Data Mining / Analysis - IT Library : ZDNet Asia

White Papers

Case Studies

Vendor Webcast

Show all content

Title Date Added Company

Estimating the False Discovery Rate Using SAS 2006-12-22 01:00:22 SAS Institute

This paper gives an exposition of recently developed methods of estimating the False Discovery Rate (FDR) under multiple comparisons and discusses their implementation using SAS. For example, microarray experiments typically involve tests of significance for hundreds or thousands of genes. For biologists confronted by this problem of multiplicity, the FDR is an appealing quantification of error. SAS code using the SAS/MACRO, SAS/STAT, and SAS/IML facilities is presented to compute this estimate, and appears in the appendix. Q-values, which are to FDR as p-values are to the type I error rate, are also obtained and used to reproduce plots generated by the R package "Qvalue" that may be helpful for conducting multiple tests.

Comparison of Data Preparation Methods for Use in Model Development With SAS Enterprise Miner 2006-12-22 01:00:22 SAS Institute

SAS Enterprise Miner is a powerful tool for model development. As most people who have developed predictive regression or other behavioral models are aware, the bulk of the time spent in developing models isn't in the final production of the regression coefficients, but in variable selection and preparing the input variables (e.g. clustering levels, imputing missing values, etc.). Enterprise Miner has a module for variable selection and level condensation which is easy to use, but how well does this module compare with some traditional methods of variable selection? Several models were developed in Enterprise Miner in parallel using traditional methods for data preparation vs the Enterprise Miner variable selection module.

Using SAS ODS to Extract and Merge Statistics From Multiple SAS Procedures Into a Single Summary Report, a Detailed Methodology 2006-12-22 01:00:22 SAS Institute

SAS procedures often provide more statistical output than is needed for a given analysis. When an analysis involves iterative processing on numerous groups of variables using multiple procedures, the number of output pages to be reviewed may be quite massive. By using SAS Output Delivery System (ODS) output datasets, one can extract only the desired statistics from a procedure. The ODS output datasets from numerous procedures can be merged together and used by the programmer to generate concise reports summarizing the results from the different SAS procedures. This paper provides a detailed blueprint for generating ODS output datasets from multiple procedures, retaining specific statistics in these datasets, and merging them together to produce one summary dataset.

The Value of Real Time Scoring Technology Using SAS 2006-12-26 01:00:57 SAS Institute

Imagine having built a Data Mining model to detect fraudulent credit card transactions. If this model is applied once a day by the analyst to determine the nature of transaction, this implies the loss of preventing fraudulent transactions at the moment it occurred due to the fact that the model could not be applied in "Real-time", in another words, at the moment of transaction. To overcome this loss, the key technology required is to be able to systemize the determination process of normal against fraud at the moment it requests for authorization. SAS technology enables to build this real-time detection system. This paper will present how to systemize a real-time Scoring Engine for Data Mining.

Wait Wait, Don't Tell Me... You're Using the Wrong Proc! 2006-12-26 01:00:57 SAS Institute

Statisticians and data analysts frequently have data sets which are difficult to analyze, with characteristics that break the underlying assumptions of the simpler analytical tools. But SAS has tools to handle more complex problems. And, now that SAS has survey analysis procedures, there's no longer a need to pretend that survey samples should be analyzed using non-survey design tools. Now that large databases are commonly sampled for marketing, data mining, and scientific research, the need to use survey analysis procedures is increasing. This paper looks at several common situations and illustrates how the data are usually analyzed.

Using the SAS System for Experimental Designs for Multicomponent Interventions in Medicine 2006-12-26 01:00:57 SAS Institute

The proper design of studies to evaluate multicomponent interventions in medicine permits the estimation of individual component effects. Because each component of an intervention adds to the cost and complexity in clinical trials, selecting the most effective components is critical. This paper illustrates how several methods available in SAS can be used to more efficiently design these types of studies.

