Paramjit S. Gill

Bayesian Analysis of Dyadic Data

SYNOPTIC ABSTRACT This paper considers the Bayesian analysis of dyadic data with particular emphasis on applications in social psychology. Various existing models are extended and unified under a class of models where a single value is elicited to complete the prior specification. Certain situations which have sometimes been problematic (e.g. incomplete data, non-standard covariates, missing data, unbalanced data) are easily handled under the proposed class of Bayesian models. Inference is straightforward using software that is based on Markov chain Monte Carlo methods. Examples are provided which highlight the variety of data sets that can be entertained and the ease in which they can now be analyzed.

A robust mixed linear model analysis for longitudinal data

This paper describes robust procedures for estimating parameters of a mixed effects linear model as applied to longitudinal data. In addition to fixed regression parameters, the model incorporates random subject effects to accommodate between-subjects variability and autocorrelation for within-subject variability. Robust empirical Bayesian estimation of subject effects is briefly discussed. As an illustration, the procedures are applied to data from a multiple sclerosis clinical trial.

Statistical analyses for round robin interaction data

This paper considers the analysis of round robin interaction data whereby individuals from a group of subjects interact with one another, producing a pair of outcomes, one for each individual. The authors provide an overview of the various analyses applied to these types of data and extend the work in several directions. In particular, they provide a fully Bayesian analysis for such data and use a real data example for illustration purposes.

Optimal batting orders in one-day cricket

This paper concerns the search for optimal or nearly optimal batting orders in one-day cricket. A search is conducted over the space of permutations of batting orders where simulated annealing is used to explore the space. A non-standard aspect of the optimization is that the objective function (which is the mean number of runs per innings) is unavailable and is approximated via simulation. The simulation component generates runs ball by ball during an innings taking into account the state of the match and estimated characteristics of individual batsmen. The methods developed in the paper are applied to the national team of India based on their performance in one-day intemational cricket matches.

Duckworth–Lewis and Twenty20 Cricket

Originally designed for 1-day cricket, this paper considers the use of the Duckworth–Lewis method as an approach to resetting targets in interrupted Twenty20 cricket matches. The Duckworth–Lewis table is reviewed and an alternative resource table is presented. The alternative table is constructed using observed scoring rates from international Twenty20 matches. A desideratum of a resource table is monotonicity in both the rows and columns corresponding to wickets and overs respectively. Consequently, a Gibbs sampling scheme related to isotonic regression is applied to the observed scoring rates to provide a non-parametric resource table. Taking into account the more aggressive batting style of Twenty20 compared to 1-day cricket, the resultant resource table is seen to possess sensible features. A discussion is provided concerning the use of the Duckworth–Lewis method applied to Twenty20.

Late-Game Reversals in Professional Basketball, Football, and Hockey

Abstract Empirical evidence suggests that in basketball, football, and hockey, the leader at the beginning of the final period (quarter or period) wins the game about 80% of the time. We discuss modeling of late-game reversals in NBA, NFL, and NHL sports. The models are built around the assumptions that basketball scores and football scores are normally distributed and hockey scores vary according to a Poisson distribution. The models also accommodate the proverbial home field advantage. We use data from the 1997–1998 regular seasons of the leagues to estimate the parameters for the models. Predictions from the probabilistic models are in excellent agreement with the actual outcomes.

Spatial Analysis of Seasonal Dynamics and Overwintering of Drosophila suzukii (Diptera: Drosophilidae) in the Okanagan-Columbia Basin, 2010–2014

Abstract Spotted wing drosophila, Drosophila suzukii (Matsumura) (Diptera: Drosophilidae), was monitored from 2010 to 2014 in 314–828 sites located in interior fruit-growing regions of OR and WA, United States, and BC, Canada, using traps baited with apple cider vinegar or sugar-water-yeast. Seasonal population dynamics and sex ratios were summarized for berry, cherry, stone fruit, grape, non-crop host plants, non-host sites, and for conventional IPM, certified organic, backyard, and feral sites, by region and year. Overwintering was detected in all regions and years, despite winter temperatures below -17°C. A spatial analysis was conducted using a Geographic Information System (GIS), daily weather data, geomorphometric measures of terrain, distance to water, and other variables, at each site. Overwintering success at a site, measured as Julian week of first capture of D. suzukii, was significantly related (R 2 = 0.49) in cherry habitats to year, agronomic treatment, and number of winter days with temperatures >-5°C. In berry, cherry, stone fruit and grape habitats, 2011–2014, it was significantly related (R 2 = 0.42) to year, agronomic treatment, the logarithm of peak population of D. suzukii in the prior autumn, latitude, elevation, and topographic wetness index. The results show that D. suzukii has adapted to exploit a succession of irrigated crops and feral habitats in mixed landscapes of a semi-arid region with cold winters and hot dry summers, and are shaping strategies for pest management and for biological control.

A Stylometric Analysis of King Alfred's Literary Works

Abstract For centuries, Alfred the Great was judged to have translated several Latin texts into Old English. Many scholars, however, have expressed doubt whether Alfred could have done all of this work. With the availability of the Old English Corpus in electronic form, it is feasible to subject the texts to statistical stylometric analysis. We approach the problem from a Bayesian perspective where key words are identified and frequencies of the key words are tabulated for seven relevant texts. The question of authorship falls into the general statistical problem of classification where several simple innovations to classical agglomerative procedures are introduced. Our results suggest that one translation that has been traditionally attributed to Alfred (The First Fifty Prose Psalms) tends to distinguish itself from texts that are known to be Alfredian.

Tests Concerning Equicorrelation Matrices with Grouped Normal Data

ABSTRACT This article considers three practical hypotheses involving the equicorrelation matrix for grouped normal data. We obtain statistics and computing formulae for common test procedures such as the score test and the likelihood ratio test. In addition, statistics and computing formulae are obtained for various small sample procedures as proposed in Skovgaard (2001). The properties of the tests for each of the three hypotheses are compared using Monte Carlo simulations.