The choice between MANCOVA (Multivariate Analysis of Covariance) and PLS-SEM (Partial Least Squares Structural Equation Modeling) for a multivariate model with both continuous and categorical independent variables depends on the research questions and objectives, as well as the characteristics of the data.

MANCOVA is a technique used to examine the relationship between a dependent variable and multiple independent variables, including both continuous and categorical variables. It is a parametric technique that assumes a linear relationship between the independent variables and the dependent variable, and assumes that the data follows a multivariate normal distribution. MANCOVA allows for the control of covariates and the examination of their effects on the dependent variable.

PLS-SEM, on the other hand, is a non-parametric technique used to examine the relationships between latent variables and observed variables. It is often used in cases where the relationships between variables are non-linear or where there are complex interactions between variables. PLS-SEM can handle both continuous and categorical variables, and can incorporate multiple dependent variables and control for covariates.

In general, if the research questions are focused on examining the relationship between a dependent variable and multiple independent variables, with the aim of controlling for covariates, MANCOVA may be the more appropriate technique. However, if the research questions are focused on examining the underlying relationships and interactions between variables, with the aim of developing a predictive model, PLS-SEM may be the more appropriate technique.

It is also important to consider the sample size, the distribution of the data,

and the level of measurement of the variables when choosing between MANCOVA and PLS-SEM. MANCOVA requires a larger sample size than PLS-SEM, and may not be appropriate for non-normal data. PLS-SEM may be more appropriate for data with small sample sizes, non-linear relationships, or complex interactions between variables.

Ultimately, the choice between MANCOVA and PLS-SEM should be based on a careful consideration of the research questions, objectives, and data characteristics, as well as a thorough understanding of the underlying assumptions and limitations of each technique.