This paper shows how you can use PROC MCMC to fit hierarchical models that have varying degrees of complexity, from frequently encountered conditional independent models to more involved cases of modeling intricate interdependence.
This paper reviews the statistical methods that are implemented in the CAUSALTRT procedure and includes examples of how you can use this procedure to estimate causal effects from observational data.
This paper reviews the existing features in PROC LOGISTIC for C-statistic and ROC curves, presents the new features in PROC PHREG, and illustrates their applications in examples. Key differences between PROC PHREG and PROC LOGISTIC are also examined.
This paper explains the concepts and benefits of quantile regression, and it introduces you to the appropriate procedures in SAS/STAT software.
This paper reviews propensity score methods for causal inference and introduces the PSMATCH procedure, which is new in SAS/STAT 14.2.
This paper will increase your awareness of modern tools in SAS/STAT by providing high-level comparisons with well-established tools and explaining the benefits of enhancements and new procedures.
The NLMIXED procedure’s ability to fit linear and nonlinear models with standard or general distributions enables you to fit a wide range of such models. SAS/STAT® 13.2 enhanced PROC NLMIXED to support multiple RANDOM statements, enabling you to fit nested multilevel mixed models. This paper uses an example to illustrate the new functionality.
This paper describes how to use the MCMC procedure to fit Bayesian mixed models and compares the Bayesian approach to how the classical models would be fit with the familiar mixed modeling procedures.
This paper provides a high-level tour of five modern approaches to model building that are available in recent releases of SAS/STAT: building sparse regression models with the GLMSELECT procedure, building generalized linear models with the HPGENSELECT procedure, building quantile regression models with the QUANTSELECT procedure, fitting generalized additive models with the GAMPL procedure, and building classification and regression trees with the HPSPLIT procedure
This paper discusses different approaches for handling nonresponse in surveys, introduces PROC SURVEYIMPUTE, and demonstrates its use with real-world applications. It also discusses connections with other ways of handling missing values in SAS/STAT.
This paper provides recommendations for circumventing memory problems and reducing execution times for your mixed-modeling analyses. It also shows how the new HPMIXED procedure can be beneficial for certain situations, as with large sparse mixed models. Lastly, it focuses on the best way to interpret and address common notes, warnings, and error messages that can occur with the estimation of mixed models in SAS software.
This paper provides guidance on how to overcome obstacles that commonly occur when you fit mixed models using the MIXED and GLIMMIX procedures.
This paper describes the SPP procedure, new in SAS/STAT 13.2, for exploring and modeling spatial point pattern data.
This paper introduces the principles of Bayesian inference and reviews the steps in a Bayesian analysis. It then describes the built-in Bayesian capabilities provided in SAS/STAT, which became available for all platforms with SAS/STAT 9.3, with examples from the GENMOD and PHREG procedures.
This paper reviews familiar and new methods for planning and analyzing equivalence and noninferiority studies in the POWER, TTEST, and FREQ procedures in SAS/STAT software.
This paper shows you how to use the HPGENSELECT procedure both for model selection and for fitting a single model. The paper also explains the differences between the HPGENSELECT procedure and the GENMOD procedure.
This paper first provides a brief review of the LASSO, adaptive LASSO, and elastic net penalized model selection methods. Then it explains how to perform model selection by applying these techniques with the GLMSELECT procedure, which includes extensive customization options and powerful graphs for steering statistical model selection.
This paper describes the additions and provides examples of using the new capabilities for survey data imputation, logistic regression using adjacent-category logits, generalized additive models, and classification trees in SAS/STAT 14.1.
This paper discusses two commonly used regression approaches for evaluating the relationship of the covariates to the cause-specific failure in competing-risks data. One approach models the cause-specific hazard, and the other models the cumulative incidence. The paper shows how to use the PHREG procedure in SAS/STAT software to fit these models
Marginal model plots enable you to evaluate model fit by comparing predicted values given all of the variables in the full model and a loess fit function for each independent variable. When the two functions are similar in each of the graphs, there is evidence that the model fits well. When the two functions differ in at least one of the graphs, there is evidence that the model does not fit well.
This paper illustrates how you can create and use path diagrams to present your model and statistical results. It also demonstrates the use of the ODS Graphics Editor to edit path diagrams that are produced from the CALIS procedure.
