COVID-19 High Frequency Phone Survey of Households, Kenya, 2020-2021 (ICPSR 38476)

Version Date: Oct 20, 2022 View help for published

Principal Investigator(s): View help for Principal Investigator(s)
Nistha Sinha, World Bank

Series:

https://doi.org/10.3886/ICPSR38476.v1

Version V1

Slide tabs to view more

The World Bank in collaboration with the Kenya National Bureau of Statistics and the University of California, Berkeley conducted the Kenya COVID-19 Rapid Response Phone Survey (RRPS) to track the socioeconomic impacts of the COVID-19 pandemic and the recovery from it to provide timely data to inform policy. This collection contains information from seven waves of the COVID-19 RRPS, which was part of a panel survey that targeted Kenyan nationals and started in May 2020. The same households were interviewed every two months for five survey rounds in the first year of data collection and every four months thereafter, with interviews conducted using Computer Assisted Telephone Interviewing (CATI) techniques. Sampled households that were not reached in earlier waves were also contacted along with households that were interviewed before. The "WAVE" variable represents in which wave the households were interviewed in. All waves of this survey included information on household background, service access, employment, food security, income loss, transfers, health, and COVID-19 knowledge and vaccinations.

The data contain information from two samples of Kenyan households. The first sample is a randomly drawn subset of all households that were part of the 2015/16 Kenya Integrated Household Budget Survey (KIHBS) Computer-Assisted Personal Interviewing (CAPI) pilot and provided a phone number. The second was obtained through the Random Digit Dialing method, by which active phone numbers created from the 2020 Numbering Frame produced by the Kenya Communications Authority were randomly selected. The samples covered urban and rural areas and were designed to be representative of the population of Kenya using cell phones. The sample size for each completed wave was:

  • Wave 1: 4,061 Kenyan households
  • Wave 2: 4,492 Kenyan households
  • Wave 3: 4,979 Kenyan households
  • Wave 4: 4,892 Kenyan households
  • Wave 5: 5,854 Kenyan households
  • Wave 6: 5,765 Kenyan households
  • Wave 7: 5,633 Kenyan households

The collection is organized into three levels. The first level is the Household Level Data, which contains household level information. The 'HHID' variable uniquely identifies all households. The second level is the Adult Level Data, which contains data at the level of adult household members. Each adult in a household is uniquely identified by the 'ADULT_ID' variable. The third level is the Child Level Data, which contains information for every child in the household. Each child in a household is uniquely identified by the 'CHILD_ID' variable.

Sinha, Nistha. COVID-19 High Frequency Phone Survey of Households, Kenya, 2020-2021. Inter-university Consortium for Political and Social Research [distributor], 2022-10-20. https://doi.org/10.3886/ICPSR38476.v1

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote
International Bank for Reconstruction and Development

Town

This data collection may not be used for any purpose other than statistical reporting and analysis. Use of these data to learn the identity of any person or establishment is prohibited. To protect respondent privacy, geographic variables were de-identified from general dissemination. Users interested in obtaining the Restricted-Use version of the data, which contains unedited geographic variables, must agree to the terms and conditions of a Restricted Data Use Agreement in accordance with existing ICPSR servicing policies.

Inter-university Consortium for Political and Social Research
Hide

2020 -- 2021
2020-05-14 -- 2020-07-07 (Wave 1), 2020-07-16 -- 2020-09-18 (Wave 2), 2020-09-28 -- 2020-12-02 (Wave 3), 2021-01-15 -- 2021-03-25 (Wave 4), 2021-03-29 -- 2021-06-13 (Wave 5), 2021-07-14 -- 2021-11-03 (Wave 6), 2021-11-15 -- 2022-03-31 (Wave 7)
  1. To protect respondent privacy, some geographic variables were de-identified in the Household Level Public-Use Data (DS1) and Adult Level Public-Use Data (DS3). Please see the ICPSR Codebook processing notes for additional information.

