Dear Mesaud,

Please see the following link and I hope it will help you:

https://statisticsbyjim.com/regression/choosing-regression-analysis/

Good luck

A general linear model (i.e. lm in R; PROC GLM in SAS) can be used for a continuous dependent variable and any number of continuous or categorical independent variables and their interactions. Usually ordinal independent variables are treated either as continuous or as categorical. ... If the data don't meet model assumptions, a generalized linear model may be appropriate.

LR, Logistic regression

Valentine Joseph Owan , the question asks about a model with a continuous dependent variable. Logistic regression would not be appropriate in this case.

LR - Linear Regression for continuous dependent variable, Logistic Regression for another case with categorical dependent variable.

You can use Linear Regression for continuous response.

Logistic regression for binary-categorical response.

Poisson regression for count-data response.

Beta regression if your response is a percentage.

I recommend this book for GLMs.

Dobson, Annette J., and Adrian G. Barnett. An introduction to generalized linear models. Chapman and Hall/CRC, 2008.

Linear Regression for continuous dependent variable and categorical variable you can use logistic regression.

Whenever the dependent is continuous and satisfied the classical LR assumptions. You can use LR to model it. However, in GLM case, the dependent variable do not have to be continuous but it can be count or categorical. Ofcourse, if it's categorical, then binary logistic regression model could be appropriate.