Latent Class Version History
- What is Latent Class?
- Latent Class is a system for estimating part worths for Choice-Based Conjoint (CBC) questionnaires.
We strongly suggest using the latest version of Latent Class.
- Latent Class 4.7.1 (11 Jan 2018)
This version fixes an issue with respondent filtering and weighting. This can occur if the locale set in the software used to read CSV files is different than the machine’s locale. Decimal values are not converted to numbers correctly.
- Latent Class 4.7.0 (20 Jan 2014)
The ability to constrain groups to a common scale has been added.
- Latent Class 4.6.2 (16 Aug 2013)
- Bug: When running a project that includes a none, if a user chose not to estimate the none option the estimation would fail with a message that the number of parameters was incorrect. This was introduced in v4.5.
- Bug: When using a .chs file containing a mix of tasks with and without none options, the build process would produce an error. This was introduced in v4.5.
- Latent Class 4.6.1 (12 Jul 2013)
- Bug: When using Dual-CSV files, and the design file does not contain the none option and the response file has constant sum with a none, the responses would not be read correctly.
- Bug: Pasting attribute or level text that contains spaces would result in only the first word of the text being pasted.
- Bug: Missing respondent demographics used as a respondent weight would result in values of NaN in the report.
- Latent Class 4.6.0 (11 Jun 2013)
- Feature: A new option to export the coded design is available from the Attributes tab under the Other Tasks button.
- Bug: Rebuilding the attribute table from file would not refresh the information on the Attributes tab until the project was reloaded.
- Bug: A .cho file with an extra newline at the end of the file would result in a read error.
- Bug: Reading previous studies could result in an error.
- Latent Class 4.5.6 (7 May 2013)
- Bug: Occasionally there was an errant warning about the demographics file being open in another application.
- Feature: The software now recognizes Academic Research licenses.
- Latent Class 4.5.5 (16 Jan 2013)
Bug: v4.5.4 introduced a problem estimating MaxDiff data.
- Latent Class 4.5.4 (7 Jan 2013)
Bug: v4.5.0 introduced a problem with detecting a none option in single CSV files.
- Latent Class 4.5.3 (14 Dec 2012)
Bug: Batch estimation would crash at the beginning of estimation.
- Latent Class 4.5.2 (29 Nov 2012)
Bug: Single CSV data could cause a slowdown in the interface.
- Latent Class 4.5.1 (23 Oct 2012)
- Feature: Latent Class now checks for circular logic in constraints.
- Change: Small modifications to the XML layout file used by the Online Simulator.
- Bug: When checking a .cho or .chs file for errors, the file would remain locked after finishing.
- Bug: An error would occur when removing a blank respondent filter from the end of the filter list.
- Bug: When viewing a CSV data file within the software, the progress bar would remain after reading the file.
- Bug: An error would occur reading a demographic file with no labels (introduced in v4.5).
- Bug: An error would occur when checking for software updates.
- Latent Class 4.5.0 (28 Sep 2012)
- Feature: Latent Class has been updated to include multiple data file inputs (.cho, .chs, .csv, design + version .csv files) as well as supports estimating Best/Worst CBC data.
- Feature: Latent Class now reports AIC, BIC, and ABIC in addition to CAIC.
- Change: The user interface has been updated in the style of CBC/HB v5.
- Change: The post estimation report has been revised to be grid-based which can be exported to Excel format.
- Change: The default starting seed is now 1 rather than 0 (which denotes to use a random starting point). This should reduce confusion as to why utilities are not exactly the same as previous runs.
- Latent Class 4.1.0 (29 May 2012)
- Change: Latent Class has been updated to use newer licenses similar to other recent products. For those wishing to update to v4.1, please contact Sawtooth Software for a new license file free of charge. Your new license will activate the v3 Latent Class within SMRT (requires updating to SMRT v4.22), as previous Latent Class v4 licenses do.
- This version includes various fixes and updated components.
- Latent Class 4.0.8 (11 Nov 2008)
Bug: Using two linear attributes in an interaction caused the none option to appear as 0.0 for all respondents.
- Latent Class 4.0.6 (25 Sep 2008)
Bug: Setting attribute codings to 'Excluded' produced incorrect labels and utilities. This bug was introduced in v 4.0.4.
- Latent Class 4.0.4 (15 July 2008)
- Bug: Using constraints on an interaction when more than one interaction was present could result in incorrect utilities or a memory error message.
- Bug: Saving CSV files in some countries would use a comma instead of the locale-specific delimeter. The preferences dialog now includes an option to select the output format.
- Bug: A new line after a linear variable was missing, causing the report to look as if there was an attribute missing and the linear was a level of the next attribute.
- Latent Class 4.0.2 (4 Sep 2007)
- Bug: Missing responses when using dual-response none were coded incorrectly. The resulting build file would not run. It did not cause incorrect utilities.
- Bug: Batch Estimation did not save the log report.
- Latent Class 4.0.0 (17 Jul 2007)
- Feature: New Windows Interface, eliminating all text-only control files.
- Feature: Support for chip allocation data (constant sum).
- Feature: Support for "Dual-Response None" data.
- Feature: New files studyname.csv and studyname_prob.csv may be opened with Excel. Studyname.csv contains the part-worth utilities for each group and studyname_prob.csv contains the probabilities of group membership for each respondent.
- Feature: Batch mode processing of multiple projects.
- Feature: Ability to add notations for the project.
- Feature: Without a license, Latent Class functions in demonstration mode.
- Bug: When displaying standard errors, the errors for the last group are displayed for each group.