******************************************************************************** /* Citation: Oxford Poverty and Human Development Initiative (OPHI), University of Oxford. 2020 Global Multidimensional Poverty Index - Papua New Guinea DHS 2016-2018 [STATA do-file]. Available from OPHI website: http://ophi.org.uk/ For further queries, contact: ophi@qeh.ox.ac.uk */ ******************************************************************************** clear all set more off set maxvar 10000 set mem 500m *** Working Folder Path *** global path_in "../rdta/Papua New Guinea DHS 2016-18" global path_out "cdta" global path_ado "ado" ******************************************************************************** *** PAPUA NEW GUINEA DHS 2016-18 *** ******************************************************************************** ******************************************************************************** *** Step 1: Data preparation *** Selecting variables from KR, BR, IR, & MR recode & merging with PR recode ******************************************************************************** /*Papua New Guinea DHS 2016-18 (p.2): In the subsample of households selected for the men's survey (every second household of the initial sample), children under 5 were weighed and measured to determine their nutritional status. It should be noted that although the survey collected anthropometric data, the results are not presented in the report due to data quality concerns (p.189 & p.341-2). As such, PNG has 9 of the 10 global MPI indicators, excluding nutrition. */ ******************************************************************************** *** Step 1.1 PR - INDIVIDUAL RECODE *** (Children under 5 years) ******************************************************************************** /*The purpose of step 1.1 is to compute anthropometric measures for children under 5 years. We did not construct the child nutrition data due to data quality issues of the anthropometric data that was collected. The child nutrition data was not analysed and presented in the DHS survey report for this reason (see explanation in page 189 of country survey report). */ ******************************************************************************** *** Step 1.2 BR - BIRTH RECODE *** (All females 15-49 years who ever gave birth) ******************************************************************************** /*The purpose of step 1.2 is to identify children under 18 who died in the last 5 years prior to the survey date.*/ use "$path_in/PGBR70FL.dta", clear *** Generate individual unique key variable required for data merging *** v001=cluster number; *** v002=household number; *** v003=respondent's line number gen double ind_id = v001*1000000 + v002*100 + v003 format ind_id %20.0g label var ind_id "Individual ID" desc b3 b7 gen date_death = b3 + b7 //Date of death = date of birth (b3) + age at death (b7) gen mdead_survey = v008 - date_death //Months dead from survey = date of interview (v008) - date of death gen ydead_survey = mdead_survey/12 //Years dead from survey gen age_death = b7 label var age_death "Age at death in months" tab age_death, miss //Age of death is reported in months codebook b5, tab (10) gen child_died = 1 if b5==0 replace child_died = 0 if b5==1 replace child_died = . if b5==. label define lab_died 1 "child has died" 0 "child is alive" label values child_died lab_died tab b5 child_died, miss /*NOTE: For each woman, sum the number of children who died and compare to the number of sons/daughters whom they reported have died */ bysort ind_id: egen tot_child_died = sum(child_died) egen tot_child_died_2 = rsum(v206 v207) //v206: sons who have died; v207: daughters who have died compare tot_child_died tot_child_died_2 //Papua New Guinea DHS 2016-18: these figures are identical. //Identify child under 18 mortality in the last 5 years gen child18_died = child_died replace child18_died=0 if age_death>=216 & age_death<. label define lab_u18died 1 "child u18 has died" 0 "child is alive/died but older" label values child18_died lab_u18died tab child18_died, miss bysort ind_id: egen tot_child18_died_5y=sum(child18_died) if ydead_survey<=5 /*Total number of children under 18 who died in the past 5 years prior to the interview date */ replace tot_child18_died_5y=0 if tot_child18_died_5y==. & tot_child_died>=0 & tot_child_died<. /*All children who are alive or who died longer than 5 years from the interview date are replaced as '0'*/ replace tot_child18_died_5y=. if child18_died==1 & ydead_survey==. //Replaced as '.' if there is no information on when the child died tab tot_child_died tot_child18_died_5y, miss bysort ind_id: egen childu18_died_per_wom_5y = max(tot_child18_died_5y) lab var childu18_died_per_wom_5y "Total child under 18 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_BR = 1 //Identification variable for observations in BR recode //Retain relevant variables keep ind_id women_BR childu18_died_per_wom_5y v222 order ind_id women_BR childu18_died_per_wom_5y v222 sort ind_id save "$path_out/PNG16-18_BR.dta", replace ******************************************************************************** *** Step 1.3 IR - WOMEN's RECODE *** (Eligible female 15-49 years in the household) ******************************************************************************** /*Note: The purpose of step 1.3 is to identify all deaths that are reported by eligible women.*/ use "$path_in/PGIR70FL.dta", clear *** Generate individual unique key variable required for data merging *** hv001=cluster number; *** hv002=household number; *** v003=respondent's line number gen double ind_id = v001*1000000 + v002*100 + v003 format ind_id %20.0g label var ind_id "Individual ID" duplicates report ind_id tab v012, miss codebook v201 v206 v207,tab (999) /*Papua New Guinea DHS 2016-18: Fertility and mortality were only collected from women 15-49 years.*/ gen women_IR=1 //Identification variable for observations in IR recode //Retain relevant variables: keep ind_id women_IR v003 v005 v012 v201 v206 v207 order ind_id women_IR v003 v005 v012 v201 v206 v207 sort ind_id save "$path_out/PNG16-18_IR.dta", replace ******************************************************************************** *** Step 1.4 PR - INDIVIDUAL RECODE *** (Girls 15-19 years in the household) ******************************************************************************** /*Note: The purpose of step 1.4 is to compute bmi-for-age for girls 15-19 years. */ /*Papua New Guinea DHS 2016-18: There is no anthropometric information for women. Hence the command lines under this section have been removed.