Linear Regression is a core technique in the field of Descriptive and Inferential Statistics (see Technique 3.9 in the IIBA Guide to Business Data Analytics). Data analysts seek to understand the strength of the association between variables in a dataset, and specifically to understand:

• Is there a relationship between variables (as seen by the P-value and the 95% Confidence Interval)?
• How quickly does one variable change in response to another variable (the slope of the line or the regression coefficient)?
• How much uncertainty is there in estimating the regression coefficient (the standard error)?

In this webinar, we introduce the technique of Linear Regression. Specifically, we will look at:

• Regression coefficients, standard errors, 95% confidence intervals, and P-values
• Measures of model fit
• Simple regression (with one variable as the predictor)
• Multiple regression (with more than one variable as the predictor)
• A brief comment about assumptions and diagnostics (how do we assess whether regression can be applied to our dataset)

Prior knowledge

- No previous knowledge of regression or statistics is assumed of webinar participants, though participants with prior knowledge will be more able to appreciate the more advanced material within the webinar.
 

Click Here to Register