Search results

This paper aims to compare residential fixed-line telephone surveys with cell phone surveys for assessing the extent of the potential undercoverage issue evaluating the necessity and feasibility of conducting cell phone surveys or dual-frame telephone surveys in Hong Kong.

The research team simultaneously carried out a conventional fixed-line telephone survey and a cell phone survey in 2015 with similar features on survey design, sampling and data collection procedures. Two samples with sample size of 801 and 1,203 were achieved separately. Data collected were analysed to see to what extent survey findings will be biased if the sampling frame of telephone surveys is solely based on residential fixed-line numbers in Hong Kong, and if such a bias does exist, whether a survey conducted through cell phones or by adding a cell phone-only (CO) group would be an ideal solution for it.

The findings show that the cooperation rates for the cell phone survey were much lower than those of the fixed-line telephone survey. The respondents from two surveys were fairly different. However, estimates of most commonly used socio-demographic characteristics from the latter group had the least bias compared with population statistics. Supplanting the traditional fixed-line survey with a cell phone survey or supplementing it with a CO group will not make the resulting sample a better representative of the population but it will amplify the sample bias on the major social socio-demographic characteristics.

This paper empirically compares the two types of telephone surveys in a well-designed scientific study.