educ.1", remove_selected_columns = TRUE)
# Step 2: Get the names of the dummy variables for Educ.1
educ_dummy_cols <- grep("^Educ.1_", names(WI.dfa.1), value = TRUE)
# Step 3: Calculate descriptive statistics for each dummy variable
educ_stats_list <- lapply(educ_dummy_cols, function(dummy_col) {
data.frame(
Dummy = dummy_col,
Min = min(WI.dfa.1[[dummy_col]], na.rm = TRUE),
Max = max(WI.dfa.1[[dummy_col]], na.rm = TRUE),
Mean = mean(WI.dfa.1[[dummy_col]], na.rm = TRUE),
SD = sd(WI.dfa.1[[dummy_col]], na.rm = TRUE)
)
})
# Step 4: Combine results into a single data frame
educ_stats_df <- bind_rows(educ_stats_list)
# View the results
print(educ_stats_df)## Dummy Min Max Mean SD
## 1 Educ.1_no elementary 0 1 0.01839947 0.1344058
## 2 Educ.1_elementary 0 1 0.12458435 0.3302836
## 3 Educ.1_high schl 0 1 0.66792286 0.4710107
## 4 Educ.1_faculty 0 1 0.18909333 0.3916261describe(WI.dfa$Full.time)## WI.dfa$Full.time
## n missing distinct
## 4511 0 2
##
## Value full time part time
## Frequency 4078 433
## Proportion 0.904 0.096# Step 1: Create dummy variables for Fulltime
WI.dfa1 <- WI.dfa %>%
mutate(Full.time.1 = as.factor(Full.time)) %>%
dummy_cols(select_columns = "Full.time.1", remove_selected_columns = TRUE)
# Step 2: Get the names of the dummy variables for Full.time.1
activ_dummy_cols <- grep("^Full.time.1_", names(WI.dfa1), value = TRUE)
# Step 3: Calculate descriptive statistics for each dummy variable
activ_stats_list <- lapply(activ_dummy_cols, function(dummy_col) {
data.frame(
Dummy = dummy_col,
Min = min(WI.dfa1[[dummy_col]], na.rm = TRUE),
Max = max(WI.dfa1[[dummy_col]], na.rm = TRUE),
Mean = mean(WI.dfa1[[dummy_col]], na.rm = TRUE),
SD = sd(WI.dfa1[[dummy_col]], na.rm = TRUE)
)
})
# Step 4: Combine results into a single data frame
activ_stats_df <- bind_rows(activ_stats_list)
# View the results
print(activ_stats_df)## Dummy Min Max Mean SD
## 1 Full.time.1_full time 0 1 0.90401241 0.2946069
## 2 Full.time.1_part time 0 1 0.09598759 0.2946069Sex_1
describe(WI.dfa$Sex_)## WI.dfa$Sex_
## n missing distinct Info Mean
## 4511 0 2 0.688 1.356
##
## Value 1 2
## Frequency 2905 1606
## Proportion 0.644 0.356# Step 1: Create dummy variables for Sex_1
WI.dfa1 <- WI.dfa %>%
mutate(Sex_1 = as.factor(Sex_)) %>%
dummy_cols(select_columns = "Sex_1", remove_selected_columns = TRUE)
# Step 2: Get the names of the dummy variables for Sex_1
sex_dummy_cols <- grep("^Sex_1_", names(WI.dfa1), value = TRUE)
# Step 3: Calculate descriptive statistics for each dummy variable
sex_stats_list <- lapply(sex_dummy_cols, function(dummy_col) {
data.frame(
Dummy = dummy_col,
Min = min(WI.dfa1[[dummy_col]], na.rm = TRUE),
Max = max(WI.dfa1[[dummy_col]], na.rm = TRUE),
Mean = mean(WI.dfa1[[dummy_col]], na.rm = TRUE),
SD = sd(WI.dfa1[[dummy_col]], na.rm = TRUE)
)
})
# Step 4: Combine results into a single data frame
sex_stats_df <- bind_rows(sex_stats_list)
# View the results
print(sex_stats_df)## Dummy Min Max Mean SD
