EMPIRICAL APPENDIX
This is an empirical appendix to the paper: Supporting the right workplace experience: A dynamic evaluation of three activation programmes for young job seekers in Slovakia
In our paper we analyse the employment chances of young jobseekers registered by the Slovak Public Employment Office (COLSAF). We aim at identifying the treatment effects of participation in three ALMP programmes facilitating workplace insertions in Slovakia during 2011.
rm(list=ls( ))
setwd("D:/Dropbox/DynamicALMP/")
library(pacman)
pacman::p_load(ggplot2,gridExtra,scales,haven,foreign,gdata,glmnet,readxl,stringr, dplyr, fmsb, ggpubr, kableExtra, matrixStats, patchwork)
#library(dplyr)
#library(kableExtra)
ro <- read_dta("enliven_Lukas_ro.dta",encoding = 'latin1')
###Correction of an old typo from the "enliven.dta" file
ro <- ro %>% mutate(
kraj7 = case_when(
ro$urad_kod %in% seq(34:40) ~ 1,
ro$urad_kod == 46 ~ 1))
ro$kraj7[is.na(ro$kraj7)]<-0
ro <- ro %>% mutate(
kraj8 = case_when(
ro$urad_kod %in% seq(41:45) ~ 1))
ro$kraj8[is.na(ro$kraj8)]<-0
###END OF Correction of an old typo from the "enliven.dta" file
##Roma population in the village
AtlasRK_obce <- read.csv2("AtlasRK/AtlasRK_obce.csv", sep=",", col.names=c("Kraj", "Okres", "Obec_name", "obec", "PocOb", "roma_share", "roma_num", "roma_segrK", "segrK_pop", "segrK_pop_out", "segrK_pop_border", "segrK_pop_in", "roma_Int", "PrefLang"))
ro<-merge(ro, select(AtlasRK_obce, obec, roma_share), by = "obec", all.x = TRUE)
ro$roma_share<-as.numeric(ro$roma_share)
ro$roma_share[is.na(ro$roma_share)]<-0
#################################
## Number of inhabitants of the place of residence
obyvatelstvo <- read_excel("AtlasRK/obyvatelstvo.xlsx")
obeckod <- read_excel("AtlasRK/obeckod.xlsx")
obyvatelstvo <- select(obyvatelstvo, obec, 'OBDOBIE:2020')
names(obyvatelstvo)[2] <- '2020'
ciselnik <- read_excel("AtlasRK/Kopia_-_Ciselnik_spravnych_uzemi_SR.xlsx")
ciselnik$Obec_kod <- str_sub(ciselnik$Obec_kod, start= -6)
obeckod <- obeckod %>% group_by(officialTitle) %>% mutate(jedin = n())
obeckod$obec <- ifelse(obeckod$jedin >= 2, paste0(ciselnik$Obec_nazov[match(obeckod$code, ciselnik$Obec_kod)],', okres ', ciselnik$Okres_nazov[match(obeckod$code, ciselnik$Obec_kod)]), obeckod$officialTitle)
obyvatelstvo$obec_kod <- obeckod$code[match(obyvatelstvo$obec, obeckod$obec)]
ro$population <- obyvatelstvo$`2020`[match(ro$obec, obyvatelstvo$obec_kod)]
ro$population[is.na(ro$population)]<-mean(ro$population, na.rm=TRUE)
ro$roma5<-as.logical(ro$roma_share>0.05)
ro$roma10<-as.logical(ro$roma_share>0.1)
ro$primary<-as.logical(ro$edulev1==1 | ro$edulev2==1)
ro$secondary<-as.logical(ro$edulev3==1)
ro$tertiary<-as.logical(ro$edulev4==1)
ro$age20<-as.logical(ro$age>20)
ro$west<-as.logical(ro$kraj1==1 | ro$kraj2==1 | ro$kraj3==1)
ro$mid<-as.logical(ro$kraj4==1 | ro$kraj5==1 | ro$kraj6==1)
ro$east<-as.logical(ro$kraj7==1 | ro$kraj8==1)
ro$village<-as.logical(ro$population<4000)
ro$town<-as.logical(ro$population>=4000)
# if columns are logical (T,F) change it to numeric columns (1,0)
groups<-c("tertiary", "age20", "west", "mid", "east", "roma5", "village", "town")
logic_cols <- sapply(ro[,groups], is.logical)
ro[,groups] <- lapply(ro[,groups], as.numeric)
attach(ro)
covariates<- read.csv("list_of_covariates.csv",encoding = 'latin1', sep = ";")Our database is constructed from COLSAF administrative data, covering the whole population of interest. This consists of all jobseekers, younger than 26, registered by COLSAF for at least one day during 2011. After excluding 1 424 individuals with a health disability and 2 143 individuals whose unemployment spell was longer than 5 years, we remain with 221 005 individuals.
Out of these:
14 475 (6.65%) participated in the first ALMP of
interest - the Graduate practice (GP)
2 941 (1.33%) participated in
the second ALMP of interest - the Activation works (AW)
1 240
(0.56%) participated in the third ALMP of interest - the Voluntary
activation works (VAW)
1. Programme implementation
All three programmes shelter workplace insertions of young unemployed. The usual length of the participation is the same (6 months). Participations shorter than six months occur mostly in the case of GP (3, 4 and 5 months) and partialy in the case of VAW (3 months). Nevertheless, in terms of duration of programme participation, the three measures are comparable.
# Graph:Programme duration in months
theme_set(theme_bw())
colors <- c("GP" = "blue", "AW" = "red", "VAW" = "orange")
ggplot(ro) +
geom_density(kernel = "gaussian", aes(x=time51, color="GP"), size=1) +
geom_density(kernel = "gaussian", aes(x=time52, color="AW"), size=1, linetype="dotted") +
geom_density(kernel = "gaussian", aes(x=time52a, color="VAW"), size=1, linetype="dashed") +
labs(title="Graph A1: Programme duration in months", x="Months", y="Programme duration (density)", color="Programme", caption="Note: Duration is measured in days, end-of-month spikes are driven by participations usually ending by the end of the month.\n Source: Authors’ calculations using the COLSAF database") +
scale_x_continuous(breaks = c(0,1,3,6,9,12)) +
scale_color_manual(values = colors) +
theme(legend.title = element_text(size=10, color = "black", face="bold"),
legend.justification=c(1,0),
legend.position=c(0.95, 0.50),
legend.background = element_blank(),
legend.key = element_blank(), plot.caption = element_text(hjust = 0)) 
A more significant difference can be observed in the usual timing of the start of the programme participation. While the participation in GP usually starts within the first 12 months, participation in AW usually takes place after one year of unemployment and also spread through later stages of the unemployment spell.
S51 <- as.numeric(entry51) - as.numeric(month_inflow)
S51[S51<0] <- NA
S52 <- as.numeric(entry52) - as.numeric(month_inflow)
S52[S52<0] <- NA
S52a <- as.numeric(entry52a) - as.numeric(month_inflow)
S52a[S52a<0] <- NA
YdurG <- as.numeric(month_outflow) - as.numeric(month_inflow)
YdurG[YdurG<0] <- NA
# Graph: Start of the programme implementation (in months)
theme_set(theme_bw())
colors <- c("GP" = "blue", "AW" = "red", "VAW" = "orange", "Unemployment duration" = "grey")
ggplot(ro) +
stat_density(geom="area", kernel = "gaussian", aes(x=YdurG, color="Unemployment duration", alpha=0.5), size=1) +
geom_density(kernel = "gaussian", aes(x=S51, color="GP"), size=1) +
geom_density(kernel = "gaussian", aes(x=S52, color="AW"), size=1, linetype="dotted") +
geom_density(kernel = "gaussian", aes(x=S52a, color="VAW"), size=1, linetype="dashed") +
labs(title="Graph A2: Start of the programme implementation in months", x="Months", y="Start of the programme implementation (density)", color="Programme", caption="Source: Authors’ calculations using the COLSAF database") +
scale_x_continuous(breaks = c(0,1,3,6,9,12,18,24,30,36,42,48), limits = c(0, 50)) +
scale_color_manual(values = colors) +
theme(legend.title = element_text(size=10, color = "black", face="bold"),
legend.justification=c(1,0),
legend.position=c(0.95, 0.50),
legend.background = element_blank(),
legend.key = element_blank(), plot.caption = element_text(hjust = 0))
Difference in the entry to the programme also drives the differences in individual characteristics of participants. These can be observed on a wide list of covariates.
2. Database and sample
Our data contain rich information on individual characteristics of these individuals reported at the start of the unemployment spell. These were complemented by information on the history of their previous employment as well as unemployment periods. Additionally, we construct a set of variables capturing the situation of their region or municipality, such as the average wage or unemployment rate in the region, but also the usual traveling time to the nearest regional COLSAF centre.
