Statistical Innovations logo

  CORExpress  go to section and expand

  XLSTAT-CCR    go to section and expand
  Latent GOLD®  >
About LC Modeling
Advanced Option
Sample Datasets
User's Guide
Online Course
Free demo

  LG-Syntax Module  go to section and expand
  Latent GOLD® Choice  go to section and expand
  SI-CHAID®    go to section and expand
  GOLDMineR®  go to section and expand
  XLSTAT-Pro    go to section and expand

  Latent GOLD® 5.0
Products > Latent GOLD

All SI products are designed to operate
      on MS Windows XP and later

      System Requirements:

      70MB Drive Space, 512MB of RAM

      Input files: .sav and .txt

Latent GOLD Screenshot

More Screenshots          Enlarge

"Latent Class segmentation was the clear winner in our extensive testing of clustering approaches. We don't use traditional clustering techniques anymore and use Latent GOLD to execute all of our segmentation studies"

Kristin Sauerhoff
Manager of Statistics & Product Development
Market Research, Kellogg's

Read More Reviews


Latent GOLD 5.0 is a powerful latent class and finite mixture program. Latent GOLD contains separate modules for estimating three different model structures:

QuestionsLearn more about Latent Class modeling

Advanced Option

Latent GOLD 5.0 Basic includes the standard features listed above. The Advanced option includes additional advanced features for continuous latent variables (CFactors), multilevel modeling, and survey options for complex sample data. The Advanced option also includes the Markov GUI module. Learn More

Major New Features in Latent GOLD 5.0

  • Much faster estimation time
  • Improved profiling of classes (see Step3 module)
  • Obtaining equation for scoring new cases (see Step3 module)
  • New GUI for Latent (Hidden) Markov / Latent Transition Modeling
  • New log-linear scale model
  • and more!

Faster Estimation Time

Latent GOLD 5.0 supports multiple processors, making estimation faster than ever!

Latent GOLD Basic

  • Step3 Module. (See Tutorials) After developing a segmentation model (Step 1), and classifying cases (Step 2), you can now use the latent class segments in followup analyses with the new Step3 module.
    • Get exact equation for scoring new cases
    • Properly adjust for misclassification error
    • Predict classes from exogenous variables
    • Predict exogenous variables from classes
  • Select Cases. The 'Selection Variable' option makes it possible to select a specific subset of cases/records from the data file for analysis.
  • New statistics:
    • SABIC(LL,N), SABIC(L2,N), and total BVR
    • Classification table for proportional assignment
  • Bootstrap p values:
    • Not only of L2, but also for X2, CR2, DI, total BVR, and BVRs
    • In 2LLdif bootstrap, also L2 for H1 model
    • Critical values are reported in addition to p values

Advanced Option

  • Latent (Hidden) Markov GUI. (See Tutorials) How do clusters change over time? Do persons change from one latent class to another over time? Do some persons change (movers) and others not change classes (stayers)? You can now use the new latent Markov GUI to analyze your longitudinal data to address these and many other important research questions. This Markov module is light years ahead of other programs!
    • Unique implementation, not available elsewhere
    • Fastest of all latent Markov programs
    • Quickly analyze even hundreds of time points (other programs can only handle a few time points)!
    • Unique interactive graphics
    • Mixture latent Markov containing multiple indicators
    • Mover-stayer structures
  • New statistics. Based on higher-level sample size for multilevel LC models: BIC(LL,K), CAIC(LL,K), and SABIC(LL,K)

LG-Syntax Module

  • Additional Scale Types. Mixture regression models for dependent variables with other distributions (gamma, beta, von Mises).
  • Scaling Models. New log-linear scale model for categorical dependent variables.

And much more!


  • Full windows implementation - point and click
  • Interactive graphics provide new insights into data and powerful model diagnostic capabilities
  • Flexible model structures can handle variables of different metrics
  • Automatic generation of sets of random starting values
  • Fast, efficient maximum likelihood and posterior mode estimation based on EM and Newton Raphson algorithms
  • Use of Bayes constants to eliminate boundary solutions
  • Bivariate residual diagnostic for local dependencies


Known Class Indicator

This feature allows more control over the segment definitions by pre-assigning selected cases (not) to be in a particular class or classes.

