In case the Dependant variables (DVs) are all continuous variables, the Multivariate Linear Regression ( continuous Independent variables) or the MANOVA framework (categorical Independent variables) or MANCOVA ( combination of categorical and continuous type independent variables )can be applied.

Or, you might just look at the DV's separately. Often this is practically what you are interested in anyway.

It's also important to consider the type of data you have. With the measures you are using, can they be considered quasi-continuous ? Or are they ordinal data ?

Yes, multivariate regression can be used to analyze data with multiple categorical variables. In fact, it is a very common approach for this type of data.

Multivariate regression is a statistical method that is used to model the relationship between one or more dependent variables and two or more independent variables. The independent variables can be continuous or categorical.

To use multivariate regression with categorical variables, you will need to create dummy variables for each categorical variable. A dummy variable is a binary variable that takes on a value of 1 if the observation belongs to the category and 0 otherwise.

Once you have created the dummy variables, you can then include them in your multivariate regression model. The coefficients of the dummy variables will represent the effect of each category on the dependent variable.

For example, suppose you are interested in studying the relationship between gender and salary. You could collect data on the gender and salary of a group of employees. Then, you could create a dummy variable for gender, with 1 representing male and 0 representing female. You could then include this dummy variable in a multivariate regression model to estimate the effect of gender on salary.

Multivariate regression is a powerful tool for analyzing data with multiple categorical variables. It can be used to identify the relationships between different variables and to predict the outcome of a dependent variable based on the values of the independent variables.

Here are some examples of how multivariate regression can be used with categorical data:

• To study the relationship between gender, ethnicity, and income.
• To study the relationship between education level, work experience, and job satisfaction.
• To study the relationship between political party affiliation, age, and voter turnout.
• To study the relationship between advertising spending, product quality, and sales.

Multivariate regression is a complex topic, but there are many resources available to help you learn more about it. If you are interested in using multivariate regression to analyze your data, I recommend that you consult with a statistician.

Ahlam Hanash Gatea , are you making a career of posting replies copied from ChatGPT ?

On my feed today there are about 10 from you, all from yesterday.

Responses from artificial intelligence tools

Ahlam Hanash Gatea , does that apply to all your responses on your profile ? Don't you think you should label each post you make at the top, "The following response is copied from artificial intelligence tools." ?

I really don't understand why people do this, but I would ask you consider: These types of responses don't help anyone. 1) If someone is capable of asking a question on ResearchGate, they are capable of asking their question to ChatGPT. 2) These responses are long, and difficult for someone to get through, especially if English isn't their first language. 3) These responses are usually filled with incorrect, misleading, or irrelevant information.

Not all responses

Ahlam Hanash Gatea, you have not responded to Sal Mangiafico's other question:

When you do post AI-generated responses, do you not agree that you should indicate very clearly (at the top) that they were generated using genAI?

You can use multivariate regression, but you need to check the assumptions for this method. The variable Y must be random and continuous. X must be a controllable variable. Similar to what was seen in simple linear regression, the following assumptions are made:

(i) the response variable Y is a linear function of the explanatory variables Xj, j = 1, 2, . . . , k;

(ii) the explanatory variables Xj are fixed;

(iii) E(εi) = 0, that is, E(") = 0, with 0 being a vector of zeros of dimensions n × 1;

(iv) the errors are homoscedastic, that is, Var(εi) = E(ε2i ) = σ2;

(v) the errors are independent, that is, Cov(εi, εi′) = E(εiεi′) = 0, i ̸= i′;

(vi) the errors have a normal distribution.