*********************************************************************************************************************** ** Human Development Report Office (HDRO), United Nations Development Programme ** Multidimensional Poverty Index 2019 release ** Methodology developed in partnership with the Oxford Poverty and Human Development Initiative, University of Oxford ************************************************************************************************************************ clear all set more off set maxvar 10000 set mem 500m cap log close *** Working Folder Path *** global path_in "C:\Users\cecilia.calderon\Documents\HDRO_MCC\MPI\MPI 2.0\Viet Nam 2014_MICS" global path_out "C:\Users\cecilia.calderon\Documents\HDRO_MCC\MPI\MPI 2.0\Viet Nam 2014_MICS" global path_logs "C:\Users\cecilia.calderon\Documents\HDRO_MCC\MPI\MPI 2.0\Viet Nam 2014_MICS" global path_qc "C:\Users\cecilia.calderon\Documents\HDRO_MCC\MPI\MPI 2.0\Viet Nam 2014_MICS" global path_ado "C:" *** Log file *** log using "$path_logs/vnm_mics14_dataprep.log", replace ******************************************************************************** *** Viet Nam MICS 2014 *** ******************************************************************************** ******************************************************************************** *** Step 1: Data preparation *** Selecting main variables from CH, WM, HH & MN recode & merging with HL recode ******************************************************************************** /* Viet Nam MICS 2014: anthropometric data was not collected */ ******************************************************************************** *** Step 1.1 CH - CHILDREN's RECODE (under 5) ******************************************************************************** ** no nutrition ** ******************************************************************************** *** Step 1.2 BR - BIRTH RECODE *** (All females 14_-49 years who ever gave birth) ******************************************************************************** /* The purpose of step 1.2 is to identify children of any age who died in the last 5 years prior to the survey date. */ use "$path_in/bh.dta", clear rename _all, lower *** Generate individual unique key variable required for data merging using: *** hh1=cluster number; *** hh2=household number; *** wm4=women's line number. codebook ln bhln, tab (100) /* Two non-identical variables exist instead of wm4 for women's line number, ln and bhln; We used ln, because it alligns with the HL dta file. */ gen double ind_id = hh1*100000 + hh2*100 + ln format ind_id %20.0g label var ind_id "Individual ID" desc bh4c bh9c gen date_death = bh4c + bh9c //Date of death = date of birth (bh4c) + age at death (bh9c) gen mdead_survey = wdoi-date_death //Months dead from survey = Date of interview (wdoi) - date of death replace mdead_survey = . if (bh9c==0 | bh9c==.) & bh5==1 /*Replace children who are alive as '.' to distinguish them from children who died at 0 months */ gen ydead_survey = mdead_survey/12 //Years dead from survey codebook bh5, tab (10) //bh5 - Child still alive: 1=Yes; 2=No gen child_died = 1 if bh5==2 //1=child dead; 0=child alive replace child_died = 0 if bh5==1 replace child_died = . if bh5==. label define lab_died 0"child is alive" 1"child has died" label values child_died lab_died tab bh5 child_died, miss replace child_died=0 if bh9c>=216 & bh9c<. bysort ind_id: egen tot_child_died = sum(child_died) //For each woman, sum the number of children who died bysort ind_id: egen tot_child_died_5y=sum(child_died) if ydead_survey<=5 /*For each woman, sum the number of children who died in the past 5 years prior to the interview date */ replace tot_child_died_5y=0 if tot_child_died_5y==. & tot_child_died>=0 & tot_child_died<. /*All children who are alive and died longer than 5 years from the interview date are replaced as '0'*/ replace tot_child_died_5y=. if child_died==1 & ydead_survey==. //Replace as '.' if there is no information on when the child died tab tot_child_died tot_child_died_5y, miss bysort ind_id: egen child_died_per_wom = max(tot_child_died) lab var child_died_per_wom "Total child death for each women (birth recode)" bysort ind_id: egen child_died_per_wom_5y = max(tot_child_died_5y) lab var child_died_per_wom_5y "Total child death for each women in the last 5 years (birth recode)" //Keep one observation per women bysort ind_id: gen id=1 if _n==1 keep if id==1 drop id duplicates report ind_id gen women_BH = 1 //Identification variable for observations in BH recode //Retain relevant variables keep ind_id hh1 hh2 women_BH child_died_per_wom child_died_per_wom_5y order ind_id hh1 hh2 women_BH child_died_per_wom child_died_per_wom_5y sort ind_id //Save a temp file for merging with HL: save "$path_out/vnm14_BH.dta", replace ******************************************************************************** *** Step 1.2 WM - WOMEN's RECODE *** (All eligible females 14_-49 years in the household) ******************************************************************************** use "$path_in/wm.dta", clear rename _all, lower *** Generate individual unique key variable required for data merging *** hh1=cluster number; *** hh2=household number; *** ln=respondent's line number *gen ln=wm4 gen double ind_id = hh1*100000 + hh2*100 + ln format ind_id %20.0g label var ind_id "Individual ID" duplicates report ind_id gen women_WM =1 //Identification variable for observations in WM recode tab wb2, miss tab cm1 cm8, miss /*Women who has never ever given birth will not have