## 1 Sex_1_1 0 1 0.6439814 0.4788739
## 2 Sex_1_2 0 1 0.3560186 0.4788739##next uradi diagnostiku i primijeni mozda weighted model i uporediti. pa onda koji mi bude najbolji raditi winner model
Zakljucak testova je da mi je bolji nonweighed model
FAZA 9: Extracting the coefficients from WINNING model
###WI.3a model
model.coef3a <- summary(WI.3a)$coefficients
model.coef3a # vidi koliko redova su koef.za druge varijable (8redova) i B.Krupa je referentna opstina## Estimate Std. Error t value
## (Intercept) 4.8820174064 1.385390e-01 35.23929966
## Age 0.0410644316 4.938568e-03 8.31504816
## as.numeric(Age^2) -0.0003955788 5.833688e-05 -6.78093837
## factor(Sex_)2 -0.1462233294 1.734289e-02 -8.43131446
## Educ.1elementary 0.1654886912 6.755574e-02 2.44966130
## Educ.1high schl 0.4823290332 6.571441e-02 7.33977534
## Educ.1faculty 0.9292422135 6.791161e-02 13.68311171
## factor(Full.time)part time -0.7410491635 3.014004e-02 -24.58686674
## factor(Munic)B.Petrovac -0.1828358917 1.880676e-01 -0.97218162
## factor(Munic)Banovici 0.3016533953 1.435173e-01 2.10186063
## factor(Munic)Banja Luka 0.1150192556 1.017768e-01 1.13011324
## factor(Munic)Bihac -0.0851187048 1.109684e-01 -0.76705331
## factor(Munic)Bijeljina -0.1147259562 1.011230e-01 -1.13451837
## factor(Munic)Bileca 0.0490915703 1.770603e-01 0.27725901
## factor(Munic)Bratunac 0.3500611443 1.767523e-01 1.98051838
## factor(Munic)Brcko 0.1160503018 1.000743e-01 1.15964185
## factor(Munic)Breza 0.2314714318 1.615308e-01 1.43298605
## factor(Munic)Brod -0.2568216114 1.401847e-01 -1.83202342
## factor(Munic)Bugojno 0.0392603818 1.139786e-01 0.34445398
## factor(Munic)Busovaca 0.0602734344 1.353958e-01 0.44516461
## factor(Munic)Buzim -0.6658529584 1.767191e-01 -3.76786037
## factor(Munic)C.Sarajevo 0.3420448207 1.192847e-01 2.86746574
## factor(Munic)Cajnice -0.1784560884 1.685907e-01 -1.05851665
## factor(Munic)Capljina 0.4760086679 1.399878e-01 3.40035750
## factor(Munic)Cazin -0.1263838686 1.144643e-01 -1.10413341
## factor(Munic)Celinac -0.1167661273 1.880239e-01 -0.62101763
## factor(Munic)Citluk 0.2927611936 1.391035e-01 2.10462823
## factor(Munic)D.Vakuf -0.1137453229 1.258726e-01 -0.90365442
## factor(Munic)Derventa -0.4716639191 1.293800e-01 -3.64556949
## factor(Munic)Doboj 0.1505261578 1.133413e-01 1.32807822
## factor(Munic)Doboj-Jug -0.1086578800 1.949907e-01 -0.55724648
## factor(Munic)Drvar 0.0266899413 1.535047e-01 0.17387054
## factor(Munic)Foca - RS -0.0323988425 1.355439e-01 -0.23902837
## factor(Munic)Fojnica 0.2496832908 1.723464e-01 1.44872951
## factor(Munic)G.Vakuf -0.1004225275 1.326466e-01 -0.75706827
## factor(Munic)Gacko 0.2474449393 1.404322e-01 1.76202422
## factor(Munic)Glamoc 0.2370568654 1.773276e-01 1.33682969
## factor(Munic)Gorazde 0.2352043382 1.288652e-01 1.82519620
## factor(Munic)Gracanica -0.1287612023 1.260310e-01 -1.02166316
## factor(Munic)Grad Mostar 0.3323133995 1.032354e-01 3.21898710
## factor(Munic)Gradacac 0.0714432098 1.237006e-01 0.57754940
