seminars:stat:160324
Differences
This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revision | |||
| seminars:stat:160324 [2016/03/21 18:01] – shang | seminars:stat:160324 [2016/05/02 01:45] (current) – aleksey | ||
|---|---|---|---|
| Line 1: | Line 1: | ||
| + | <WRAP centeralign>## | ||
| + | ~~META: | ||
| + | <WRAP 70% center> | ||
| + | ^ **DATE: | ||
| + | ^ **TIME: | ||
| + | ^ **LOCATION: | ||
| + | ^ **SPEAKER: | ||
| + | ^ **TITLE: | ||
| + | </ | ||
| + | \\ | ||
| + | |||
| + | <WRAP center box 80%> | ||
| + | <WRAP centeralign> | ||
| + | We propose a new diagnostic plotting method, | ||
| + | called the marginal distribution plots, | ||
| + | for the linear regression model. | ||
| + | The method induces a class of model checking tests. | ||
| + | The MD approach has certain | ||
| + | existing model checking tests. | ||
| + | It can be a nice complement to the existing approaches. | ||
| + | Simulation results suggest that the MD tests are more powerful | ||
| + | than the existing tests when the linear regression models are not | ||
| + | appropriate. </ | ||
