SUDAAN
Encyclopedia
SUDAAN is a statistical software package for the analysis of correlated data
, including correlated data encountered in complex sample surveys. SUDAAN originated in 1972 at RTI International (the trade name of Research Triangle Institute).
used to analyze data from complex sample surveys and other observational and experimental studies involving repeated measures and cluster-correlated data
. It provides estimates that account for complex design features of a study, including:
s of ratio estimates, mean
s, totals, regression coefficients
, and other statistics in accordance with the sample design, greatly increasing the accuracy and validity of results. Many, if not most, data set
s require attention to correlation
and weighting
, but few statistical software packages offer the user the opportunity to specify how data are correlated and weighted. For many years, SUDAAN remained the only broadly applicable software for analysis of correlated and weighted data. Currently Mplus offers similar capacities for a much broader set of models.
Currently, all nine of SUDAAN's analytic procedures offer three popular robust variance estimation methods:
Correlation
In statistics, dependence refers to any statistical relationship between two random variables or two sets of data. Correlation refers to any of a broad class of statistical relationships involving dependence....
, including correlated data encountered in complex sample surveys. SUDAAN originated in 1972 at RTI International (the trade name of Research Triangle Institute).
Current version
SUDAAN Release 10.0, released in August 2008, is a single program consisting of a family of eleven analytic proceduresAnalytic and enumerative statistical studies
Analytic and enumerative statistical studies are two types of scientific studies:In any statistical study the ultimate aim is to provide a rational basis for action. Enumerative and analytic studies differ by where the action is taken...
used to analyze data from complex sample surveys and other observational and experimental studies involving repeated measures and cluster-correlated data
Data clustering
Cluster analysis or clustering is the task of assigning a set of objects into groups so that the objects in the same cluster are more similar to each other than to those in other clusters....
. It provides estimates that account for complex design features of a study, including:
- unequally weightedWeight functionA weight function is a mathematical device used when performing a sum, integral, or average in order to give some elements more "weight" or influence on the result than other elements in the same set. They occur frequently in statistics and analysis, and are closely related to the concept of a...
or unweighted data - stratificationStratified samplingIn statistics, stratified sampling is a method of sampling from a population.In statistical surveys, when subpopulations within an overall population vary, it is advantageous to sample each subpopulation independently. Stratification is the process of dividing members of the population into...
- with- or without-replacement designs
- multistage and cluster designs
- repeated measures
- general cluster-correlation (e.g., correlation due to multiple measures taken from patients)
- multiply imputed analysis variables
Example fields of use
SUDAAN enables the analysis of correlated data encountered in various fields of statistical research, including:- survey research (RDDRandom digit dialingRandom digit dialing is a method for selecting people for involvement in telephone statistical surveys by generating telephone numbers at random. Random digit dialing has the advantage that it includes unlisted numbers that would be missed if the numbers were selected from a phone book...
/telephone studies, area sample designs, cluster and stratified designsStratified samplingIn statistics, stratified sampling is a method of sampling from a population.In statistical surveys, when subpopulations within an overall population vary, it is advantageous to sample each subpopulation independently. Stratification is the process of dividing members of the population into...
, list sampling) - clinical trialClinical trialClinical trials are a set of procedures in medical research and drug development that are conducted to allow safety and efficacy data to be collected for health interventions...
s (safety and efficacy data from multiple sites in multisite trials) - group or community randomized trials
- observations on related family members
- toxicologyToxicologyToxicology is a branch of biology, chemistry, and medicine concerned with the study of the adverse effects of chemicals on living organisms...
(observations on littermates) - multiple subjects within a cluster (patients within physician clinics or students within school classrooms)
- social statisticsSocial statisticsSocial statistics is the use of statistical measurement systems to study human behavior in a social environment. This can be accomplished through polling a particular group of people, evaluating a particular subset of data obtained about a group of people, or by observation and statistical...
- health outcomes research
- longitudinal data analyses
- repeated measures.
Strengths
SUDAAN's strength lies it its ability to compute standard errorStandard error (statistics)
The standard error is the standard deviation of the sampling distribution of a statistic. The term may also be used to refer to an estimate of that standard deviation, derived from a particular sample used to compute the estimate....
s of ratio estimates, mean
Mean
In statistics, mean has two related meanings:* the arithmetic mean .* the expected value of a random variable, which is also called the population mean....
s, totals, regression coefficients
Regression analysis
In statistics, regression analysis includes many techniques for modeling and analyzing several variables, when the focus is on the relationship between a dependent variable and one or more independent variables...
, and other statistics in accordance with the sample design, greatly increasing the accuracy and validity of results. Many, if not most, data set
Data set
A data set is a collection of data, usually presented in tabular form. Each column represents a particular variable. Each row corresponds to a given member of the data set in question. Its values for each of the variables, such as height and weight of an object or values of random numbers. Each...
s require attention to correlation
Correlation
In statistics, dependence refers to any statistical relationship between two random variables or two sets of data. Correlation refers to any of a broad class of statistical relationships involving dependence....
and weighting
Weighting
The process of weighting involves emphasizing the contribution of some aspects of a phenomenon to a final effect or result — giving them 'more weight' in the analysis. That is, rather than each variable in the data contributing equally to the final result, some data are adjusted to contribute...
, but few statistical software packages offer the user the opportunity to specify how data are correlated and weighted. For many years, SUDAAN remained the only broadly applicable software for analysis of correlated and weighted data. Currently Mplus offers similar capacities for a much broader set of models.
Currently, all nine of SUDAAN's analytic procedures offer three popular robust variance estimation methods:
- Taylor seriesTaylor seriesIn mathematics, a Taylor series is a representation of a function as an infinite sum of terms that are calculated from the values of the function's derivatives at a single point....
linearization (generalized estimation equations [GEE] for regression models) - jackknifeResampling (statistics)In statistics, resampling is any of a variety of methods for doing one of the following:# Estimating the precision of sample statistics by using subsets of available data or drawing randomly with replacement from a set of data points # Exchanging labels on data points when performing significance...
(with or without user-specified replicate weights) - balance repeated replication (BRR).