information on child mortality*/ lookfor marital codebook mstatus ma6, tab (10) tab mstatus ma6, miss gen marital = 1 if mstatus == 3 & ma6==. //1: Never married replace marital = 2 if mstatus == 1 & ma6==. //2: Currently married replace marital = 3 if mstatus == 2 & ma6==1 //3: Widowed replace marital = 4 if mstatus == 2 & ma6==2 //4: Divorced replace marital = 5 if mstatus == 2 & ma6==3 //5: Separated/not living together label define lab_mar 1"never married" 2"currently married" 3"widowed" /// 4"divorced" 5"not living together" label values marital lab_mar label var marital "Marital status of household member" tab marital, miss tab ma6 marital, miss tab mstatus marital, miss //Retain relevant variables: keep wm7 cm1 cm8 cm9a cm9b ind_id women_WM marital order wm7 cm1 cm8 cm9a cm9b ind_id women_WM marital sort ind_id //Save a temp file for merging with HL: save "$path_out/vnm14_WM.dta", replace ******************************************************************************** *** Step 1.3 MN - MEN'S RECODE ***(All eligible man: 14_-49 years in the household) ******************************************************************************** ** no MN recode ** ******************************************************************************** *** Step 1.4 HH - HOUSEHOLD RECODE ***(All households interviewed) ******************************************************************************** use "$path_in/hh.dta", clear rename _all, lower *** Generate individual unique key variable required for data merging *** hh1=cluster number; *** hh2=household number; gen double hh_id = hh1*100 + hh2 format hh_id %20.0g lab var hh_id "Household ID" duplicates report hh_id //Save a temp file for merging with HL: save "$path_out/vnm14_HH.dta", replace ******************************************************************************** *** Step 1.5 HL - HOUSEHOLD MEMBER ******************************************************************************** use "$path_in/hl.dta", clear rename _all, lower gen cty = "Viet Nam" gen ccty = "VNM" gen year = "2014" gen survey = "MICS" gen ccnum = 704 gen country = "Viet Nam" gen countrycode = "VNM" *** Generate a household unique key variable at the household level using: ***hh1=cluster number ***hh2=household number gen double hh_id = hh1*100 + hh2 format hh_id %20.0g label var hh_id "Household ID" *** Generate individual unique key variable required for data merging using: *** hh1=cluster number; *** hh2=household number; *** hl1=respondent's line number. gen double ind_id = hh1*100000 + hh2*100 + hl1 format ind_id %20.0g label var ind_id "Individual ID" duplicates report ind_id sort ind_id ******************************************************************************** *** Step 1.6 DATA MERGING ******************************************************************************** *** Merging BR Recode ***************************************** merge 1:1 ind_id using "$path_out/vnm14_BH.dta" drop _merge erase "$path_out/vnm14_BH.dta" *** Merging WM Recode ***************************************** merge 1:1 ind_id using "$path_out/vnm14_WM.dta" tab hl7, miss gen temp = (hl7>0) tab women_WM temp, miss col tab wm7 if temp==1 & women_WM==., miss //Total of eligible women not interviewed drop temp drop _merge erase "$path_out/vnm14_WM.dta" *** Merging HH Recode ***************************************** merge m:1 hh_id using "$path_out/vnm14_HH.dta" tab hh9 if _m==2 drop if _merge==2 //Drop households that were not interviewed drop _merge erase "$path_out/vnm14_HH.dta" ******************************************************************************** *** Step 1.7 CONTROL VARIABLES ******************************************************************************** /* Households are identified as having 'no eligible' members if there are no applicable population, that is, children 0-5 years, adult women 14_-49 years or men 14_-49 years. These households will not have information on relevant indicators of health. As such, these households are considered as non-deprived in those relevant indicators.*/ *** No Eligible Women 14_-49 years ***************************************** gen fem_eligible = (hl7>0) if hl7!=. bys hh_id: egen hh_n_fem_eligible = sum(fem_eligible) //Number of eligible women for interview in the hh gen no_fem_eligible = (hh_n_fem_eligible==0) //Takes value 1 if the household had no eligible females for an interview lab var no_fem_eligible "Household has no eligible women" tab no_fem_eligible, miss sort hh_id ******************************************************************************** *** Step 1.8 RENAMING DEMOGRAPHIC VARIABLES *** ******************************************************************************** //Sample weight clonevar weight = hhweight label var weight "Sample weight" //Area: urban or rural desc hh6 clonevar area = hh6 replace area=0 if area==2 label define lab_area 1 "urban" 0 "rural" label values area lab_area label var area "Area: urban-rural" //Relationship to the head of household desc hl3 clonevar relationship = hl3 codebook relationship, tab (20) recode relationship (1=1)(2=2)(3=3)(13=3)(4/12=4)(14=6)(96=5)(98/99=.) /*Please ensure recoding follows these 6 broad categories: 1"head" 2"spouse" 3"child" 4"extended family" 5"not related" 6"maid" */ label define lab_rel 1"head" 2"spouse" 3"child" 4"extended family" /// 5"not related" 6"maid" label values relationship lab_rel label var relationship "Relationship to the head of household" tab hl3 relationship, miss //Sex of household member codebook hl4 clonevar sex = hl4 label var sex "Sex of