## factor(Munic)Gradiska -0.0495593918 1.509196e-01 -0.32838271
## factor(Munic)Grude 0.4015864622 1.354478e-01 2.96487917
## factor(Munic)I.Ilidza -0.0129577300 1.615006e-01 -0.08023330
## factor(Munic)Ilidza 0.5109311837 1.213849e-01 4.20918174
## factor(Munic)Ilijas 0.1765869018 1.646209e-01 1.07268834
## factor(Munic)Jajce 0.2767950564 1.555703e-01 1.77922800
## factor(Munic)K.Dubica -0.1379123331 1.722778e-01 -0.80052296
## factor(Munic)Kakanj 0.0780721742 1.279619e-01 0.61012063
## factor(Munic)Kalesija -0.1258889572 1.436310e-01 -0.87647505
## factor(Munic)Kiseljak 0.2476207118 1.314476e-01 1.88379772
## factor(Munic)Kladanj 0.1331337133 1.767690e-01 0.75315075
## factor(Munic)Kljuc -0.0100623402 1.646436e-01 -0.06111590
## factor(Munic)Knezevo -0.0282840147 1.820768e-01 -0.15534115
## factor(Munic)Konjic 0.2337023837 1.161409e-01 2.01223094
## factor(Munic)Kotor Varos 0.1407311704 1.767694e-01 0.79612880
## factor(Munic)Kresevo 0.3692902596 1.470536e-01 2.51126361
## factor(Munic)Kupres 0.2036694262 1.642973e-01 1.23963968
## factor(Munic)Laktasi 0.0235345614 1.241203e-01 0.18961095
## factor(Munic)Livno 0.4060325482 1.331447e-01 3.04955810
## factor(Munic)Lopare -0.0123681621 1.260554e-01 -0.09811685
## factor(Munic)Lukavac 0.1164707504 1.343077e-01 0.86719366
## factor(Munic)Ljubuski 0.4160130281 1.345058e-01 3.09290034
## factor(Munic)Maglaj 0.0661564022 1.377775e-01 0.48016838
## factor(Munic)Modrica -0.0635310175 1.194994e-01 -0.53164297
## factor(Munic)Mrkonjic 0.2657356976 1.951913e-01 1.36141191
## factor(Munic)N.G.Sarajevo 0.3454167452 1.022333e-01 3.37871201
## factor(Munic)N.Gorazde -0.4082614358 1.949913e-01 -2.09374232
## factor(Munic)N.Sarajevo 0.4298509631 1.193930e-01 3.60030410
## factor(Munic)N.Travnik -0.1673090938 1.125284e-01 -1.48681702
## factor(Munic)Nevesinje -0.0349373647 1.821560e-01 -0.19179918
## factor(Munic)Novi Grad -0.0504538219 1.192999e-01 -0.42291603
## factor(Munic)Orasje 0.3446396132 1.377899e-01 2.50119590
## factor(Munic)Pale 0.0730904827 1.452237e-01 0.50329590
## factor(Munic)Posusje 0.4059994225 1.557602e-01 2.60656645
## factor(Munic)Prijedor 0.1439496058 1.119961e-01 1.28530924
## factor(Munic)Prnjavor 0.0196426833 1.242357e-01 0.15810814
## factor(Munic)Prozor 0.2233714878 1.771515e-01 1.26090636
## factor(Munic)Ribnik -0.0195693403 1.614201e-01 -0.12123238
## factor(Munic)Rogatica 0.1830572232 1.535595e-01 1.19209305
## factor(Munic)Rudo -0.1641534327 1.614626e-01 -1.01666533
## factor(Munic)S.Brijeg 0.6098130173 1.190223e-01 5.12351911
## factor(Munic)S.G.Sarajevo 0.3636204138 1.217854e-01 2.98574672
## factor(Munic)Samac 0.0210317727 1.123612e-01 0.18718009
## factor(Munic)Sanski Most -0.0125448276 1.128992e-01 -0.11111529
## factor(Munic)Sokolac -0.1642980421 1.824111e-01 -0.90070221
## factor(Munic)Srbac 0.0575557836 1.583404e-01 0.36349408
## factor(Munic)Srebrenica 0.3277554536 1.949379e-01 1.68133236
## factor(Munic)Srebrenik 0.1607166511 1.878565e-01 