Table A1: List of covariates
| Variable_label | Variable_name |
|---|---|
| Male | male |
| Age of the jobseeker | age |
| Level of education -No education | edulev1 |
| Level of education -Primary | edulev2 |
| Level of education -Secondary | edulev3 |
| Level of education -Tertiary | edulev4 |
| Speaks foreign language | aj |
| The caseworker identifies a barrier to instant placement | barrier |
| Length of the previous employment (in months) | dlzka_zamestnania |
| Field of education - dummies | eduf_# |
| Was in registered employment 12 months before the current unemployment spell | empl_before12_un |
| Was in registered employment 24 months before the current unemployment spell | empl_before24_un |
| Was in registered employment 6 months before the current unemployment spell | empl_before6_un |
| Documented termination of previous employment | employed_before |
| Income from registered employment 12 months before the current unemployment spell | inc_before12_un |
| Income from registered employment 18 months before the current unemployment spell | inc_before18_un |
| Income from registered employment 24 months before the current unemployment spell | inc_before24_un |
| Income from registered employment 6 months before the current unemployment spell | inc_before6_un |
| Occupation of previous employment - ISCO 0 | isco_1 |
| Occupation of previous employment - ISCO 1 | isco_2 |
| Occupation of previous employment - ISCO 2 | isco_3 |
| Occupation of previous employment - ISCO 3 | isco_4 |
| Occupation of previous employment - ISCO 4 | isco_5 |
| Occupation of previous employment - ISCO 5 | isco_6 |
| Occupation of previous employment - ISCO 6 | isco_7 |
| Occupation of previous employment - ISCO 7 | isco_8 |
| Occupation of previous employment - ISCO 8 | isco_9 |
| Occupation of previous employment - ISCO 9 | isco_10 |
| Has kids under 10 years of age | kids |
| Traveling time to the capital city - Bratislava (in minutes) | min_BA |
| Travelling time to the local administrative centre (in minutes) | min_kraj |
| Traveling time to the self-governing capital (in minutes) | min_kraj |
| Travelling time to the local Labour Office (in minutes) | min_urad |
| Traveling time to the nearest regional COLSAF office (in minutes) | min_urad |
| Not a Slovak nationality | notSK |
| Commands a computer | pc |
| Regional Labour Office - dummies | reg_office# |
| Sector of economic activity in previous employment - Agriculture | sector1 |
| Sector of economic activity in previous employment - Industry | sector2 |
| Sector of economic activity in previous employment - Private services | sector3 |
| Sector of economic activity in previous employment - Public services | sector4 |
| Marital status - single | single |
| Length of the first unemployment spell (in days) | spell1 |
| Number of previous unemployment spells | spells |
| Average unemployment rate in the region during 2008 | un_rr2008 |
| Has a driving licence | vp |
| Average wage in the region during 2009 | wage2009 |
| Number of days in unemployment before January 1st 2011 | zaradenie |
| Bratislava district | kraj1 |
| Trnava district | kraj2 |
| Trencin district | kraj3 |
| Nitra district | kraj4 |
| Zilina district | kraj5 |
| Banska Bystrica district | kraj6 |
| Presov district | kraj7 |
| Kosice district | kraj8 |
| Population of the municipality of permanent residence | population |
| Share of roma population in the municipality of permanent residence | roma_share |
| Share of roma population in the municipality over 5 percent | roma5 |
Collinear covariates were dropped, by applying the condition of
VIF<10, in a step-wise manner using a user written function: https://www.r-bloggers.com/collinearity-and-stepwise-vif-selection/
downloaded from: https://gist.githubusercontent.com/fawda123/4717702/raw/4878688f9539db4304033f1a8bc26dfd0e1e9e28/vif_fun.r
After accounting for collinearity we end up with a list of 52
covariates.
Considering these attributes, participants differ substantially from the eligible non-participants, as well as between the programmes.
Table A2: Mean values of selected individuals´ characteristics by subgroups
| Eligible | Graduate practice | Activation works | Voluntary activation works | |
|---|---|---|---|---|
| Age of the jobseeker | 21.28 | 21.12 | 20.70 | 21.76 |
| Speaks foreign language | 0.82 | 0.96 | 0.34 | 0.90 |
| The caseworker identifies a barrier to instant placement | 0.36 | 0.37 | 0.53 | 0.39 |
| Length of the previous employment (in months) | 4.12 | 3.71 | 1.44 | 2.50 |
| Level of education -No education | 0.01 | 0.00 | 0.09 | 0.00 |
| Level of education -Primary | 0.11 | 0.01 | 0.41 | 0.04 |
| Level of education -Secondary | 0.62 | 0.67 | 0.17 | 0.59 |
| Level of education -Tertiary | 0.26 | 0.32 | 0.32 | 0.37 |
| Was in registered employment 12 months before the current unemployment spell | 0.26 | 0.21 | 0.04 | 0.19 |
| Was in registered employment 24 months before the current unemployment spell | 0.21 | 0.17 | 0.04 | 0.16 |
| Was in registered employment 6 months before the current unemployment spell | 0.28 | 0.23 | 0.04 | 0.21 |
| Documented termination of previous employment | 0.01 | 0.01 | 0.00 | 0.00 |
| Income from registered employment 12 months before the current unemployment spell | 80.32 | 47.13 | 10.80 | 45.91 |
| Income from registered employment 24 months before the current unemployment spell | 66.04 | 36.69 | 9.10 | 32.80 |
| Income from registered employment 6 months before the current unemployment spell | 94.05 | 55.81 | 9.24 | 56.73 |
| Occupation of previous employment - ISCO 9 | 0.07 | 0.04 | 0.10 | 0.06 |
| Occupation of previous employment - ISCO 1 | 0.00 | 0.00 | 0.00 | 0.00 |
| Occupation of previous employment - ISCO 2 | 0.01 | 0.01 | 0.00 | 0.02 |
| Occupation of previous employment - ISCO 3 | 0.03 | 0.03 | 0.00 | 0.05 |
| Occupation of previous employment - ISCO 4 | 0.02 | 0.02 | 0.01 | 0.03 |
| Occupation of previous employment - ISCO 5 | 0.06 | 0.07 | 0.01 | 0.06 |
| Occupation of previous employment - ISCO 7 | 0.05 | 0.02 | 0.02 | 0.01 |
| Occupation of previous employment - ISCO 8 | 0.04 | 0.02 | 0.02 | 0.02 |
| Has kids under 10 years of age | 0.05 | 0.02 | 0.13 | 0.04 |
| Trnava district | 0.09 | 0.11 | 0.01 | 0.12 |
| Trencin district | 0.10 | 0.10 | 0.01 | 0.06 |
| Nitra district | 0.12 | 0.14 | 0.04 | 0.12 |
| Zilina district | 0.13 | 0.14 | 0.01 | 0.06 |
| Banska Bystrica district | 0.08 | 0.08 | 0.13 | 0.10 |
| Presov district | 0.15 | 0.12 | 0.09 | 0.13 |
| Kosice district | 0.10 | 0.07 | 0.01 | 0.09 |
| Male | 0.57 | 0.36 | 0.58 | 0.30 |
| Traveling time to the capital city - Bratislava (in minutes) | 217.56 | 222.20 | 318.25 | 230.37 |
| Travelling time to the local administrative centre (in minutes) | 41.29 | 42.44 | 62.00 | 53.40 |
| Traveling time to the self-governing capital (in minutes) | 41.29 | 42.44 | 62.00 | 53.40 |
| Traveling time to the nearest regional COLSAF office (in minutes) | 11.98 | 10.81 | 17.40 | 12.89 |
| Travelling time to the local Labour Office (in minutes) | 11.98 | 10.81 | 17.40 | 12.89 |
| Not a Slovak nationality | 0.00 | 0.00 | 0.00 | 0.00 |
| Commands a computer | 0.41 | 0.54 | 0.10 | 0.51 |
| Population of the municipality of permanent residence | 16653.51 | 16929.07 | 4412.51 | 12969.39 |
| Share of roma population in the municipality of permanent residence | 0.11 | 0.07 | 0.43 | 0.12 |
| Share of roma population in the municipality over 5 percent | 0.36 | 0.32 | 0.89 | 0.49 |
| Sector of economic activity in previous employment - Industry | 0.05 | 0.03 | 0.03 | 0.03 |
| Sector of economic activity in previous employment - Private services | 0.02 | 0.01 | 0.02 | 0.01 |
| Sector of economic activity in previous employment - Public services | 0.11 | 0.10 | 0.03 | 0.12 |
| Marital status - single | 0.87 | 0.89 | 0.66 | 0.85 |
| Length of the first unemployment spell (in days) | 101.62 | 73.55 | 192.89 | 124.23 |
| Number of previous unemployment spells | 0.79 | 0.53 | 0.62 | 0.69 |
| Average unemployment rate in the region during 2008 | 9.70 | 9.79 | 13.14 | 10.94 |
| Population in the municipality of permanent residence under 4000 | 0.48 | 0.44 | 0.80 | 0.48 |
| Has a driving licence | 0.35 | 0.44 | 0.11 | 0.42 |
| Average wage in the region during 2009 | 676.02 | 662.76 | 657.89 | 675.17 |
| Number of days in unemployment before January 1st 2011 | 18650.33 | 18620.86 | 18089.31 | 18544.58 |
Table A2.1: Mean values of selected individuals´ characteristics by subgroups and period (quarter) of participation
|
Variable
|
Quarter 3
|
Quarter 4
|
Quarter 5
|
Quarter 6
|
