[IxDA Discuss] Asking questions to participants in a positive or negative way ?

[Jessica Enders]

Chiwah Liu says:

"If we don't have enough user to reach a statistical significance
(let's say less than 100 users) for our survey, we should add a
'neutral' option. The users who don't have any idea can bias the
survey."

I'm not sure what you mean by a 'neutral' option but it sounds
like what you are referring to is a middle option on a scale. 

I think it is important to distinguish between a middle option (e.g.
neither agree or disagree) and a don't know/no opinion option. A
middle option can allow the users to say "I feel a little bit in the
positive and a little bit in the negative, at the same time" whereas
a don't know/no opinion option allows them to say they genuinely
don't have a view.

Research on the effect of a middle option on the distribution of
answers is mixed. In some, but not all, research cases, the middle
option did not have an affect on the overall relative proportion of
positive and negative responses. 

As to users with no idea biasing the survey, I would ask what
evidence you have of this? Presumably, if you don't provide a don't
know/no opinion option, some users will resign themselves to a
positive response and some will resign themselves to a negative
response. I'm not aware of any research that suggests absence of an
opinion leading to bias in survey results.


. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Posted from the new ixda.org
http://www.ixda.org/discuss?post=29233