0.85552860
## factor(Munic)Stolac 0.3131976234 1.647674e-01 1.90084684
## factor(Munic)Tesanj 0.0012990188 1.188165e-01 0.01093298
## factor(Munic)Teslic -0.0376860150 1.287540e-01 -0.29269772
## factor(Munic)Tomislavgrad 0.1667336034 1.820880e-01 0.91567581
## factor(Munic)Travnik 0.3328100303 1.056003e-01 3.15160040
## factor(Munic)Trebinje 0.0339378713 1.274372e-01 0.26631046
## factor(Munic)Tuzla 0.1672624447 1.118753e-01 1.49507904
## factor(Munic)Ugljevik 0.1734186954 1.434156e-01 1.20920414
## factor(Munic)V.Kladusa -0.2491723445 1.243046e-01 -2.00453001
## factor(Munic)Visegrad -0.1452941187 1.684744e-01 -0.86241053
## factor(Munic)Visoko 0.1285958545 1.181222e-01 1.08866806
## factor(Munic)Vitez -0.0681471761 1.131371e-01 -0.60234159
## factor(Munic)Vlasenica 0.1152210905 1.582518e-01 0.72808699
## factor(Munic)Vogosca 0.1411544974 1.435292e-01 0.98345500
## factor(Munic)Zavidovici -0.0415413631 1.197557e-01 -0.34688423
## factor(Munic)Zenica 0.1012596903 1.038040e-01 0.97548960
## factor(Munic)Zivinice -0.0541166033 1.208023e-01 -0.44797642
## factor(Munic)Zvornik -0.3264987028 1.163042e-01 -2.80728324
## Pr(>|t|)
## (Intercept) 7.233233e-240
## Age 1.209020e-16
## as.numeric(Age^2) 1.352056e-11
## factor(Sex_)2 4.576044e-17
## Educ.1elementary 1.433774e-02
## Educ.1high schl 2.534592e-13
## Educ.1faculty 9.057415e-42
## factor(Full.time)part time 3.397987e-125
## factor(Munic)B.Petrovac 3.310136e-01
## factor(Munic)Banovici 3.562214e-02
## factor(Munic)Banja Luka 2.584901e-01
## factor(Munic)Bihac 4.430909e-01
## factor(Munic)Bijeljina 2.566389e-01
## factor(Munic)Bileca 7.815942e-01
## factor(Munic)Bratunac 4.770744e-02
## factor(Munic)Brcko 2.462575e-01
## factor(Munic)Breza 1.519328e-01
## factor(Munic)Brod 6.701543e-02
## factor(Munic)Bugojno 7.305213e-01
## factor(Munic)Busovaca 6.562227e-01
## factor(Munic)Buzim 1.668056e-04
## factor(Munic)C.Sarajevo 4.157389e-03
## factor(Munic)Cajnice 2.898780e-01
## factor(Munic)Capljina 6.789631e-04
## factor(Munic)Cazin 2.695956e-01
## factor(Munic)Celinac 5.346202e-01
## factor(Munic)Citluk 3.538020e-02
## factor(Munic)D.Vakuf 3.662281e-01
## factor(Munic)Derventa 2.698804e-04
## factor(Munic)Doboj 1.842211e-01
## factor(Munic)Doboj-Jug 5.773874e-01
## factor(Munic)Drvar 8.619752e-01
## factor(Munic)Foca - RS 8.110947e-01
## factor(Munic)Fojnica 1.474843e-01
## factor(Munic)G.Vakuf 4.490495e-01
## factor(Munic)Gacko 7.813457e-02
## factor(Munic)Glamoc 1.813473e-01
## factor(Munic)Gorazde 6.803913e-02
## factor(Munic)Gracanica 3.069965e-01
## factor(Munic)Grad Mostar 1.295777e-03
## factor(Munic)Gradacac 5.635979e-01
## factor(Munic)Gradiska 7.426379e-01
## factor(Munic)Grude 3.044260e-03
## factor(Munic)I.Ilidza 9.360554e-01
## factor(Munic)Ilidza 2.614068e-05
## factor(Munic)Ilijas 2.834698e-01
## factor(Munic)Jajce 7.527134e-02
## factor(Munic)K.Dubica 4.234510e-01
## factor(Munic)Kakanj 5.418134e-01
## factor(Munic)Kalesija 3.808196e-01
## factor(Munic)Kiseljak 