I have a data set where I want to applied three methods: Logistic regression , linear regression and survival models, of couse each method focalise on an information part of the data set, my questions are:
It's coherent to incorporat all in the same study?
are they complementary methods ?
After estimation, can we select the best method and if so, which criterion we should use?
The Logistic Regression is appropriate for binary data, and Survival Analysis is appropriate for time to event data. There are similarities between the two and Logistic Regression can be used to analyze time-to-event data although it's not ideal.
As usual this depends on your research question(s). One can think of cases where the three could be combined in one paper But not on the same data. As noted by Salwa A. Mousa Binomial Logistic regression is about binary dependent variables, Cox regression is about time to event data. Both of these are linear statistical models. I presume you meant by your question OLS regression, where the DV is continuous. Again if your data is appropriate the answer is yes. For example, the attached uses more than one method, though the purposes are a bit different than I suspect you have in mind. Best wishes, David Booth
Thank you so much dear professor@David Eugen, yes I want to applied them on the same data set, and see how the explanatory variables behave when we change the target and the scale of the dependent variable.
Thank you also for Dr @salwa, yes I know the difference dear professor.
I agree with everyone else about needing to know your research question and the outcome measure(s) you want to study. I'll add that with your mention of OLS regression and logistic regression, I wonder if ordinal logistic regression would also be something to consider because it is midway between the two. You could divide your outcome into tertiles or quantiles, say, and look at which factors predict upward or downward movement through them. I'll finish by saying that both methods -- transforming a continuous regression into either and ordinal logistic regression or logistic regression -- lose information, so you should have a good reason for doing them that outweighs that con.
Thank you dear professor Linda Hermer , I want to modelise the age at first marriage; for that I want to estimate the effect of explantory variables on; statisticaly, this variable can be measured as :
Continuois, where we have two possble methods: linear regression or survival models (because we have censord observations; persons not married).
or we can target the probability of get married vs not married ; so we can use logistic models (as shown in attached ifgure).
My question dears is: can we applied the 3 methods on the same data set, and see what are the effects of explanatory variables on age at first marriage in the continuos scale, and dichotomous scale; and is it a logical appraoch ?
Chellai Fatih do notice that the DVs are of different types so all methodswill only work with am paricular DV type and hence can't be compared on the same data.