3
$\begingroup$

I am conducting a quantitative correlational study. The ultimate goal of this research is to determine the relationship between the multiple independent variables and a single dependent variable.

So, my question is what statistical can you recommend to approach this study?

Any recommendation and insights will be much appreciated.

PS. I am a newbie in quantitative research. I am willing to learn.

Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ You can use structural equation modeling (SEM) with diagonal weighted least squares (DWLS) estimation :-) $\endgroup$
    – john.abraham
    Commented Jan 8, 2022 at 0:39

2 Answers 2

Reset to default
2
$\begingroup$

You can build a logistic regression and compute p-values for each covariate using the t-test, i.e., using the parameter estimate divided by its standard error. The significance of this statistic based on the t distribution is given by the p-value, so the effects with the smallest p-values are the most significant.

Improve this answer
$\endgroup$
2
$\begingroup$

The first thing I would (always) do is simply plot the data. That‘s probably the fastest and most intuitive way to get a solid understanding of your data and will help you to identify possible relationships between variables. This will also help you to come up with a suitable statistical model if needed.

As far as I can tell, Mosaic plots seem to be a good format for the kind of data you are investigating: https://en.wikipedia.org/wiki/Mosaic_plot

Improve this answer
$\endgroup$
7
  • $\begingroup$ I believe OP wanted to determine the relationship between his covariates and the target variable, i.e., how well does the covariates predict the target set, and to which degree do each covariate contributes to the prediction. $\endgroup$
    – Jay Ekosanmi
    Commented Jan 8, 2022 at 0:26
  • 1
    $\begingroup$ The stated goal is to "analyze the relationship". As far as I'm.concerned, my answer is not mispaced here. If I missed something, could you please elaborate? Thanks $\endgroup$
    – Daniel Koska
    Commented Jan 8, 2022 at 8:10
  • 1
    $\begingroup$ Btw. @Jay, isn't your answer with p values for every covariate a classic example of multiple comparisons (and needs correction therefore)? Unfortunately I can't comment under your post, my CV score is just too low at this point. $\endgroup$
    – Daniel Koska
    Commented Jan 8, 2022 at 8:15
  • $\begingroup$ I think logistic regression is great advice, I'm just not so sure about the p value part (I'm not a big fan of p values in general, but let's not go into too much detail at this point). First of all, I think it's not a valid approach to judge effects on the size of a p value. A p value is either smaller or bigger than an a priori specified threshold. For 'everything else' you need effect sizes and estimates of precision (such as e.g. confidence intervals). $\endgroup$
    – Daniel Koska
    Commented Jan 8, 2022 at 13:30
  • $\begingroup$ Concerning the question of multiple comparisons I brought up (which I guess applies to multiple regression in general), I kinda liked this answer to a similar question: statalist.org/forums/forum/general-stata-discussion/general/… I think this question is probably interesting enough for a new/own thread at some point ;-) $\endgroup$
    – Daniel Koska
    Commented Jan 8, 2022 at 13:30

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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