1
$\begingroup$

Nonstatistician needs help with terms. Is the following an example of a univariate analysis?: Chances of getting a job at Microsoft with respect to demographic variables such as age, gender, race, etc. The odds are calculated both for individual variables (say, gender) and for combinations of variables (say, gender + age). What's the best way to describe such a study?

"This study consists of a _______ analysis of Microsoft employees to determine the correlation between getting a job at Microsoft and demographic variables such as . . ."

What's stumping me is the presence of multiple variables, so how can this be a univariate analysis?

Thank you!

$\endgroup$
1
  • $\begingroup$ In a regression setting, we typically use “multivariate” with respect to the response. An example of a multivariate regression variant of what you posted is one variable measuring the probability of working for Microsoft and one variable measuring the probability of having a dog. $\endgroup$
    – Dave
    Aug 5 at 23:52
3
$\begingroup$

This is a great question. Univariate means you have a single outcome you are studying -- chances of getting a job. To describe the multiple factors involved in analyzing this outcome, you would describe the analysis as multivariable. This refers to the independent variables age, gender, etc. The study could be described as both univariate (one outcome) and multivariable (many factors). The term multivariate would describe analyzing more than one outcome in the same analysis.

$\endgroup$
3
  • $\begingroup$ Hi: both answers above were great but just to add slightly to this: if you have muitiple independent factors-variables, then rather than referring to this as multivariate analysis ( because, as Geoffrey pointed out, the term multivariate analysis is referring to the response ), they refer to this case as multiple regression.. If you had multiple responses in the regression setting, this would be referred to as multivariate regression. So, definitely the terminology can be confusing. Usually, one can figure out the setting from the context and not worry too much about the terminology. $\endgroup$
    – mlofton
    Aug 6 at 1:25
  • $\begingroup$ Aha! I see I was confusing "multivariate" with "multivariable." Thanks so much for clarifying the difference! So I think this should be written as: "This study consists of a univariate analysis of Microsoft employees to determine the correlation between getting a job at Microsoft and demographic variables such as . . ." $\endgroup$
    – Eggy
    Aug 6 at 14:55
  • $\begingroup$ Given that this is an intersectional study that also considers combinations of variables, is there anything I need to add to that basic description of the study? $\endgroup$
    – Eggy
    Aug 6 at 15:02

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.