[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
Mandy fu <mandy.fu1@gmail.com> |

To |
statalist@hsphsun2.harvard.edu |

Subject |
st: matsize 5000 is too small for a matrix [231722,18] |

Date |
Fri, 21 Aug 2009 16:15:41 -0400 |

Hi all, I am working on a data set and met the matsize is too small problem. The detailed information is as follows: ----------------------------------------------------------- I am using Stata 10.0 SE. data set: observations:3,897,934 variables: 86 total size: 432,670,674, (58.4% of memory free). The matsize I set is 5000 (the largest value the system permits). When I try to do a simple matrix multipation, the stata gives error message that "matsize is too small for a [231722,18] matrix". The data set has been compressed already and unnecessary data has been dropped. ------------------------------------------------------------ I checked previous post and find most people say matsize 400 is enough usually. So, I was wondering if this means I can not do the matrix operation on this data set with Stata SE. If not, which other statistical software would you suggest me to use instead? Thanks a lot! Mandy * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

- Prev by Date:
**Re: st: svyset for survey with oversampling** - Next by Date:
**RE: st: Standard deviation of a moving window** - Previous by thread:
**st: Forecasting values are the same using ARMA (only its MA component)** - Next by thread:
**RE: st: matsize 5000 is too small for a matrix [231722,18]** - Index(es):

© Copyright 1996–2016 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |