Skip to Main Navigation

Representativeness of Individual-Level Data in COVID-19 Phone Surveys : Findings from Sub-Saharan Africa (English)

The COVID-19 pandemic has created urgent demand for timely data, leading to a surge in mobile phone surveys for tracking the impacts of and responses to the pandemic. This paper assesses, and attempts to mitigate, selection biases in individual-level analyses based on phone survey data. The research uses data from (i) national phone surveys that have been implemented in Ethiopia, Malawi, Nigeria, and Uganda during the pandemic, and (ii) the pre-COVID-19 national face-to-face surveys that served as the sampling frames for the phone surveys. The availability of pre-COVID-19 face-to-face survey data permits comparisons of phone survey respondents with the general adult population. Phone survey respondents are more likely to be household heads or their spouses and non-farm enterprise owners, and on average, are older and better educated vis-à-vis the general adult population. To improve the representativeness of individual-level phone survey data, the household-level phone survey sampling weights are calibrated based on propensity score adjustments that are derived from a model of an individual’s likelihood of being interviewed as a function of individual- and household-level attributes. Reweighting improves the representativeness of the estimates for the phone survey respondents, moving them closer to those of the general adult population. This holds for women and men and a range of demographic, education, and labor market outcomes. However, reweighting increases the variance of the estimates and fails to overcome selection biases. Obtaining reliable data on men and women through phone surveys requires random selection of adult interviewees within sampled households.


  • Author

    Brubaker,Joshua Milton, Kilic,Talip, Wollburg,Philip Randolph

  • Document Date


  • Document Type

    Policy Research Working Paper

  • Report Number


  • Volume No


  • Total Volume(s)


  • Country


  • Region


  • Disclosure Date


  • Disclosure Status


  • Doc Name

    Representativeness of Individual-Level Data in COVID-19 Phone Surveys : Findings from Sub-Saharan Africa

  • Keywords

    adult population; phone number; survey respondent; household head; survey data; high spatial resolution; complete primary education; labor market outcome; household and individual; estimation of equation; high opportunity cost; old age group; labor market impact; household consumption expenditure; complete secondary education; expenditure per capita; household sample; survey household; individual weight; sampling frame; response rate; selection bias; survey sampling; household enterprise; independent variable; public use; household weight; secondary certificate; random selection; response bias; household survey; consumption quintile; individual level; best practice; confidence interval; employment outcome; mean differences; age range; sample household; marital status; descriptive statistic; educational degree; wage employment; age category; fixed effect; adjustment factor; data availability; Learning and Innovation Credit; household population; household level; household size; longitudinal survey; marginal effect; household headship; linear regression; differential impact; public dissemination; sample selection; survey cost; available data; Time of Use; significant challenge; rural level; phone call; survey questionnaire; recent studies; national statistical; chronically ill; vulnerable population; fundamental changes; employment data; annual consumption; per household; several points; casual work; International Phone Call; survey sample; Research Support; Population Projection; global initiative; telephone surveys; business impact; academic institution; comparative assessment; weighting method; survey methodology; alternative benchmark; travel restriction; sampling error; general population; standard error; statistical significance; gender dynamic; household wealth; open access; development policy; several advantages; sampling strategy; regression coefficient; labor activity; individual characteristic; mobile network; interview questions; graphical analysis; data needs; high frequency; urban districts



Official version of document (may contain signatures, etc)

  • Official PDF
  • TXT*
  • Total Downloads** :
  • Download Stats
  • *The text version is uncorrected OCR text and is included solely to benefit users with slow connectivity.


Brubaker,Joshua Milton Kilic,Talip Wollburg,Philip Randolph

Representativeness of Individual-Level Data in COVID-19 Phone Surveys : Findings from Sub-Saharan Africa (English). Policy Research working paper,no. WPS 9660,COVID-19 (Coronavirus),LSMS Washington, D.C. : World Bank Group.