Question

What are a few day-to-day (or work) situations in which regression is used (consciously or not)? Why is regression appropriate? Would another analysis type be more appropriate, and why? For example, instrument calibrations often make use of regression.

Answer 1

The example given below explains Regression with a daily life situation :

Let's say you are taking a cab ride to some place. The moment you step foot in the cab, you see that there's a fixed amount there, say 'X' dollars. That's the amount the you have to pay the driver, if you have stepped into a cab. Then as ride begins, for every fixed distance lenght say a km, the fare increases by a certain amount. So, there's a relationship between the distance covered and the amount you would be paying, plus that constant of 'X' dollars. If you're stuck in traffic, then every additional minute you are in the cab, you have to pay accordingly. As the time passes, your fare increases, as the distance increases, your fare increases too, and while all this is happening, you've already paid a base fare, which is the constant 'X'. Now here comes the use of Regression. It tells you what the base fare is and explains the relationship between time and the fare you have paid and the distance you have traveled and the fare you have paid. Because in the absence of knowing those relationships, and just knowing how much people traveled for, and how much they paid, regression allows you to compute that constant that you didn't know earlier and it would compute the relationship between the fare and the distance, and the fare and the time. That's regression.

Other examples where Regression is applicable can be :

• Does the social and economic status of a country has any affect educational achievement of it's individuals?
• Do fitness regimes and controlled diet effect gain/ loss in weight?
• Is drinking alcohol related to mortality rate?

There is not only but more than one regression models and the most appropriate model depends on the type of question that is asked before us and the specific answers that we need to obtain. To name some of them, we have :

• Linear Regression
• Logistic Regression
• Polynomial Regression
• Quantile Regression
• Ridge Regression
• Ordinal Regression
• Poisson Regression
• Negative Binomial Regression
• Quasi-Poisson Regression
• Cox Regression

If it were for 1 or 2 models then it would have been relatively easier to decide which regression model would be the most appropriate to meet our current needs but there are numerous types of regression models that we can put into use. And to come up to a decision to choose the best model we need to look into the kind of data that we have for the dependent variable and the type of model which is providing us with the best fit.