||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Eligible | Graduate practice | Activation works | Voluntary activation works | Eligible | Graduate practice | Activation works | Voluntary activation works | Eligible | Graduate practice | Activation works | Voluntary activation works | Eligible | Graduate practice | Activation works | Voluntary activation works | |
| Age of the jobseeker | 21.20 | 20.99 | 21.85 | 21.60 | 21.18 | 21.11 | 20.87 | 22.09 | 21.22 | 21.25 | 20.04 | 21.67 | 21.19 | 21.54 | 20.79 | 22.17 |
| Speaks foreign language | 0.77 | 0.96 | 0.31 | 0.92 | 0.75 | 0.95 | 0.29 | 0.96 | 0.72 | 0.93 | 0.31 | 0.92 | 0.70 | 0.94 | 0.27 | 0.92 |
| The caseworker identifies a barrier to instant placement | 0.38 | 0.38 | 0.53 | 0.38 | 0.39 | 0.38 | 0.54 | 0.39 | 0.38 | 0.41 | 0.52 | 0.39 | 0.38 | 0.40 | 0.53 | 0.37 |
| Length of the previous employment (in months) | 3.98 | 2.60 | 1.87 | 2.03 | 3.66 | 2.66 | 2.40 | 1.70 | 3.61 | 2.69 | 1.21 | 1.50 | 3.49 | 2.34 | 2.55 | 2.76 |
| Level of education -No education | 0.02 | 0.00 | 0.13 | 0.00 | 0.02 | 0.00 | 0.01 | 0.00 | 0.02 | 0.00 | 0.07 | 0.00 | 0.03 | 0.00 | 0.09 | 0.00 |
| Level of education -Primary | 0.14 | 0.01 | 0.49 | 0.03 | 0.16 | 0.01 | 0.50 | 0.01 | 0.18 | 0.02 | 0.45 | 0.04 | 0.20 | 0.02 | 0.42 | 0.02 |
| Level of education -Secondary | 0.60 | 0.76 | 0.15 | 0.58 | 0.58 | 0.80 | 0.24 | 0.62 | 0.57 | 0.79 | 0.15 | 0.64 | 0.56 | 0.80 | 0.14 | 0.54 |
| Was in registered employment 12 months before the current unemployment spell | 0.21 | 0.20 | 0.07 | 0.15 | 0.19 | 0.20 | 0.06 | 0.16 | 0.18 | 0.23 | 0.03 | 0.16 | 0.17 | 0.19 | 0.06 | 0.19 |
| Was in registered employment 24 months before the current unemployment spell | 0.18 | 0.18 | 0.18 | 0.16 | 0.17 | 0.17 | 0.09 | 0.17 | 0.16 | 0.18 | 0.04 | 0.14 | 0.14 | 0.13 | 0.07 | 0.15 |
| Was in registered employment 6 months before the current unemployment spell | 0.23 | 0.22 | 0.05 | 0.16 | 0.21 | 0.24 | 0.08 | 0.15 | 0.20 | 0.23 | 0.04 | 0.13 | 0.19 | 0.19 | 0.06 | 0.17 |
| Documented termination of previous employment | 0.01 | 0.00 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Income from registered employment 12 months before the current unemployment spell | 63.74 | 49.82 | 15.13 | 36.11 | 56.51 | 50.77 | 17.12 | 37.54 | 53.25 | 50.30 | 8.07 | 27.65 | 49.00 | 45.38 | 15.13 | 42.92 |
| Income from registered employment 24 months before the current unemployment spell | 54.46 | 41.33 | 37.14 | 28.40 | 47.78 | 38.85 | 23.30 | 26.63 | 44.26 | 38.12 | 11.69 | 23.91 | 40.16 | 22.36 | 17.39 | 33.84 |
| Income from registered employment 6 months before the current unemployment spell | 70.51 | 55.98 | 1.48 | 35.93 | 63.09 | 60.08 | 14.21 | 28.39 | 59.61 | 52.77 | 6.71 | 25.51 | 55.57 | 45.67 | 11.21 | 35.79 |
| Occupation of previous employment - ISCO 9 | 0.08 | 0.04 | 0.24 | 0.04 | 0.08 | 0.06 | 0.14 | 0.05 | 0.09 | 0.08 | 0.07 | 0.01 | 0.09 | 0.07 | 0.10 | 0.10 |
| Occupation of previous employment - ISCO 1 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Occupation of previous employment - ISCO 2 | 0.01 | 0.00 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.01 | 0.00 | 0.00 | 0.00 | 0.00 |
| Occupation of previous employment - ISCO 3 | 0.02 | 0.03 | 0.00 | 0.03 | 0.02 | 0.03 | 0.00 | 0.04 | 0.02 | 0.03 | 0.00 | 0.03 | 0.02 | 0.01 | 0.00 | 0.05 |
| Occupation of previous employment - ISCO 4 | 0.02 | 0.02 | 0.02 | 0.02 | 0.02 | 0.03 | 0.01 | 0.03 | 0.02 | 0.03 | 0.00 | 0.00 | 0.02 | 0.00 | 0.01 | 0.03 |
| Occupation of previous employment - ISCO 5 | 0.06 | 0.07 | 0.04 | 0.08 | 0.06 | 0.08 | 0.00 | 0.07 | 0.06 | 0.06 | 0.01 | 0.07 | 0.05 | 0.07 | 0.02 | 0.03 |
| Occupation of previous employment - ISCO 7 | 0.05 | 0.03 | 0.05 | 0.01 | 0.05 | 0.02 | 0.00 | 0.02 | 0.05 | 0.03 | 0.01 | 0.00 | 0.05 | 0.04 | 0.03 | 0.02 |
| Occupation of previous employment - ISCO 8 | 0.04 | 0.03 | 0.04 | 0.01 | 0.04 | 0.04 | 0.01 | 0.02 | 0.04 | 0.04 | 0.01 | 0.02 | 0.04 | 0.03 | 0.01 | 0.00 |
| Has kids under 10 years of age | 0.06 | 0.02 | 0.29 | 0.01 | 0.06 | 0.03 | 0.09 | 0.03 | 0.07 | 0.02 | 0.12 | 0.06 | 0.07 | 0.03 | 0.16 | 0.05 |
| Trnava district | 0.07 | 0.10 | 0.04 | 0.09 | 0.06 | 0.09 | 0.03 | 0.11 | 0.06 | 0.06 | 0.01 | 0.10 | 0.06 | 0.12 | 0.01 | 0.15 |
| Trencin district | 0.09 | 0.09 | 0.00 | 0.06 | 0.08 | 0.11 | 0.05 | 0.04 | 0.08 | 0.10 | 0.00 | 0.02 | 0.07 | 0.10 | 0.01 | 0.05 |
| Nitra district | 0.11 | 0.18 | 0.04 | 0.14 | 0.11 | 0.17 | 0.03 | 0.14 | 0.11 | 0.16 | 0.06 | 0.15 | 0.10 | 0.13 | 0.04 | 0.05 |
| Zilina district | 0.12 | 0.13 | 0.00 | 0.03 | 0.11 | 0.13 | 0.04 | 0.07 | 0.11 | 0.14 | 0.01 | 0.04 | 0.10 | 0.13 | 0.01 | 0.07 |
| Banska Bystrica district | 0.09 | 0.08 | 0.18 | 0.09 | 0.09 | 0.08 | 0.09 | 0.09 | 0.09 | 0.09 | 0.12 | 0.12 | 0.09 | 0.12 | 0.12 | 0.15 |
| Presov district | 0.13 | 0.12 | 0.05 | 0.12 | 0.12 | 0.11 | 0.10 | 0.11 | 0.12 | 0.09 | 0.08 | 0.12 | 0.11 | 0.13 | 0.11 | 0.14 |
| Kosice district | 0.07 | 0.07 | 0.02 | 0.07 | 0.06 | 0.08 | 0.01 | 0.07 | 0.06 | 0.06 | 0.01 | 0.07 | 0.05 | 0.06 | 0.01 | 0.12 |
| Male | 0.57 | 0.42 | 0.67 | 0.24 | 0.57 | 0.45 | 0.55 | 0.23 | 0.58 | 0.44 | 0.53 | 0.27 | 0.59 | 0.48 | 0.57 | 0.31 |
| Traveling time to the capital city - Bratislava (in minutes) | 235.42 | 214.60 | 331.51 | 228.51 | 242.16 | 222.67 | 308.98 | 228.14 | 247.20 | 234.61 | 304.93 | 251.68 | 250.75 | 223.80 | 317.24 | 251.39 |
| Travelling time to the local administrative centre (in minutes) | 44.75 | 41.43 | 62.33 | 53.63 | 46.02 | 41.52 | 52.19 | 53.61 | 47.22 | 44.89 | 63.00 | 56.27 | 48.05 | 46.90 | 59.00 | 58.62 |
| Traveling time to the self-governing capital (in minutes) | 44.75 | 41.43 | 62.33 | 53.63 | 46.02 | 41.52 | 52.19 | 53.61 | 47.22 | 44.89 | 63.00 | 56.27 | 48.05 | 46.90 | 59.00 | 58.62 |
| Traveling time to the nearest regional COLSAF office (in minutes) | 12.74 | 11.50 | 16.53 | 11.29 | 13.07 | 11.93 | 18.73 | 11.26 | 13.39 | 13.05 | 18.09 | 16.42 | 13.68 | 13.09 | 16.34 | 13.42 |
| Travelling time to the local Labour Office (in minutes) | 12.74 | 11.50 | 16.53 | 11.29 | 13.07 | 11.93 | 18.73 | 11.26 | 13.39 | 13.05 | 18.09 | 16.42 | 13.68 | 13.09 | 16.34 | 13.42 |
| Not a Slovak nationality | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 | 0.00 |
| Commands a computer | 0.39 | 0.55 | 0.15 | 0.54 | 0.38 | 0.55 | 0.08 | 0.49 | 0.36 | 0.58 | 0.10 | 0.52 | 0.36 | 0.55 | 0.10 | 0.51 |
| Population of the municipality of permanent residence | 14772.85 | 16414.07 | 5021.35 | 14294.75 | 14055.84 | 18032.43 | 6094.12 | 13871.22 | 13304.94 | 14486.54 | 4418.54 | 7659.00 | 12812.45 | 15005.04 | 5364.76 | 14475.44 |
| Share of roma population in the municipality of permanent residence | 0.14 | 0.07 | 0.36 | 0.12 | 0.15 | 0.08 | 0.31 | 0.11 | 0.17 | 0.07 | 0.42 | 0.14 | 0.18 | 0.09 | 0.45 | 0.14 |
| Sector of economic activity in previous employment - Industry | 0.05 | 0.03 | 0.04 | 0.02 | 0.05 | 0.04 | 0.05 | 0.03 | 0.05 | 0.05 | 0.02 | 0.03 | 0.05 | 0.04 | 0.03 | 0.02 |
| Sector of economic activity in previous employment - Private services | 0.02 | 0.01 | 0.05 | 0.01 | 0.02 | 0.01 | 0.00 | 0.01 | 0.02 | 0.01 | 0.01 | 0.00 | 0.02 | 0.02 | 0.03 | 0.00 |
| Sector of economic activity in previous employment - Public services | 0.10 | 0.10 | 0.09 | 0.08 | 0.10 | 0.12 | 0.06 | 0.09 | 0.10 | 0.07 | 0.03 | 0.08 | 0.10 | 0.10 | 0.02 | 0.14 |
| Marital status - single | 0.84 | 0.90 | 0.58 | 0.87 | 0.83 | 0.90 | 0.76 | 0.78 | 0.82 | 0.90 | 0.67 | 0.85 | 0.82 | 0.92 | 0.64 | 0.80 |
| Length of the first unemployment spell (in days) | 113.88 | 70.60 | 501.98 | 100.82 | 119.98 | 75.38 | 353.09 | 115.77 | 127.45 | 94.93 | 164.08 | 136.60 | 130.39 | 52.84 | 233.09 | 159.02 |
| Number of previous unemployment spells | 0.70 | 0.53 | 1.98 | 0.55 | 0.69 | 0.55 | 0.96 | 0.57 | 0.69 | 0.56 | 0.62 | 0.64 | 0.68 | 0.46 | 0.66 | 0.66 |
| Average unemployment rate in the region during 2008 | 10.35 | 9.72 | 13.33 | 11.17 | 10.58 | 9.52 | 13.30 | 10.62 | 10.77 | 10.00 | 12.97 | 10.96 | 10.90 | 9.91 | 13.11 | 12.10 |
| Has a driving licence | 0.35 | 0.45 | 0.05 | 0.43 | 0.35 | 0.43 | 0.06 | 0.33 | 0.34 | 0.41 | 0.07 | 0.46 | 0.34 | 0.42 | 0.10 | 0.44 |
| Average wage in the region during 2009 | 666.67 | 665.63 | 643.02 | 679.90 | 663.96 | 668.27 | 657.63 | 670.42 | 661.90 | 655.49 | 668.97 | 692.27 | 660.84 | 665.70 | 655.11 | 660.17 |
| Number of days in unemployment before January 1st 2011 | 18545.35 | 18559.05 | 18530.51 | 18515.68 | 18505.66 | 18494.32 | 18459.79 | 18482.95 | 18464.45 | 18425.96 | 18415.22 | 18443.66 | 18435.75 | 18252.41 | 18258.91 | 18280.39 |
The mean values reported above and the ATETs reported later in this appendix are counted based on the following samples. Please note that the samples of AW participants are limited in the early stages of the unemployment spell. In contrast, the VAW participants become less numerous in the sixth quarter of unemployment.
