Damaraju Raghavarao

Choice-Based Conjoint Analysis : Models and Designs

Introduction Conjoint Analysis (CA) Discrete Choice Experimentation (DCE) Random Utility Models The Logistic Model Contributions of the Book Some Statistical Concepts Principles of Experimental Design Experimental versus Treatment Design Balanced Incomplete Block Designs and 3-Designs Factorial Experiments Fractional Factorial Experiments Hadamard Matrices and Orthogonal Arrays Foldover Designs Mixture Experiments Estimation Transformations of the Multinomial Distribution Testing Linear Hypotheses Generic Designs Introduction Four Linear Models Used in CA and DCE Brands-Only Designs Attribute-Only Designs Brands-Plus-Attributes Designs Brands, Attributes, and Interaction Design Estimation and Hypothesis Testing Appendix: Logit Analysis of Traditional Conjoint Rating Scale Data Designs with Ordered Attributes Introduction Linear, Quadratic, and Cubic Effects Interaction Components: Linear and Quadratic An Illustration Pareto Optimal Designs Inferences on Main Effects Inferences on Main Effects in 2m Experiments Inferences on Interactions Orthogonal Polynomials Substitution Rate of Attributes Reducing Choice Set Sizes Introduction Subsetting Choice Sets Subsetting Levels into Overlapping Sets Subsetting Attributes into Overlapping Sets Designs Generated from a BIBD Cyclic Construction: s Choice Sets of Size s Each for an ss Experiment Estimating a Subset of Interactions Availability (Cross-Effects) Designs Introduction Brands-Only Availability Designs Portfolio Designs Brand and One (or More) Attributes Brands and More Than One Attribute Sequential Methods Introduction Sequential Experiment to Estimate All Two- and Three-Attribute Interactions Sequential Methods to Estimate Main Effects and Interactions, Including a Common Attribute in 2m Experiments CA Testing Main Effects and a Two-Factor Interaction Sequentially Interim Analysis Some Sequential Plans for 3m Experiments Mixture Designs Introduction Mixture Designs: CA Example Mixture Designs: DCE Example Mixture-Amount Designs Other Mixture Designs Mixture Designs: Field Study Illustration References Index

Block designs : analysis, combinatorics, and applications

# Linear Estimation and Tests for Linear Hypotheses # General Analysis of Block Designs # Randomized Block Designs # Balanced Incomplete Block Designs -- Analysis and Combinatorics # Balanced Incomplete Block Designs -- Applications # t-Designs # Linked Block Designs: Partially Balanced Incomplete Block Designs # Lattice Designs: Miscellaneous Designs

New Combinatorial Designs and their Applications to Group Testing

Abstract A class of designs with property C(t) are introduced for the first time, and their applications in group testing of samples are studied.

A test for detecting untruthful answering in randomized response procedures

Abstract Randomized response procedures are used to elicit responses to sensitive questions. Assuming that the probability of providing an untruthful answer is the same in sensitive and non-sensitive categories and using Warners (1965) procedure twice, Krishnamoorthy and Raghavarao (1991) developed methods of testing this probability to be zero and estimating this probability. Using the same framework provided by them, we develop an asymptotic chi-square test and give a lower bound for the power of the test.

CHARACTERISTICS FOR DISTINGUISHING AMONG BALANCED INCOMPLETE BLOCK DESIGNS WITH REPEATED BLOCKS

Abstract The class B of balanced incomplete block designs with parameters ν, b, r, k, λ considered here includes designs with repeated blocks. Attention to date has centered on constructing the members of B and on finding the minimum number of distinct blocks d ≤ b. Under the classical model, the usual statistical characteristics do not distinguish among members of B ; however, effects related to block totals can be used as distinguishing characteristics. A competing effects model is introduced and is shown to distinguish among members of B . This model is appropriate for intercropping, marketing, and survey investigations. The model is applied to the ten nonisomorphic BIB designs with parameters 7, 21, 9, 3, 3. A computer algorithm for obtaining the pairwise treatment by block incidence matrix of this model is given.

Expiration Dating of Pharmaceutical Compounds in Relation to Analytical Variation, Degradation Rate, and Matrix Designs

In order to establish a shelf life claim for the potency of pharmaceutical compounds drug stability studies are conducted by pharmaceutical companies. Frequently, the effects on stability of a variety of fixed factors are investigated, leading to large and expensive study designs. Consequently, the use of fractional factorial or matrix designs have received increasing attention from statisticians, with a view toward managing the size of such studies. Fixed factors of interest have been studied with respect to matrixing; however, matrixing on the choice of time points has not been thoroughly investigated. This paper studies the effect on the expiration dating of various matrix designs specifically on the choice of sampling time points, in relation to analytical variation and degradation rate. Some useful tables are also given comparing expiration dates from matrixing across sampling time points in relation to the analytical variation and degradation rate.

A class of do designs for two-way elimination of heterogeneity

In this paper we give a class of row-column designs with the property that the i-th row and the j-th column have precisely r treatments in common. A conjecture that such designs are quasi-factorial is disproved by showing that the designs given in this paper are not quasi-factorial. It is also shown that the designs given here are nearly optimal.

Estimating main effects with pareto optimal subsets

A subset T of S is said to be a Pareto Optimal subset of m ordered attributes (factors) if for profiles (combination of attribute levels) (x1, …, xm) and (y1, …, ym) ∈T, no profile ‘dominates’ another; that is, there exists no pair such that xi≤yi, for i = 1, …, m. Pareto Optimal designs have specific applications in economics, cognitive psychology, and marketing research where investigators use main effects linear models to infer how respondents values level of costs and benefits from their preferences for sets of profiles offered them. In such studies, it is desirable that no profile dominates the others in a set. This paper shows how to construct a Pareto Optimal subset, proves that a single Pareto Optimal subset is not a connected main effects plan, provides subsets of two or more attributes that are connected in symmetric designs and gives corresponding results for asymmetric designs.

Use of Distance Function in Sequential Treatment Assignment for Prognostic Factors in the Controlled Clinical Trial

In controlled clinical trials, the treatments are likely to be influenced by various prognostic factors, and while assigning treatments sequentially to the patients it is desirable to allot the treatments in such a way that the treatments are balanced over the main effects of prognostic factors and also on some or all interactions between the prognostic factors if the interactions are present. Efran (1971), Pocock and Simon (1975) and Freedman and White (1976) described some methods of balancing the treatments over the prognostic factors. In this paper, we shall describe a new approach in assigning the treatments using multivariate methods.

COMPARISON OF BRACKETING AND MATRIXING DESIGNS FOR A TWO-YEAR STABILITY STUDY

In the U.S. Food and Drug Administration (FDA) guidelines for stability testing of new drug products, both bracketing and matrixing designs were suggested as the statistical designs. More recently, they have increasing attention from pharmaceutical companies, because both designs reduce the cost of stability studies. The purpose of this paper is to investigate both designs in terms of the power of detection of significant difference between slopes, and use the mean square error to evaluate the precision of estimated drug shelf life. Additionally, the distributions of both designs are compared by using 1000 simulations.