5.965817e-02
## factor(Munic)Kladanj 4.513996e-01
## factor(Munic)Kljuc 9.512697e-01
## factor(Munic)Knezevo 8.765595e-01
## factor(Munic)Konjic 4.425637e-02
## factor(Munic)Kotor Varos 4.260001e-01
## factor(Munic)Kresevo 1.206550e-02
## factor(Munic)Kupres 2.151747e-01
## factor(Munic)Laktasi 8.496227e-01
## factor(Munic)Livno 2.305409e-03
## factor(Munic)Lopare 9.218440e-01
## factor(Munic)Lukavac 3.858832e-01
## factor(Munic)Ljubuski 1.994518e-03
## factor(Munic)Maglaj 6.311315e-01
## factor(Munic)Modrica 5.950001e-01
## factor(Munic)Mrkonjic 1.734532e-01
## factor(Munic)N.G.Sarajevo 7.345870e-04
## factor(Munic)N.Gorazde 3.633998e-02
## factor(Munic)N.Sarajevo 3.213461e-04
## factor(Munic)N.Travnik 1.371347e-01
## factor(Munic)Nevesinje 8.479084e-01
## factor(Munic)Novi Grad 6.723772e-01
## factor(Munic)Orasje 1.241350e-02
## factor(Munic)Pale 6.147814e-01
## factor(Munic)Posusje 9.176328e-03
## factor(Munic)Prijedor 1.987518e-01
## factor(Munic)Prnjavor 8.743788e-01
## factor(Munic)Prozor 2.074094e-01
## factor(Munic)Ribnik 9.035125e-01
## factor(Munic)Rogatica 2.332890e-01
## factor(Munic)Rudo 3.093685e-01
## factor(Munic)S.Brijeg 3.127144e-07
## factor(Munic)S.G.Sarajevo 2.844435e-03
## factor(Munic)Samac 8.515281e-01
## factor(Munic)Sanski Most 9.115300e-01
## factor(Munic)Sokolac 3.677959e-01
## factor(Munic)Srbac 7.162533e-01
## factor(Munic)Srebrenica 9.276928e-02
## factor(Munic)Srebrenik 3.923051e-01
## factor(Munic)Stolac 5.738730e-02
## factor(Munic)Tesanj 9.912774e-01
## factor(Munic)Teslic 7.697670e-01
## factor(Munic)Tomislavgrad 3.598871e-01
## factor(Munic)Travnik 1.634680e-03
## factor(Munic)Trebinje 7.900126e-01
## factor(Munic)Tuzla 1.349655e-01
## factor(Munic)Ugljevik 2.266493e-01
## factor(Munic)V.Kladusa 4.507442e-02
## factor(Munic)Visegrad 3.885086e-01
## factor(Munic)Visoko 2.763599e-01
## factor(Munic)Vitez 5.469778e-01
## factor(Munic)Vlasenica 4.665990e-01
## factor(Munic)Vogosca 3.254376e-01
## factor(Munic)Zavidovici 7.286949e-01
## factor(Munic)Zenica 3.293710e-01
## factor(Munic)Zivinice 6.541922e-01
## factor(Munic)Zvornik 5.018104e-03model.coef3a[,c("Estimate","Pr(>|t|)")]## Estimate Pr(>|t|)
## (Intercept) 4.8820174064 7.233233e-240
## Age 0.0410644316 1.209020e-16
## as.numeric(Age^2) -0.0003955788 1.352056e-11
## factor(Sex_)2 -0.1462233294 4.576044e-17
## Educ.1elementary 0.1654886912 1.433774e-02
## Educ.1high schl 0.4823290332 2.534592e-13
## Educ.1faculty 0.9292422135 9.057415e-42
## factor(Full.time)part time -0.7410491635 3.397987e-125
## factor(Munic)B.Petrovac -0.1828358917 3.310136e-01
## factor(Munic)Banovici 0.3016533953 3.562214e-02
## factor(Munic)Banja Luka 0.1150192556 2.584901e-01
## factor(Munic)Bihac -0.0851187048 4.430909e-01
## factor(Munic)Bijeljina -0.1147259562 2.566389e-01
## factor(Munic)Bileca 0.0490915703 7.815942e-01
## factor(Munic)Bratunac 0.3500611443 4.770744e-02
## factor(Munic)Brcko 0.1160503018 2.462575e-01
## factor(Munic)Breza 