*/ ******************************************************************************** *** Step 1.5 MR - MEN'S RECODE ***(Eligible man 15-54 years in the household) ******************************************************************************** /*Note: The purpose of step 1.5 is to identify all deaths that are reported by eligible men.*/ use "$path_in/PGMR70FL.dta", clear *** Generate individual unique key variable required for data merging *** mv001=cluster number; *** mv002=household number; *** mv003=respondent's line number gen double ind_id = mv001*1000000 + mv002*100 + mv003 format ind_id %20.0g label var ind_id "Individual ID" duplicates report ind_id tab mv012, miss codebook mv201 mv206 mv207,tab (999) /*Papua New Guinea DHS 2016-18: Fertility and mortality question was only collected from men 15-49 years.*/ gen men_MR=1 //Identification variable for observations in MR recode keep ind_id men_MR mv003 mv005 mv012 mv201 mv206 mv207 order ind_id men_MR mv003 mv005 mv012 mv201 mv206 mv207 sort ind_id save "$path_out/PNG16-18_MR.dta", replace ******************************************************************************** *** Step 1.6 PR - INDIVIDUAL RECODE *** (Boys 15-19 years in the household) ******************************************************************************** /*Note: The purpose of step 1.6 is to compute bmi-for-age for boys 15-19 years. */ /*Papua New Guinea DHS 2016-18: There is no anthropometric information for men. Hence the command lines under this section have been removed.*/ ******************************************************************************** *** Step 1.7 PR - HOUSEHOLD MEMBER'S RECODE ******************************************************************************** use "$path_in/PGPR70FL.dta", clear *** Generate a household unique key variable at the household level using: ***hv001=cluster number ***hv002=household number gen double hh_id = hv001*10000 + hv002 format hh_id %20.0g label var hh_id "Household ID" codebook hh_id *** Generate individual unique key variable required for data merging using: *** hv001=cluster number; *** hv002=household number; *** hvidx=respondent's line number. gen double ind_id = hv001*1000000 + hv002*100 + hvidx format ind_id %20.0g label var ind_id "Individual ID" codebook ind_id sort hh_id ind_id ******************************************************************************** *** Step 1.8 DATA MERGING ******************************************************************************** *** Merging BR Recode ***************************************** merge 1:1 ind_id using "$path_out/PNG16-18_BR.dta" drop _merge erase "$path_out/PNG16-18_BR.dta" *** Merging IR Recode ***************************************** merge 1:1 ind_id using "$path_out/PNG16-18_IR.dta" tab women_IR hv117, miss col tab ha65 if hv117==1 & women_IR ==., miss //Total number of eligible women not interviewed drop _merge erase "$path_out/PNG16-18_IR.dta" /*Check if the number of women in BR recode matches the number of those who provided birth history information in IR recode. */ count if women_BR==1 count if v201!=0 & v201!=. & women_IR==1 /*Check if the number of women in BR and IR recode who provided birth history information matches with the number of eligible women identified by hv117. */ count if hv117==1 count if women_BR==1 | v201==0 count if (women_BR==1 | v201==0) & hv117==1 tab v201 if hv117==1, miss tab v201 ha65 if hv117==1, miss /*Note: Some 16.38% eligible women did not provide information on their birth history. This will result in considerable missing value for the child mortality indicator that we will construct later */ *** Merging 15-19 years: girls ***************************************** //Anthropometric data was not collected for women gen age_month_g = . lab var age_month_g "Age in months, individuals 15-19 years (girls)" gen low_bmiage_g = . lab var low_bmiage_g "Teenage low bmi 2sd - WHO (girls)" gen low_bmiage_g_u = . lab var low_bmiage_g_u "Teenage very low bmi 3sd - WHO (girls)" *** Merging MR Recode ***************************************** merge 1:1 ind_id using "$path_out/PNG16-18_MR.dta" tab men_MR hv118 if hv027==1, miss col drop _merge erase "$path_out/PNG16-18_MR.dta" *** Merging 15-19 years: boys ***************************************** //Anthropometric data was not collected for men gen age_month_b = . lab var age_month_b "Age in months, individuals 15-19 years (boys)" gen low_bmiage_b = . lab var low_bmiage_b "Teenage low bmi 2sd - WHO (boys)" gen low_bmiage_b_u = . lab var low_bmiage_b_u "Teenage very low bmi 3sd - WHO (boys)" sort ind_id ******************************************************************************** *** Step 1.9 KEEP ONLY DE JURE HOUSEHOLD MEMBERS *** ******************************************************************************** /*The Global MPI is based on de jure (permanent) household members only. As such, non-usual residents will be excluded from the sample. */ clonevar resident = hv102 tab resident, miss label var resident "Permanent (de jure) household member" drop if resident!=1 tab resident, miss /*PNG DHS 2016-18: 1,317 individuals (1.57%) who were non-usual residents were dropped from the sample. */ ******************************************************************************** *** Step 1.10 KEEP HOUSEHOLDS SELECTED FOR ANTHROPOMETRIC SUBSAMPLE *** *** if relevant ******************************************************************************** /*In PNG 2016-18, a subsample of households (50%) were selected for anthropometric measure. However, we are not able to use the anthropometric data due to poor quality. As such, we retain the full sample of households for analyses, since our work excludes nutrition . */ gen subsample = . label var subsample "Households selected as part of nutrition subsample" ******************************************************************************** *** Step 1.11 CONTROL VARIABLES ******************************************************************************** /* Households are identified as having 'no eligible' members if there are no applicable population, that is, children 0-5 years, adult women 15-49 years or men 15-49 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 15-49 years *** for adult nutrition indicator *********************************************** //Papua New Guinea DHS 2016-18 has no anthropometric data for adults. gen no_fem_nutri_eligible = . lab var no_fem_nutri_eligible "Household