  2. For additional information on the COVID-19 High Frequency Phone Survey of Households, Kenya, 2020-2021 study, please visit the World Bank website.
Hide

The purpose of the Kenya COVID-19 Rapid Response Phone Survey (RRPS) was to track the socioeconomic impacts of the COVID-19 pandemic and the recovery from it to provide timely data to inform policy. The RRPS covers the following topics:

  • household roster
  • travel patterns and interactions
  • employment
  • food security
  • income loss
  • transfers
  • subjective welfare (50 percent of sample)
  • health
  • COVID-19 knowledge and vaccinations
  • household and social relations (50 percent of sample).

Pre-loaded Information: Basic household information was pre-loaded in the Computer Assisted Telephone Interviewing (CATI) assignments for each enumerator. The information, for example the household's location, household head name, phone numbers, etc., was used to help enumerators call and identify the target households. The list of individuals from the Kenya Integrated Household Budget Survey (KIHBS) Computer-Assisted Personal Interviewing (CAPI) pilot and their basic characteristics were uploaded as well as basic information from previous survey waves where available from wave 2 onward.

Respondents: The COVID-19 Rapid Response Phone Survey (RRPS) had one respondent per household. For the sample from the 2015/16 KIHBS CAPI pilot, the target respondent was defined as the primary male or female adult household member. They were randomly chosen where both existed to maintain gender balance. If the target respondent was not available for a call, the field team spoke to any adult currently living in the household of the target respondent. If the target respondent was deceased, the field team spoke to any adults that lived with the target respondent in 2015/16. Finally, if the household from 2015/16 split up, the field team targeted anyone in the household of the target respondent but did not survey a household member that no longer lived with the target respondent. For the sample based on Random Digit Dialing, the target respondent was the owner the phone number that was randomly selected. Where the target respondent was not available for the interview, the research team spoke to any other adult household member of the target respondent.

Series Information: The first five waves extended over a period of two months each, while waves 6 and 7 extended over a period of four months. Data collections were implemented between May 2020 and March 2022.

The COVID-19 Rapid Response Phone Survey (RRPS) with Kenyan households included two samples. The first sample consisted of households that were part of the 2015/16 Kenya Integrated Household Budget Survey (KIHBS) Computer-Assisted Personal Interviewing (CAPI) pilot and provided a phone number. The 2015/16 KIHBS CAPI pilot was representative at the national level stratified by county and place of residence (urban and rural areas). At least one valid phone number was obtained for 9,007 households and all of them were included in the COVID-19 RRPS sample. The target respondent was the primary male or female household member from the 2015/16 KIHBS CAPI pilot. The second sample consisted of households selected using the Random Digit Dialing method. A list of random mobile phone numbers was created using a random number generator from the 2020 Numbering Frame produced by the Kenya Communications Authority. The initial sampling frame therefore consisted of 92,999,970 randomly ordered phone numbers assigned to three networks: Safaricom, Airtel, and Telkom. An introductory text message was sent to 5,000 randomly selected numbers to determine if numbers were in operation. Out of these, 4,075 were found to be active and formed the final sampling frame. There was no stratification and individuals that were called were asked about the households they lived in.

Longitudinal: Panel

Households in Kenya that are representative of the population using cell phones.

Indivdiual, Household
Hide

2022-10-20

2022-10-20 ICPSR data undergo a confidentiality review and are altered when necessary to limit the risk of disclosure. ICPSR also routinely creates ready-to-go data files along with setups in the major statistical software formats as well as standard codebooks to accompany the data. In addition to these procedures, ICPSR performed the following processing steps for this data collection:

  • Checked for undocumented or out-of-range codes.
Hide

Cross-Section Weights: For the Kenya National Bureau of Statistics (KNBS) and Random Digit Dialing (RDD) samples, to make the sample nationally representative of the current population of households with mobile phone access, the research team created weights in two steps.

