Statistical method to analyze data with one continuous IV and two categorical DVs

Hi,

I'm trying to find the right statistical method to analyze data with one continuous independent variable and two categorical dependent variables.

IV is Perceived Usefulness (scale coded:  1,2,3,4, or 5)
DV is Usage (scale coded:
Item 1:  (1) Never, (2) About once, (3) 2-3 times, (4) 4-5 times, and (5) More than 5 times a day.  
Item 2 (1) None, (2) Less than 1 hour, (3) 1-2 hours, (4) 2-3 hours, and (5) More than 3 hours. )
Please, no links to general discussion sites - I've been looking this up for hours.

Thanks for any help
LVL 1
taborrgAsked:
Who is Participating?
I wear a lot of hats...

"The solutions and answers provided on Experts Exchange have been extremely helpful to me over the last few years. I wear a lot of hats - Developer, Database Administrator, Help Desk, etc., so I know a lot of things but not a lot about one thing. Experts Exchange gives me answers from people who do know a lot about one thing, in a easy to use platform." -Todd S.

duttcomCommented:
Wouldn't the IV be ordinal (and therefore categorical) rather than continuous? Or are there any number of values possible between 1,2,3,4 and 5 for perceived usefulness? I am currently doing a stats subject at uni so I am quite interested in this question.
0
taborrgAuthor Commented:
Hi Duttcom,

Perceived Usefulness has always been treated as continuous, in the literature I've seen, even though there are only 5 to 7 discrete choices on a Likert scale.  Some new surveys use a slider to get real continuous data.

Thanks.
0
duttcomCommented:
Ah yes, I can see why now. A perceived usefulness of 3.75 would be a perfectly valid result, whereas there is no value possible between two categories.

Hmmm. Is there some way you can combine the two DVs (say, with a matrix) and then compare the matrix value with the IV? I'm not sure if that's even a valid approach strictly statistically speaking.

But hey, you came here for an answer, not more questions, so don't feel you have to keep responding - you clearly know what you are doing.
0
Angular Fundamentals

Learn the fundamentals of Angular 2, a JavaScript framework for developing dynamic single page applications.

taborrgAuthor Commented:
Well, I think I know what I'm trying to do.  But why does this not come up with a simple Google search?  I think this might be muddy waters.

Thanks.
0
duttcomCommented:
I think you may be right about this being muddy. I can think of lots of ways to compare variables, but not three at once in that combination. There must be a way to combine the two DVs in such a way that you can still make sense of the data, since I am assuming what you are trying to do is compare the perceived usefulness with the amount of time spent using the resource? This is what I meant before about using a matrix to combine the two DVs into a set of scores -
Score matrixThe columns would be Item 1 and the rows would be Item 2, so a score of 43 would be 4-5 time for 1-2 hours.
0
TommySzalapskiCommented:
This looks like a simple multivariate regression analysis problem.
Make sure you check for multicollinearity.

You could also just do two normal regression analysis problems, use one DV as the DV and the other as a second IV and do the calculation and then swap them and do it again.
0
taborrgAuthor Commented:
Hey  TommySzalapski,

I don't understand what you're saying.

It's a basic Technology Acceptance Model 3  (TAM 3) problem.
TAM 3

Thanks.
0
TommySzalapskiCommented:
You asked for a statistical method to analyze two DVs. Multivariate linear regression is what I would use. You can do a Google search for Analysis of Multivariate Categorical Variables and you will see several other methods (and books and scholarly articles and whatnot).
0

Experts Exchange Solution brought to you by

Your issues matter to us.

Facing a tech roadblock? Get the help and guidance you need from experienced professionals who care. Ask your question anytime, anywhere, with no hassle.

Start your 7-day free trial
taborrgAuthor Commented:
I'm totally ignorant in this subject.  What I need is the name of an analysis technique, such as "One way ANOVA", "PPMC", etc.  

Then I will run the data through SPSS.

Thanks
0
taborrgAuthor Commented:
Thanks.  But I think I asked the wrong question.
0
taborrgAuthor Commented:
BTW:

The real answer is .....

Multinomial Logistic Regression.

Found it on my last Google gasp.


Any kind(s) of IV ----> Categorical (nominal) DV
0
It's more than this solution.Get answers and train to solve all your tech problems - anytime, anywhere.Try it for free Edge Out The Competitionfor your dream job with proven skills and certifications.Get started today Stand Outas the employee with proven skills.Start learning today for free Move Your Career Forwardwith certification training in the latest technologies.Start your trial today
Math / Science

From novice to tech pro — start learning today.