has no eligible women for anthropometric" *** No eligible women 15-49 years *** for child mortality indicator ***************************************** gen fem_eligible = (hv117==1) bysort 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 women for an interview lab var no_fem_eligible "Household has no eligible women for interview" drop fem_eligible hh_n_fem_eligible tab no_fem_eligible, miss *** No eligible men 15-59 years *** for adult nutrition indicator (if relevant) *********************************************** //Papua New Guinea DHS 2016-18 has no anthropometric data for adults gen no_male_nutri_eligible = . lab var no_male_nutri_eligible "Household has no eligible men for anthropometric" *** No eligible men 15-49 years *** for child mortality indicator (if relevant) ***************************************** gen male_eligible = (hv118==1) bysort hh_id: egen hh_n_male_eligible = sum(male_eligible) //Number of eligible men for interview in the hh gen no_male_eligible = (hh_n_male_eligible==0) //Takes value 1 if the household had no eligible men for an interview lab var no_male_eligible "Household has no eligible man for interview" drop male_eligible hh_n_male_eligible tab no_male_eligible, miss *** No eligible children under 5 *** for child nutrition indicator ***************************************** /*Papua New Guinea DHS 2016-18: we did not use the anthropometric data for children under 5 due to data quality issues highlighted in the DHS report (p.189)*/ gen no_child_eligible = . lab var no_child_eligible "Household has no children eligible for anthropometric" *** No eligible women and men *** for adult nutrition indicator *********************************************** //Papua New Guinea DHS 2016-18 has no anthropometric data for adults. gen no_adults_eligible = . lab var no_adults_eligible "Household has no eligible women or men for anthropometrics" *** No Eligible Children and Women *** for child and women nutrition indicator *********************************************** //Papua New Guinea DHS 2016-18 has no anthropometric data for adults. gen no_child_fem_eligible = . lab var no_child_fem_eligible "Household has no children or women eligible for anthropometric" *** No Eligible Women, Men or Children *** for nutrition indicator *********************************************** //Papua New Guinea DHS 2016-18 has no anthropometric data for adults. gen no_eligibles = . lab var no_eligibles "Household has no eligible women, men, or children" sort hh_id ind_id ******************************************************************************** *** Step 1.12 RENAMING DEMOGRAPHIC VARIABLES *** ******************************************************************************** //Sample weight /*Note: DHS sample weight are calculated to six decimals but are presented in the standard recode files without the decimal point. As such, all DHS weights should be divided by 1,000,000 before applying the weights to calculation or analysis. */ desc hv005 clonevar weight = hv005 replace weight = weight/1000000 label var weight "Sample weight" //Area: urban or rural desc hv025 codebook hv025, tab (5) clonevar area = hv025 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" //Sex of household member codebook hv104 clonevar sex = hv104 label var sex "Sex of household member" //Age of household member codebook hv105, tab (100) clonevar age = hv105 replace age = . if age>=98 label var age "Age of household member" //Age groups recode age (0/4 = 1 "0-4")(5/9 = 2 "5-9")(10/14 = 3 "10-14") /// (15/17 = 4 "15-17")(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)" recode age (0/17 = 1 "0-17") (18/max = 2 "18+"), gen(agec2) lab var agec2 "age groups (2 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 drop member //Subnational region /*The sample for Papua New Guinea DHS 2016-18 was designed to provide estimates of key indicators for the country as a whole, for urban and rural areas separately, for the four regions and for each of the 22 provinces (p.2).*/ codebook hv024 shprovince, tab (99) decode shprovince, gen(temp) replace temp = proper(temp) encode temp, gen(region) drop temp codebook region, tab (99) label define lab_reg /// 1"Autonomous Region of Bougainville" /// 2"Central" /// 3"Chimbu" /// 4"East New Britain" /// 5"East Sepik" /// 6"Eastern Highlands" /// 7"Enga" 8"Gulf" 9"Hela" 10"Jiwaka" /// 11"Madang" 12"Manus" 13"Milne Bay" /// 14"Morobe" 15"National Capital District" /// 16"New Ireland" 17"Northern (Oro)" /// 18"Southern Highlands" /// 19"West New Britain" /// 20"West Sepik (Sandaun)" /// 21"Western Highlands" /// 22"Western" label values region lab_reg lab var region "Province for subnational decomposition" tab shprovince region, miss ******************************************************************************** *** Step 2 Data preparation *** *** Standardization of the 10 Global MPI indicators *** Identification of non-deprived & deprived individuals ******************************************************************************** ******************************************************************************** *** Step 2.1 Years of Schooling *** ******************************************************************************** codebook hv108, tab(30) clonevar eduyears = hv108 //Total number of years of education replace eduyears = . if eduyears>30 //Recode any unreasonable years of highest education as missing value tab hv108 hv106,miss codebook hv106, tab (99) count if eduyears==. & (hv106==2 | hv106==3) replace eduyears = 6 if eduyears==. & (hv106==2 | hv106==3) /* There are individuals with missing hv108 but according to hv106 we know they are in secondary or higher and so have completed 6 years in primary level. As such we assume they have completed at least 6 years of schooling.*/ replace eduyears = . if eduyears>=age & age>0 /*The variable "eduyears" was replaced with a '.' if total years of education was more than individual's age */ replace eduyears = 0 if age < 10 replace eduyears = 0 if (age==10 | age==11 | age==12) & eduyears < 6 /*The variable "eduyears" was replaced with a '0' for ineligible household members, i.e.: those who have not completed 6 years of schooling following their starting school age */ /*A control variable is created on whether there is information on years of education for at least 2/3 of the eligible household members*/ gen temp = 1 if eduyears!=. & age>=13 & age!