Random Spatial and Systematic Random Sampling Approach to Development Survey Data: Evidence from Field Application in Malawi

Abstract

Implementing development surveys in developing countries can be challenging. Limited time, high survey costs, lack of information, and technical difficulties are some of the general constraints that plague development researchers. These constraints can hinder data collection and introduce selection bias into the survey data. We outline a multilevel sampling approach for use in areas where comprehensive information on geographical or household characteristics of local population are not readily available. Our approach includes the use of geographical information systems (GIS) for random spatial sampling and personal digital assistants (PDAs) with a global positioning system (GPS) for household systematic random sampling with random walk. Evidence from our field application in Malawi show that the multilevel sampling approach yields relevant survey data which is comparable to historical and nationally representative values; and supports rapid aggregation of preliminary results after the survey. This multilevel design is cost-effective in implementation and reduces bias avenues in the household selection. Overall, this multilevel sampling approach can be used to generate survey data in developing countries where detailed geographical information and household characteristics data are not readily available. It also presents ways of reducing bias in survey data given budget constraints.

Predicting residents' intention to conserve the hooded vulture (Necrosyrtes monachus) in the Birem North District, Ghana

“…In townships, main streets were identified and the survey started at the center of the town ( Bauer, 2014 ). From the center (usually the main bus-stop area), every other pedestrian street to the right and left of the main street was selected and every other housing unit off the pedestrian streets was selected for interviews ( Bauer, 2014 ; Maduekwe and Timo de Vries, 2019 ). When a selected housing unit was non-residential or members of the household declined to grant an interview, the next housing unit was used.…”

“…When a selected housing unit was non-residential or members of the household declined to grant an interview, the next housing unit was used. The number of households interviewed in a township was proportional to the total number of households in the township and total samples covered at least 10% of the population in the community ( Maduekwe and Timo de Vries, 2019 ). Face-to-face interviews were conducted by university graduates who had training and experience in administering survey questionnaires.…”

Seasonal Distribution of AOT and Its Relationship with Air Pollutants in Central Bangladesh Using Remote Sensing and Machine Learning Tools

“…This paper collected 190 sample points from different areas of the study locations using a random sampling method [27][28][29]. Each district contained a minimum of 37 sample points, which were uniformly distributed across the study location (Figure 1).…”

Comparing households’ perception of flood hazard with historical climate and hydrological data in the Lower Mono River catchment (West Africa), Benin and Togo

“…Systematic random sampling of household was used to determine the number households to interview. A central point in the village was selected and a random direction for walking was chosen (North, East, South or West) by the interviewer [46]. Systematic interval of selecting households was chosen from the starting point into the randomly selected direction (North, East, South or West) and selects for example every 2th house.…”