household member" //Age of household member codebook hl6, tab (100) clonevar age = hl6 replace age = . if age>=98 label var age "Age of household member" //Age group recode age (0/4 = 1 "0-4")(5/9 = 2 "5-9")(10/14 = 3 "10-14") /// (14/17 = 4 "14-17")(18/59 = 5 "18-59")(60/max=6 "60+"), gen(agec7) lab var agec7 "age groups (7 groups)" recode age (0/9 = 1 "0-9") (10/17 = 2 "10-17")(18/59 = 3 "18-59") /// (60/max=4 "60+"), gen(agec4) lab var agec4 "age groups (4 groups)" //Total number of de jure hh members in the household gen member = 1 bysort hh_id: egen hhsize = sum(member) label var hhsize "Household size" tab hhsize, miss compare hhsize hh11 drop member //Subnational region //Representative at the 37 subnational states lookfor region lookfor state codebook hh7, tab (100) decode hh7, gen(temp) replace temp = proper(temp) encode temp, gen(region) lab var region "Region for subnational decomposition" tab hh7 region, miss drop temp ******************************************************************************** *** Step 2 Data preparation *** *** Standardization of the 10 Global MPI indicators *** Identification of non-deprived & deprived individuals ******************************************************************************** ******************************************************************************** *** Step 2.1 Years of Schooling *** ******************************************************************************** /* Basic education in Viet Nam consists of 9 years in total: 6 years of compulsory primary and 3 years of compulsory junior secondary. An additional 3 years of senior secondary education is not compulsory. The admission age to compulsory education is 6 years. Preschool education takes place from age 3-5 years. Primary education takes place from age 6-11+ (grades 1-3, lower basic education; grades 4-6, middle basic education). Junior secondary education takes place from age 12-14 (grades 7-9). Senior secondary education takes place from age 14_-18 (grades 10-12). Reference: http://www.ibe.unesco.org/fileadmin/user_upload/Publications/WDE/2010/pdf-versions/Viet Nam.pdf */ tab ed4b ed4a, miss codebook ed4b ed4a ed3, tab (30) tab age ed6a if ed5==1, miss //Check: For those currently in school, check their level of schooling /*In the case of Viet Nam MICS 2014, there is inconsistency such as individuals showing too much schooling given their age. This issue will be addressed in the subsequent set of commands, that is, cleaning the inconsistencies*/ gen eduhighyear=ed4b if ed4a==1 & ed4b<=5 replace eduhighyear=ed4b if ed4a==2 & ed4b>=6 & ed4b<=9 replace eduhighyear=ed4b if ed4a==3 & ed4b>=10 & ed4b<=12 replace eduhighyear=14 if ed4a==4 | ed4a==5 replace eduhighyear=0 if ed4a==0 | ed3==2 replace eduhighyear=5 if ed4a==2 & ed4b==0 replace eduhighyear=9 if ed4a==3 & ed4b==0 lab var eduhighyear "Highest year of education completed" replace eduhighyear=9 if ed4a==3 & eduhighyear==. /* this line imputes the minumun grade of 9 years for those in upper econdary who did not report the number of years in this level */ *** Cleaning inconsistencies replace eduhighyear = 0 if age<10 /*The variable "eduhighyear" was replaced with a '0' given that the criteria for this indicator is household member aged 10 years or older */ *** Now we create the years of schooling tab eduhighyear ed4a, miss clonevar eduyears = eduhighyear *** Checking for further inconsistencies replace eduyears = . if age<=eduyears & age>0 /*There are cases in which the years of schooling are greater than the age of the individual. This is clearly a mistake in the data. Please check whether this is the case and correct when necessary */ replace eduyears = 0 if age< 10 /*The variable "eduyears" was replaced with a '0' given that the criteria for this indicator is household member aged 10 years or older */ lab var eduyears "Total number of years of education accomplished" /*A control variable is created on whether there is information on years of education for at least 2/3 of the household members aged 10 years and older */ gen temp = 1 if eduyears!=. & age>=10 & age!=. bysort hh_id: egen no_missing_edu = sum(temp) /*Total household members who are 10 years and older with no missing years of education */ gen temp2 = 1 if age>=10 & age!=. bysort hh_id: egen hhs = sum(temp2) /*Total number of household members who are 10 years and older */ replace no_missing_edu = no_missing_edu/hhs replace no_missing_edu = (no_missing_edu>=2/3) /*Identify whether there is information on years of education for at least 2/3 of the household members aged 10 years and older */ tab no_missing_edu, miss label var no_missing_edu "No missing edu for at least 2/3 of the HH members aged 10 years & older" drop temp temp2 hhs /*The entire household is considered deprived if no household member aged 10 years or older has completed SIX years of schooling. */ gen years_edu6 = (eduyears>=6) /* The years of schooling indicator takes a value of "1" if at least someone in the hh has reported 6 years of education or more */ replace years_edu6 = . if eduyears==. bysort hh_id: egen hh_years_edu6_1 = max(years_edu6) gen hh_years_edu6 = (hh_years_edu6_1==1) replace hh_years_edu6 = . if hh_years_edu6_1==. replace hh_years_edu6 = . if hh_years_edu6==0 & no_missing_edu==0 lab var hh_years_edu6 "Household has at least one member with 6 years of edu" ******************************************************************************** *** Step 2.2 Child School Attendance *** ******************************************************************************** codebook