Multiple Regression Analysis - Determine the objectives of MRA

6 important questions on Multiple Regression Analysis - Determine the objectives of MRA

Within the objectives stage, we check the aim of the MRA (prediction vs explanation) (whether it's appropriate to use MRA or not), we specify statistical relationships and select independent and dependent variables. What is the difference between the aims prediction vs explanation?

Prediction; try to maximize the predicted value of the dependent variable. Interested in what set of predictors (independent variables) has the highest prediction power in the dependent variable.

Explanation; interested in the lineair dependencies between different independent variables and the dependent variable. You check the importance of the independent variables, types of relationships found or the interrelationships among the independent variables.

When specifying the statistical relationship, we check whether the relationships have lineair forms. What should we do when we do not have lineair forms?

Then we should include polyneme terms: quadratic or cubic.

What are the two characteristics of a statistical relationship?

1. More than one value of the dependent variable will be observed for any value of an independent variable.
2. Error in the dependent variable is assumed to be random.
  • Higher grades + faster learning
  • Never study anything twice
  • 100% sure, 100% understanding
Discover Study Smart

What is the difference between SEM and MRA regarding error?

The difference between SEM and MRA regarding error is that SEM can handle error terms and directly assess the error. This is not possible for MRA.

What is omitted bias, what is its impact and how can this be avoided?

Omitted bias is that you forgot to include one or some relevant independent variable to the model. This results in the IV's included might explain more variance, than they indeed do.

You can avoid omitted bias by trying out MRA for also irrelevant variables.

What are curvilinear relationships?

These are relationships that are not lineair, either being positive or negative quadratic, cubic etc. We can use polynomials to overcome this.

The question on the page originate from the summary of the following study material:

  • A unique study and practice tool
  • Never study anything twice again
  • Get the grades you hope for
  • 100% sure, 100% understanding
Remember faster, study better. Scientifically proven.
Trustpilot Logo