turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- Analytics
- /
- Data Mining
- /
- Proc Logistic , please help. Thanks

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

03-14-2013 03:29 PM

Hi All,

Just a quick one regarding proc logistic in SAS, I have entered 15 variables in my model and 14 variables seem to be good, does it mean that I should keep all of them in my model? Also I have troubles at understanding the concordent and disconcordent. Does it mean that the model has predicted 80.5% correctly??If I add variables or remove which statistic should tell me that the model is still good. Is it C (AUC value)? In the past, I was using another software to build models, so I am bit lost..

Many Thanks

Summary of Forward Selection | |||||

Step | Effect | DF | Number | Score | Pr > ChiSq |

Entered | In | Chi-Square | |||

1 | HOLIDAYS_EVER | 1 | 1 | 25674.4253 | <.0001 |

2 | No_Open_Emails | 1 | 2 | 9588.2483 | <.0001 |

3 | ATTRIBUTE1 | 2 | 3 | 5585.7066 | <.0001 |

4 | PROMO | 1 | 4 | 2264.6877 | <.0001 |

5 | AcornCategory | 6 | 5 | 2352.6139 | <.0001 |

6 | WEEKLY_AVG_TRANSACTI | 1 | 6 | 1488.1469 | <.0001 |

7 | PREFERENCE_CODE | 1 | 7 | 1126.3222 | <.0001 |

8 | TOT_PRODUCTS | 1 | 8 | 777.0709 | <.0001 |

9 | AFFLUENCE_KEY_DESC | 4 | 9 | 425.1519 | <.0001 |

10 | LIFESTAGE_KEY_DESC | 3 | 10 | 478.32 | <.0001 |

11 | TOTAL_VALUE | 1 | 11 | 354.7241 | <.0001 |

12 | REGISTRATION_DELIVER | 1 | 12 | 261.7896 | <.0001 |

13 | DISCOUNT | 1 | 13 | 34.4105 | <.0001 |

14 | REFERER | 1 | 14 | 9.2234 | 0.0024 |

Association of Predicted Probabilities and Observed Responses | |||

Percent Concordant | 80.5 | Somers' D | 0.611 |

Percent Discordant | 19.4 | Gamma | 0.612 |

Percent Tied | 0.2 | Tau-a | 0.279 |

Pairs | 9109345450 | c | 0.806 |

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to Question

03-14-2013 03:46 PM

I highly suggest you review the following pages and then try asking your question again. This is a very broad question, in my opinion.

Statistical Computing Seminars: Introduction to SAS proc logistic

https://www.google.com/search?q=proc+logistic+site%3Alexjansen.com

Google search using: proc logistic site:lexjansen.com

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to Question

03-14-2013 03:53 PM

Hi,

being a classically trained statistician who was introduced to data mining only later in my career, I consider myself biased against data dredging. Stepwise selection is often brought up as a pragmatic example of using computational power to replace domain knowledge. In data mining is it not uncommon to start with hundreds or thousands of variables. It is just unpractical to analyze one variable at a time. That’s where I tend to use stepwise regression, as an initial variable selection method used in combination with other variable selection methods such as decision trees, IV,…

In your case it seems like you’re starting with a small number of variables. That’s where domain knowledge should come in to help decide what to include and what to exclude, sometimes regardless of their p-value.

G

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to Question

03-14-2013 04:09 PM

A quick one you say? Not sure.

You have a large number of cases, which means that you could detect very subtle effects which in fact don't make any practical difference. A statistically significant effect is not necessarily an important effect. One way you can assess the importance of an effect empirically is by looking at the change in Percent Concordant when you remove a variable from the model.

Percent concordant is the proportion of matching prediction changes, i.e. if case i is not an event and case j is an event, then if predicted P(i) < P(j) then the ij pair is concordant, if P(i) > P(j) the pair is discordant and if P(i)=P(j) then the pair is tied.

hth

Pg

PG

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

Posted in reply to PGStats

03-14-2013 04:18 PM

This seems to be an overfitting problem, I suggest check collinearity before adding variables in the analysis.

Naeem