Survey Mode Effects in a Developing Country

Responses to phone surveys tend exhibit higher rates of social desirability bias and extreme responses when compared face-to-face surveys. Yet, studies mode effects typically compare either representative that implausibly assume comparability or experimental rely on convenience samples. Our study compares two national probability samples but uses matching address comparability. We Costa Rica, a middle-income democracy, see whether the conventional wisdom drawn from Western Europe North America extends Global South. analyze nationally surveys, one fielded by face-to-face, allowing us identically worded items we placed both find respondents exhibited more socially desirable responding were likely choose negative endpoints scalar items. This suggests survey researchers practitioners should carefully assess tradeoffs in shifting modes employing mixed modes.