0.2314714318 1.519328e-01
## factor(Munic)Brod -0.2568216114 6.701543e-02
## factor(Munic)Bugojno 0.0392603818 7.305213e-01
## factor(Munic)Busovaca 0.0602734344 6.562227e-01
## factor(Munic)Buzim -0.6658529584 1.668056e-04
## factor(Munic)C.Sarajevo 0.3420448207 4.157389e-03
## factor(Munic)Cajnice -0.1784560884 2.898780e-01
## factor(Munic)Capljina 0.4760086679 6.789631e-04
## factor(Munic)Cazin -0.1263838686 2.695956e-01
## factor(Munic)Celinac -0.1167661273 5.346202e-01
## factor(Munic)Citluk 0.2927611936 3.538020e-02
## factor(Munic)D.Vakuf -0.1137453229 3.662281e-01
## factor(Munic)Derventa -0.4716639191 2.698804e-04
## factor(Munic)Doboj 0.1505261578 1.842211e-01
## factor(Munic)Doboj-Jug -0.1086578800 5.773874e-01
## factor(Munic)Drvar 0.0266899413 8.619752e-01
## factor(Munic)Foca - RS -0.0323988425 8.110947e-01
## factor(Munic)Fojnica 0.2496832908 1.474843e-01
## factor(Munic)G.Vakuf -0.1004225275 4.490495e-01
## factor(Munic)Gacko 0.2474449393 7.813457e-02
## factor(Munic)Glamoc 0.2370568654 1.813473e-01
## factor(Munic)Gorazde 0.2352043382 6.803913e-02
## factor(Munic)Gracanica -0.1287612023 3.069965e-01
## factor(Munic)Grad Mostar 0.3323133995 1.295777e-03
## factor(Munic)Gradacac 0.0714432098 5.635979e-01
## factor(Munic)Gradiska -0.0495593918 7.426379e-01
## factor(Munic)Grude 0.4015864622 3.044260e-03
## factor(Munic)I.Ilidza -0.0129577300 9.360554e-01
## factor(Munic)Ilidza 0.5109311837 2.614068e-05
## factor(Munic)Ilijas 0.1765869018 2.834698e-01
## factor(Munic)Jajce 0.2767950564 7.527134e-02
## factor(Munic)K.Dubica -0.1379123331 4.234510e-01
## factor(Munic)Kakanj 0.0780721742 5.418134e-01
## factor(Munic)Kalesija -0.1258889572 3.808196e-01
## factor(Munic)Kiseljak 0.2476207118 5.965817e-02
## factor(Munic)Kladanj 0.1331337133 4.513996e-01
## factor(Munic)Kljuc -0.0100623402 9.512697e-01
## factor(Munic)Knezevo -0.0282840147 8.765595e-01
## factor(Munic)Konjic 0.2337023837 4.425637e-02
## factor(Munic)Kotor Varos 0.1407311704 4.260001e-01
## factor(Munic)Kresevo 0.3692902596 1.206550e-02
## factor(Munic)Kupres 0.2036694262 2.151747e-01
## factor(Munic)Laktasi 0.0235345614 8.496227e-01
## factor(Munic)Livno 0.4060325482 2.305409e-03
## factor(Munic)Lopare -0.0123681621 9.218440e-01
## factor(Munic)Lukavac 0.1164707504 3.858832e-01
## factor(Munic)Ljubuski 0.4160130281 1.994518e-03
## factor(Munic)Maglaj 0.0661564022 6.311315e-01
## factor(Munic)Modrica -0.0635310175 5.950001e-01
## factor(Munic)Mrkonjic 0.2657356976 1.734532e-01
## factor(Munic)N.G.Sarajevo 0.3454167452 7.345870e-04
## factor(Munic)N.Gorazde -0.4082614358 3.633998e-02
## factor(Munic)N.Sarajevo 0.4298509631 3.213461e-04
## factor(Munic)N.Travnik -0.1673090938 1.371347e-01
## factor(Munic)Nevesinje -0.0349373647 8.479084e-01
## factor(Munic)Novi Grad -0.0504538219 6.723772e-01
## factor(Munic)Orasje 0.3446396132 1.241350e-02
## factor(Munic)Pale 0.0730904827 6.147814e-01
## factor(Munic)Posusje 0.4059994225 9.176328e-03