This paper presents a series of examples that show how to use PROC MCMC to fit Bayesian models.
This paper discusses the new, experimental BCHOICE procedure in SAS/STAT 13.1 which enables you to perform Bayesian analysis for discrete choice models. PROC BCHOICE fits multinomial logit, nested logit, mixed multinomial logit, multinomial probit, and mixed multinomial probit models. Brief summaries of the properties of the various models are provided along with a series of examples that highlight the capabilities of PROC BCHOICE.
This paper shows you how to use the HPGENSELECT procedure both for model selection and for fitting a single model. The paper also explains the differences between the HPGENSELECT procedure and the GENMOD procedure.
This paper discusses two commonly used regression approaches for evaluating the relationship of the covariates to the cause-specific failure in competing-risks data. One approach models the cause-specific hazard, and the other models the cumulative incidence. The paper shows how to use the PHREG procedure in SAS/STAT to fit these models.
This paper introduces you to the ICLIFETEST procedure and presents examples that illustrate how you can use it to perform analyses of interval-censored data.
This paper describes how to use the GLIMMIX procedure in SAS/STAT to analyze hierarchical data that have a wide variety of distributions. Examples are included to illustrate the flexibility that PROC GLIMMIX offers for modeling within-unit correlation, disentangling explanatory variables at different levels, and handling unbalanced data.
This paper demonstrates the new case-level residuals in the CALIS procedure and how they differ from classic residuals in structural equation modeling (SEM).
Through examples, this paper provides guidance in using PROC SURVEYLOGISTIC to apply logistic regression modeling techniques to data that are collected from a complex survey design.
This paper introduces the principles of Bayesian inference and reviews the steps in a Bayesian analysis. It then describes the built-in Bayesian capabilities provided in SAS/STAT, which became available for all platforms with SAS/STAT 9.3, with examples from the GENMOD and PHREG procedures.
This paper presents the the diagnostic and inferential features that were added to PROC NLIN in SAS/STAT® 9.3, 12.1, and 13.1and explains how to use them. This paper highlights how measures of nonlinearity help you diagnose models and decide on potential reparameterization.
This paper describes a variety of IRT models, such as the Rasch model, two-parameter model, and graded response model, and demonstrates their application by using real-data examples. It also shows how to use the IRT procedure, which is new in SAS/STAT 13.1, to calibrate items, interpret item characteristics, and score respondents. Finally, the paper explains how the application of IRT models can help improve test scoring and develop better tests.
This paper reviews the definition of LS-means, focusing on their interpretation as predicted population marginal means, and it illustrates their broad range of use with numerous examples.
This paper reviews the new repeated measures features of PROC GLMPOWER, demonstrates their use in several examples, and discusses the pros and cons of the MANOVA and repeated measures approaches.
This paper provides overviews and introductory examples for each of the new focus areas in SAS/STAT 13.1. The paper also provides a sneak preview of the follow-up release, SAS/STAT 13.2, which brings additional strategies for missing data analysis and other important updates to statistical customers.
This paper presents the %SCDMixed SAS macro, which implements a generalization of Cook's Distance for analyzing influence in mixed models for longitudinal or clustered data. The macro calculates the degree of perturbation and scaled Cook's distance measures of Zhu et al. (2012) and presents the results with useful tabular and graphical summaries. Download the zip file.
This paper reviews the concepts of multiple imputation and explains how you can apply the pattern-mixture model approach in the MI procedure by using the MNAR statement, which is new in SAS/STAT 13.1.
This paper reviews the concepts and statistical methods. Examples illustrate how you can apply the GEE procedure to incomplete longitudinal data. Download the zip file.
This paper reviews the concepts of standardized rate and risk and introduces the STDRATE procedure, which is new in SAS/STAT 12.1. PROC STDRATE computes directly standardized rates and risks by using Mantel-Haenszel estimates, and it computes indirectly standardized rates and risks by using standardized morbidity/mortality ratios (SMR). PROC STDRATE also provides stratum-specific summary statistics, such as rate and risk estimates and confidence limits.
This paper provides examples of survival plot modifications using procedure options, graph template modifications using macros, and style template modifications.