=. replace temp = 1 if age==10 & eduyears>=6 & eduyears<. replace temp = 1 if age==11 & eduyears>=6 & eduyears<. replace temp = 1 if age==12 & eduyears>=6 & eduyears<. bysort hh_id: egen no_missing_edu = sum(temp) //Total eligible household members with no missing years of education gen temp2 = 1 if age>=13 & age!=. replace temp2 = 1 if age==10 & eduyears>=6 & eduyears<. replace temp2 = 1 if age==11 & eduyears>=6 & eduyears<. replace temp2 = 1 if age==12 & eduyears>=6 & eduyears<. bysort hh_id: egen hhs = sum(temp2) /*Total number of eligible household members who should have information on years of education */ 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 eligible household members */ tab no_missing_edu, miss //The values for 0 (missing) is 2.36% label var no_missing_edu "No missing edu for at least 2/3 of the HH members aged 13 years & older" drop temp temp2 hhs *** Standard MPI *** /*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" tab hh_years_edu6, miss *** Destitution MPI *** /*The entire household is considered deprived if no household member aged 10 years or older has completed at least one year of schooling.*/ ******************************************************************* gen years_edu1 = (eduyears>=1) replace years_edu1 = . if eduyears==. bysort hh_id: egen hh_years_edu_u = max(years_edu1) replace hh_years_edu_u = . if hh_years_edu_u==0 & no_missing_edu==0 lab var hh_years_edu_u "Household has at least one member with 1 year of edu" tab hh_years_edu_u, miss *** Quality check *** /* We compare the proportion of women and men with less than 6 years of education obtained from our work with the proportion of women and men with incomplete primary or no education as reported in the country survey report. Please note that the figure in the survey report is produced using the hv109 variable, while we apply the hv108 variable. There is bound to be minimal differences in the sample estimation. In the country survey report, we refer to the tables on 'Educational Attainment: Women' and 'Educational Attainment: Men'. The computation in the survey report covers women and men age 6 and over, but limited to those who slept the night before in the household. But the global MPI takes into account of all usual members, including those who slept and did not sleep the night before in the household. To account for this difference, in the quality check, we apply the hv103 (slept last night) variable. So we get a sense how close our weighted estimates matches with the survey report.*/ ***************************************************************************** **Women tab eduyears [aw = weight] if hv104==2 & hv105>5 & hv105<. & hv103==1,m tab hv109 [aw = weight] if hv104==2 & hv105>5 & hv105<. & hv103==1,m /*Using the hv108 variable, which is of interest to the global MPI, we find that 62.67% of de facto women have less than 6 years of education. Using the hv109 variable, we find that 76.52% of women have incomplete primary education or no education. The country survey report indicate that a total 76% of women have some primary education or no education (p.28). We may thus conclude that the figure based on this dataset closely corresponds to the figure reported in the survey report.*/ **Men tab eduyears [aw = weight] if hv104==1 & hv105>5 & hv105<. & hv103==1,m tab hv109 [aw = weight] if hv104==1 & hv105>5 & hv105<. & hv103==1,m /*Using the hv108 variable, which is of interest to the global MPI, we find that 55.70% of men have less than 6 years of education. Using the hv109 variable, we find that 71.02% of men have incomplete primary education or no education. The country survey report indicate that a total 70.6% of men have some primary education or no education (p.29). We may thus conclude that the figure based on this dataset closely corresponds to the figure reported in the survey report.*/ ******************************************************************************** *** Step 2.2 School Attendance *** ******************************************************************************** codebook hv121, tab (99) clonevar attendance = hv121 //1=attending, 0=not attending //If 2=attended at some time: recode attendance (2=1) 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" codebook attendance, tab (99) *** Standard MPI *** /*The entire household is considered deprived if any school-aged child is not attending school up to class 8. */ ******************************************************************* gen child_schoolage = (age>=7 & age<=15) /* Note: In Papua New Guinea, the official school entrance age to primary school is 7 years for 2016-18. So, age range is 7-15 (=7+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==. //How many eligible school aged children are not attending school: 169 children gen temp = 1 if child_schoolage==1 & attendance!=. /*Generate a variable that captures the number of eligible school aged children who are attending school */ 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 //Papua New Guinea DHS 2016-2018: values for 0 (missing) are 1.64% 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) //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. */ *** Destitution MPI *** /*The entire household is considered deprived if any school-aged child is not attending school up to class 6. */ ******************************************************************* gen child_schoolage_6 = (age>=7 & age<=13) /*Note: In Papua New Guinea, the official school entrance age is 6 years. So, age range for destitution measure is 6-12 (=6+6) */ /*A control variable is created on whether there is no information on school attendance for at least 2/3 of the children attending school up to class 6 */ count if child_schoolage_6==1 & attendance==. gen temp = 1 if child_schoolage_6==1 & attendance!