Predicting Child Support Payment Delinquency Using SAS Enterprise Miner 5.1 2006-12-26 01:00:57 SAS Institute

To ensure the health and welfare of children and to reduce welfare costs, child support agencies around the country are tasked with successfully collecting child support payments for the children in their respective states. This paper describes two case studies that illustrate how a data mining approach has helped agencies collect more support payments and use their collection resources more effectively. Using data mining to identify payers who are likely to become delinquent helps child support agencies build effective intervention strategies for collecting payments. Sequence analysis and binary response modeling are emphasized in this approach, using SAS Enterprise Miner 5.1 as the modeling environment.

Fixed Effects Regression Methods in SAS 2006-12-26 01:00:57 SAS Institute

Fixed effects regression methods are used to analyze longitudinal data with repeated measures on both independent and dependent variables. They have the attractive feature of controlling for all stable characteristics of the individuals, whether measured or not. This is accomplished by using only within-individual variation to estimate the regression coefficients. This paper surveys the wide variety of fixed effects methods and their implementation in SAS, specifically, linear models with PROC GLM, logistic regression models with PROC LOGISTIC, models for count data with PROC GENMOD, and survival models with PROC PHREG.

An Application of Survival Analysis to Population Dynamics in Human Capital Management 2006-12-26 01:00:57 SAS Institute

Using Base SAS, SAS/STAT and SAS/GRAPH, a decision support infrastructure is built to monitor and forecast workforce retention dynamics relative to the economic value of Unicru Personality Assessments. Using PROC LIFEREG the authors developed best fit survival models for employee lengths of stay and with these best fit model's hazard rates and apply a semi-Markov population dynamic model to forecast the rate of replacement of employees with new hires with targeted personality traits. SAS/GRAPH is utilized to present historical data, fitted survival models and forecasted replacement levels.

Investigating Open Source Project Success: A Data Mining Approach to Model Formulation, Validation and Testing 2006-12-26 01:00:57 SAS Institute

This paper demonstrates the use of Data Mining (DM) techniques in exploratory research. A robust model for identifying the factors that explain the success of Open Source Software (OSS) projects is created, validated and tested. The predictive modeling techniques of Logistic Regression (LR), Decision Trees (DT) and Neural Networks (NN) are used together in this analysis. Using Text Mining results in the predictive modeling process strengthens the model. SAS Enterprise Miner and SAS Text Miner are used in this research.