This paper provides examples of survival plot modifications using procedure options, graph template modifications using macros, and style template modifications.
This paper describes recent areas of development focus, such as Bayesian analysis, missing data methods, postfitting inference, quantile modeling, finite mixture models, specialized survival analysis, structural equation modeling, and spatial statistics. It also introduces you to the concepts and illustrates them with practical applications.
This paper first shows how the EFFECT statement fits into the general architecture of SAS/STAT linear modeling tools and then explains and demonstrates specific effect-types. You will see how this powerful new feature easily enhances the statistical analyses that you can perform.
This paper describes the various execution modes and data access methods for high-performance analytics procedures. It also discusses the design principles for high-performance statistical modeling procedures and offers guidance about how and when these procedures provide performance benefits.
This paper shows you how to use PROC ADAPTIVEREG (a new SAS/STAT procedure for multivariate adaptive regression spline models) by presenting a series of examples that show the relationship between adaptive regression models and other statistical modeling techniques.
This paper reviews the Bayesian approach and describes how the MCMC procedure implements it.
This paper describes how you can use the LOGISTIC procedure to model ordinal responses. Before SAS/STAT 12.1, you could use cumulative logit response functions with proportional odds. In SAS/STAT 12.1, you can fit partial proportional odds models to ordinal responses. This paper also discusses methods of determining which covariates have proportional odds.
This paper compares the performance of the HPGENSELECT procedure with results cited for the RevoScaleR package by using data that are similar to the insurer's data. The paper also demonstrates the scalability of the HPGENSELECT procedure by using two sizes of data sets and three different computing environments.
This paper compares the quantile regression model with the Cox and accelerated failure time models, which are commonly used in survival analysis.
The SAS macro %CIF implements appropriate nonparametric methods for estimating cumulative incidence functions. The macro also implements Gray’s method (Gray 1988) for testing differences between these functions in multiple groups. This paper discusses these methods and illustrates the macro.
This paper provides an overview of the capabilities of the FMM procedure and illustrates them with applications drawn from a variety of fields.
This paper reviews highlights from earlier releases and describes highlights of SAS/STAT 12.1, slated for release during 2012.
This paper provides recommendations for circumventing memory problems and reducing execution times for your mixed modeling analyses. It also shows how the new HPMIXED procedure can be beneficial for certain situations, as with large sparse mixed models. Lastly, the paper focuses on the best way to interpret and address common notes, warnings, and error messages that can occur with the estimation of mixed models in SAS software.
Documentation for many SAS analytical products has long been created from a single-source system that embeds SAS code in LaTeX files and generates statistical results from those files. This system is now available to SAS users as an open-source package. This paper describes how to access and implement the package, and it illustrates typical usage with several examples.
The CONTRAST and ESTIMATE statements enable a variety of custom hypothesis tests, but using these statements correctly is often challenging. The new LSMESTIMATE statement, available in ten procedures in SAS/STAT 9.22 software, greatly simplifies the use of these statements. This paper discusses the new features available with the LSMESTIMATE statement and demonstrates them with examples from actual user questions to the Statistical Procedures group in SAS Technical Support.
This paper illustrates how you can use PROC CALIS to deal with random missing values in the following data-analytic situations: (1) estimating means and covariances, (2) regression analysis, and (3) structural equation or path modeling. This paper also illustrates some new features of PROC CALIS for analyzing missing patterns and data coverages.
This paper reviews the highlights of SAS/STAT 9.22 and then describes important SAS/STAT 9.3 enhancements with practical illustrations, mainly from the SAS/STAT 9.3 documentation.
This paper describes key enhancements of PROC MCMC in SAS/STAT 9.22 and 9.3 and illustrates the use of these enhancements with examples.
This paper describes the use of the MIXED, IML, and MCMC procedures to fit unit-level and area-level models, and to obtain small area predictions and the mean squared error of predictions. Hierarchical Bayes models are also discussed as extensions to the basic models.
This paper demonstrates the use of the MI, MIANALYSIS, and CALIS procedures of SAS/STAT (version 9.22 or later) to fit structural equation models with incomplete observations (or missing data).
This paper reviews some of the basic tenets of categorical data analysis today and describes the newer techniques that have become common practice.