=. bysort hh_id: egen no_missing_atten_u = sum(temp) gen temp2 = 1 if child_schoolage_6==1 bysort hh_id: egen hhs = sum(temp2) replace no_missing_atten_u = no_missing_atten_u/hhs replace no_missing_atten_u = (no_missing_atten_u>=2/3) tab no_missing_atten_u, miss label var no_missing_atten_u "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_6 = sum(child_schoolage_6) replace hh_children_schoolage_6 = (hh_children_schoolage_6>0) lab var hh_children_schoolage_6 "Household has children in school age (6 years of school)" gen child_atten_6 = (attendance==1) if child_schoolage_6==1 replace child_atten_6 = . if attendance==. & child_schoolage_6==1 bysort hh_id: egen any_child_atten_6 = max(child_atten_6) gen hh_child_atten_u = (any_child_atten_6==1) replace hh_child_atten_u = . if any_child_atten_6==. replace hh_child_atten_u = 1 if hh_children_schoolage_6==0 replace hh_child_atten_u = . if hh_child_atten_u==0 & no_missing_atten_u==0 lab var hh_child_atten_u "Household has at least one school age children up to class 6 in school" tab hh_child_atten_u, miss ******************************************************************************** *** Step 2.3 Nutrition *** ******************************************************************************** /*Note: Papua New Guinea DHS 2016-18 has no anthropometric data for adults. The child anthropometric data was not used due to data quality issues. Hence no nutrition data. */ gen underweight = . lab var underweight "Child is undernourished (weight-for-age) 2sd - WHO" gen stunting = . lab var stunting "Child is stunted (length/height-for-age) 2sd - WHO" gen wasting = . lab var wasting "Child is wasted (weight-for-length/height) 2sd - WHO" gen underweight_u = . lab var underweight_u "Child is undernourished (weight-for-age) 3sd - WHO" gen stunting_u = . lab var stunting_u "Child is stunted (length/height-for-age) 3sd - WHO" gen wasting_u = . lab var wasting_u "Child is wasted (weight-for-length/height) 3sd - WHO" gen f_bmi = . lab var f_bmi "Women's BMI" gen m_bmi = . lab var m_bmi "Male's BMI " gen hh_no_low_bmiage = . lab var hh_no_low_bmiage "Household has no adult with low BMI or BMI-for-age" gen hh_no_low_bmiage_u = . lab var hh_no_low_bmiage_u "Household has no adult with low BMI or BMI-for-age (<17)" gen low_bmi_byage = . gen hh_no_underweight = . lab var hh_no_underweight "Household has no child underweight - 2 stdev" gen hh_no_stunting = . lab var hh_no_stunting "Household has no child stunted - 2 stdev" gen hh_no_wasting = . lab var hh_no_wasting "Household has no child wasted - 2 stdev" gen hh_no_uw_st = . lab var hh_no_uw_st "Household has no child underweight or stunted" gen hh_no_underweight_u = . lab var hh_no_underweight_u "Destitute: Household has no child underweight" gen hh_no_stunting_u = . lab var hh_no_stunting_u "Destitute: Household has no child stunted" gen hh_no_wasting_u = . lab var hh_no_wasting_u "Destitute: Household has no child wasted" gen hh_no_uw_st_u = . lab var hh_no_uw_st_u "Destitute: Household has no child underweight or stunted" gen hh_nutrition_uw_st = . lab var hh_nutrition_uw_st "Household has no child underweight/stunted or adult deprived by BMI/BMI-for-age" gen hh_nutrition_uw_st_u = . lab var hh_nutrition_uw_st_u "Household has no child underweight/stunted or adult deprived by BMI/BMI-for-age (destitute)" ******************************************************************************** *** Step 2.4 Child Mortality *** ******************************************************************************** codebook v206 v207 mv206 mv207 /*v206 or mv206: number of sons who have died v207 or mv207: number of daughters who have died */ egen temp_f = rowtotal(v206 v207), missing //Total child mortality reported by eligible women replace temp_f = 0 if v201==0 //This line replaces women who have never given birth 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 temp_m = rowtotal(mv206 mv207), missing //Total child mortality reported by eligible men replace temp_m = 0 if mv201==0 bysort hh_id: egen child_mortality_m = sum(temp_m), missing lab var child_mortality_m "Occurrence of child mortality reported by men" tab child_mortality_m, miss drop temp_m egen child_mortality = rowmax(child_mortality_f child_mortality_m) lab var child_mortality "Total child mortality within household" tab child_mortality, miss *** Standard MPI *** /* Members of the household are considered deprived if women in the household reported mortality among children under 18 in the last 5 years from the survey year. Members of the household is considered non-deprived if eligible women within the household reported (i) no child mortality or (ii) if any child died longer than 5 years from the survey year or (iii) if any child 18 years and older died in the last 5 years. In adddition, members of the household were identified as non-deprived if eligible men within the household reported no child mortality in the absence of information from women. Households that have no eligible women or adult are considered non-deprived. The indicator takes a missing value if there was missing information on reported death from eligible individuals. */ ************************************************************************ tab childu18_died_per_wom_5y, miss /* The 'childu18_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 childu18_died_per_wom_5y = 0 if v201==0 /*Assign a value of "0" for: - all eligible women who never ever gave birth */ replace childu18_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 childu18_mortality_5y = sum(childu18_died_per_wom_5y), missing replace childu18_mortality_5y = 0 if childu18_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 childu18_mortality_5y "Under 18 child mortality within household past 5 years reported by women" tab childu18_mortality_5y, miss gen hh_mortality_u18_5y = (childu18_mortality_5y==0) replace hh_mortality_u18_5y = . if childu18_mortality_5y==. lab var hh_mortality_u18_5y "Household had no under 18 child mortality in the last 5 years" tab hh_mortality_u18_5y, miss *** Destitution MPI *** *** (same as standard MPI) *** ************************************************************************ gen hh_mortality_u = hh_mortality_u18_5y lab var hh_mortality_u "Household had no under 18 child mortality in the last 5 years" ******************************************************************************** *** Step 2.5 Electricity *** ******************************************************************************** *** Standard MPI *** /*Members of the household are considered deprived if the household has no electricity */ *************************************************** clonevar electricity = hv206 codebook electricity, tab (9) replace electricity = . if electricity==9 //Please replace the missing value accordingly label var electricity "Household has electricity" tab electricity, miss *** Destitution MPI *** *** (same as standard MPI) *** *************************************************** gen electricity_u = electricity label var electricity_u "Household has electricity" *** Quality check *** /* We compare the proportion of households with electricity obtained from our work and as reported in the country survey report. */ ********************************************************* bysort hh_id: gen id = _n tab electricity [aw = weight] if