|
Dear all,
I was trying to create a dataset consisting of polychoric correlations with the following syntax. DATASET DECLARE @cor. OMS /SELECT TABLES /IF COMMANDS=['Heterogeneous Correlation'] SUBTYPES=['Correlations'] /DESTINATION FORMAT=SAV NUMBERED=TableNumber_ [hidden email] /TAG='@cor'. SPSSINC HETCOR v2 v3 v4 v5 v6 v7 v8 /OPTIONS ESTIMATOR=twostep STDERR=TRUE MISSING=PAIRWISE N=TRUE TYPE=TRUE. omsend tag=['@cor']. However, I end up with an empty dataset. My guess (and I hope I'm wrong): everything OMS can catch has been built into OMS and since HETCOR is an extension, it hasn't been built into OMS. If so, then could Python spssaux.GetValuesFromXMLWorkspace 'grab' the correlation matrix? Or does it use OMS 'underneath the surface' in order to get such values? If so, is there any other not-extremely-unelegant way (Output Export to EXCEL?) to get my correlations out of the viewer and into a .sav file? Eventually, I want to run a PCA on them. TIA! Ruben van den Berg Consultant Models & Methods TNS NIPO Email: [hidden email] Mobiel: +31 6 24641435 Telefoon: +31 20 522 5738 Internet: www.tns-nipo.com Express yourself instantly with MSN Messenger! MSN Messenger |
|
See below. Jon Peck SPSS, an IBM Company [hidden email] 312-651-3435
Dear all, I was trying to create a dataset consisting of polychoric correlations with the following syntax. DATASET DECLARE @cor. OMS /SELECT TABLES /IF COMMANDS=['Heterogeneous Correlation'] SUBTYPES=['Correlations'] /DESTINATION FORMAT=SAV NUMBERED=TableNumber_ [hidden email] /TAG='@cor'. SPSSINC HETCOR v2 v3 v4 v5 v6 v7 v8 /OPTIONS ESTIMATOR=twostep STDERR=TRUE MISSING=PAIRWISE N=TRUE TYPE=TRUE. omsend tag=['@cor']. However, I end up with an empty dataset. My guess (and I hope I'm wrong): everything OMS can catch has been built into OMS and since HETCOR is an extension, it hasn't been built into OMS. >>>Not so. OMS is designed to catch everything specified by the selectors. You just need to specify the right OMS command identifier and table type. (In this case you could just omit the command identifier, since the subtype alone would pick out what you want.) You can find these items by right clicking in the outline on the item of interest. In this case you will find that the command type is 'SPSSINC HETCOR', and the table type is 'HeterogeneousCorrelations'. You don't see these items in the OMS Identifiers dialog or the OMS Control Panel, because those lists are predefined. If so, then could Python spssaux.GetValuesFromXMLWorkspace 'grab' the correlation matrix? Or does it use OMS 'underneath the surface' in order to get such values? If so, is there any other not-extremely-unelegant way (Output Export to EXCEL?) to get my correlations out of the viewer and into a .sav file? Eventually, I want to run a PCA on them. >>> Programmability uses the OMS mechanism to capture output items. OUTPUT EXPORT provides another way to capture tables from the Viewer, but that will be more roundabout and is slower. HTH, Jon Peck TIA! Ruben van den Berg Consultant Models & Methods TNS NIPO Email: [hidden email] Mobiel: +31 6 24641435 Telefoon: +31 20 522 5738 Internet: www.tns-nipo.com Express yourself instantly with MSN Messenger! MSN Messenger |
|
Thanks a lot, Jon!
The modified OMS block works fine! OMS /SELECT TABLES /IF subtypes=['HeterogeneousCorrelations'] /DESTINATION FORMAT=SAV NUMBERED=TableNumber_ [hidden email] /TAG='@cor'. Best, Ruben van den Berg Consultant Models & Methods TNS NIPO Email: [hidden email] Mobiel: +31 6 24641435 Telefoon: +31 20 522 5738 Internet: www.tns-nipo.com Date: Thu, 22 Jul 2010 06:47:04 -0600 From: [hidden email] Subject: Re: Can OMS catch HETCOR output? To: [hidden email] See below. Jon Peck SPSS, an IBM Company [hidden email] 312-651-3435
Dear all, I was trying to create a dataset consisting of polychoric correlations with the following syntax. DATASET DECLARE @cor. OMS /SELECT TABLES /IF COMMANDS=['Heterogeneous Correlation'] SUBTYPES=['Correlations'] /DESTINATION FORMAT=SAV NUMBERED=TableNumber_ [hidden email] /TAG='@cor'. SPSSINC HETCOR v2 v3 v4 v5 v6 v7 v8 /OPTIONS ESTIMATOR=twostep STDERR=TRUE MISSING=PAIRWISE N=TRUE TYPE=TRUE. omsend tag=['@cor']. However, I end up with an empty dataset. My guess (and I hope I'm wrong): everything OMS can catch has been built into OMS and since HETCOR is an extension, it hasn't been built into OMS. >>>Not so. OMS is designed to catch everything specified by the selectors. You just need to specify the right OMS command identifier and table type. (In this case you could just omit the command identifier, since the subtype alone would pick out what you want.) You can find these items by right clicking in the outline on the item of interest. In this case you will find that the command type is 'SPSSINC HETCOR', and the table type is 'HeterogeneousCorrelations'. You don't see these items in the OMS Identifiers dialog or the OMS Control Panel, because those lists are predefined. If so, then could Python spssaux.GetValuesFromXMLWorkspace 'grab' the correlation matrix? Or does it use OMS 'underneath the surface' in order to get such values? If so, is there any other not-extremely-unelegant way (Output Export to EXCEL?) to get my correlations out of the viewer and into a .sav file? Eventually, I want to run a PCA on them. >>> Programmability uses the OMS mechanism to capture output items. OUTPUT EXPORT provides another way to capture tables from the Viewer, but that will be more roundabout and is slower. HTH, Jon Peck TIA! Ruben van den Berg Consultant Models & Methods TNS NIPO Email: [hidden email] Mobiel: +31 6 24641435 Telefoon: +31 20 522 5738 Internet: www.tns-nipo.com Express yourself instantly with MSN Messenger! MSN Messenger Express yourself instantly with MSN Messenger! MSN Messenger |
| Free forum by Nabble | Edit this page |
