Эффекты учета неоднородности характеристик в ценовых индексах видеоигр

Прикладная эконометрика. 2024. № 3(75). С. 78–97.

Арсланов М. В., Ratnikova T. A.

In this paper, an attempt is made to construct hedonistic price indices for the computer game market for the period from 2007 to 2023. The peculiarity of the work is that the hedonistic regressions used take into account additional factors reflecting the consumer's reaction to the object of study, while at the previous stage of the study only the parameters of the objects set by the manufacturer were considered. In addition, the prices set by the manufacturer at the time of the game's release were previously modeled, and the study period did not cover 2022 and 2023. In this work, the final product prices recorded at the time of data collection are used, and the period covers 2023.

In hedonistic regression, the dependence of price on time is cleared of the influence of a number of characteristics of games and some factors of demand for them, but there are unobservable sets of characteristics that are difficult to specify, for example, such as features of the genre or game mode. It is difficult to take into account the effects of the described variables directly in the equation of the model, but if we assume their uncorrelation with the variables explicitly specified in the equation of the model, then they can be interpreted as various kinds of random effects, which allows us to obtain effective and, perhaps even, consistent estimates of the price index.

To build indexes, a standard hedonistic approach with temporary dummy variables is used, which is modified to take into account the random effects described above. The constructed models are evaluated using OLS and simulation likelihood method. The applied approach makes it possible to identify factors whose effects on prices differ significantly depending on which genres, modes and groups of objects appear in terms of the scale of the user audience.

The final part of the study analyzes monthly data from 2020 to 2023 for a deeper study of the effects of events following February 24, 2022.

The indices based on annual data in the period 2007–2023 reflect key global economic events, which, at first glance, contradicts the opinion of gaming industry experts about the weak sensitivity of the gaming market to crises, however, the analysis conducted on monthly data makes it possible to verify that the gaming industry has a very high rate of adaptation to economic and political upheavals.

Keywords: видеоигры, video games, ценовые индексы, price indices, hedonic regressions, fixed-effect models, random effects models, гедонистические регрессии, модели со случайными эффектами, многоуровневые модели, multilevel mixed-effects models, модели с фиксированными эффектами