Conditional Bootstrap p-value

Model difference bootstrap can be used to formally assess the significance in improvement associated with adding additional classes, additional DFactors and/or an additional DFactor levels to the model, or to relax any other model restriction.

Overdispersed (Count and Binomial Count in Regression)

Overdispersion is a common phenomenon in count data. It means that, as a result of unobserved heterogeneity, the variance of the count variable is larger than estimated by the Poisson (binomial) model. The overdispersed option makes it possible to account for unobserved heterogeneity by assuming that the rates (success probabilities) follow a gamma (beta) distribution. This yields a negative-binomial model for overdispersed Poisson counts and a negative-binomial model for overdispersed binomial counts. Note that this option is conceptually similar to including a normally distributed random intercept in a regression model for a count variable.

The overdispersion option is useful if one wishes to analyze count data using mixture or zero-inflated variants of (truncated) negative-binomial or beta-binomial models (Agresti, 2000; Long, 1997; Simonoff, 2003). The negative-binomial model is a Poisson model with an extra error term coming from a gamma distribution. The beta-binomial model is a variant of the binomial count model that assumes that the success probabilities come from a beta distribution. These models are common in fields such as criminology, political sciences, medicine, biology, and marketing.


All sample datasets and sample .lgf files used the tutorials below are downloaded to your computer when you install the demo version of Latent GOLD. To download individual datasets and .lgf files, please refer to our Sample Datasets Page.

Tutorial 1: Using Latent GOLD® to Estimate LC Cluster Models  
download PDF          Watch Video Tutorial          + overview

Tutorial 2: Using Latent GOLD® to Estimate DFactor Models  
download PDF          Watch Video Tutorial          + overview

Tutorial 3: LC Regression with Repeated Measures
download PDF          + overview

Tutorial 4: Profiling LC Segments using the CHAID Option
download PDF          + overview

Tutorial 6A: Comparing Segments obtained from LC Cluster and DFactor Models in a Consumer Preference Study
download PDF          + overview

Tutorial 7A: Latent Class Growth Model
download PDF          + overview

Tutorial 7B: Latent Class Growth Model Using an Active Covariate
download PDF          + overview

Tutorial 8: LC Regression with High-dimensional Data
download PDF          + overview

Advanced Tutorial: Latent GOLD and IRT Modeling
download PDF          + overview

New Latent GOLD 5.0 Tutorials

Step-Three Tutorial #1
download PDF          + overview

Step-Three Tutorial #2
download PDF          + overview

Step-Three Tutorial #3
download PDF          + overview

Markov Tutorial #1: Latent GOLD Longitudinal Analysis of Brand Loyalty
download PDF          + overview

Markov Tutorial #2: Latent GOLD Longitudinal Analysis of Life Satisfaction
download PDF          + overview

Markov Tutorial #3: Latent GOLD Longitudinal Analysis of Sparse Data
download PDF          + overview

We would like to thank our colleagues at the Statistical Consulting Group at UCLA Academic Technology Services for creating video seminars for our tutorials. Tutorials for which video is available are marked with the icon.

Related Products

LG-Syntax Module

Unleash the full power of the Advanced versions Latent GOLD and/or LG Choice with the new LG-Syntax module. Learn More

LG Choice

LG Choice is a specialized program designed strictly for estimating discrete choice models. Learn More


SI-CHAID is a program for performing CHAID (CHi-squared Automatic Interaction Detector) analyses. Results can be displayed simultaneously in the form of an intuitive tree diagram, crosstabulations, and a gains chart summary. Learn More

Using SI-CHAID, a CHAID analysis may be performed following the estimation of any LC model in Latent GOLD to profile the resulting LC segments based on demographics and/or other exogenous variables (Covariates). Learn More

E-mail Contact:
Address: Statistical Innovations, 375 Concord Avenue, Belmont, MA 02478-3084
Phone: +1.617.489.4490
Fax: +1.617.489.4499