ed5, tab (10) gen attendance = . replace attendance = 1 if ed5==1 //Replace attendance with '1' if currently attending school replace attendance = 0 if ed5==2 //Replace attendance with '0' if currently not attending school replace attendance = 0 if ed3==2 //Replace attendance with '0' if never ever attended school *replace attendance = 0 if ed3==1 & ed4a==4 //Replace attendance with '0' if attended school but informal schooling //informal education is not a category in Viet Nam tab age ed5, miss //Check individuals who are not of school age replace attendance = 0 if age<5 | age>24 //Replace attendance with '0' for individuals who are not of school age tab attendance, miss label define lab_attend 1 "currently attending" 0 "not currently attending" label values attendance lab_attend label var attendance "Attended school during current school year" /*The entire household is considered deprived if any school-aged child is not attending school up to class 8. */ gen child_schoolage = (schage>=6 & schage<=14) /* Note: In Viet Nam, the official school entrance age is 6 years. So, age range is 6-14 (=6+8). Source: "http://data.uis.unesco.org/?ReportId=163" Go to Education>Education>System>Official entrance age to primary education. Look at the starting age and add 8. */ /*A control variable is created on whether there is no information on school attendance for at least 2/3 of the school age children */ count if child_schoolage==1 & attendance==. //Understand how many eligible school aged children are not attending school gen temp = 1 if child_schoolage==1 & attendance!=. bysort hh_id: egen no_missing_atten = sum(temp) /*Total school age children with no missing information on school attendance */ gen temp2 = 1 if child_schoolage==1 bysort hh_id: egen hhs = sum(temp2) //Total number of household members who are of school age replace no_missing_atten = no_missing_atten/hhs replace no_missing_atten = (no_missing_atten>=2/3) /*Identify whether there is missing information on school attendance for more than 2/3 of the school age children */ tab no_missing_atten, miss label var no_missing_atten "No missing school attendance for at least 2/3 of the school aged children" drop temp temp2 hhs bysort hh_id: egen hh_children_schoolage = sum(child_schoolage) replace hh_children_schoolage = (hh_children_schoolage>0) //Control variable: //It takes value 1 if the household has children in school age lab var hh_children_schoolage "Household has children in school age" gen child_not_atten = (attendance==0) if child_schoolage==1 replace child_not_atten = . if attendance==. & child_schoolage==1 bysort hh_id: egen any_child_not_atten = max(child_not_atten) gen hh_child_atten = (any_child_not_atten==0) replace hh_child_atten = . if any_child_not_atten==. replace hh_child_atten = 1 if hh_children_schoolage==0 replace hh_child_atten = . if hh_child_atten==1 & no_missing_atten==0 /*If the household has been intially identified as non-deprived, but has missing school attendance for at least 2/3 of the school aged children, then we replace this household with a value of '.' because there is insufficient information to conclusively conclude that the household is not deprived */ lab var hh_child_atten "Household has all school age children up to class 8 in school" tab hh_child_atten, miss /*Note: The indicator takes value 1 if ALL children in school age are attending school and 0 if there is at least one child not attending. Households with no children receive a value of 1 as non-deprived. The indicator has a missing value only when there are all missing values on children attendance in households that have children in school age. */ ******************************************************************************** *** Step 2.3 Nutrition *** ******************************************************************************** ******************************************************************************** *** Step 2.3a Child Nutrition *** ******************************************************************************** *** Child Underweight Indicator *** ************************************************************************ ******************************************************************************** *** Step 2.3b Household Nutrition Indicator *** ******************************************************************************** /* The indicator takes value 1 if there is no children under 5 underweight or stunted. It also takes value 1 for the households that have no eligible children. The indicator takes value missing "." only if all eligible children have missing information in their respective nutrition variable. */ ************************************************************************ gen hh_nutrition_uw_st = . lab var hh_nutrition_uw_st "Household has no child underweight or stunted" ******************************************************************************** *** Step 2.4 Child Mortality *** ******************************************************************************** codebook cm9a cm9b *codebook cm9a cm9b //cm9a or mcm9a: number of sons who have died //cm9b or mcm9b: number of daughters who have died egen temp_f = rowtotal(cm9a cm9b), missing //Total child mortality reported by eligible women replace temp_f = 0 if (cm1==1 & cm8==2) | cm1==2 /*Assign a value of "0" for: - all eligible women who have ever gave birth but reported no child death - all eligible women who never ever gave birth */ replace temp_f = 0 if no_fem_eligible==1 /*Assign a value of "0" for: - individuals living