| Abstract: |
This paper examines how a respondent’s socioeconomic characteristics
influence her willingness to support tax increases for spending on highway
transportation infrastructure and four modes of public transportation (i.e.,
bus, light rail, commuter rail, and streetcar) in a fast growing urban area in
the United States. We use and analyze detailed survey data at household level
collected from a phone interview survey conducted in the Charlotte, North
Carolina, area. We consider two types of response bias in the survey data. One
is a systematic response bias which arises from protest zeros and
respondents’ tendency to under-report their willingness. The other is from
the randomized response when a respondent answers survey questions by guessing
because she does not have memory or knowledge of the questions and choices.
Along with random utility model, these two response bias models are estimated
and compared to each other. Empirical results show that an individual’s
attitudes towards paying higher taxes are affected by the individual’s
location, home ownership, and the level of educational attainment. It is found
that respondents tend to grossly under-report their willingness to support
higher taxes for investments on highways, bus, and commuter rail in the
survey. Respondents also exhibit positive tendency to choose no increase in
taxes in the survey about highway, bus, and commuter rail, although they
actually prefer an increase over no increase. They have positive chance of
randomly choosing slightly higher taxes for more investment on streetcar
whatever her true preference is. We discuss policy implications of the
empirical results. |