Thurstone scaling via binary response regression

Lipovetsky, Stan; Conklin, W. Michael

doi:10.1016/j.statmet.2004.04.001

Cited by 26 publications

(17 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pair-wise comparisons are widely used in applied psychology, marketing, food tasting, and advertising research [28–31]. Recently, two statistical methods have been described that produce an outcome very similar to Thurstone scaling while also providing inferential statistics [32, 33]. We [34] compared these two approaches, binary logistic regression [32] and linear regression [33], and found very similar outcomes.…”

Section: Introductionmentioning

confidence: 99%

“…We prefer the binary logistic regression approach [32], as the statistical significance can be obtained with commonly-used statistical software without the need for additional calculations or custom software. In addition, since logistic regression is a widely used statistical method it is well understood and it facilitates the development and testing of models that account for experimental variables and uncontrolled or confounding variables (as illustrated in the Appendix), a capability that is not currently available with the Bradley-Terry-Luce analyses [26, 37, 38].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Factors Affecting Enhanced Video Quality Preferences

Satgunam

Woods

Bronstad

et al. 2013

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

The development of video quality metrics requires methods for measuring perceived video quality. Most such metrics are designed and tested using databases of images degraded by compression and scored using opinion ratings. We studied video quality preferences for enhanced images of normally-sighted participants using the method of paired comparisons with a thorough statistical analysis. Participants (n=40) made pair-wise comparisons of high definition (HD) video clips enhanced at four different levels using a commercially available enhancement device. Perceptual scales were computed with binary logistic regression to estimate preferences for each level and to provide statistical inference of the differences among levels and the impact of other variables. While moderate preference for enhanced videos was found, two unexpected effects were also uncovered: (1) Participants could be broadly classified into two groups: those who preferred enhancement ("Sharp") and those who disliked enhancement ("Smooth"). (2) Enhancement preferences depended on video content, particularly for human faces to be enhanced less. The results suggest that algorithms to evaluate image quality (at least for enhancement) may need to be adjusted or applied differentially based on video content and viewer preferences. The possible impact of similar effects on image quality of compressed video needs to be evaluated.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Factors Affecting Enhanced Video Quality Preferences

Satgunam

Woods

Bronstad

et al. 2013

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…In the approach developed in (Lipovetsky & Conklin, 2002) the analytic hierarchy process (AHP) matrix of pairwise ratios was transformed to a share matrix with the elements of the kind (9), and a specific eigenproblem was designed for evaluating the priorities among the items. The results of that work applied to a Thurstone matrix (8) (that corresponds to the transposition of a transformed AHP matrix) can be presented in the eigenproblem:…”

Section: Stochastic Modeling By Chapman-kolmogorovmentioning

confidence: 99%

“…This technique is widely used in fields of applied psychology, particularly, in marketing and advertising research (Edwards, 1957;Torgerson, 1958;Bock & Jones, 1968;Green & Tull, 1978;Conklin & Lipovetsky, 1999, 2004a, 2004bLipovetsky, 2007aLipovetsky, , 2007b. Thurstone scaling transforms ranked or paired comparison data into a scale that is used for displaying the results of a ranking procedure.…”

Section: Introductionmentioning

confidence: 99%

Priorities in Thurstone Scaling and Steady-State Probabilities in Markov Stochastic Modeling

Lipovetsky

2013

J. Mod. App. Stat. Meth.

Self Cite

View full text Add to dashboard Cite

Thurstone scaling is widely used in marketing and advertising research where various methods of applied psychology are utilized. This article considers several analytical tools useful for positioning a set of items on a Thurstone scale via regression modeling and Markov stochastic processing in the form of ChapmanKolmogorov equations. These approaches produce interval and ratio scales of preferences and enrich the possibilities of paired comparison estimation applied for solving practical problems of prioritization and probability of choice modeling.

show abstract

“…Next, a linear scale is developed in which the score of each product is obtained by averaging the quantiles corresponding to the paired comparisons including this product. Montag (2006) proposed Monte Carlo simulations to obtain confidence intervals of the scores whereas Lipovetsky and Conklin (2004) and Luker, Beaver, Leinster, Owens, Degner, and Sloan (1995) used ttests to analyse the significance of the differences between scores.…”

Section: Introductionmentioning

confidence: 99%