in households that have non-eligible women */ bysort hh_id: egen child_mortality_f = sum(temp_f), missing lab var child_mortality_f "Occurrence of child mortality reported by women" tab child_mortality_f, miss drop temp_f egen child_mortality = rowmax(child_mortality_f) lab var child_mortality "Total child mortality within household reported by women" tab child_mortality, miss gen hh_mortality = (child_mortality==0) replace hh_mortality = . if child_mortality==. tab hh_mortality, miss lab var hh_mortality "Household had no child mortality any time" /*Deprived if any children died in the household in the last 5 years from the survey year */ ************************************************************************ tab child_died_per_wom_5y, miss /* The 'child_died_per_wom_5y' variable was constructed in Step 1.2 using information from individual women who ever gave birth in the BR file. The missing values represent eligible woman who have never ever given birth and so are not present in the BR file. But these 'missing women' may be living in households where there are other women with child mortality information from the BR file. So at this stage, it is important that we aggregate the information that was obtained from the BR file at the household level. This ensures that women who were not present in the BR file is assigned with a value, following the information provided by other women in the household.*/ replace child_died_per_wom_5y = 0 if cm1==2 /*Assign a value of "0" for: - all eligible women who never ever gave birth */ replace child_died_per_wom_5y = 0 if no_fem_eligible==1 /*Assign a value of "0" for: - individuals living in households that have non-eligible women */ bysort hh_id: egen child_mortality_5y = sum(child_died_per_wom_5y), missing replace child_mortality_5y = 0 if child_mortality_5y==. & child_mortality==0 /*Replace all households as 0 death if women has missing value and men reported no death in those households */ label var child_mortality_5y "Total child mortality within household past 5 years reported by women" tab child_mortality_5y, miss /* The new standard MPI indicator takes a value of "1" if eligible women within the household reported no child mortality or if any child died longer than 5 years from the survey year. The indicator takes a value of "0" if women in the household reported any child mortality in the last 5 years from the survey year. Households were replaced with a value of "1" if eligible men within the household reported no child mortality in the absence of information from women. The indicator takes a missing value if there was missing information on reported death from eligible individuals. */ gen hh_mortality_5y = (child_mortality_5y==0) replace hh_mortality_5y = . if child_mortality_5y==. tab hh_mortality_5y, miss lab var hh_mortality_5y "Household had no child mortality in the last 5 years" ******************************************************************************** *** Step 2.5 Electricity *** ******************************************************************************** /*Members of the household are considered deprived if the household has no electricity */ clonevar electricity = hc8a codebook electricity, tab (9) replace electricity = 0 if electricity==2 //0=no; 1=yes replace electricity = . if electricity==9 label var electricity "Household has electricity" ******************************************************************************** *** Step 2.6 Sanitation *** ******************************************************************************** /*Members of the household are considered deprived if the household's sanitation facility is not improved, according to MDG guidelines, or it is improved but shared with other household. We also checked the country reports on how the sanitation categories have been grouped. In cases of mismatch, we have followed the country report */ lookfor toilet clonevar toilet = ws8 codebook toilet, tab(30) codebook ws9, tab(30) clonevar shared_toilet = ws9 recode shared_toilet (2=0) (9=.) tab ws9 shared_toilet, miss nol //0=no;1=yes;.=missing gen toilet_mdg = 0 if ws8==23 | ws8==41 | ws8==51 | ws8==95 | ws8==96 replace toilet_mdg = 1 if ws8==11 | ws8==12 | ws8==13 | ws8==14 | ws8==15 | ws8==21 | ws8==22 | ws8==31 replace toilet_mdg = 0 if ws9==1 /*shared*/ /*Household is assigned a value of '0' if it uses improved sanitation but shares toilet with other households */ lab var toilet_mdg "Household has improved sanitation with MDG Standards" tab toilet toilet_mdg, miss /* Follows MICS report (page 122) Flush to piped sewer system | 429 1.09 1.09 11 y Flush to septic tank | 25,220 64.04 65.13 12 y Flush to pit (latrine) | 1,128 2.86 68.00 13 y Flush to somewhere else | 318 0.81 68.80 14 y Flush to unknown place / Not sure / DK | 20 0.05 68.85 15 y Ventilated Improved Pit latrine (VIP) | 140 0.36 69.21 21 y Pit latrine with slab | 2,455 6.23 75.44 22 y Pit latrine without slab / Open pit | 1,662 4.22 79.66 23 n Composting toilet | 2,292 5.82 85.49 31 y Bucket | 23 0.06 85.54 41 n Hanging toilet, Hanging latrine | 2,300 5.84 91.38 51 n No facility, Bush, Field | 3,173 8.06 99.44 95 n Other | 220 0.56 100.00 96 n ----------------------------------------+----------------------------------- Total | 39,380 100.00 */ ******************************************************************************** *** Step 2.7 Drinking Water *** ******************************************************************************** /*Members of the household are considered deprived if the household does not have