Multi regression with Standard Errors in C# using GSL [C# .NET GSL]

Main : .NET :

Category: .NET	View Full Details
Multi regression with Standard Errors in C# using GSL
Submitter: vanna	Date: 2011/1/19

Description: The attached file contains a function DoMultiParameterFit to perform multi parameter regression. Cioefficients are returned in parameter betaVec, while Standard Error is returned in out parameter stdErrorResiduals Example usage: static void TestMultiParameterFit() { double[] obs = new double[]{ 0.775152156, 0.212969663, 0.494751764, 0.77712995, 1, //0.748404191, 0.779557101, 2, //0.38384782, 0.696799969, 0.674492839, 0.284649573, 0.496014531, 0.838613229 }; double[,] indepmat = new double[,]{ {1,0.788096265218347,0.746593708978196}, {1,0.0255426131849941,0.00457187860244002}, {1,0.248018064297132,0.514105818411815}, {1,0.552009242813257,0.953928496986185}, {1,0.616359144209673,0.823678881758479}, {1,0.910346382602459,0.627853132497875}, {1,0.120170501107987,0.347017026347369}, {1,0.333580471002668,0.936537292790489}, {1,0.820704328615048,0.457125411270979}, {1,0.115441459553873,0.10251203158771}, {1,0.0807673391304329,0.650217706388172}, {1,0.92757999311497,0.77972171347426} }; double residualSumOfSquares; double[] stdErrorResiduals; double[] betavec; GSLHelper.DoMultiParameterFit(obs, indepmat, out betavec, out residualSumOfSquares, out stdErrorResiduals); } Got a question or problem with this link? Just enter your message and click on submit. No registration is required. Note: A copy of this message will also be emailed to the submitter of this link
279 0 bytes C# .NET GSL http://www.quantcode.com/
Rating: 0.00 (0 votes) Rate this File \| Modify \| Delete \| Report Broken File \| Tell a Friend \| Comments (10)

Poster	Thread
Anonymous	Posted: 2012/3/8 17:34 Updated: 2012/3/18 11:06
	Multi regression with Standard Errors in C# using GSL My name is Sergei Belov (QuantCode user hyperstrings2003, email hyperstrings2003@yahoo.com) I am MIT Math Ph.D with 15-year financial quant experience I am testing your "Multi regression with Standard Errors in C# using GSL" and am experiencing 2 strange problems: 1) when I compile "x86" (Debug or Release" I am getting the following error message: Managed Debugging Assistant 'PInvokeStackImbalance' has detected a problem in 'C:\gsl-1.8-src\bin\Release\ConsoleApplication.vshost.exe'. Additional Information: A call to PInvoke function 'ConsoleApplication!multfittest.GSL::gsl_matrix_set' has unbalanced the stack. This is likely because the managed PInvoke signature does not match the unmanaged target signature. Check that the calling convention and parameters of the PInvoke signature match the target unmanaged signature. But when I press "F5" many times (about 20) the program steps through all these error messages and continues correctly as successfully 2) When I am compiling with the options "x64" (Debug or Release" and copying GSL 64-bit DLL for C# use (which you provided in another download) the program crashes Which DLLs should I use for 64-bit version I really appreciate your help. Hope to be able to contribute my code as well (at least privately to you) Sergei

Discuss this file. Just enter your message and click on submit. No registration is required.