id==1,m /*The report (p.20) states that 14.6% of households have electricity. The data, show that 14.61% of households have access to electricity. The figure matches with the report. */ ******************************************************************************** *** Step 2.6 Sanitation *** ******************************************************************************** /* Improved sanitation facilities include flush or pour flush toilets to sewer systems, septic tanks or pit latrines, ventilated improved pit latrines, pit latrines with a slab, and composting toilets. These facilities are only considered improved if it is private, that is, it is not shared with other households. Source: https://unstats.un.org/sdgs/metadata/files/Metadata-06-02-01.pdf Note: In cases of mismatch between the country report and the internationally agreed guideline, we followed the report. */ desc hv205 hv225 clonevar toilet = hv205 clonevar shared_toilet = hv225 codebook shared_toilet, tab(99) //0=no;1=yes;.=missing *** Standard MPI *** /*Members of the household are considered deprived if the household's sanitation facility is not improved (according to the SDG guideline) or it is improved but shared with other households*/ ******************************************************************** codebook toilet, tab(99) gen toilet_mdg = ((toilet<23 | toilet==41) & shared_toilet!=1) /*Household is assigned a value of '1' if it uses improved sanitation and does not share toilet with other households */ replace toilet_mdg = 0 if (toilet<23 | toilet==41) & shared_toilet==1 /*Household is assigned a value of '0' if it uses improved sanitation but shares toilet with other households */ replace toilet_mdg = 0 if toilet == 14 | toilet == 15 /*Household is assigned a value of '0' if it uses non-improved sanitation: "flush to somewhere else" and "flush don't know where" (p.18) */ replace toilet_mdg = . if toilet==. | toilet==99 //Household is assigned a value of '.' if it has missing information replace toilet_mdg = 0 if shared_toilet==1 /*It may be the case that there are individuals who did not respond on the type of toilet, but they indicated that they share their toilet facilities. In such case, we replace these individuals as deprived following the information on shared toilet.*/ lab var toilet_mdg "Household has improved sanitation" tab toilet toilet_mdg, miss tab toilet_mdg, miss *** Destitution MPI *** /*Members of the household are considered deprived if household practises open defecation or uses other unidentifiable sanitation practises */ ******************************************************************** gen toilet_u = . replace toilet_u = 0 if toilet==31 | toilet==96 /*Household is assigned a value of '0' if it practises open defecation or others */ replace toilet_u = 1 if toilet!=31 & toilet!=96 & toilet!=. & toilet!=99 /*Household is assigned a value of '1' if it does not practise open defecation or others */ lab var toilet_u "Household does not practise open defecation or others" tab toilet toilet_u, miss tab toilet_u, miss *** Quality check *** /* We compare the proportion of households with improved sanitation obtained from our work and as reported in the country survey report. */ ********************************************************* tab toilet_mdg [aw = weight] if id==1,miss /*The country report (p.18) states that 22.1% of households use improved facilities that are not shared with other households. The data indicate that 22.21% of the households have improved sanitation that are not shared. The figure matches with the report. */ ******************************************************************************** *** Step 2.7 Drinking Water *** ******************************************************************************** /* Improved drinking water sources include the following: piped water into dwelling, yard or plot; public taps or standpipes; boreholes or tubewells; protected dug wells; protected springs; packaged water; delivered water and rainwater which is located on premises or is less than a 30-minute walk from home roundtrip. Source: https://unstats.un.org/sdgs/metadata/files/Metadata-06-01-01.pdf Note: In cases of mismatch between the country report and the internationally agreed guideline, we followed the report. */ desc hv201 hv204 hv202 clonevar water = hv201 clonevar timetowater = hv204 clonevar ndwater = hv202 *** Standard MPI *** /* Members of the household are considered deprived if the household does not have access to improved drinking water (according to the SDG guideline) or safe drinking water is at least a 30-minute walk from home, roundtrip */ ******************************************************************** codebook water, tab(99) gen water_mdg = 1 if water==11 | water==12 | water==13 | water==14 | /// water==21 | water==31 | water==41 | water==51 | /// water==61 | water==62 | water==71 /*Non deprived if water is piped into dwelling, piped to yard/plot, public tap/standpipe, tube well or borehole, protected well, protected spring, rainwater, bottled water.*/ replace water_mdg = 0 if water==32 | water==42 | /// water==43 | water==96 /*Deprived if it is unprotected well, unprotected spring, surface water (river/lake, etc), other */ 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 tab water_mdg, miss *** Quality check *** /* We compare the proportion of households with improved access to safe drinking water obtained from our work and as reported in the country survey report. */ ********************************************************* tab water_mdg [aw = weight] if id==1,miss /*In the report (p.16), 45.5% of households have improved or safe drinking facilities. The results obtained from our work is 45.50%. The figure matches the report. */ *** Time to water *** ********************************************************* codebook timetowater, tab(9999) replace water_mdg = 0 if water_mdg==1 & timetowater >= 30 & timetowater!=. & /// timetowater!=996 & timetowater!=998 & timetowater!=999 //Deprived if water source is 30 minutes or more from home, roundtrip. tab timetowater if water==99 | water==.,miss replace water_mdg = 0 if (water==99 | water==.) & water_mdg==. & /// timetowater >= 30 & timetowater!=. & /// timetowater!=996 & timetowater!=998 /*It may be the case that there are individuals who did not respond on their source of drinking water, but they indicated the water source is 30 minutes or more from home, roundtrip. In such case, we replace these individuals as deprived following the information on distance to water.