Table A2.2: Sample of participants by programme and the quarter of participation
###SampleTable
nPeriods<-6
SampleTable <- matrix(NA, nrow=nPeriods, ncol=5)
for (k in seq(3,nPeriods)) {
SampleTable[k,1] <- paste("Quarter ",k, sep="")
SampleTable[k,2]<-sum(as.logical((aotp51==0)*(aotp52==0)*(aotp52a==0)*(Ydur>=k)))
SampleTable[k,3] <- sum(as.logical((aotp51==1)*(S51==k)))
SampleTable[k,4] <- sum(as.logical((aotp52==1)*(S52==k)))
SampleTable[k,5] <- sum(as.logical((aotp52a==1)*(S52a==k)))
}
kbl(SampleTable[c(3:6),] , col.names = c("Participation period (s)", "Eligible","GP", "AW", "VAW")) %>%
kable_classic(full_width = F) %>%
add_header_above(c("Sample size" = 5)) |
Sample size
|
||||
|---|---|---|---|---|
| Participation period (s) | Eligible | GP | AW | VAW |
| Quarter 3 | 108038 | 2348 | 55 | 201 |
| Quarter 4 | 84228 | 758 | 78 | 148 |
| Quarter 5 | 67096 | 428 | 473 | 98 |
| Quarter 6 | 56807 | 252 | 387 | 59 |
3. Estiamtion of the treatment effects on the treated
In order to estimate unbiased treatment effects of participation in one of the three programmes of interest, we account for the different composition of programme participants driven by selection into the programme. Out of the full list of covariates available in our data, we have dropped collinear variables (correlation threshold 0.8) and concentrated dummy variables (concentration threshold 0.01 resp. 0.99).
Additionally, because of the difference in the usual start of the programme participation, we adopt a dynamic evaluation framework following the routine introduced in Vikström (2017). We discretize the continuous time by quarter-of-year increments and change the risk set in every point in time. We found this to be a practical choice balancing the precision of the estimated probabilities \(\hat p_s(X_{i,s}) = \textrm{Pr}(S=s|X_{i,s},S \geq s, \overline{Y}_{s-1}=0)\) and loosing the precision in the measurement of the outcome and treatment timing (by month). The pool of not-yet-treated participants that are used to recover the fundamentally unobserved counterfactual probability of never being treated is shrinking in every time period. The indicator functions \(\mathbb{1}(\overline{Y}_{k-1,i}=0)\) in the expression of \(\widehat{ATET_t(s)}\) on the top of p10 ensures that only unemployed job-seekers enter the sums in both the numerator and the denominator.
\[ \widehat{ATET_t(s)}= - \left(\underbrace{\prod_{k=s}^{t}\left[ 1 - \frac{\sum_{i=1}^{N} Y_{k,i}\mathbb{1}(\overline{Y}_{k-1,i}=0)\cdot \mathbb{1}(S_i=s)} {\sum_{i=1}^{N} \mathbb{1}(\overline{Y}_{k-1,i}=0) \cdot \mathbb{1}(S_i=s)}\right]}_{\substack{\text{Estimator of observable probability} \\ \text{of not finding a job until $t$ if treated in $s$}}} \right. - \left. \underbrace{\prod_{k=s}^{t} \left[ 1 - \frac{\sum_{i=1}^{N} \hat{\omega}_i(s,k)\cdot Y_{k,i}\cdot \mathbb{1}(\overline{Y}_{k-1,i}=0)\cdot \mathbb{1}(S_i>k) }{\sum_{i=1}^{N}\hat{\omega}_i(s,k)\cdot \mathbb{1}(\overline{Y}_{k-1,i}=0) \cdot \mathbb{1}(S_i>k)}\right]}_{\substack{\text{Estimator of counterfactual probability} \\ \text{of not finding a job until $t$ if never treated}}}\right)\]
For an illustration, consider a JS who enters the programme in the third quarter (\(s=3\)) after he or she becomes unemployed. We are interested in comparing the probability of this person finding a job in the fifth quarter (\(t=5\)) after the beginning of the unemployment period with that of another treated person who would, counterfactually, never enter the programme. While we observe the first person, identifying assumptions must be used to recover the probability of finding a job for the second person. We provide a graphical illustration of the approach in the appendix.
This scheme illustrates the quantity of interest the \(ATET_{t}(s),\) for \(s=3\) and \(t=5:\) \[ ATET_{5}(3) = -\big( \textrm{Pr}(\overline{Y}_5(3)=0|S=3, \overline{Y}_{2}(3)=0) - \textrm{Pr}(\overline{Y}_5(0)=0|S=3, \overline{Y}_{2}(3)=0)\big).\]
Above the time axis we use the subset of people who are unemployed by that time (\(\bar{Y}_2=0\)) and treated in period (\(S=3\)). Among these people 70% remain unemployed. In between periods 3 and 4, 20% find a job and then in between periods 4 and 5, further 25% find a job. These proportions are used to estimate \(\textrm{Pr}(\overline{Y}_5(3)=0|S=3, \overline{Y}_{2}(3)=0)\). Below the time axis the counter-factual quantity \(\textrm{Pr}(\overline{Y}_5(0)=0|S=3, \overline{Y}_{2}(3)=0)\) is estimated by sequentially using the sample of not-yet-treated individuals (\(S>3\)) and by re-weighting them via \(\hat \omega,\) so that they are comparable to the \(S=3\) group.
Under this framework, the definition of the control group shifts in time after the start of the unemployment spell.
The estimator applied is based on inverse probability weighting estimating a probit model of the propensity to participate in the particular programme of interest. For this purpose we use the R-function [dynamicALMP.R] (http://www.lmevidence.sav.sk/data_uploads/dynamicALMP.R) implementing the estimator introduced by Vikström (2017) followed by a R-function [dynamicALMPbalance.R] (http://www.lmevidence.sav.sk/data_uploads/dynamicALMPbalance.R) developed to assess pre and post-weighting balance of the groups of participants and the quasi-control group. Following the notation of Vikström (2017) the “dynamicALMP.R” function takes the following arguments:
- s - (small s), time of program
- nPeriods - number of periods to look ahead
- Ydur - outcomes N x 1 duration of an unemployment spell
- X - covariate N x k matrix (here we assume that X do not change in time)
- S - time between entry into unemployment and the start of the program N x 1 vector
In our case periods are quarters, with time measuring the duration of unemployment (Ydur) as well as th time elapsed between the start of the unemployment spell and the start of participation (S) measured in quarters (See the following chunk of R-code displaying the data preparation and estimation). We have aggregated our periods from months to quarters to acquire more observations in each or the periods and thus narrowing the confidence intervals of our estimates. In the following example estimation we only estimate the ATETs for participation taking place in the third quarter of the unemployment spell (s=3). Please explore the following chunk of commented R-code to follow our steps in one example estimation.
3.1 Balance improvement achieved by weighting
The following graphs display the post-weighting balance improvement of the groups of participants and the quasi-control group on the observed characteristics of individuals.
#To save time we Load the estimation results acquired by the previous chunk (instead of running the chunk)
load("D:/CloudStation/APVV/LM_evidence/DynamicALMP/DynamicALMP/DynamicALMP.RData")
balPlot51<-balance51$GraphX+balance51$GraphP+ plot_annotation(
"Graph A3.1: Balance improvement achieved by weighting - GP participants",
caption = "Source: Authors’ calculations using the COLSAF database")
balPlot51
#annotate_figure(balPlot51,
# top = text_grob("Graph A3.1: Balance improvement achieved by weighting - GP participants", color = "black", face = "bold", size = 14),
# bottom = text_grob("Source: Authors’ calculations using the COLSAF database", color = "black", hjust = 1, x = 1, face = "italic", size = 10))
balPlot52<-balance52$GraphX+balance52$GraphP + plot_annotation(
"Graph A3.2: Balance improvement achieved by weighting - AW participants",
caption = "Source: Authors’ calculations using the COLSAF database")
balPlot52
#annotate_figure(balPlot52,
# top = text_grob("Graph A3.2: Balance improvement achieved by weighting - AW participants", color = "black", face = "bold", size = 14),
# bottom = text_grob("Source: Authors’ calculations using the COLSAF database", color = "black", hjust = 1, x = 1, face = "italic", size = 10))
balPlot52a<-balance52a$GraphX + balance52a$GraphP + plot_annotation(
"Graph A3.3: Balance improvement achieved by weighting - VAW participants",
caption = "Source: Authors’ calculations using the COLSAF database")
balPlot52a
#annotate_figure(balPlot52a,
# top = text_grob("Graph A3.3: Balance improvement achieved by weighting - VAW participants", color = "black", face = "bold", size = 14),
# bottom = text_grob("Source: Authors’ calculations using the COLSAF database", color = "black", hjust = 1, x = 1, face = "italic", size = 10))3.2 ATETs reported for the extended period participation
In this section we report the ATETs for the quarters reported in the paper (s=3,4,5) plus one succeeding period (s=6) allowed by the sample. Please note, that in the case of the second quarter (4th to 6th months in unemployment), the second identifying assumption of (No anticipation assumption) is hard to justify, because the eligibility for the unemployment benefit spans through the first six months of unemployment.
Note: Outcomes are measured based on presence in or absence from the registry of unemployed persons. Ninety-five percent confidence intervals are acquired based on 500 bootstraps. The intervals are bordered by the 95th The horizontal axes show the number of quarters since the start of the programme (t-s).