Jump to 1 2 3 4 5 [6] 7 8 9 10

Title	Date Added	Company
Estimating the False Discovery Rate Using SAS	2006-12-22 01:00:22	SAS Institute
This paper gives an exposition of recently developed methods of estimating the False Discovery Rate (FDR) under multiple comparisons and discusses their implementation using SAS. For example, microarray experiments typically involve tests of significance for hundreds or thousands of genes. For biologists confronted by this problem of multiplicity, the FDR is an appealing quantification of error. SAS code using the SAS/MACRO, SAS/STAT, and SAS/IML facilities is presented to compute this estimate, and appears in the appendix. Q-values, which are to FDR as p-values are to the type I error rate, are also obtained and used to reproduce plots generated by the R package "Qvalue" that may be helpful for conducting multiple tests.
Comparison of Data Preparation Methods for Use in Model Development With SAS Enterprise Miner	2006-12-22 01:00:22	SAS Institute
SAS Enterprise Miner is a powerful tool for model development. As most people who have developed predictive regression or other behavioral models are aware, the bulk of the time spent in developing models isn't in the final production of the regression coefficients, but in variable selection and preparing the input variables (e.g. clustering levels, imputing missing values, etc.). Enterprise Miner has a module for variable selection and level condensation which is easy to use, but how well does this module compare with some traditional methods of variable selection? Several models were developed in Enterprise Miner in parallel using traditional methods for data preparation vs the Enterprise Miner variable selection module.
Using SAS ODS to Extract and Merge Statistics From Multiple SAS Procedures Into a Single Summary Report, a Detailed Methodology	2006-12-22 01:00:22	SAS Institute
SAS procedures often provide more statistical output than is needed for a given analysis. When an analysis involves iterative processing on numerous groups of variables using multiple procedures, the number of output pages to be reviewed may be quite massive. By using SAS Output Delivery System (ODS) output datasets, one can extract only the desired statistics from a procedure. The ODS output datasets from numerous procedures can be merged together and used by the programmer to generate concise reports summarizing the results from the different SAS procedures. This paper provides a detailed blueprint for generating ODS output datasets from multiple procedures, retaining specific statistics in these datasets, and merging them together to produce one summary dataset.
The Value of Real Time Scoring Technology Using SAS	2006-12-26 01:00:57	SAS Institute
Imagine having built a Data Mining model to detect fraudulent credit card transactions. If this model is applied once a day by the analyst to determine the nature of transaction, this implies the loss of preventing fraudulent transactions at the moment it occurred due to the fact that the model could not be applied in "Real-time", in another words, at the moment of transaction. To overcome this loss, the key technology required is to be able to systemize the determination process of normal against fraud at the moment it requests for authorization. SAS technology enables to build this real-time detection system. This paper will present how to systemize a real-time Scoring Engine for Data Mining.
Wait Wait, Don't Tell Me... You're Using the Wrong Proc!	2006-12-26 01:00:57	SAS Institute
Statisticians and data analysts frequently have data sets which are difficult to analyze, with characteristics that break the underlying assumptions of the simpler analytical tools. But SAS has tools to handle more complex problems. And, now that SAS has survey analysis procedures, there's no longer a need to pretend that survey samples should be analyzed using non-survey design tools. Now that large databases are commonly sampled for marketing, data mining, and scientific research, the need to use survey analysis procedures is increasing. This paper looks at several common situations and illustrates how the data are usually analyzed.
Using the SAS System for Experimental Designs for Multicomponent Interventions in Medicine	2006-12-26 01:00:57	SAS Institute
The proper design of studies to evaluate multicomponent interventions in medicine permits the estimation of individual component effects. Because each component of an intervention adds to the cost and complexity in clinical trials, selecting the most effective components is critical. This paper illustrates how several methods available in SAS can be used to more efficiently design these types of studies.
Predicting Child Support Payment Delinquency Using SAS Enterprise Miner 5.1	2006-12-26 01:00:57	SAS Institute
To ensure the health and welfare of children and to reduce welfare costs, child support agencies around the country are tasked with successfully collecting child support payments for the children in their respective states. This paper describes two case studies that illustrate how a data mining approach has helped agencies collect more support payments and use their collection resources more effectively. Using data mining to identify payers who are likely to become delinquent helps child support agencies build effective intervention strategies for collecting payments. Sequence analysis and binary response modeling are emphasized in this approach, using SAS Enterprise Miner 5.1 as the modeling environment.
Fixed Effects Regression Methods in SAS	2006-12-26 01:00:57	SAS Institute
Fixed effects regression methods are used to analyze longitudinal data with repeated measures on both independent and dependent variables. They have the attractive feature of controlling for all stable characteristics of the individuals, whether measured or not. This is accomplished by using only within-individual variation to estimate the regression coefficients. This paper surveys the wide variety of fixed effects methods and their implementation in SAS, specifically, linear models with PROC GLM, logistic regression models with PROC LOGISTIC, models for count data with PROC GENMOD, and survival models with PROC PHREG.
An Application of Survival Analysis to Population Dynamics in Human Capital Management	2006-12-26 01:00:57	SAS Institute
Using Base SAS, SAS/STAT and SAS/GRAPH, a decision support infrastructure is built to monitor and forecast workforce retention dynamics relative to the economic value of Unicru Personality Assessments. Using PROC LIFEREG the authors developed best fit survival models for employee lengths of stay and with these best fit model's hazard rates and apply a semi-Markov population dynamic model to forecast the rate of replacement of employees with new hires with targeted personality traits. SAS/GRAPH is utilized to present historical data, fitted survival models and forecasted replacement levels.
Investigating Open Source Project Success: A Data Mining Approach to Model Formulation, Validation and Testing	2006-12-26 01:00:57	SAS Institute
This paper demonstrates the use of Data Mining (DM) techniques in exploratory research. A robust model for identifying the factors that explain the success of Open Source Software (OSS) projects is created, validated and tested. The predictive modeling techniques of Logistic Regression (LR), Decision Trees (DT) and Neural Networks (NN) are used together in this analysis. Using Text Mining results in the predictive modeling process strengthens the model. SAS Enterprise Miner and SAS Text Miner are used in this research.