*/ tab water_mdg, miss *** Destitution MPI *** /* Members of the household is identified as destitute if household does not have access to safe drinking water, or safe water is more than 45 minute walk from home, round trip.*/ ******************************************************************** gen water_u = . replace water_u = 1 if water==11 | water==12 | water==13 | water==14 | /// water==21 | water==31 | water==41 | water==51 | /// water==61 | water==62 | water==71 replace water_u = 0 if water==32 | water==42 | water==43 | water==96 replace water_u = 0 if water_u==1 & timetowater>45 & timetowater!=. & /// timetowater!=995 & timetowater!=996 & /// timetowater!=998 & timetowater!=999 replace water_u = . if water==99 | water==. replace water_u = 0 if (water==99 | water==.) & water_u==. & /// timetowater > 45 & timetowater!=. & /// timetowater!=996 & timetowater!=998 lab var water_u "Household has drinking water with MDG standards (45 minutes distance)" tab water_u, miss ******************************************************************************** *** Step 2.8 Housing *** ******************************************************************************** /* Members of the household are considered deprived if the household has a dirt, sand or dung floor */ lookfor floor clonevar floor = hv213 codebook floor, tab(99) gen floor_imp = 1 replace floor_imp = 0 if floor<=12 | floor==96 //Deprived if mud/earth, sand, dung, other replace floor_imp = . if floor==. | floor==99 lab var floor_imp "Household has floor that is not earth/sand/dung" tab floor floor_imp, miss /* Members of the household are considered deprived if the household has walls made of natural or rudimentary materials. We followed the report's definitions of natural or rudimentary materials. */ lookfor wall clonevar wall = hv214 codebook wall, tab(99) gen wall_imp = 1 replace wall_imp = 0 if wall<=26 | wall==96 /*Deprived if no wall, cane/palms/trunk, mud/dirt, grass/reeds/thatch, pole/bamboo with mud, stone with mud, plywood, cardboard, carton/plastic, uncovered adobe, canvas/tent, unburnt bricks, reused wood, other */ replace wall_imp = . if wall==. | wall==99 lab var wall_imp "Household has walls that are 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. We followed the report's definitions of natural and rudimentary materials. */ lookfor roof clonevar roof = hv215 codebook roof, tab(99) gen roof_imp = 1 replace roof_imp = 0 if roof<=23 | roof==96 /*Deprived if no roof, thatch/palm leaf, mud/earth/lump of earth, sod/grass, plastic/polythene sheeting, rustic mat, cardboard, canvas/tent, wood planks/reused wood, unburnt bricks, other */ replace roof_imp = . if roof==. | roof==99 lab var roof_imp "Household has roof that is not of low quality materials" tab roof roof_imp, miss *** Standard MPI *** /* Members of the household is deprived in housing if the roof, floor OR walls are constructed from 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 is not of low quality material" tab housing_1, miss *** Destitution MPI *** /* Members of the household is deprived in housing if two out of three components (roof and walls; OR floor and walls; OR roof and floor) the are constructed from low quality materials. */ ************************************************************** gen housing_u = 1 replace housing_u = 0 if (floor_imp==0 & wall_imp==0 & roof_imp==1) | /// (floor_imp==0 & wall_imp==1 & roof_imp==0) | /// (floor_imp==1 & wall_imp==0 & roof_imp==0) | /// (floor_imp==0 & wall_imp==0 & roof_imp==0) replace housing_u = . if floor_imp==. & wall_imp==. & roof_imp==. lab var housing_u "Household has one of three aspects(either roof,floor/walls) that is not of low quality material" tab housing_u, miss *** Quality check *** /* We compare the proportion of households with improved floor from our work and as reported in the country survey report. */ ********************************************************* tab floor_imp [aw = weight] if id==1,m /*The report(p.26) indicate that 80.1% of households have improved floor (built using rudimentary or finished material). The results obtained from our work is 80.16%. This figure closely matches the report.*/ ******************************************************************************** *** Step 2.9 Cooking Fuel *** ******************************************************************************** /* Solid fuel are solid materials burned as fuels, which includes coal as well as solid biomass fuels (wood, animal dung, crop wastes and charcoal). Source: https://apps.who.int/iris/bitstream/handle/10665/141496/9789241548885_eng.pdf */ lookfor cooking combustible clonevar cookingfuel = hv226 *** Standard MPI *** /* Members of the household are considered deprived if the household uses solid fuels and solid biomass fuels for cooking. */ ***************************************************************** codebook cookingfuel, tab(99) gen cooking_mdg = 1 replace cooking_mdg = 0 if cookingfuel>=7 & cookingfuel<=8 replace cooking_mdg = . if cookingfuel==. | cookingfuel==99 lab var cooking_mdg "Household uses clean fuels for cooking" /* Deprived if: coal/lignite, charcoal, wood, straw/shrubs/grass, agricultural crop, animal dung */ tab cookingfuel cooking_mdg, miss tab cooking_mdg, miss *** Destitution MPI *** *** (same as standard MPI) *** **************************************** gen cooking_u = cooking_mdg lab var cooking_u "Household uses clean fuels for cooking" *** Quality check *** /* We compare the proportion of households using solid fuel for cooking obtained from our work and as reported in the country survey report. */ ********************************************************* tab cooking_mdg [aw = weight] if id==1,m /*The report (p.26) indicate that 91.5% of households use solid fuel for cooking. The results obtained from our work is 91.51%. The figure produced from our work closely matches the figure published in the survey report. */ ******************************************************************************** *** Step 2.10 Assets ownership *** ******************************************************************************** /*Assets that are included in the global MPI: Radio, TV, telephone, bicycle, motorbike, refrigerator, car, computer and animal cart */ *** Television/LCD TV/plasma TV/color TV/black & white tv lookfor tv television plasma lcd codebook hv208 //1=yes; 0=no clonevar television = hv208 lab var television "Household has television" *** Radio/walkman/stereo/kindle lookfor radio walkman stereo codebook hv207 //1=yes; 0=no clonevar radio = hv207 lab var radio "Household has radio" *** Handphone/telephone/iphone/mobilephone/ipod lookfor telephone téléphone mobilephone ipod codebook hv221 hv243a //1=yes; 0=no clonevar telephone = hv221 replace telephone=1 if telephone!