3.3 Heterogeneity of estimated ATETs by sub-groups of interest
The following tables display the differences in the ATETs when estimated to subgroups splitting the sample based on:
- Gender
- Level of education (primary vs. higher education = upper secondary and above)
- Age (aged over and under 20 years)
- Size of the settlement of the place of residence (village vs. town = over and under 4000 inhabitants)
- The presence of Roma population in the place of residence (over and under 5 percent of the total population)
Table A3: ATETs estimated for selected sub-groups of interest
|
Quarter after the start of the participation
|
||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Group | Programme | Quarter of participation | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | N | |
| Gender | ||||||||||||||
| Male | GP | 3 | ATET | -0.089* | 0.004 | 0.025 | 0.043* | 0.046* | 0.046* | 0.045* | 0.05* | 0.048* | 0.045* | 986 |
| Male | GP | 3 | s.e. | (0.014) | (0.014) | (0.015) | (0.013) | (0.013) | (0.011) | (0.01) | (0.009) | (0.01) | (0.009) | |
| Male | GP | 4 | ATET | -0.069* | 0.012 | 0.017 | 0.033* | 0.046* | 0.049* | 0.071* | 0.07* | 0.071* | 0.064* | 339 |
| Male | GP | 4 | s.e. | (0.022) | (0.024) | (0.025) | (0.023) | (0.023) | (0.021) | (0.021) | (0.019) | (0.018) | (0.016) | |
| Male | GP | 5 | ATET | -0.074* | -0.016 | 0.028 | 0.024 | 0.034 | 0.052* | 0.059* | 0.106* | 0.097* | 0.073* | 189 |
| Male | GP | 5 | s.e. | (0.029) | (0.035) | (0.032) | (0.035) | (0.035) | (0.034) | (0.033) | (0.027) | (0.025) | (0.025) | |
| Male | AW | 3 | ATET | 0.111* | 0.142* | 0.086 | 0.03 | 0.046 | 0.059 | 0.06 | 0.098 | 0.104* | 0.095* | 37 |
| Male | AW | 3 | s.e. | (0.064) | (0.066) | (0.069) | (0.074) | (0.07) | (0.067) | (0.064) | (0.065) | (0.059) | (0.055) | |
| Male | AW | 4 | ATET | 0.103* | 0.118* | 0.132* | 0.106* | 0.072 | 0.066 | 0.025 | -0.01 | -0.021 | 0.022 | 43 |
| Male | AW | 4 | s.e. | (0.059) | (0.068) | (0.062) | (0.062) | (0.063) | (0.066) | (0.064) | (0.064) | (0.064) | (0.063) | |
| Male | AW | 5 | ATET | 0.048* | 0.051* | 0.037 | 0.047 | 0.036 | 0.043 | 0.038 | 0.028 | 0.022 | 0.012 | 250 |
| Male | AW | 5 | s.e. | (0.025) | (0.029) | (0.031) | (0.032) | (0.032) | (0.03) | (0.031) | (0.031) | (0.03) | (0.029) | |
| Male | VAW | 3 | ATET | 0.066 | 0.116* | 0.106* | 0.157* | 0.129* | 0.118* | 0.099* | 0.099* | 0.09* | 0.113* | 48 |
| Male | VAW | 3 | s.e. | (0.067) | (0.062) | (0.058) | (0.045) | (0.044) | (0.04) | (0.04) | (0.037) | (0.036) | (0.035) | |
| Male | VAW | 4 | ATET | -0.076 | 0.135* | 0.133 | 0.14* | 0.148* | 0.187* | 0.204* | 0.165* | 0.143* | 0.124* | 34 |
| Male | VAW | 4 | s.e. | (0.069) | (0.087) | (0.088) | (0.081) | (0.069) | (0.064) | (0.054) | (0.049) | (0.05) | (0.049) | |
| Male | VAW | 5 | ATET | -0.015 | 0.094 | 0.167* | 0.14* | 0.121 | 0.169* | 0.154* | 0.126* | 0.133 | 0.11 | 26 |
| Male | VAW | 5 | s.e. | (0.095) | (0.093) | (0.103) | (0.098) | (0.091) | (0.073) | (0.068) | (0.07) | (0.066) | (0.067) | |
| Female | GP | 3 | ATET | -0.121* | -0.035* | -0.015 | 0.011 | 0.015 | 0.026* | 0.021* | 0.024* | 0.019* | 0.021* | 1362 |
| Female | GP | 3 | s.e. | (0.011) | (0.01) | (0.01) | (0.011) | (0.01) | (0.009) | (0.009) | (0.008) | (0.008) | (0.007) | |
| Female | GP | 4 | ATET | -0.145* | -0.078* | -0.028 | -0.015 | 0 | -0.011 | -0.011 | 0.006 | 0.013 | 0.002 | 419 |
| Female | GP | 4 | s.e. | (0.016) | (0.021) | (0.02) | (0.02) | (0.02) | (0.021) | (0.019) | (0.017) | (0.016) | (0.016) | |
| Female | GP | 5 | ATET | -0.181* | -0.054* | -0.013 | 0.007 | 0.007 | 0.023 | 0.014 | 0.012 | 0.025 | 0.018 | 239 |
| Female | GP | 5 | s.e. | (0.02) | (0.028) | (0.028) | (0.026) | (0.026) | (0.026) | (0.025) | (0.025) | (0.024) | (0.024) | |
| Female | AW | 3 | ATET | 0.052 | 0.015 | 0.031 | 0.077 | 0.061 | 0.042 | 0.077 | 0.134* | 0.097 | 0.056 | 18 |
| Female | AW | 3 | s.e. | (0.084) | (0.089) | (0.096) | (0.11) | (0.114) | (0.113) | (0.098) | (0.08) | (0.078) | (0.078) | |
| Female | AW | 4 | ATET | -0.066 | -0.057 | -0.055 | 0.019 | 0.038 | 0.056 | 0.045 | 0.028 | 0.022 | 0.019 | 35 |
| Female | AW | 4 | s.e. | (0.054) | (0.064) | (0.072) | (0.08) | (0.073) | (0.068) | (0.068) | (0.07) | (0.067) | (0.07) | |
| Female | AW | 5 | ATET | -0.062* | -0.034 | -0.001 | -0.036 | -0.034 | -0.018 | 0.005 | 0.025 | 0.04 | 0.032 | 223 |
| Female | AW | 5 | s.e. | (0.022) | (0.03) | (0.031) | (0.031) | (0.029) | (0.03) | (0.029) | (0.027) | (0.025) | (0.026) | |
| Female | VAW | 3 | ATET | -0.067* | 0.15* | 0.174* | 0.173* | 0.15* | 0.132* | 0.119* | 0.114* | 0.114* | 0.094* | 153 |
| Female | VAW | 3 | s.e. | (0.038) | (0.03) | (0.028) | (0.025) | (0.025) | (0.024) | (0.022) | (0.02) | (0.017) | (0.017) | |
| Female | VAW | 4 | ATET | -0.09* | 0.019 | 0.075* | 0.089* | 0.109* | 0.109* | 0.114* | 0.106* | 0.097* | 0.091* | 114 |
| Female | VAW | 4 | s.e. | (0.041) | (0.045) | (0.045) | (0.041) | (0.034) | (0.031) | (0.028) | (0.026) | (0.025) | (0.023) | |
| Female | VAW | 5 | ATET | -0.169* | -0.105* | -0.023 | -0.032 | -0.006 | 0.045 | 0.042 | 0.089 | 0.058 | 0.06 | 72 |
| Female | VAW | 5 | s.e. | (0.044) | (0.052) | (0.056) | (0.054) | (0.059) | (0.052) | (0.051) | (0.044) | (0.045) | (0.043) | |
| Age | ||||||||||||||
| Over 20 | GP | 3 | ATET | -0.127* | -0.045* | -0.022 | 0.002 | 0.007 | 0.024* | 0.022* | 0.024* | 0.024* | 0.023* | 1205 |
| Over 20 | GP | 3 | s.e. | (0.012) | (0.015) | (0.015) | (0.013) | (0.013) | (0.012) | (0.011) | (0.009) | (0.009) | (0.008) | |
| Over 20 | GP | 4 | ATET | -0.111* | -0.051* | -0.024 | -0.005 | 0.008 | 0.009 | 0.012 | 0.031* | 0.04* | 0.036* | 422 |
| Over 20 | GP | 4 | s.e. | (0.02) | (0.021) | (0.024) | (0.024) | (0.022) | (0.019) | (0.018) | (0.016) | (0.015) | (0.015) | |
| Over 20 | GP | 5 | ATET | -0.11* | -0.001 | 0.036 | 0.054* | 0.046* | 0.066* | 0.059* | 0.063* | 0.064* | 0.047* | 265 |
| Over 20 | GP | 5 | s.e. | (0.023) | (0.027) | (0.027) | (0.027) | (0.026) | (0.022) | (0.022) | (0.022) | (0.019) | (0.019) | |
| Over 20 | AW | 3 | ATET | 0.1 | 0.112* | 0.062 | 0.058 | 0.074 | 0.081 | 0.087 | 0.134* | 0.119* | 0.087 | 34 |
| Over 20 | AW | 3 | s.e. | (0.068) | (0.064) | (0.07) | (0.073) | (0.074) | (0.068) | (0.065) | (0.057) | (0.058) | (0.059) | |
| Over 20 | AW | 4 | ATET | 0.09* | 0.082 | 0.098 | 0.094 | 0.075 | 0.068 | 0.029 | 0.011 | 0.015 | 0.04 | 44 |
| Over 20 | AW | 4 | s.e. | (0.063) | (0.064) | (0.065) | (0.062) | (0.059) | (0.065) | (0.064) | (0.063) | (0.061) | (0.054) | |
| Over 20 | AW | 5 | ATET | -0.005 | -0.01 | -0.003 | -0.022 | -0.025 | -0.014 | -0.002 | -0.007 | 0.005 | 0 | 201 |
| Over 20 | AW | 5 | s.e. | (0.023) | (0.027) | (0.028) | (0.029) | (0.03) | (0.029) | (0.03) | (0.03) | (0.029) | (0.028) | |
| Over 20 | VAW | 3 | ATET | -0.025 | 0.133* | 0.158* | 0.159* | 0.121* | 0.106* | 0.104* | 0.096* | 0.088* | 0.088* | 120 |