access to safe drinking water according to MDG guidelines, or safe drinking water is more than a 30-minute walk from home roundtrip. */ clonevar water = ws1 clonevar timetowater = ws4 codebook water, tab(100) clonevar ndwater = ws2 //Non-drinking water tab ws2 if water==91 /*Because the quality of bottled water is not known, households using bottled water for drinking are classified as using an improved or unimproved source according to their water source for non-drinking activities such as cooking and hand washing. However, it is important to note that households using bottled water for drinking are classified as unimproved source if this is explicitly mentioned in the country report. */ /* Follows MICS report page 112: Piped into dwelling | 9,958 25.29 25.29 11 y Piped into compound, yard or plot | 747 1.90 27.18 12 y Piped to neighbour | 79 0.20 27.38 13 y Public tap / standpipe | 21 0.05 27.44 14 y Tube well, Borehole | 6,496 16.50 43.93 21 y Protected well | 6,492 16.49 60.42 31 y Unprotected well | 1,264 3.21 63.63 32 n Protected spring | 2,220 5.64 69.27 41 y Unprotected spring | 1,148 2.92 72.18 42 n Rainwater collection | 4,120 10.46 82.64 51 y Surface water (river, stream, dam, lake | 384 0.98 83.62 81 n Bottled water | 6,423 16.31 99.93 91 y/n Other | 28 0.07 100.00 96 n ----------------------------------------+----------------------------------- Total | 39,380 100.00 */ gen water_mdg = 1 if ws1==11 | ws1==12 | ws1==13 | ws1==14 | ws1==21 | ws1==31 | ws1==41 | ws1==51 | (ws1==91 & (ws2==11 | ws2==12 | ws2==13 | ws2==14 | ws2==21 | ws2==31 | ws2==41 | ws2==51 | ws2==99)) replace water_mdg = 0 if ws1==32 | ws1==42 | ws1==81 | ws1==96 | (ws1==91 & (ws2==32 | ws2==42 | ws2==61 | ws2==71 | ws2==81 | ws2==96)) replace water_mdg = 0 if timetowater>=30 & timetowater!=. & timetowater!=998 & timetowater!=999 *replace water_mdg = . if water==. | water==99 lab var water_mdg "Household has drinking water with MDG standards (considering distance)" tab water water_mdg, miss ******************************************************************************** *** Step 2.8 Housing *** ******************************************************************************** /* Members of the household are considered deprived if the household has a dirt, sand or dung floor */ clonevar floor = hc3 codebook floor, tab(99) gen floor_imp = 1 replace floor_imp = 0 if floor<=12 | floor==96 replace floor_imp = . if floor==. | floor==99 lab var floor_imp "Household has floor that it is not earth/sand/dung" tab floor floor_imp, miss /* Members of the household are considered deprived if the household has wall made of natural or rudimentary materials */ clonevar wall = hc5 codebook wall, tab(99) gen wall_imp = 1 replace wall_imp = 0 if wall<=28 | wall==96 replace wall_imp = . if wall==. | wall==99 lab var wall_imp "Household has wall that it is not of low quality materials" tab wall wall_imp, miss /* Members of the household are considered deprived if the household has roof made of natural or rudimentary materials */ clonevar roof = hc4 codebook roof, tab(99) gen roof_imp = 1 replace roof_imp = 0 if roof<=25 | roof==96 replace roof_imp = . if roof==. | roof==99 lab var roof_imp "Household has roof that it is not of low quality materials" tab roof roof_imp, miss /*Household is deprived in housing if the roof, floor OR walls uses low quality materials.*/ gen housing_1 = 1 replace housing_1 = 0 if floor_imp==0 | wall_imp==0 | roof_imp==0 replace housing_1 = . if floor_imp==. & wall_imp==. & roof_imp==. lab var housing_1 "Household has roof, floor & walls that it is not low quality material" tab housing_1, miss ******************************************************************************** *** Step 2.9 Cooking Fuel *** ******************************************************************************** /* Members of the household are considered deprived if the household cooks with solid fuels, wood, charcoal, crop residues or dung. "Indicators for Monitoring the Millennium Development Goals", p. 63 */ clonevar cookingfuel = hc6 codebook cookingfuel, tab(99) gen cooking_mdg = 1 replace cooking_mdg = 0 if cookingfuel>5 & cookingfuel<95 replace cooking_mdg = . if cookingfuel==. | cookingfuel==99 lab var cooking_mdg "Household has cooking fuel by MDG standards" /* Deprived if: "coal/lignite", "charcoal", "wood", "straw/shrubs/grass" "agricultural crop", "animal dung" */ tab cookingfuel cooking_mdg, miss ******************************************************************************** *** Step 2.10 Assets ownership *** ******************************************************************************** /* Members of the household are considered deprived if the household does not own more than one of: radio, TV, telephone, bike, motorbike or refrigerator and does not own a car or truck. */ //Check that for standard assets in living standards: "no"==0 and yes=="1" codebook hc8c hc8b hc8d hc9b hc8e hc9c hc8o hc8p hc9d hc8j //hc8q not available. clonevar television = hc8c gen bw_television = . clonevar radio = hc8b clonevar telephone = hc8d clonevar mobiletelephone = hc9b clonevar refrigerator = hc8e clonevar car = hc8p clonevar bicycle = hc9c clonevar motorbike = hc9d clonevar computer = hc8j gen animal_cart = . /* no animal cart */ foreach var in television radio telephone mobiletelephone refrigerator /// car bicycle motorbike computer animal_cart { replace `var' = 0 if `var'==2 replace `var' = . if `var'==9 | `var'==99 | `var'==8 | `var'==98 } *** //Group telephone and mobiletelephone as a single variable replace telephone=1 if telephone==0 & mobiletelephone==1 replace telephone=1 if telephone==. & mobiletelephone==1 /* Members of the household are considered deprived in assets if the household does not own more than one of: radio, TV, telephone, bike, motorbike, refrigerator, computer or animal_cart and does not own a car or truck.