## factor(Munic)Prijedor 0.1439496058 1.987518e-01
## factor(Munic)Prnjavor 0.0196426833 8.743788e-01
## factor(Munic)Prozor 0.2233714878 2.074094e-01
## factor(Munic)Ribnik -0.0195693403 9.035125e-01
## factor(Munic)Rogatica 0.1830572232 2.332890e-01
## factor(Munic)Rudo -0.1641534327 3.093685e-01
## factor(Munic)S.Brijeg 0.6098130173 3.127144e-07
## factor(Munic)S.G.Sarajevo 0.3636204138 2.844435e-03
## factor(Munic)Samac 0.0210317727 8.515281e-01
## factor(Munic)Sanski Most -0.0125448276 9.115300e-01
## factor(Munic)Sokolac -0.1642980421 3.677959e-01
## factor(Munic)Srbac 0.0575557836 7.162533e-01
## factor(Munic)Srebrenica 0.3277554536 9.276928e-02
## factor(Munic)Srebrenik 0.1607166511 3.923051e-01
## factor(Munic)Stolac 0.3131976234 5.738730e-02
## factor(Munic)Tesanj 0.0012990188 9.912774e-01
## factor(Munic)Teslic -0.0376860150 7.697670e-01
## factor(Munic)Tomislavgrad 0.1667336034 3.598871e-01
## factor(Munic)Travnik 0.3328100303 1.634680e-03
## factor(Munic)Trebinje 0.0339378713 7.900126e-01
## factor(Munic)Tuzla 0.1672624447 1.349655e-01
## factor(Munic)Ugljevik 0.1734186954 2.266493e-01
## factor(Munic)V.Kladusa -0.2491723445 4.507442e-02
## factor(Munic)Visegrad -0.1452941187 3.885086e-01
## factor(Munic)Visoko 0.1285958545 2.763599e-01
## factor(Munic)Vitez -0.0681471761 5.469778e-01
## factor(Munic)Vlasenica 0.1152210905 4.665990e-01
## factor(Munic)Vogosca 0.1411544974 3.254376e-01
## factor(Munic)Zavidovici -0.0415413631 7.286949e-01
## factor(Munic)Zenica 0.1012596903 3.293710e-01
## factor(Munic)Zivinice -0.0541166033 6.541922e-01
## factor(Munic)Zvornik -0.3264987028 5.018104e-03model.coef3a <- model.coef3a
model.coef3a <- as.data.frame.array(model.coef3a[-c(1:8),]) # da bude dataframe a ne matrix i da mi brise prvih 8 redova koji su drugi koeficijenti
Munic <- rownames(model.coef3a)
model.coef3a$Munic <- Municza 3a
dim(model.coef3a) #da vidim koliko redova## [1] 99 5rownames(model.coef3a) <- 1:99 #nedostaje B.Krupa koje je 0, B.Grahovo nije u modelu
head(model.coef3a)## Estimate Std. Error t value Pr(>|t|) Munic
## 1 -0.18283589 0.1880676 -0.9721816 0.33101360 factor(Munic)B.Petrovac
## 2 0.30165340 0.1435173 2.1018606 0.03562214 factor(Munic)Banovici
## 3 0.11501926 0.1017768 1.1301132 0.25849005 factor(Munic)Banja Luka
## 4 -0.08511870 0.1109684 -0.7670533 0.44309094 factor(Munic)Bihac
## 5 -0.11472596 0.1011230 -1.1345184 0.25663892 factor(Munic)Bijeljina
## 6 0.04909157 0.1770603 0.2772590 0.78159424 factor(Munic)Bilecamodela
Munic1 <- sapply(strsplit(Munic, split=')', fixed=TRUE), function(x) (x[2]))
Munic1## [1] "B.Petrovac" "Banovici" "Banja Luka" "Bihac" "Bijeljina"