| Over 20 | VAW | 3 | s.e. | (0.038) | (0.04) | (0.042) | (0.039) | (0.036) | (0.032) | (0.026) | (0.025) | (0.024) | (0.021) | |
| Over 20 | VAW | 4 | ATET | -0.124* | 0.003 | 0.063 | 0.092* | 0.092* | 0.102* | 0.117* | 0.11* | 0.101* | 0.099* | 106 |
| Over 20 | VAW | 4 | s.e. | (0.044) | (0.049) | (0.047) | (0.043) | (0.039) | (0.036) | (0.03) | (0.027) | (0.025) | (0.022) | |
| Over 20 | VAW | 5 | ATET | -0.089* | -0.024 | 0.056 | 0.057 | 0.059 | 0.106* | 0.075 | 0.115* | 0.086* | 0.065* | 62 |
| Over 20 | VAW | 5 | s.e. | (0.049) | (0.051) | (0.054) | (0.053) | (0.052) | (0.05) | (0.049) | (0.037) | (0.038) | (0.038) | |
| 20 and younger | GP | 3 | ATET | -0.09* | 0.008 | 0.014 | 0.03* | 0.028* | 0.025* | 0.021* | 0.027* | 0.022* | 0.025* | 1143 |
| 20 and younger | GP | 3 | s.e. | (0.014) | (0.016) | (0.014) | (0.013) | (0.013) | (0.013) | (0.011) | (0.01) | (0.009) | (0.009) | |
| 20 and younger | GP | 4 | ATET | -0.108* | -0.039 | -0.007 | -0.003 | 0.015 | 0.001 | 0.017 | 0.011 | 0.014 | 0.003 | 336 |
| 20 and younger | GP | 4 | s.e. | (0.02) | (0.024) | (0.022) | (0.021) | (0.021) | (0.021) | (0.019) | (0.018) | (0.016) | (0.016) | |
| 20 and younger | GP | 5 | ATET | -0.183* | -0.117* | -0.071* | -0.075* | -0.051 | -0.044 | -0.036 | 0.005 | 0.022 | 0.009 | 163 |
| 20 and younger | GP | 5 | s.e. | (0.027) | (0.039) | (0.039) | (0.039) | (0.039) | (0.037) | (0.032) | (0.03) | (0.026) | (0.025) | |
| 20 and younger | AW | 3 | ATET | 0.045 | 0.055 | 0.058 | 0.036 | 0.025 | 0.01 | 0.037 | 0.08 | 0.078 | 0.086 | 21 |
| 20 and younger | AW | 3 | s.e. | (0.089) | (0.095) | (0.084) | (0.091) | (0.087) | (0.089) | (0.092) | (0.089) | (0.083) | (0.076) | |
| 20 and younger | AW | 4 | ATET | -0.066 | -0.027 | -0.027 | 0.019 | 0.013 | 0.044 | 0.027 | -0.009 | -0.033 | -0.015 | 34 |
| 20 and younger | AW | 4 | s.e. | (0.062) | (0.078) | (0.076) | (0.079) | (0.077) | (0.078) | (0.078) | (0.077) | (0.077) | (0.071) | |
| 20 and younger | AW | 5 | ATET | 0.006 | 0.032 | 0.047* | 0.041 | 0.035 | 0.051 | 0.054* | 0.064* | 0.062* | 0.046* | 272 |
| 20 and younger | AW | 5 | s.e. | (0.018) | (0.022) | (0.029) | (0.029) | (0.031) | (0.033) | (0.034) | (0.035) | (0.035) | (0.032) | |
| 20 and younger | VAW | 3 | ATET | -0.045 | 0.15* | 0.144* | 0.175* | 0.163* | 0.144* | 0.114* | 0.116* | 0.116* | 0.097* | 81 |
| 20 and younger | VAW | 3 | s.e. | (0.052) | (0.05) | (0.046) | (0.039) | (0.033) | (0.031) | (0.032) | (0.031) | (0.027) | (0.027) | |
| 20 and younger | VAW | 4 | ATET | -0.003 | 0.089 | 0.103 | 0.092 | 0.157* | 0.161* | 0.148* | 0.117* | 0.097* | 0.074 | 42 |
| 20 and younger | VAW | 4 | s.e. | (0.074) | (0.073) | (0.069) | (0.072) | (0.056) | (0.051) | (0.047) | (0.047) | (0.046) | (0.046) | |
| 20 and younger | VAW | 5 | ATET | -0.16* | -0.072 | -0.021 | -0.055 | -0.023 | 0.033 | 0.066 | 0.06 | 0.047 | 0.077 | 36 |
| 20 and younger | VAW | 5 | s.e. | (0.051) | (0.068) | (0.082) | (0.078) | (0.082) | (0.076) | (0.065) | (0.063) | (0.058) | (0.051) | |
| Education level | ||||||||||||||
| Primary | GP | 3 | ATET | -0.089 | 0.031 | 0.066 | 0.122 | 0.066 | 0.08 | 0.104 | 0.143* | 0.175* | 0.174* | 29 |
| Primary | GP | 3 | s.e. | (0.068) | (0.085) | (0.078) | (0.07) | (0.069) | (0.069) | (0.072) | (0.067) | (0.048) | (0.041) | |
| Primary | GP | 4 | ATET | -0.054 | 0.021 | 0.112 | 0.115 | 0.046 | 0 | -0.031 | 0.031 | -0.026 | 0.026 | 9 |
| Primary | GP | 4 | s.e. | (0.149) | (0.161) | (0.178) | (0.155) | (0.15) | (0.148) | (0.149) | (0.138) | (0.116) | (0.103) | |
| Primary | GP | 5 | ATET | -0.019 | 0.014 | 0.052 | -0.015 | 0.027 | 0.092 | 0.18 | 0.145 | 0.118 | 0.199 | 9 |
| Primary | GP | 5 | s.e. | (0.202) | (0.207) | (0.24) | (0.227) | (0.247) | (0.243) | (0.224) | (0.225) | (0.226) | (0.178) | |
| Primary | AW | 3 | ATET | 0.068 | 0.121 | 0.075 | 0.026 | 0.016 | 0.027 | 0.052 | 0.069 | 0.078 | 0.07 | 34 |
| Primary | AW | 3 | s.e. | (0.078) | (0.083) | (0.086) | (0.085) | (0.083) | (0.076) | (0.074) | (0.069) | (0.067) | (0.061) | |
| Primary | AW | 4 | ATET | 0.041 | 0.055 | 0.036 | 0.021 | 0.03 | 0.041 | 0.018 | -0.024 | -0.039 | -0.025 | 40 |
| Primary | AW | 4 | s.e. | (0.055) | (0.067) | (0.069) | (0.069) | (0.066) | (0.062) | (0.064) | (0.065) | (0.066) | (0.067) | |
| Primary | AW | 5 | ATET | 0.041* | 0.045* | 0.041* | 0.02 | 0.009 | 0.005 | -0.005 | 0.009 | 0.009 | -0.004 | 244 |
| Primary | AW | 5 | s.e. | (0.022) | (0.025) | (0.025) | (0.026) | (0.027) | (0.027) | (0.027) | (0.031) | (0.03) | (0.029) | |
| Primary | VAW | 3 | ATET | -0.149* | -0.05 | -0.103 | -0.161 | -0.077 | -0.135 | -0.16 | -0.206 | -0.23 | 0.07 | 6 |
| Primary | VAW | 3 | s.e. | (0.097) | (0.202) | (0.19) | (0.193) | (0.211) | (0.218) | (0.21) | (0.195) | (0.191) | (0.194) | |
| Primary | VAW | 4 | ATET | -0.229* | 0.387 | 0.119 | -0.004 | -0.06 | 0.431* | NA | NA | NA | NA | 2 |
| Primary | VAW | 4 | s.e. | (0.153) | (0.391) | (0.317) | (0.347) | (0.335) | (0.238) | (NA) | (NA) | (NA) | (NA) | |
| Primary | VAW | 5 | ATET | 0.112 | 0.274 | 0.043 | -0.001 | -0.036 | -0.069 | -0.112 | -0.15 | -0.256 | -0.301 | 4 |
| Primary | VAW | 5 | s.e. | (0.252) | (0.259) | (0.274) | (0.272) | (0.267) | (0.265) | (0.277) | (0.276) | (0.232) | (0.225) | |
| Secondary | GP | 3 | ATET | -0.116* | -0.027* | -0.003 | 0.021* | 0.03* | 0.035* | 0.031* | 0.036* | 0.032* | 0.034* | 1776 |
| Secondary | GP | 3 | s.e. | (0.009) | (0.011) | (0.011) | (0.01) | (0.009) | (0.009) | (0.009) | (0.008) | (0.007) | (0.007) | |
| Secondary | GP | 4 | ATET | -0.111* | -0.047* | -0.014 | 0.002 | 0.022 | 0.02 | 0.033* | 0.035* | 0.039* | 0.026* | 605 |
| Secondary | GP | 4 | s.e. | (0.015) | (0.016) | (0.017) | (0.017) | (0.017) | (0.016) | (0.015) | (0.014) | (0.012) | (0.011) | |
| Secondary | GP | 5 | ATET | -0.132* | -0.039* | -0.007 | 0.001 | 0.007 | 0.025 | 0.025 | 0.049* | 0.06* | 0.043* | 340 |
| Secondary | GP | 5 | s.e. | (0.021) | (0.024) | (0.025) | (0.025) | (0.026) | (0.023) | (0.023) | (0.021) | (0.019) | (0.019) | |
| Secondary | AW | 3 | ATET | 0.268* | 0.191* | 0.116 | 0.113 | 0.056 | 0.082 | 0.107 | 0.142 | 0.109 | 0.085 | 8 |
| Secondary | AW | 3 | s.e. | (0.145) | (0.139) | (0.138) | (0.124) | (0.116) | (0.118) | (0.107) | (0.099) | (0.095) | (0.094) | |
| Secondary | AW | 4 | ATET | -0.121 | -0.135 | -0.12 | -0.062 | -0.069 | -0.111 | -0.144* | -0.142 | -0.119 | -0.05 | 19 |
| Secondary | AW | 4 | s.e. | (0.084) | (0.103) | (0.102) | (0.099) | (0.099) | (0.095) | (0.095) | (0.107) | (0.101) | (0.089) | |
| Secondary | AW | 5 | ATET | -0.062 | -0.072 | -0.102* | -0.112* | -0.121* | -0.112* | -0.046 | -0.064 | -0.037 | -0.046 | 73 |
| Secondary | AW | 5 | s.e. | (0.04) | (0.051) | (0.057) | (0.058) | (0.064) | (0.061) | (0.053) | (0.053) | (0.046) | (0.045) | |
| Secondary | VAW | 3 | ATET | -0.046 | 0.121* | 0.135* | 0.145* | 0.129* | 0.111* | 0.107* | 0.117* | 0.108* | 0.094* | 116 |
| Secondary | VAW | 3 | s.e. | (0.034) | (0.037) | (0.039) | (0.036) | (0.033) | (0.03) | (0.03) | (0.025) | (0.022) | (0.021) | |
