From the course: The Data Science of Economics, Banking, and Finance

Unlock the full course today

Join today to access over 24,900 courses taught by industry experts.

Bias and risk in financial and economic modeling

Bias and risk in financial and economic modeling

From the course: The Data Science of Economics, Banking, and Finance

Bias and risk in financial and economic modeling

- [Narrator] In 1972, Luther Ingram had a hit with the song "If Loving You Is Wrong, I Don't Want to Be Right." And when it comes to data, maybe you don't want to be right either, at least not in the strictest possible sense of the word. You may be familiar with the famous line from the statistician George Box who said, "All models," all statistical models, "are wrong, but some are useful." What he meant by that is the analysis will never mirror the data exactly perfectly a hundred percent, but that's okay. It's okay to be approximate as long as it is useful. You think about this. Analysis is by necessity, by its nature, a simplification of the original data. And it makes me think of the simplifications in a game. You see these icons here. You know what they all are even though they are extremely low resolution. The game can still be enormously engaging even when it has low resolution representations like this. The simplifications are useful. They allow the game to run faster and on…

Contents