COVID-19 MENA Monitor Household Survey, CMMHH- Apr. 2021
COVID-19 MENA Monitor Household Survey (HH/CMMHH)
The COVID-19 MENA Monitor Household Survey includes a panel data set for Tunisia that integrates and harmonizes data and variables from up to 4 rounds across years 2020 and 2021.
To better understand the impact of the shock induced by the COVID-19 pandemic on Tunisia and assess the policy responses in a rapidly changing context, reliable data is imperative, and the need to resort to a dynamic data collection tool at a time when countries in the region are in a state of flux cannot be overstated.
The COVID-19 MENA Monitor Survey was led by the Economic Research Forum (ERF) to provide data for researchers and policy makers on the socio-economic and labor market impact of the global COVID-19 pandemic on households.
The ERF COVID-19 MENA Monitor Survey is constructed using a series of short panel phone surveys that are conducted approximately every two months, covering topics such as demographic and household characteristics, education and children, labor market status, income, social safety net, employment and unemployment detection, employment characteristics, and social distancing. In addition to the survey's panel design, which will permit the study of various phenomena over time, the survey also takes into account the key demographic and socio-economic characteristics of each country in the questionnaires' design to understand the different distributional consequences of the impact of COVID-19 and responses to it. This design allows further study of the effect of the pandemic on different vulnerable groups including women, informal and irregular workers, low skilled workers, and youth.
The ERF COVID-19 MENA Monitor Survey is a wide-ranging, nationally representative panel survey.Wave 3 of this dataset was collected in April 2021, harmonized by the Economic Research Forum (ERF) and is featured as data for Household/Individual. The survey is in the process of further expansion to include other waves.
The harmonization was designed to create comparable data that can facilitate cross-country and comparative research between other Arab countries (Egypt, Morocco, Jordan, and Sudan). All the COVID-19 MENA Monitor surveys incorporate similar survey designs, with data on households and individuals within those households.
Kind of Data
Sample survey data [ssd]
Unit of Analysis
Household and Individuals
V5.0: Version 5 of the COVID 19 MENA Monitor surveys prepared for public dissemination.
The ERF COVID-19 MENA Monitor Household Survey includes a questionnaire that covers the demographic and household characteristics, education and children, labor market status, food security, income, social safety net, employment and unemployment detection, attitudes towards risks, mental health, social distancing. Additionally, it includes:
• A worker module on occupation, job formality, impact of COVID-19 on employment, work from home.
• A farmer module on crops, inputs, harvest, prices, markets ...etc.
• A household enterprise module on industry, employment, sales/revenue, impact of COVID-19 on business, policy response, plans for future...etc.
• A women module on caregiving time for children and housework, and activities that she spent time doing for her household
• A tracking module (contact information for panel follow-up)
The survey covered a national random sample of mobile phone users aged 18-64.
Producers and sponsors
Economic Research Forum
Economic Research Forum
Swedish International Development Cooperation Agency
Funding is provided by the Swedish International Development Cooperation Agency (Sida), through the International Labour Organisation’s (ILO) Advancing the Decent Work Agenda in North Africa – ADWA Project.
International Labour Organization (ADWA Project)
Arab Fund for Economic and Social Development
The sample universe for the household survey was mobile phone users aged 18-64. Random digit dialing (RDD), within the range of valid numbers, was used, with up to three attempts if a phone number was not picked up/answered, was disconnected or busy, or picked up but could not complete the interview at that time. Samples were stratified by country-specific market shares of mobile operators. The sample is designed to cover at least 2000 unique households and individuals. A question is included in the survey for the number of phone numbers within the household to weight appropriately. Further weighting of the household and individual samples was done to reflect the demographic composition of the population as obtained by the most recent publicly available data with individual phone ownership and relevant demographic and labour market characteristics. In the individual interview, respondents who are employers or self-employed were asked to respond to either the household enterprise or farmer modules.
For follow-up waves, previous wave respondents were recontacted if they consented to follow-up in the previous wave. Up to three attempts were used, including contacting second and family/friend numbers, if provided in wave one, on the third call. If the individual could not be reached or refused, a refresher individual was added to the sample in their place, randomly selected as with base wave respondents.
All the respondents who consented to follow up in the prior wave were contacted in order to include them in the subsequent wave. Households are be followed up every two months up to a total of four interviews. Interviews are conducted by experienced survey research or polling firms in each country using computer-assisted telephone interviewing (CATI) techniques.
Essentially, inverse probability weighting was used to reduce bias within a number of observable dimensions. Weights were created on three levels: Individual, household, and household member. Weights had the following inputs:
· Telephone operators and their market shares, provided by the data collection firm
· Number of phones by operator for individuals (individual weight) and household members (household weight and household member weight)
· Representative data with comparable demographic and household characteristics to weight for non-response
The panel attrition models use a few base wave variables in addition to those used for initial weighting. Specific additional variables are:
· Telephone operator
· Household income (categorically) in Feb. 2020
· Base wave labor market status (employed, unemployed (search required), out of labor force)
· Interactions with sex for categorical income and base wave labor market status
Household member weights were calculated by multiplying household weights by household size. Household and individual weights (but not member weights, for internal consistency) were all winsorized at the 99th percentile to ensure that no outlier weight drove statistics. Weights were then normalized by dividing by the mean weight.
Individual weights should be used for all analyses where the outcome is at the individual level. If outcomes are at the household level (e.g. household income, household food security) then the weight will depend on whether you are generalizing to households (e.g. X% of households are food insecure) or household members (e.g. X% of individuals live in a food insecure household).
Cross-sectional weight variable names:
• Individual weight: ind_wt
• Household weight: hh_wt
• Household member weight: hh_mem_wt
Panel weight variable names [where first # is base wave and second # is subsequent wave]:
· Individual weight: panel_ind_wt_#_#
· Household weight: panel_hh_wt_#_#
· Household member weight: panel_hh_mem_wt_#_#
Note: there is more details on the weights and sampling at the “COVID-19 MENA monitor weights” document at the documentation materials.
Dates of Data Collection
Data Collection Mode
Computer Assisted Telephone Interview [cati]
Data Collection Notes
ERF seeks IRB (Institutional Research Board) approval for all its data collection exercises to ensure the protection of the rights and welfare of human subjects participating in the research project. All interviews are conditioned upon receiving informed consent (which spells out the respondent's rights) from respondents.
Data are collected through up to four waves of phone surveys, every two months, covering at least 2000 unique households and individuals in each wave.
PHI Field & Tab
Economic Research Forum
Economic Research Forum (ERF) - 21 Al-Sad Al-Aaly St., Dokki, Giza, Egypt
To access the micro-data, researchers are required to register on the ERF website and comply with the data access agreement. The data will be used only for scholarly, research, or educational purposes. Users are prohibited from using data acquired from the Economic Research Forum in the pursuit of any commercial or private ventures.
Licensed datasets, accessible under conditions.
The users should cite the Economic Research Forum as follows:
"OAMDI, 2021. COVID-19 MENA Monitor Household Survey (CMMHH), http://www.erfdataportal.com/index.php/catalog . Version 5.0 of the licensed data files; Tunisia-CMMHH Apr-2021. Egypt: Economic Research Forum (ERF).”
Disclaimer and copyrights
The Economic Research Forum has granted the researcher access to relevant data following exhaustive efforts to protect the confidentiality of individual data. The researcher is solely responsible for any analysis or conclusions drawn from available data.