| Secondary | VAW | 4 | ATET | -0.052 | 0.027 | 0.073 | 0.092* | 0.12* | 0.106* | 0.109* | 0.085* | 0.081* | 0.069* | 92 |
| Secondary | VAW | 4 | s.e. | (0.042) | (0.05) | (0.055) | (0.05) | (0.044) | (0.041) | (0.039) | (0.037) | (0.034) | (0.032) | |
| Secondary | VAW | 5 | ATET | -0.191* | -0.071 | -0.023 | -0.018 | 0.032 | 0.09* | 0.091* | 0.087* | 0.074 | 0.083* | 63 |
| Secondary | VAW | 5 | s.e. | (0.039) | (0.061) | (0.06) | (0.058) | (0.053) | (0.046) | (0.043) | (0.039) | (0.04) | (0.037) | |
| Tertiary | GP | 3 | ATET | -0.096* | -0.01 | 0.006 | 0.023 | 0.02 | 0.023* | 0.019 | 0.015 | 0.011 | 0.006 | 543 |
| Tertiary | GP | 3 | s.e. | (0.017) | (0.018) | (0.018) | (0.016) | (0.016) | (0.015) | (0.014) | (0.013) | (0.012) | (0.012) | |
| Tertiary | GP | 4 | ATET | -0.118* | -0.015 | 0.008 | 0.017 | 0.017 | 0.01 | 0.014 | 0.036 | 0.05* | 0.045 | 144 |
| Tertiary | GP | 4 | s.e. | (0.031) | (0.038) | (0.039) | (0.036) | (0.034) | (0.033) | (0.033) | (0.032) | (0.029) | (0.027) | |
| Tertiary | GP | 5 | ATET | -0.147* | -0.026 | 0.05 | 0.054 | 0.045 | 0.058 | 0.045 | 0.045 | 0.023 | 0.003 | 79 |
| Tertiary | GP | 5 | s.e. | (0.046) | (0.055) | (0.061) | (0.054) | (0.047) | (0.045) | (0.041) | (0.04) | (0.04) | (0.04) | |
| Tertiary | AW | 3 | ATET | -0.047 | -0.086 | -0.055 | -0.013 | 0.13 | 0.091 | 0.034 | 0.132 | 0.087 | 0.059 | 13 |
| Tertiary | AW | 3 | s.e. | (0.121) | (0.129) | (0.145) | (0.154) | (0.134) | (0.128) | (0.136) | (0.107) | (0.095) | (0.091) | |
| Tertiary | AW | 4 | ATET | 0.122 | 0.141 | 0.19* | 0.248* | 0.195* | 0.236* | 0.193* | 0.162* | 0.135* | 0.146* | 19 |
| Tertiary | AW | 4 | s.e. | (0.1) | (0.098) | (0.093) | (0.083) | (0.082) | (0.073) | (0.074) | (0.072) | (0.073) | (0.068) | |
| Tertiary | AW | 5 | ATET | -0.027 | -0.003 | 0.038 | 0.03 | 0.038 | 0.073* | 0.082* | 0.083* | 0.078* | 0.069* | 156 |
| Tertiary | AW | 5 | s.e. | (0.031) | (0.035) | (0.035) | (0.037) | (0.037) | (0.038) | (0.033) | (0.031) | (0.031) | (0.03) | |
| Tertiary | VAW | 3 | ATET | 0.001 | 0.187* | 0.207* | 0.228* | 0.186* | 0.175* | 0.149* | 0.129* | 0.13* | 0.112* | 79 |
| Tertiary | VAW | 3 | s.e. | (0.047) | (0.043) | (0.036) | (0.03) | (0.031) | (0.028) | (0.029) | (0.03) | (0.024) | (0.027) | |
| Tertiary | VAW | 4 | ATET | -0.17* | 0.009 | 0.058 | 0.086 | 0.086* | 0.123* | 0.139* | 0.143* | 0.12* | 0.122* | 54 |
| Tertiary | VAW | 4 | s.e. | (0.048) | (0.06) | (0.055) | (0.051) | (0.05) | (0.043) | (0.036) | (0.029) | (0.029) | (0.027) | |
| Tertiary | VAW | 5 | ATET | -0.032 | -0.052 | 0.072 | 0.041 | -0.009 | 0.045 | 0.039 | 0.12* | 0.089 | 0.064 | 31 |
| Tertiary | VAW | 5 | s.e. | (0.085) | (0.094) | (0.089) | (0.091) | (0.093) | (0.084) | (0.086) | (0.06) | (0.057) | (0.055) | |
| Size of settlement | ||||||||||||||
| Village | GP | 3 | ATET | -0.082* | -0.017 | 0.014 | 0.047* | 0.045* | 0.041* | 0.029* | 0.028* | 0.024* | 0.023* | 1091 |
| Village | GP | 3 | s.e. | (0.012) | (0.013) | (0.014) | (0.014) | (0.013) | (0.013) | (0.013) | (0.012) | (0.011) | (0.01) | |
| Village | GP | 4 | ATET | -0.11* | -0.017 | 0.013 | 0.025 | 0.049* | 0.05* | 0.055* | 0.064* | 0.062* | 0.051* | 342 |
| Village | GP | 4 | s.e. | (0.02) | (0.027) | (0.026) | (0.026) | (0.024) | (0.022) | (0.02) | (0.019) | (0.019) | (0.018) | |
| Village | GP | 5 | ATET | -0.152* | -0.057* | 0.015 | 0.032 | 0.038 | 0.063* | 0.059* | 0.068* | 0.077* | 0.062* | 206 |
| Village | GP | 5 | s.e. | (0.024) | (0.032) | (0.036) | (0.029) | (0.03) | (0.028) | (0.026) | (0.024) | (0.022) | (0.022) | |
| Village | AW | 3 | ATET | 0.112* | 0.117* | 0.075 | 0.048 | 0.058 | 0.033 | 0.062 | 0.12* | 0.119* | 0.102* | 41 |
| Village | AW | 3 | s.e. | (0.058) | (0.062) | (0.062) | (0.064) | (0.055) | (0.056) | (0.055) | (0.049) | (0.049) | (0.048) | |
| Village | AW | 4 | ATET | 0.021 | 0.038 | 0.065 | 0.052 | 0.036 | 0.051 | 0.026 | -0.011 | -0.023 | 0.023 | 52 |
| Village | AW | 4 | s.e. | (0.057) | (0.058) | (0.063) | (0.061) | (0.06) | (0.062) | (0.062) | (0.061) | (0.059) | (0.055) | |
| Village | AW | 5 | ATET | -0.012 | 0.006 | 0.012 | 0.002 | -0.008 | -0.001 | 0.014 | 0.018 | 0.019 | 0.007 | 375 |
| Village | AW | 5 | s.e. | (0.017) | (0.019) | (0.02) | (0.022) | (0.021) | (0.022) | (0.023) | (0.022) | (0.022) | (0.021) | |
| Village | VAW | 3 | ATET | -0.012 | 0.105* | 0.147* | 0.156* | 0.143* | 0.128* | 0.112* | 0.099* | 0.095* | 0.1* | 94 |
| Village | VAW | 3 | s.e. | (0.044) | (0.044) | (0.041) | (0.038) | (0.034) | (0.035) | (0.033) | (0.031) | (0.029) | (0.029) | |
| Village | VAW | 4 | ATET | -0.133* | -0.012 | -0.008 | 0.024 | 0.112* | 0.122* | 0.129* | 0.112* | 0.102* | 0.08* | 62 |
| Village | VAW | 4 | s.e. | (0.049) | (0.061) | (0.064) | (0.059) | (0.048) | (0.049) | (0.042) | (0.04) | (0.04) | (0.04) | |
| Village | VAW | 5 | ATET | -0.144* | -0.045 | -0.004 | -0.013 | -0.018 | 0.026 | 0.017 | 0.07 | 0.054 | 0.052 | 51 |
| Village | VAW | 5 | s.e. | (0.044) | (0.064) | (0.071) | (0.069) | (0.071) | (0.064) | (0.062) | (0.051) | (0.05) | (0.043) | |
| Town | GP | 3 | ATET | -0.132* | -0.024* | -0.009 | 0.004 | 0.016 | 0.029* | 0.032* | 0.039* | 0.036* | 0.037* | 1257 |
| Town | GP | 3 | s.e. | (0.012) | (0.013) | (0.012) | (0.012) | (0.011) | (0.011) | (0.01) | (0.009) | (0.008) | (0.008) | |
| Town | GP | 4 | ATET | -0.109* | -0.057* | -0.025 | -0.004 | 0.003 | -0.005 | 0.008 | 0.015 | 0.025 | 0.016 | 416 |
| Town | GP | 4 | s.e. | (0.02) | (0.024) | (0.022) | (0.021) | (0.022) | (0.022) | (0.019) | (0.017) | (0.016) | (0.015) | |
| Town | GP | 5 | ATET | -0.121* | -0.021 | 0.001 | 0.004 | 0.008 | 0.013 | 0.012 | 0.038 | 0.039 | 0.023 | 222 |
| Town | GP | 5 | s.e. | (0.025) | (0.031) | (0.034) | (0.034) | (0.033) | (0.032) | (0.03) | (0.027) | (0.024) | (0.025) | |
| Town | AW | 3 | ATET | 0.052 | 0.065 | 0.031 | 0.062 | 0.065 | 0.15 | 0.111 | 0.125 | 0.071 | 0.052 | 14 |
| Town | AW | 3 | s.e. | (0.102) | (0.112) | (0.108) | (0.106) | (0.102) | (0.089) | (0.093) | (0.091) | (0.088) | (0.089) | |
| Town | AW | 4 | ATET | 0.059 | 0.054 | 0.037 | 0.109 | 0.104 | 0.087 | 0.049 | 0.04 | 0.037 | 0.009 | 26 |
| Town | AW | 4 | s.e. | (0.077) | (0.083) | (0.078) | (0.076) | (0.078) | (0.071) | (0.071) | (0.069) | (0.075) | (0.075) | |
| Town | AW | 5 | ATET | 0.047 | 0.036 | 0.049 | 0.033 | 0.047 | 0.074* | 0.06 | 0.065* | 0.08* | 0.08* | 98 |
| Town | AW | 5 | s.e. | (0.041) | (0.042) | (0.045) | (0.043) | (0.043) | (0.042) | (0.042) | (0.041) | (0.039) | (0.037) | |
| Town | VAW | 3 | ATET | -0.043 | 0.174* | 0.161* | 0.178* | 0.142* | 0.126* | 0.117* | 0.12* | 0.113* | 0.095* | 107 |
| Town | VAW | 3 | s.e. | (0.044) | (0.036) | (0.034) | (0.033) | (0.033) | (0.031) | (0.026) | (0.023) | (0.02) | (0.019) | |
| Town | VAW | 4 | ATET | -0.057 | 0.078 | 0.146* | 0.145* | 0.117* | 0.123* | 0.132* | 0.121* | 0.107* | 0.109* | 86 |
