Create a new research question about attitudes for which you can define 2 good variables.  For each of the variables for that research question, create a survey question to measure it.  Format...

Create a new research question about attitudes for which you can define 2 good variables.  For each of the variables for that research question, create a survey question to measure it.  Format your response as follows:

Research question

1. Variable 1 name

  • measurement scale of variable 1 (nominal, ordinal, interval, ratio)
  • survey question to measure variable 1
  • allowed responses to survey question 1

2.  Variable 2 name

  • measurement scale of variable 2 (nominal, ordinal, interval, ratio)
  • survey question to measure variable 2
  • allowed responses to survey question 2

1 Answer | Add Yours

pohnpei397's profile pic

pohnpei397 | College Teacher | (Level 3) Distinguished Educator

Posted on

One possible research question would be about the connection, if any, between attitudes having to do with global warming and those having to do with gay marriage.  We could measure each of these attitudes separately and then see if there were correlations between them.  Our research question would be something like “are people who do not believe that global warming is caused by humans more likely to be opposed to same-sex marriage?”

First, we would need to measure attitudes towards global warming.  We could ask a question like “respond to the following statement: global warming is caused by human activity.”  We would then give the respondents five options for their answers.  These options would be not sure, strongly disagree, somewhat disagree, somewhat agree, and strongly agree.  The last four of these are probably ordinal data.  There is a clear ordering to these variables as they move from least to most agreement with the statement.  However, they are probably not interval data because the “distance” between strongly agree and somewhat agree may not be the same as the distance between somewhat agree and somewhat disagree.  “Not sure” does not go with the other options and should be considered to be part of a nominal scale.  On the nominal scale there is “not sure” as one option and everything else as the second option.  Once a respondent has chosen anything other than “not sure” their response falls somewhere on the ordinal scale.

Our question for the second variable could be similar to the first.  It could be “respond to the following statement: same-sex couples should have the right to marry.”  The respondents would have the same options for answers.  

Sources:

We’ve answered 318,929 questions. We can answer yours, too.

Ask a question