Can cheap panel-based internet surveys substitute costly in-person interviews in CV surveys?

With the current growth in broadband penetration, Internet is likely to be the data collection mode of choice for stated preference research in the not so distant future. However, little is known about how this survey mode may influence data quality and welfare estimates. In a first controlled field experiment to date as part of a national contingent valuation (CV) survey estimating willingness to pay (WTP) for biodiversity protection plans, we assign two groups sampled from the same panel of respondents either to an Internet or in-person (in-house) interview mode. Our design is better able than previous studies to isolate measurement effects from sample composition effects. We find little evidence of social desirability bias in the in-person interview setting or satisficing (shortcutting the response process) in the Internet survey. The share of “don’t knows”, zeros and protest responses to the WTP question with a payment card is very similar between modes. Equality of mean WTP between samples cannot be rejected. Considering equivalence, we can reject that mean WTP from the in-person sample is more than 30% higher. Results are quite encouraging for the use of Internet in CV as stated preferences do not seem to be significantly different or biased compared to in-person interviews.