Evaluating survey responses- Multiple regression vs. ordered logistic regression

[Jim Johnson]

I'm analyzing results for a survey that asked about satisfaction and provided potential options of

1-Very dissatisfied
2-Dissatisfied
3-Somewhat dissatisfied
4-Neutral
5-Somewhat satisfied
6-Satisfied
7-Very satisfied

Is this scale interval or ordinal? A reviewer is asking me to convert analysis from multiple regression to ordered logit, but in my mind these are interval responses.

[Andrew Musau]

You may be able to assume that the categories are spaced equidistant on the latent scale. But that may not be true of the respondents who answered the questions. I wouldn't argue with the reviewer on this point.