Using a nested logit model to forecast television ratings

Research output: Contribution to journalArticleResearchpeer-review

19 Citations (Scopus)

Abstract

The television environment has become increasingly complex over the past decade, but scant attention has been paid to the modeling and forecasting of television ratings. In this study we use a little-known version of the nested logit model that is suitable for aggregate choice decision data, since television ratings are aggregate measures. We extend this model to include television program random effects, and develop a novel method for predicting program random effects for programs that have not previously been broadcast. Our dataset is comprehensive, spanning the period 2004-2008, and has program ratings for each main broadcaster, as well as some satellite channels, in a market with over 70 channels. We compare our model s forecasts with those of several other models and show that it markedly outperforms these models.
Original languageEnglish
Pages (from-to)607 - 622
Number of pages16
JournalInternational Journal of Forecasting
Volume28
Issue number3
DOIs
Publication statusPublished - 2012

Cite this

@article{a2f2d3a208c1485aa0061213a0b79bbc,
title = "Using a nested logit model to forecast television ratings",
abstract = "The television environment has become increasingly complex over the past decade, but scant attention has been paid to the modeling and forecasting of television ratings. In this study we use a little-known version of the nested logit model that is suitable for aggregate choice decision data, since television ratings are aggregate measures. We extend this model to include television program random effects, and develop a novel method for predicting program random effects for programs that have not previously been broadcast. Our dataset is comprehensive, spanning the period 2004-2008, and has program ratings for each main broadcaster, as well as some satellite channels, in a market with over 70 channels. We compare our model s forecasts with those of several other models and show that it markedly outperforms these models.",
author = "Danaher, {Peter Joseph} and Dagger, {Tracey Sara}",
year = "2012",
doi = "10.1016/j.ijforecast.2012.02.008",
language = "English",
volume = "28",
pages = "607 -- 622",
journal = "International Journal of Forecasting",
issn = "0169-2070",
publisher = "Elsevier",
number = "3",

}

Using a nested logit model to forecast television ratings. / Danaher, Peter Joseph; Dagger, Tracey Sara.

In: International Journal of Forecasting, Vol. 28, No. 3, 2012, p. 607 - 622.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Using a nested logit model to forecast television ratings

AU - Danaher, Peter Joseph

AU - Dagger, Tracey Sara

PY - 2012

Y1 - 2012

N2 - The television environment has become increasingly complex over the past decade, but scant attention has been paid to the modeling and forecasting of television ratings. In this study we use a little-known version of the nested logit model that is suitable for aggregate choice decision data, since television ratings are aggregate measures. We extend this model to include television program random effects, and develop a novel method for predicting program random effects for programs that have not previously been broadcast. Our dataset is comprehensive, spanning the period 2004-2008, and has program ratings for each main broadcaster, as well as some satellite channels, in a market with over 70 channels. We compare our model s forecasts with those of several other models and show that it markedly outperforms these models.

AB - The television environment has become increasingly complex over the past decade, but scant attention has been paid to the modeling and forecasting of television ratings. In this study we use a little-known version of the nested logit model that is suitable for aggregate choice decision data, since television ratings are aggregate measures. We extend this model to include television program random effects, and develop a novel method for predicting program random effects for programs that have not previously been broadcast. Our dataset is comprehensive, spanning the period 2004-2008, and has program ratings for each main broadcaster, as well as some satellite channels, in a market with over 70 channels. We compare our model s forecasts with those of several other models and show that it markedly outperforms these models.

U2 - 10.1016/j.ijforecast.2012.02.008

DO - 10.1016/j.ijforecast.2012.02.008

M3 - Article

VL - 28

SP - 607

EP - 622

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

IS - 3

ER -