| Town | VAW | 4 | s.e. | (0.051) | (0.053) | (0.044) | (0.043) | (0.04) | (0.034) | (0.033) | (0.029) | (0.029) | (0.027) | |
| Town | VAW | 5 | ATET | -0.097 | -0.035 | 0.078 | 0.07 | 0.096 | 0.145* | 0.143* | 0.127* | 0.102* | 0.093* | 47 |
| Town | VAW | 5 | s.e. | (0.066) | (0.076) | (0.073) | (0.072) | (0.064) | (0.056) | (0.052) | (0.049) | (0.048) | (0.043) | |
| Roma population in the place of residence | ||||||||||||||
| With Roma population | GP | 3 | ATET | -0.112* | -0.021* | 0.004 | 0.025* | 0.029* | 0.041* | 0.038* | 0.046* | 0.039* | 0.039* | 724 |
| With Roma population | GP | 3 | s.e. | (0.011) | (0.012) | (0.013) | (0.011) | (0.011) | (0.01) | (0.009) | (0.008) | (0.008) | (0.007) | |
| With Roma population | GP | 4 | ATET | -0.118* | -0.058* | -0.012 | 0.026 | 0.036 | 0.028 | 0.061* | 0.063* | 0.055* | 0.043* | 241 |
| With Roma population | GP | 4 | s.e. | (0.027) | (0.033) | (0.032) | (0.031) | (0.029) | (0.027) | (0.025) | (0.023) | (0.022) | (0.023) | |
| With Roma population | GP | 5 | ATET | -0.113* | -0.035 | 0 | -0.001 | 0.003 | 0.01 | 0.016 | 0.04 | 0.059* | 0.046* | 139 |
| With Roma population | GP | 5 | s.e. | (0.026) | (0.031) | (0.034) | (0.034) | (0.035) | (0.033) | (0.031) | (0.027) | (0.027) | (0.026) | |
| With Roma population | AW | 3 | ATET | 0.1* | 0.103 | 0.076 | 0.066 | 0.079 | 0.054 | 0.055 | 0.103* | 0.095* | 0.08* | 46 |
| With Roma population | AW | 3 | s.e. | (0.057) | (0.064) | (0.063) | (0.063) | (0.061) | (0.062) | (0.058) | (0.055) | (0.053) | (0.048) | |
| With Roma population | AW | 4 | ATET | -0.019 | 0.002 | 0.015 | 0.054 | 0.042 | 0.049 | 0.009 | -0.02 | -0.024 | -0.016 | 61 |
| With Roma population | AW | 4 | s.e. | (0.046) | (0.055) | (0.055) | (0.058) | (0.05) | (0.053) | (0.054) | (0.052) | (0.049) | (0.051) | |
| With Roma population | AW | 5 | ATET | 0.005 | 0.02 | 0.027 | 0.018 | 0.018 | 0.034* | 0.041* | 0.048* | 0.052* | 0.038* | 422 |
| With Roma population | AW | 5 | s.e. | (0.015) | (0.017) | (0.019) | (0.019) | (0.018) | (0.018) | (0.017) | (0.02) | (0.019) | (0.019) | |
| With Roma population | VAW | 3 | ATET | -0.025 | 0.148* | 0.144* | 0.174* | 0.147* | 0.13* | 0.112* | 0.118* | 0.115* | 0.112* | 101 |
| With Roma population | VAW | 3 | s.e. | (0.035) | (0.034) | (0.032) | (0.029) | (0.027) | (0.026) | (0.025) | (0.02) | (0.019) | (0.017) | |
| With Roma population | VAW | 4 | ATET | -0.082 | 0.078 | 0.131* | 0.114* | 0.122* | 0.13* | 0.154* | 0.135* | 0.122* | 0.123* | 77 |
| With Roma population | VAW | 4 | s.e. | (0.056) | (0.061) | (0.061) | (0.056) | (0.05) | (0.043) | (0.035) | (0.034) | (0.034) | (0.03) | |
| With Roma population | VAW | 5 | ATET | -0.145* | -0.035 | 0.045 | 0.054 | 0.076 | 0.125* | 0.107* | 0.142* | 0.115* | 0.102* | 55 |
| With Roma population | VAW | 5 | s.e. | (0.049) | (0.065) | (0.059) | (0.061) | (0.059) | (0.055) | (0.052) | (0.04) | (0.04) | (0.037) | |
| Without Roma population | GP | 3 | ATET | -0.105* | -0.018 | 0 | 0.024* | 0.03* | 0.027* | 0.023* | 0.019* | 0.021* | 0.02* | 1624 |
| Without Roma population | GP | 3 | s.e. | (0.013) | (0.014) | (0.013) | (0.013) | (0.012) | (0.011) | (0.01) | (0.01) | (0.009) | (0.008) | |
| Without Roma population | GP | 4 | ATET | -0.11* | -0.036* | -0.013 | -0.005 | 0.012 | 0.009 | 0.009 | 0.019 | 0.029* | 0.021* | 517 |
| Without Roma population | GP | 4 | s.e. | (0.018) | (0.021) | (0.019) | (0.017) | (0.018) | (0.016) | (0.016) | (0.014) | (0.014) | (0.014) | |
| Without Roma population | GP | 5 | ATET | -0.162* | -0.043 | 0.008 | 0.029 | 0.03 | 0.057* | 0.052* | 0.064* | 0.052* | 0.033 | 289 |
| Without Roma population | GP | 5 | s.e. | (0.024) | (0.032) | (0.033) | (0.031) | (0.029) | (0.025) | (0.026) | (0.023) | (0.023) | (0.023) | |
| Without Roma population | AW | 3 | ATET | 0.007 | 0.091 | 0.025 | -0.074 | -0.116 | 0.147 | 0.309* | NA | NA | NA | 9 |
| Without Roma population | AW | 3 | s.e. | (0.234) | (0.276) | (0.279) | (0.265) | (0.275) | (0.231) | (0.201) | (NA) | (NA) | (NA) | |
| Without Roma population | AW | 4 | ATET | 0.156* | 0.141 | 0.12 | 0.101 | 0.096 | 0.09 | 0.083 | 0.05 | 0.025 | 0.071 | 17 |
| Without Roma population | AW | 4 | s.e. | (0.097) | (0.102) | (0.099) | (0.097) | (0.089) | (0.077) | (0.081) | (0.081) | (0.084) | (0.071) | |
| Without Roma population | AW | 5 | ATET | -0.039 | -0.047 | -0.045 | -0.083 | -0.135* | -0.168* | -0.149* | -0.181* | -0.171* | -0.144* | 51 |
| Without Roma population | AW | 5 | s.e. | (0.053) | (0.064) | (0.064) | (0.068) | (0.067) | (0.071) | (0.072) | (0.073) | (0.078) | (0.074) | |
| Without Roma population | VAW | 3 | ATET | -0.046 | 0.123* | 0.176* | 0.158* | 0.147* | 0.129* | 0.122* | 0.093* | 0.084* | 0.064* | 100 |
| Without Roma population | VAW | 3 | s.e. | (0.051) | (0.052) | (0.045) | (0.041) | (0.038) | (0.034) | (0.031) | (0.031) | (0.029) | (0.029) | |
| Without Roma population | VAW | 4 | ATET | -0.108* | -0.013 | 0.03 | 0.078 | 0.105* | 0.11* | 0.104* | 0.087* | 0.077* | 0.056* | 71 |
| Without Roma population | VAW | 4 | s.e. | (0.051) | (0.057) | (0.056) | (0.048) | (0.041) | (0.036) | (0.033) | (0.032) | (0.031) | (0.031) | |
| Without Roma population | VAW | 5 | ATET | -0.076 | -0.056 | 0.013 | -0.027 | -0.024 | 0.011 | 0.021 | 0.033 | 0.024 | 0.03 | 43 |
| Without Roma population | VAW | 5 | s.e. | (0.074) | (0.08) | (0.085) | (0.088) | (0.083) | (0.075) | (0.072) | (0.061) | (0.056) | (0.053) | |
Note: Statistical significance at the level 0.05 is marked with * Source: COLSAF database
3.4 Placebo test estimates
As we are aware of the limited options in supporting our assumptions empirically, we support the credibility of our results with a placebo test, using a randomly generated variable copying the observed distribution of the time elapsed between the start of unemployment and the start of participation in one of the ALMP programmes. We create our placebo variable in the following steps. First, we generate the observed time difference between the starting date of registered unemployment and the date of the start of the ALMP participation (S). While participants have low values of S (under 20, since our sample only contains participation taking place during 2011 and job seekers registered not earlier than 2005), depending on the start of their participation in the ALMP programme, non-participants were assigned an extremely high value of S = 333. In the second step, we extract the distribution of S for each of our programme-specific samples. Finally, we randomly assign a value of PSR to each individual in the sample and use the PSR variable instead of the S variable in the specification of our model. The procedure is performed by the R-code reported in the following chunk of code.
Following this procedure, we acquire results that are uniformly not statistically significant.
References:
Vikström J (2017) Dynamic treatment assignment and evaluation of active labor market policies. Labour Economics 49(C):42–54