## [6] "Bileca" "Bratunac" "Brcko" "Breza" "Brod"
## [11] "Bugojno" "Busovaca" "Buzim" "C.Sarajevo" "Cajnice"
## [16] "Capljina" "Cazin" "Celinac" "Citluk" "D.Vakuf"
## [21] "Derventa" "Doboj" "Doboj-Jug" "Drvar" "Foca - RS"
## [26] "Fojnica" "G.Vakuf" "Gacko" "Glamoc" "Gorazde"
## [31] "Gracanica" "Grad Mostar" "Gradacac" "Gradiska" "Grude"
## [36] "I.Ilidza" "Ilidza" "Ilijas" "Jajce" "K.Dubica"
## [41] "Kakanj" "Kalesija" "Kiseljak" "Kladanj" "Kljuc"
## [46] "Knezevo" "Konjic" "Kotor Varos" "Kresevo" "Kupres"
## [51] "Laktasi" "Livno" "Lopare" "Lukavac" "Ljubuski"
## [56] "Maglaj" "Modrica" "Mrkonjic" "N.G.Sarajevo" "N.Gorazde"
## [61] "N.Sarajevo" "N.Travnik" "Nevesinje" "Novi Grad" "Orasje"
## [66] "Pale" "Posusje" "Prijedor" "Prnjavor" "Prozor"
## [71] "Ribnik" "Rogatica" "Rudo" "S.Brijeg" "S.G.Sarajevo"
## [76] "Samac" "Sanski Most" "Sokolac" "Srbac" "Srebrenica"
## [81] "Srebrenik" "Stolac" "Tesanj" "Teslic" "Tomislavgrad"
## [86] "Travnik" "Trebinje" "Tuzla" "Ugljevik" "V.Kladusa"
## [91] "Visegrad" "Visoko" "Vitez" "Vlasenica" "Vogosca"
## [96] "Zavidovici" "Zenica" "Zivinice" "Zvornik"model.coef3a$Munic1 <- Munic1add B.Krupa to dataframe 3a
model.coef3a[nrow(model.coef3a) + 1,] = c(0, NA, NA, NA,"B.Krupa","B.Krupa" )
model.coef3a$Estimate <- as.numeric(model.coef3a$Estimate)top10.m3a <- model.coef3a %>%
dplyr::select(Estimate, Munic1) %>%
arrange (desc(Estimate))%>%
head(10) #top ten municipalities
top10.m3a## Estimate Munic1
## 1 0.6098130 S.Brijeg
## 2 0.5109312 Ilidza
## 3 0.4760087 Capljina
## 4 0.4298510 N.Sarajevo
## 5 0.4160130 Ljubuski
## 6 0.4060325 Livno
## 7 0.4059994 Posusje
## 8 0.4015865 Grude
## 9 0.3692903 Kresevo
## 10 0.3636204 S.G.Sarajevobot10.m.empl <- model.coef3a %>%
dplyr::select(Estimate, Munic1) %>%
arrange (Estimate)%>%
head(10) #bottom ten municipalities
bot10.m.empl## Estimate Munic1
## 1 -0.6658530 Buzim
## 2 -0.4716639 Derventa
## 3 -0.4082614 N.Gorazde
## 4 -0.3264987 Zvornik
## 5 -0.2568216 Brod
## 6 -0.2491723 V.Kladusa
## 7 -0.1828359 B.Petrovac
## 8 -0.1784561 Cajnice
## 9 -0.1673091 N.Travnik
## 10 -0.1642980 SokolacZakljucak za doktorat ovjde da je to sve moguce samo sto model posmatra gdje ljudi zive i moguce je da neko iz recimo Posusja radi u S.Brijeg, ali treba imati na umu to nije bas ispravno. Potrebni su podaci plata prema mjestu gdje neko radi a ne gdje zivi.
The log-linear wage model is:
\[ \log(w_i) = X_i^\top \beta + \mu_{k(i)} + \varepsilon_i \]
where: - \(w_i\) is the wage for individual \(i\), - \(X_i\) is a vector of explanatory variables, - \(\beta\) is the vector of coefficients for the explanatory variables, - \(\mu_{k(i)}\) is the fixed effect for the municipality \(k\) where individual \(i\) resides, - \(\varepsilon_i\) is the error term.
To calculate the final coefficient for wages at the municipal level, you exponentiate the log estimates and multiply them by the share of employment in each municipality:
\[ w_k = \left( \exp(X_i^\top \beta + \mu_{k}) \right) \cdot s_k \]
where: - \(w_k\) is the adjusted wage estimate for municipality \(k\), - \(s_k\) is the share of employment in municipality \(k\).
If \(s_k\) represents the employment share for all individuals in \(k\), and we want to adjust the wage to account for these shares, so we used this formula to combine the effects.