When analyzing data with a regression, statisticians are often concerned with the residuals. What are residuals and why are they important?
What will be an ideal response?
The difference between predicted and observed values is called a residual. Although a formal analysis of residuals in the multivariate context can be tricky, a systematic scrutiny of their sizes may reveal some aspects of the data worth exploring further. By subtracting the predicted value from the observed value of Y, we can identify large or small values that stand out from the rest. For whatever reason, these cases do not seem to fit the mold. It is important to try to understand why these cases stand out to better understand the relationship between variables. Perhaps, a mistake was made in coding the data. Maybe these are particularly interesting cases that need further explanation. One way or the other, they are important.
You might also like to view...
The fact that many people were surprised when Barack Obama came to office and pursued health care reform, strengthened financial market regulations, and ended America's involvement in Iraq can be seen as a result of what?
a. media coverage of the election as a horse race b. stringers who go after sound bites c. social media discussion of the election d. microtargeting strategy by advertisers e. media bias reflected in election coverage
Which of the following is typically provided to hospitals and health facilities in order to privatize the provision of government services?
A. vouchers B. franchises C. contracts D. grants