Interval-censored survival data comes from event time that is not directly observed and the event is known only to have occurred within some interval of time. The focus of this paper is how to use SAS software to analyze this type of data.
The paper demonstrates new features to the SAS suite of spatial procedures to augment, simplify, and streamline spatial analysis in one and two dimensions and discusses key elements and underlying complexities of stochastic spatial analysis.
This paper discusses how the PLM procedure, new in SAS/STAT 9.22, works in conjunction with a new STORE statement in many familiar SAS/STAT procedures to provide a full complement of postprocessing features for a wide spectrum of linear models. The paper also discusses the new EFFECT statement, newly available in a number of procedures in SAS/STAT 9.22, which makes it easy for you to add many more types of effects to your general linear models—splines, polynomials, lags, and more.
This paper discusses the following how-to techniques of the CALIS procedure (SAS/STAT 9.22) are covered: (1) Specifying structural equation models with latent variables by using the PATH modeling language; (2) Interpreting the model fit statistics and estimation results; (3) Testing models with multiple groups and multiple models; (4) Analyzing direct and indirect effects; (5) Modifying structural equation models.
This paper provides an overview of the exciting new enhancements to SAS/STAT 9.22.
This paper introduces the SURVEYPHREG procedure, a new SAS/STAT procedure for finite population inference for the Cox proportional hazards model for complex surveys.
The paper concentrates on common CLASS variable parameterization methods such as reference coding and GLM coding. Caveats regarding CLASS variables and time (including time-dependent covariates) are also discussed.
This paper introduces applications of large mixed models, discusses the specialized techniques of the HPMIXED procedure to handle them, and demonstrates the utility of the procedure with examples from agriculture and genomics.
This paper explores applications of the GLMSELECT procedure in SAS/STAT software and discusses the modeling possibilities available when you can select regression models from tens of thousands of effects.
This paper introduces the new MCMC procedure in SAS/STAT 9.2, which is designed for general-purpose Bayesian computations. It also describes how to use the MCMC procedure for estimation, inference, and prediction.
This paper reviews basic concepts of group sequential analysis and introduces two SAS/STAT procedures: the SEQDESIGN and SEQTEST procedures.
This paper discusses the theory and methods for exact logistic regression and illustrates their application with the LOGISTIC procedure in SAS/STAT 9.2 software.
This paper discusses an example of fitting generalized additive models with the GAM procedure, which provides multiple types of smoothers with automatic selection of smoothing parameters. This paper uses the ODS Statistical Graphics to produce plots of integrated additive and smoothing components.
This paper discusses replication methods, comparing them to the Taylor series expansion method with respect to both technical characteristics and practical utility. This paper also discusses other significant enhancements to the survey design and analysis procedures in SAS 9.2.
This paper highlights the new features of the power analysis and sample size determination procedures and describes the new desktop application.
This paper describes the key changes and enhancements to PROC GLIMMIX between the SAS 9.1 and SAS 9.2 releases.
This paper describes the GLMSELECT procedure, a new procedure in SAS/STAT software that performs model selection in the framework of general linear models.
This paper describes the new features of PROC TTEST in SAS 9.2 and illustrates their use in a number of examples.
This paper describes the statistical development that will surface in SAS 9.2. First, the "post" SAS 9.1 download procedures will be reviewed, with examples from the GLIMMIX and GLMSELECT procedures. Attention turns next to a preview of SAS Stat Studio, the successor to SAS/INSIGHT software. ODS Graphics becomes production with SAS 9.2, and this paper reviews its many enhancements and describes the use of the new effect plot in PROC LOGISTIC.
Growth charts of body mass index (BMI) are constructed from the recent four-year national cross-sectional survey data (1999-2002) using parametric quantile regression methods, which are implemented with a newly developed SAS procedure and SAS macros.
This paper describes a new SAS/STAT procedure for fitting models to non-normal or normal data with correlations or nonconstant variability. The GLIMMIX procedure is an add-on for the SAS/STAT product in SAS 9.1 on the Windows platform.
This paper describes the new QUANTREG procedure in SAS 9.1, which computes estimates and related quantities for quantile regression by solving a modification of the least-squares criterion.
