If y is a dependent variable (aka the response variable) and x1, …, xk are independent variables (aka predictor variables), then the multiple regression model provides a prediction of y from the xi of the form
Topics
- Basic Concepts
- Matrix Approach to Multiple Regression Analysis
- Using Excel to Perform the Analysis
- Real Statistics Capabilities
- Regression using the Solver option
- Categorical Coding
- Testing Regression Coefficients
- Seasonal Forecasts using Regression
- Sample Size Requirements
- Alternative Approach to Multiple Regression Analysis
- Interpreting Regression Coefficients
In addition, some theoretical issues are described on the following webpage that may be of interest to some readers who know calculus:
Reference
Howell, D. C. (2010) Statistical methods for psychology (7th ed.). Wadsworth, Cengage Learning.
https://labs.la.utexas.edu/gilden/files/2016/05/Statistics-Text.pdf
Good afternoon,
for a study project I’d like to predict something unconventional. I want to test if there’s a relationship between increasing / decreasing interest rates and suicides (including timefactor (day, month, year), gender, ethnicity & age-group). Unfortunately I don’t know if the muliple regression analysis is the right analysis to test this?! But if so, am I’m right in my assumption that the absolute suicides is my dependent variable? I categorized the independent variables with 0/1 for gender, ethnicity, interest rate increase / decrease –> for age groups I used 1-5, weekday = 1-7, month = 1-12 and year 1999-2020.
Can I use the data like this to fill the modell?
Many thanks for your answer in forward.
Kind regards
Daniel
Hello Daniel,
Yes, you can use these as independent variables in multiple regression. Note that interactions between weekday D, month M, and year Y won’t be considered unless you add the variables D*M, D*Y, M*Y, and D*M*Y to the model. This is only necessary if you want to consider these interactions.
Charles