Investigating Undercurrents of Stationarity and Growth With Long-Term Panel Data

Abstract

There have been frequent calls in the literature for a more comprehensive understanding of marketing impact on long-term firm performance. Retail scanner data has been the principal source of empirical evidence in this strategic domain, but it cannot explain the behavioural shifts that underpin the sales dynamics it reports. With the availability of far larger and extended household panels, it is now possible to observe the effects of accumulating penetration on brand and category buying over many years. This type of data nevertheless presents theoretical and methodological challenges to researchers. In this article, we discuss an approach to extending established marketing theory to long-run repeat buying and then outline the inherent constraints of long-term panels. We illustrate these challenges using one-, five- and 10-year panel datasets and present a research agenda to progress explanatory theories of long-run brand building and category growth in this new but so far mostly untapped resource.

Using neural data to forecast aggregate consumer behavior in neuromarketing: Theory, metrics, progress, and outlook

“…Additionally, interpreting results in the context of neuroimaging meta-analyses related to the research topic is advisable, as meta-analysis findings are often more robust due to aggregation and analysis across multiple studies in the field (Plassmann et al, 2015;Wang & Yao, 2024). (Genevsky & Knutson, 2015;Tong et al, 2020).Particularly when your laboratory sample is matched to a market-level sample, the behavioral choice of the laboratory sample are highly effective predictor variable (Tong, 2021).Moreover, insights from the long-term panel data on past purchasing behavior can provide further insights into shifts in the firm's category revenues across varying conditions, including factors such as purchaser count and purchase amounts (Dunn et al, 2021).…”

“…Particularly when your laboratory sample is matched to a market‐level sample, the behavioral choice of the laboratory sample are highly effective predictor variable (Tong, 2021). Moreover, insights from the long‐term panel data on past purchasing behavior can provide further insights into shifts in the firm's category revenues across varying conditions, including factors such as purchaser count and purchase amounts (Dunn et al, 2021). Multiple studies have consistently demonstrated that the optimal approach to enhancing forecasting results is by combining multiple types of data (Motoki et al, 2020; Tong et al, 2020; Varga et al, 2021; Venkatraman et al, 2015).…”

Valuing the contribution of ultra‐light buyers

“…When a brand grows, penetration typically increases at a greater rate than any other measures (Romaniuk et al, 2018), especially at three times the rate of loyalty (Romaniuk et al, 2014). Being a time‐dependent measure, penetration grows when examining extended periods (Dunn et al, 2021; Ehrenberg, 2000; Sharp, 2010). Cumulative analysis comparing the buying metrics from one and 5 years shows repertoire size, category and brand penetrations increase with longer periods (Banelis et al, 2013).…”

“…Consequently, when cumulative penetration is observed for longer periods, firms gain insights into brand growth changes and contributions for various buyers. Recent studies identify that long‐run brand performance depends on maintaining cumulative penetration growth (Dawes et al, 2022; Dunn et al, 2021; Graham & Kennedy, 2022). Therefore, the first research question is:RQ1 How much does brand penetration accumulate in successively longer periods from one to five years?…”