|
|
|
| (Intercept) | 0.364653* |
| (0.212242) | |
| TV | 0.002901 |
| (0.002203) | |
| Radio | 0.046434*** |
| (0.002908) | |
| TV2 | -0.000006 |
| (0.000005) | |
| log(TV) | 1.876490*** |
| (0.074863) | |
| TV * Radio | 0.001020*** |
| (0.000017) | |
|
|
|
| AIC | 98.854463 |
| BIC | 121.942685 |
| CV | 0.094609 |
| R2 | 0.996696 |
| R2 | 0.996611 |
| F statistic | 11704.434016 |
| Observations | 200 |
|
|
|
| Note: *p < 0.1; **p < 0.05; ***p < 0.01 | |
This analysis explores the relationship between advertising budgets across TV and radio channels and their effect on sales, providing insights into how investments in these areas contribute to revenue. The 3D plot visualizes actual and predicted sales figures based on the optimal regression model (evaluated using cross-validation), illustrating the interaction between TV and radio spending. The light blue markers indicate observed sales data, while the darker surface represents predicted sales. Alongside, the static 2D plot showcases the alignment between actual sales points and the regression model's predictions for each predictor. Together, these visuals highlight the strength of the model in capturing the influence of media budgets on sales outcomes, offering a clear guide for data-driven advertising strategies.