Step 1: Constructed raw weights combining the two national samples: The population consisted of

  • (I) households that existed in 2015/16, and did not change phone numbers,
  • (II) households that existed in 2015/16, but changed phone number,
  • (III) households that did not exist in 2015/16.
Abstracting from differential attrition, the weights from the 2015/16 Kenya Integrated Household Budget Survey (KIHBS) Computer-Assisted Personal Interviewing (CAPI) pilot made the KIHBS sample representative of type (I) households. RDD households were asked whether they existed in 2015/16, when they had acquired their phone number, and where they lived in 2015/16, allowing them to be classified into type (I), (II), and (III) households and assigned to KIHBS strata. The weights of each RDD household were adjusted to be inversely proportional to the number of mobile phone numbers used by the household, and scaled relative to the average number of mobile phone numbers used in the KIHBS within each stratum. RDD therefore gave a representative sample of type (II) and (III) households. The research team then combined RDD and KIHBS type (I) households by ex-post adding RDD households into the 2015/16 sampling frame and adjusting weights accordingly. Last, the research team combined the representative samples of type (I), type (II), and type (III), using the share of each type within each stratum from RDD (inversely weighted by number of mobile phone numbers). Variable: WEIGHT_RAW

Step 2: Scaled the weights to population proportions in each county and urban/rural stratum: The research team used post stratification to adjust for differential attrition and response rates across counties and rural/urban strata. They scaled the raw weights from step 1 to reflect the population size in each county and rural/urban stratum as recorded in the 2019 Kenya Population and Housing Census conducted by the KNBS (2019 Kenya Population and Housing Census, Volume II: Distribution of Population by Administrative Units, December 2019, Kenya National Bureau of Statistics, https://www.knbs.or.ke/?wpdmpro=2019-kenya-population-and-housing-census-volume-ii-distribution-of-population-by-administrative-units). Variable: WEIGHT

Panel Weights: To construct panel weights, the research team followed the approach outlined in Himelein (2014): "Weight Calculations for Panel Surveys with Subsampling and Split-off Tracking". One target respondent was followed in each household. Wherever households were split, only the current household of the target respondent was interviewed.

The weights for the wave 1 and 2 balanced panel were constructed by applying the following steps to the full sample of Kenyan nationals:

  1. Wave 1 cross-sectional weights after post-stratification adjustment were used as a base. W_1 = W_wave1
  2. Attrition adjustment through propensity score-based method: The predicted probability that a sample household was successfully re-interviewed in the second survey wave was estimated through a propensity score estimation. The propensity score (PS) was modeled with a linear logistic model at the level of the household. The dependent variable was a dummy indicating whether a household that completed the survey in wave 1 had also done so in wave. The following covariates were used in the linear logistic model: Urban/rural dummy; County dummies; Household head gender; Household head age; Household size; Dependency ratio; Dummy: Is anyone in the household working; Asset ownership: radio; Asset ownership: mattress; Asset ownership: charcoal jiko; Asset ownership: fridge; Wall material: 3 dummies; Floor materials: 3 dummies; Connection to electricity grid; Number of mobile phones numbers household uses; Number of phone numbers recorded for follow-up; and Sample dummy for estimation with national samples.
  3. Ranked households by PS and split into 10 equal groups
  4. Calculated attrition adjustment factor: ac (attrition correction) = the reciprocal of the mean empirical response rate for the propensity score decile
  5. Adjusted base weights for attrition: W_2 = W_1 * ac
  6. Trimmed top 1 percent of the weights distribution (), by replacing the weights among the top 1 percent of the distribution with the highest value of a weight below the cutoff. W_3 = trim(W_2)
  7. Applied post-stratification in the same way as for cross-sectional weights (step 2) Variable: WEIGHT_PANEL_W1_2. The balanced panel weights including waves 3, 4, 5, 6, and 7 were constructed using the same procedure. Variables: WEIGHT_PANEL_W1_2_3, WEIGHT_PANEL_W1_2_3_4, WEIGHT_PANEL_W1_2_3_4_5, WEIGHT_PANEL_W1_2_3_4_5_6, and WEIGHT_PANEL_W1_2_3_4_5_6_7.

Hide

Notes

  • The public-use data files in this collection are available for access by the general public. Access does not require affiliation with an ICPSR member institution.

  • One or more files in this data collection have special restrictions. Restricted data files are not available for direct download from the website; click on the Restricted Data button to learn more.