=1 & hv243a==1 //hv243a=mobilephone. Combine information on telephone and mobilephone. tab hv243a hv221 if telephone==1,miss lab var telephone "Household has telephone (landline/mobilephone)" *** Refrigerator/icebox/fridge lookfor refrigerator réfrigérateur codebook hv209 //1=yes; 0=no clonevar refrigerator = hv209 lab var refrigerator "Household has refrigerator" *** Car/van/lorry/truck lookfor car voiture truck van codebook hv212 //1=yes; 0=no clonevar car = hv212 lab var car "Household has car" *** Bicycle/cycle rickshaw lookfor bicycle bicyclette codebook hv210 //1=yes; 0=no clonevar bicycle = hv210 lab var bicycle "Household has bicycle" *** Motorbike/motorized bike/autorickshaw lookfor motorbike moto codebook hv211 //1=yes; 0=no clonevar motorbike = hv211 lab var motorbike "Household has motorbike" *** Computer/laptop/tablet lookfor computer ordinateur laptop ipad tablet codebook hv243e //1=yes; 0=no clonevar computer = hv243e lab var computer "Household has computer" *** Animal cart lookfor cart codebook hv243c //1=yes; 0=no clonevar animal_cart = hv243c lab var animal_cart "Household has animal cart" foreach var in television radio telephone refrigerator car /// bicycle motorbike computer animal_cart { replace `var' = . if `var'==9 | `var'==99 | `var'==8 | `var'==98 } //Missing values replaced *** Quality check *** /* We compare the proportion of households owning each assets obtained from our work and as reported in the country survey report. */ ********************************************************* tab radio [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 23.7% of households own radio. The results obtained from our work is 24.86% (1/2 sample) and 23.70% (full sample) which closely matches the report. */ tab television [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 12.6% of households own television. The results obtained from our work is 12.93% (1/2 sample) and 12.55% (full sample) which closely matches the report.*/ tab hv243a [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 56.3% of households own mobile phone. The results obtained from our work is 56.69% (1/2 sample) and 56.34% (full sample) which closely matches the report.*/ tab computer [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 10.6% of households own computer. The results obtained from our work is 10.28% (1/2 sample) and 10.62% (full sample) which closely matches the report.*/ tab refrigerator [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 10.0% of households own refrigerator. The results obtained from our work is 9.97% (1/2 sample) and 9.98% (full sample) which closely matches the report.*/ tab bicycle [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 10.3% of households own bicycle. The results obtained from our work is 11.15% (1/2 sample) and 10.29% (full sample) which closely matches the report.*/ tab animal_cart [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 0.4% of households own animal cart. The results obtained from our work is 0.29% (1/2 sample) and 0.41% (full sample) which closely matches the report.*/ tab motorbike [aw = weight]if id==1,m /*Table 2.5 (p.21) indicate that 0.6% of households own motorbike. The results obtained from our work is 0.73% (1/2 sample) and 0.60% (full sample) which closely matches the report.*/ tab car [aw = weight] if id==1,m /*Table 2.5 (p.21) indicate that 5.1% of households own car. The results obtained from our work is 5.55% (1/2 sample) and 5.05% (full sample) which closely matches the report.*/ *** Standard MPI *** /* 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" tab hh_assets2, miss *** Destitution MPI *** /* Members of the household are considered deprived in assets if the household does not own any assets.*/ ***************************************************************************** gen hh_assets2_u = (car==1 | n_small_assets2>0) replace hh_assets2_u = . if car==. & n_small_assets2==. lab var hh_assets2_u "Household Asset Ownership: HH has car or at least 1 small assets incl computer & animal cart" ******************************************************************************** *** Step 2.11 Rename and keep variables for MPI calculation ******************************************************************************** //Retain DHS wealth index: desc hv270 clonevar windex=hv270 desc hv271 clonevar windexf=hv271 //Retain data on sampling design: desc hv022 hv021 clonevar strata = hv022 clonevar psu = hv021 //Retain year, month & date of interview: desc hv007 hv006 hv008 clonevar year_interview = hv007 clonevar month_interview = hv006 clonevar date_interview = hv008 *** Rename key global MPI indicators for estimation *** recode hh_mortality_u18_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) *** Rename key global MPI indicators for destitution estimation *** recode hh_mortality_u (0=1)(1=0) , gen(dst_cm) recode hh_nutrition_uw_st_u (0=1)(1=0) , gen(dst_nutr) recode hh_child_atten_u (0=1)(1=0) , gen(dst_satt) recode hh_years_edu_u (0=1)(1=0) , gen(dst_educ) recode electricity_u (0=1)(1=0) , gen(dst_elct) recode water_u (0=1)(1=0) , gen(dst_wtr) recode toilet_u (0=1)(1=0) , gen(dst_sani) recode housing_u (0=1)(1=0) , gen(dst_hsg) recode cooking_u (0=1)(1=0) , gen(dst_ckfl) recode hh_assets2_u (0=1)(1=0) , gen(dst_asst) *** Total number of missing values for each variable *** mdesc psu strata area age /// d_cm d_nutr d_satt d_educ d_elct d_wtr d_sani d_hsg d_ckfl d_asst *** Keep main variables require for MPI calculation *** keep hh_id ind_id psu strata subsample weight area region agec4 agec2 /// d_cm d_nutr d_satt d_educ d_elct d_wtr d_sani d_hsg d_ckfl d_asst order hh_id ind_id psu strata subsample weight area region agec4 agec2 /// d_cm d_nutr d_satt d_educ d_elct d_wtr d_sani d_hsg d_ckfl d_asst *** Generate country and survey details for estimation *** char _dta[cty] "Papua New Guinea" char _dta[ccty] "PNG" char _dta[year] "2016-2018" char _dta[survey] "DHS" char _dta[ccnum] "598" char _dta[type] "micro" char _dta[class] "new_country" *** Sort, compress and save data for estimation *** sort ind_id compress la da "Micro data for `_dta[ccty]' (`_dta[ccnum]') from `c(current_date)' (`c(current_time)')." save "$path_out/png_dhs16-18.dta", replace