*/ egen n_small_assets2 = rowtotal(television radio telephone refrigerator bicycle motorbike computer animal_cart), missing lab var n_small_assets2 "Household Number of Small Assets Owned" gen hh_assets2 = (car==1 | n_small_assets2 > 1) replace hh_assets2 = . if car==. & n_small_assets2==. lab var hh_assets2 "Household Asset Ownership: HH has car or more than 1 small assets incl computer & animal cart" ******************************************************************************** *** Step 2.11 Rename and keep variables for MPI calculation ******************************************************************************** //Retain data on sampling design: desc psu stratum clonevar strata = stratum //Retain year, month & date of interview: desc hh5y hh5m hh5d clonevar year_interview = hh5y clonevar month_interview = hh5m clonevar date_interview = hh5d //Generate presence of subsample gen subsample = . *** Rename key global MPI indicators for estimation *** recode hh_mortality_5y (0=1)(1=0) , gen(d_cm) recode hh_nutrition_uw_st (0=1)(1=0) , gen(d_nutr) recode hh_child_atten (0=1)(1=0) , gen(d_satt) recode hh_years_edu6 (0=1)(1=0) , gen(d_educ) recode electricity (0=1)(1=0) , gen(d_elct) recode water_mdg (0=1)(1=0) , gen(d_wtr) recode toilet_mdg (0=1)(1=0) , gen(d_sani) recode housing_1 (0=1)(1=0) , gen(d_hsg) recode cooking_mdg (0=1)(1=0) , gen(d_ckfl) recode hh_assets2 (0=1)(1=0) , gen(d_asst) *** Keep selected variables for global MPI estimation *** keep hh_id ind_id ccty ccnum cty survey year subsample /// strata psu weight area relationship sex age agec7 agec4 marital hhsize /// region year_interview month_interview date_interview /// d_cm d_nutr d_satt d_educ d_elct d_wtr d_sani d_hsg d_ckfl d_asst hh_mortality_5y hh_nutrition_uw_st hh_child_atten hh_years_edu6 electricity water_mdg toilet_mdg housing_1 cooking_mdg hh_assets2 country countrycode order hh_id ind_id ccty ccnum country countrycode cty survey year subsample /// strata psu weight area relationship sex age agec7 agec4 marital hhsize /// region year_interview month_interview date_interview /// d_cm d_nutr d_satt d_educ d_elct d_wtr d_sani d_hsg d_ckfl d_asst hh_mortality_5y hh_nutrition_uw_st hh_child_atten hh_years_edu6 electricity water_mdg toilet_mdg housing_1 cooking_mdg hh_assets2 *** Sort, compress and save data for estimation *** sort ind_id compress save "$path_out/vnm_mics14_pov.dta", replace log close ******************************************************************************** *** MPI Calculation (TTD file) ******************************************************************************** **SELECT COUNTRY POV FILE RUN ON LOOP FOR MORE COUNTRIES use "$path_out\vnm_mics14_pov.dta", clear ******************************************************************************** *** Define Sample Weight and total population *** ******************************************************************************** gen sample_weight = weight /* change to weight if MICS*/ ******************************************************************************** *** List of the 10 indicators included in the MPI *** ******************************************************************************** gen edu_1 = hh_years_edu6 gen atten_1 = hh_child_atten gen cm_1 = hh_mortality_5y /* change countries with no child mortality 5 year to child mortality ever*/ gen nutri_1 = hh_nutrition_uw_st gen elec_1 = electricity gen toilet_1 = toilet_mdg gen water_1 = water_mdg gen house_1 = housing_1 gen fuel_1 = cooking_mdg gen asset_1 = hh_assets2 global est_1 edu_1 atten_1 cm_1 elec_1 toilet_1 water_1 house_1 fuel_1 asset_1 ******************************************************************************** *** List of sample without missing values *** ******************************************************************************** foreach j of numlist 1 { gen sample_`j' = (edu_`j'!=. & atten_`j'!=. & cm_`j'!=. & elec_`j'!=. & toilet_`j'!=. & water_`j'!=. & house_`j'!=. & fuel_`j'!=. & asset_`j'!=.) replace sample_`j' = . if subsample==0 /* Note: If the anthropometric data was collected from a subsample of the total population that was sampled, then the final analysis only includes the subsample population. */ *** Percentage sample after dropping missing values *** sum sample_`j' [iw = sample_weight] gen per_sample_weighted_`j' = r(mean) sum sample_`j' gen per_sample_`j' = r(mean) } *** ******************************************************************************** *** Define deprivation matrix 'g0' *** which takes values 1 if individual is deprived in the particular *** indicator according to deprivation cutoff z as defined during step 2 *** ******************************************************************************** foreach j of numlist 1 { foreach var in ${est_`j'} { gen g0`j'_`var' = 1 if `var'==0 replace g0`j'_`var' = 0 if `var'==1 } } *** Raw Headcount Ratios foreach j of numlist 1 { foreach var in ${est_`j'} { sum g0`j'_`var' if sample_`j'==1 [iw = sample_weight] gen raw`j'_`var' = r(mean)*100 lab var raw`j'_`var' "Raw Headcount: Percentage of people who are deprived in `var'" } } ******************************************************************************** *** Define vector 'w' of dimensional and indicator weight *** ******************************************************************************** /*If survey lacks one or more indicators, weights need to be adjusted within / each dimension such that each dimension weighs 1/3 and the indicator weights add up to one (100%). CHECK COUNTRY FILE*/ foreach j of numlist 1 { // DIMENSION EDUCATION foreach var in edu_`j' atten_`j' { capture drop w`j'_`var' gen w`j'_`var' = 1/6 } // DIMENSION HEALTH foreach var in cm_`j' { capture drop w`j'_`var' gen w`j'_`var' = 1/3 } // DIMENSION LIVING STANDARD foreach var in elec_`j' toilet_`j' water_`j' house_`j' fuel_`j' asset_`j' { capture drop w`j'_`var' gen w`j'_`var' = 1/18 } } ******************************************************************************** *** Generate the weighted deprivation matrix 'w' * 'g0' ******************************************************************************** foreach j of numlist 1 { foreach var in ${est_`j'} { gen w`j'_g0_`var' = w`j'_`var' * g0`j'_`var' replace w`j'_g0_`var' = . if sample_`j'!=1 /*The estimation is based only on observations that have non-missing values for all variables in varlist_pov*/ } } ******************************************************************************** *** Generate the vector of individual weighted deprivation count 'c' ******************************************************************************** foreach j of numlist 1 { egen c_vector_`j' = rowtotal(w`j'_g0_*) replace c_vector_`j' = . if sample_`j'!=1 *drop w_g0_* } ******************************************************************************** *** Identification step according to poverty cutoff k (20 33.33 50) *** ******************************************************************************** foreach j of numlist 1 { foreach k of numlist 20 33 50 { gen multidimensionally_poor_`j'_`k' = (c_vector_`j'>=`k'/100) replace multidimensionally_poor_`j'_`k' = . if sample_`j'!=1 //Takes value 1 if individual is multidimensional poor } } ******************************************************************************** *** Generate the censored vector of individual weighted deprivation count 'c(k)' ******************************************************************************** foreach j of numlist 1 { foreach k of numlist 20 33 50 { gen c_censured_vector_`j'_`k' = c_vector_`j' replace c_censured_vector_`j'_`k' = 0 if multidimensionally_poor_`j'_`k'==0 } //Provide a score of zero if a person is not poor } * ******************************************************************************** *** Define censored deprivation matrix 'g0(k)' *** ******************************************************************************** foreach j of numlist 1 { foreach var in ${est_`j'} { gen g0`j'_k_`var' = g0`j'_`var' replace g0`j'_k_`var' = 0 if multidimensionally_poor_`j'_33==0 replace g0`j'_k_`var' = . if sample_`j'!=1 } } ******************************************************************************** *** Generates Multidimensional Poverty Index (MPI), *** Headcount (H) and Intensity of Poverty (A) *** ******************************************************************************** *** Multidimensional Poverty Index (MPI) *** foreach j of numlist 1 { foreach k of numlist 20 33 50 { sum c_censured_vector_`j'_`k' [iw = sample_weight] if sample_`j'==1 gen MPI_`j'_`k' = r(mean) lab var MPI_`j'_`k' "MPI with k=`k'" } sum c_censured_vector_`j'_33 [iw = sample_weight] if sample_`j'==1 gen MPI_`j' = r(mean) lab var MPI_`j' "`j' Multidimensional Poverty Index (MPI = H*A): Range 0 to 1" *** Headcount (H) *** sum multidimensionally_poor_`j'_33 [iw = sample_weight] if sample_`j'==1 gen H_`j' = r(mean)*100 lab var H_`j' "`j' Headcount ratio: % Population in multidimensional poverty (H)" *** Intensity of Poverty (A) *** sum c_censured_vector_`j'_33 [iw = sample_weight] if multidimensionally_poor_`j'_33==1 & sample_`j'==1 gen A_`j' = r(mean)*100 lab var A_`j' "`j' Intensity of deprivation among the poor (A): Average % of weighted deprivations" *** Population vulnerable to poverty (who experience 20-32.9% intensity of deprivations) *** gen temp = 0 replace temp = 1 if c_vector_`j'>=0.2 & c_vector_`j'<0.3332 replace temp = . if sample_`j'!=1 sum temp [iw = sample_weight] gen vulnerable_`j' = r(mean)*100 lab var vulnerable_`j' "`j' % Population vulnerable to poverty (who experience 20-32.9% intensity of deprivations)" drop temp *** Population in severe poverty (with intensity 50% or higher) *** gen temp = 0 replace temp = 1 if c_vector_`j'>0.49 replace temp = . if sample_`j'!=1 sum temp [iw = sample_weight] gen severe_`j' = r(mean)*100 lab var severe_`j' "`j' % Population in severe poverty (with intensity 50% or higher)" drop temp } * *** Censored Headcount *** foreach j of numlist 1 { foreach var in ${est_`j'} { sum g0`j'_k_`var' [iw = sample_weight] if sample_`j'==1 gen cen`j'_`var' = r(mean)*100 lab var cen`j'_`var' "Censored Headcount: Percentage of people who are poor and deprived in `var'" } } *** Dimensional Contribution *** foreach j of numlist 1 { foreach var in ${est_`j'} { gen cont`j'_`var' = (w`j'_`var' * cen`j'_`var')/MPI_`j' if sample_`j'==1 lab var cont`j'_`var' "% Contribution in MPI of indicator..." } } *** Prepare results to export *** keep country year survey per_sample_weighted* per_sample* MPI* H* A* vulnerable* severe* raw* cen* cont* gen temp = (_n) keep if temp==1 drop temp order MPI_1 H_1 A_1 vulnerable_1 severe_1 cont1_cm_1 cont1_edu_1 cont1_atten_1 cont1_fuel_1 cont1_toilet_1 cont1_water_1 cont1_elec_1 cont1_house_1 cont1_asset_1 per_sample_1 per_sample_weighted_1 codebook, compact clear