Choosing the most popular NFL games in a local TV market

Abstract

This paper models the TV audience for NFL games in a market without a local team. The model is estimated using all NFL games shown in the Salt Lake City market over the last 10 years. Team popularity varies season to season, with fans preferring high-scoring close games between good teams. The primary motivation of the model was to advise the local station in week-toweek selection of high TV audience games from the slate of FOX games. In 2013 the most popular team was the San Francisco 49ers and the local station broadcast more of their games than any other team. While the predictions offer modest discrimination between popular games, the predicted error precision must be reduced to compete with local station expertise. Reviewing the prediction performance in 2013 reveals insight into strengths and weaknesses of predictive analytics in business decisions.

Competition between sports hurts TV ratings: How to shift league calendars to optimize viewership

“…Other studies have examined NFL TV ratings based on factors such as the performance of teams and uncertainty of games. One study by Paul and Weinbach (2007) found that fans tuned in at higher rates for high-scoring and winning teams where the game outcome was uncertain, results later confirmed by Grimshaw and Burwell's (2014) study of NFL games in the Salt Lake City market. This research has also been applied to European soccer by Buraimo, Forrest, and Simmons (2007), which found that TV audiences are more likely to tune in to games that are uncertain as dictated by the pre-game betting lines.…”

Effect of Star Power on NBA All-Star Game TV Audience

“…Fans of successful teams, on the other hand, cite the team's superior performance as the main reason for their attachment to the team. Though "bandwagon" or "fair-weather" fans (i.e., fans who increase and decrease their attachment to a team in response to a team's performance) are considered scornfully by many sports fans, research shows attendance and TV viewing is influenced significantly by the team's winning record after adjusting for game characteristics (Coates & Humphreys, 2010;Grimshaw & Burwell, 2014).…”

Analysis of monday night football viewership

“…Given the relative uniqueness of its content, we opt for a time‐series model rather than a discrete choice model. In a related piece of work, Grimshaw and Burwell develop a regression model to predict the Salt Lake City television audience for locally broadcast NFL games and find evidence that viewers favor games anticipated to be high‐scoring and competitive, but games involving teams with a new coach tend to be less watched. Grimshaw and Burwell acknowledge that the relatively large error in their model (exacerbated by the fact that the FOX Salt Lake City affiliate must select the games to broadcast at the beginning of the season) erodes the advantage of this analytical approach versus the expertise of the local station personnel.…”

“…In a related piece of work, Grimshaw and Burwell develop a regression model to predict the Salt Lake City television audience for locally broadcast NFL games and find evidence that viewers favor games anticipated to be high‐scoring and competitive, but games involving teams with a new coach tend to be less watched. Grimshaw and Burwell acknowledge that the relatively large error in their model (exacerbated by the fact that the FOX Salt Lake City affiliate must select the games to broadcast at the beginning of the season) erodes the advantage of this analytical approach versus the expertise of the local station personnel. For MNF, there is also a relatively high level of variability in viewership forecasts; for a single season, the coefficient of variation in weekly viewership ranges from 0.066 to 0.209 over the 1993–2014 seasons and averages 0.138 over this period.…”