I thought you were someone else, but now that I know you're not - I want to make something clear: I think that social desirability bias affected the answers of respondents much more [1].
To be clear, that's not the MARGIN of error in those statistics, but rather the difference between predicted and actual. In a five-tier scale, separated between groups, there is already statistical manipulation by having fewer respondents per-category, and therefore a higher margin of error between each. A margin of error even in low single-digit percentages can completely compromise the outcomes of data presented in this fashion.
How wrong do you believe this poll is? Can you use some methodology to come up with a modified margin of error that encompasses what you believe to be more realistic?
"How wrong" is something I can't quantify. It’s tough to pin down a single “modified margin of error,” but I’d say it’s bigger than what the poll shows. Multi-tier questions automatically have smaller sample sizes per option, which inflates the margin of error. Throw in social desirability bias (people not wanting to admit an unpopular opinion) and you get systematic skews on top of random error.
To be clear, that's not the MARGIN of error in those statistics, but rather the difference between predicted and actual. In a five-tier scale, separated between groups, there is already statistical manipulation by having fewer respondents per-category, and therefore a higher margin of error between each. A margin of error even in low single-digit percentages can completely compromise the outcomes of data presented in this fashion.
1 - https://news.ycombinator.com/item?id=42643027