.NET Tutorials, Forums, Interview Questions And Answers
Welcome :Guest
Sign In
Register
 
Win Surprise Gifts!!!
Congratulations!!!


Top 5 Contributors of the Month
Kaviya Balasubramanian
Sgraph Infotech
Imran Ghani
Post New Web Links

Could not derive coefficient and regression coefficients from Logistic Regression predictions.

Posted By:      Posted Date: May 22, 2011    Points: 0   Category :
 

Does anyone know how I can get the coefficient and regression coefficients for each prediction that the Logistic Regression made? I've sifted through all of the mining functions and none of them seems to be the same.

Thanks in advance!


MCP, MCSD, MCDBA (dB Wizards)


View Complete Post


More Related Resource Links

SSAS logistic regression vs. vanilla logistic regression

  
I recently ran the same data set through the SSAS logistic regression (Neural network - Hidden layer disabled) as well as a vanilla logistic regression procedure. I am aware that different processes are followed in order to obtain the resulting co-efficients, however, has anyone got further information as to how close the results of the SSAS logistic regression equation are in comparison to logistic regression equations contained in other statistical packages such as SAS or SPSS? I do understand that the respective procedures are dependant on the quality of the data that they are applied to. I assume that the SSAS logistic regression may perform more favourably on one dataset in comparison to a vanilla logistic regression and vice versa. I am aware of the following post however it does not go into much detail concerning the results of the comparison. http://social.msdn.microsoft.com/Forums/en/sqldatamining/thread/4f381c6b-2471-4d4c-a022-316a1073184d Further info would certainly be appreciated.

Logistic regression co-efficients

  

I am currently conducting my own benchmarking exercise on a dataset making use of the SSAS logistic regression algorithm.

The issue that I currently face is that I am obtaining a very linear set of results, i.e. the co-efficients of the regression equation are all neatly staggered, when run through two alternate software packages other than SSAS. When I run the same dataset through the SSAS logistic regression algorithm and extract the results, i.e. I extract the co-efficients from the model, the neat linear set of co-efficients become completely non-sensical and do not follow any trend whatsoever.

I am conducting some preperation of the dataset before it is run into each algorithm i.e. I am discretising the dataset into "classes" of my choosing by conducting additional analysis on the underlying data trends. One of my variables is set to "predict only" while all of the other variables are set as "discrete" and "input". The reason for the use of "discrete" is due to the fact that I am assigning a class ID to each piece of data depending on the which "class" the particular value falls into. As a result, I obtain a corresponding co-efficient for each class. e.g. variable = Age. I break this into classes 0-18, 19-35, 36 - 74, >=75, assign a class ID and feed this, along with all

T-SQL linear regression in multiple dimensions

  
Hi! I'm trying to make linear regression T-SQL in multiple dimensions  (y = a + a1*x1+ ... a2*xn) like LINEST function in Excel.I need create a similar stored procedure in SQL Server.I also created the code using the article http://charlottecredittechnology.blogspot.com/2008/11/sql-2008-excel-like-linest-function.html but i have troubles in re-adapt to a model with multiple dimensions...thanks!

Making Batch Predictions from a stored procedure

  
I have a decision tree that will make predictions about customers as they make their first purchase with our company. I'd like to have a table append the predictions and the probabilities of these predictions to a customer table in our reporting database.  So from a table that has all my inputs how can I make a stored procedure that would append my prediction and the probability without having to call an open query statement for each row?   In other words how can I make a batch prediction on Table with a stored procedure? Select t.[Key], Predict([Predict_Tree].[Predict Variable]) as [Prediction], predictProbability([Predict_Tree].[Predict Variable]) as [Probability] From [Predict_Tree] Natural Prediction Join (Select 12280 as [Key], 999 as [Input1], 'Stuff' as [Input2], 'MoreStuffl' as [Input3], 'LotsOfStuff' as [Input4], 'Deleted' as [Input5], 'For' as [Input6], 'Privacy' as [Input7], 1 as [Input8], 2 as [Input9], 'Purposes' as [Input10], 3 as [Input11], 1 as [Input12], 0 as [Input13], 'bTard' as [Input14]) AS t

How to derive actual physical memory consumption by a process?

  

Hello,

I am doing performance analysis of SSRS reports (2008).

Before doing anything, I check in Task Manager(Performance tab) and see that my overall physical memory which is 8GB, is already divided between available memory and system cache. I have also setup perfmon counters and logging data for available memory counter.

Now when I launch a huge report with 2 million records, it starts consuming the available memory and I notice in Task Manager(Performance tab) the available memory is reducing BUT I also notice that the system cache is also reducing (I assume that perhaps OS is borrowing memory from system cache to put it in available memory?) If my assumption is correct, then I would not be able to calculate how much physical memory my report used because it also includes a portion of system cache(?)

OR is the system cache reducing due to disk I/O?

This is getting confusing for me, please help me out experts.

Regards.

 

 


How to derive actual physical memory consumption by a process?

  

Hello,

I am doing performance analysis of SSRS reports (2008).

Before doing anything, I check in Task Manager(Performance tab) and see that my overall physical memory which is 8GB, is already divided between available memory and system cache. I have also setup perfmon counters and logging data for available memory counter.

Now when I launch a huge report with 2 million records, it starts consuming the available memory and I notice in Task Manager(Performance tab) the available memory is reducing BUT I also notice that the system cache is also reducing (I assume that perhaps OS is borrowing memory from system cache to put it in available memory?) If my assumption is correct, then I would not be able to calculate how much physical memory my report used because it also includes a portion of system cache(?)

OR is the system cache reducing due to disk I/O?

This is getting confusing for me, please help me out experts.

Regards.

 

 


C# why class cannot derive from type parameter?

  

Unlike C++, why template class can not be derived from type parameter in C#

public class FeatureObject <Interface> : FeatureBase, Interface
{

}

it give compiler error: cannot derive from 'Interface' because it is a type parameter.

Any reason?

 

.


C--s
Categories: 
ASP.NetWindows Application  .NET Framework  C#  VB.Net  ADO.Net  
Sql Server  SharePoint  Silverlight  Others  All   

Hall of Fame    Twitter   Terms of Service    Privacy Policy    Contact Us    Archives   Tell A Friend