This paper examines extensions of influence measures in linear mixed models and their implementation in the MIXED procedure.
This paper describes methods for the analysis of recurrent events data. Nonparametric methods involving extensive use of graphics for the analysis of such data are discussed in a new book by Nelson (2003). These methods are illustrated using the SAS/QC RELIABILITY procedure. The use of the SAS/STAT GENMOD and PHREG procedures to fit regression models to recurrent events data is also illustrated.
In this paper, new model-checking techniques of Lin et al. (1993, 2002) based on cumulative sums and other aggregates of residuals are described.
This paper outlines how Version 9 of SAS/STAT software brings you a variety of new tools for your statistical computing needs.
This paper introduces the ROBUSTREG procedure, which is experimental in SAS/STAT Version 9. The ROBUSTREG procedure implements the most commonly used robust regression techniques
This paper provides a survey of this development and the performance gains obtained in several procedures in SAS/STAT and Enterprise Miner.
This paper describes the underlying approach used in %Distribute and demonstrates its application for Monte Carlo simulation.
This paper describes the use of the GAM procedure for fitting generalized additive models (Hastie and Tibshirani, 1990).
This powerpoint presentation has been given to numerous audiences as a two hour seminar and describes useful applications of ODS for statisticians and data analysts.
The purpose of this article is to systematically explore combined error rates (CER) of stepwise testing methods relevant to ANOVA studies involving correlated comparisons by using both analytic and simulation-based methods.
This paper reviews methods for analyzing missing data, including basic concepts and applications of multiple imputation techniques. The paper presents SAS procedures, PROC MI and PROC MIANALYZE, for creating multiple imputations for incomplete multivariate data and for analyzing results from multiply imputed data sets. It also describes new experimental features in Version 9.0 for specification of classification variables in the MI and MIANALYZE procedures.
This paper compares two methods of modeling repeated measures data with many zeros. The first method models the nonzero observations as lognormal and the zeros are modeled as a mixture of Bernoulli and left-censored lognormal. The second method omits the censoring, leaving a logistic model for the zeros and a lognormal model for the nonzero values.
This presentation demonstrates issues involved in power analysis, summarizes the current state of methodology and software, and outlines future directions.
Modern methods of combinatorial chemistry screen huge spaces of compounds for those which have the most potential as new drugs, new catalysts, and new materials. The task of identifying which compounds to test is formally quite similar to the task of selecting which factor combinations to observe in a statistical experimental design. This paper explores this similarity, demonstrating that computer-aided space-filling experimental design techniques may complement traditional, information-based approaches.
This presentation will introduce you to software for creating high-resolution graphics displays of data distributions, including histograms, probability plots, and quantile-quantile plots, which have been added to the UNIVARIATE procedure in Version 8.
This paper presents some of the primary features of PROC NLMIXED and illustrates its use with two examples.
This paper describes the LOESS procedure which is a new procedure in SAS/STAT software for performing local regression.
This paper describes software currently available in the SAS System and indicates the areas in which new software should be available in the next few years.
This paper demonstrates how to use the SAS Analyst Application software's powerful statistical and graphical capabilities to investigate basic assay questions.
This paper discusses advances made in the output generated by all Version 7 SAS Software procedures.
This paper describes the capabilities of the SURVEYSELECT, SURVEYMEANS, and SURVEYREG procedures and illustrates their use.
This paper provides an overview of the use of GEEs in the analysis of correlated data using the SAS System.
This paper introduces the NPAR1WAY procedure's new exact statistics capabilities in SAS 6.11 software.
Repeated measures analyses in the GLM procedure involve the traditional univariate and multivariate approaches. The MIXED procedure employs a more general covariance structure approach. This paper compares the two procedures and helps you understand their methodologies
This tutorial answers some frequently asked questions about the LOGISTIC procedure.
The paper gives a brief overview of how PLS works, an extended chemometric example is presented that demonstrates how PLS models are evaluated and how their components are interpreted, and finally it discusses alternatives and extensions of PLS.
This paper introduces generalized linear models and reviews the SAS software that fits the models.
Papers are in Portable Document Format (PDF) and can be viewed with the free Adobe Acrobat Reader.
Powerpoint presentations and SAS programs can be downloaded as zip files.