Measurement Issues in Time-Series Research: Reliability and Validity Assessment in Modeling the Macroeconomic Effects of Advertising

Methods for the analysis of time series have become widely known and are now applied regularly by marketers and other social scientists. Time-series analysis has proved useful in such areas as forecasting (e.g., Kapoor, Madhok, and Wu 1981; Moriarty and Adams 1979), assessing the relationship between advertising and sales (e.g., Aaker, Carman, and Jacobson 1982; Jagpal and Hui 1980), examining market responses to specified interventions (e.g., Franke and Didow 1981; Wichern and Jones 1977), and testing hypothesized concomitancies in time-series designs (e.g., Hanssens 1980). In contrast to cross-sectional research, time-series designs generally challenge the researcher's ability to discover and analyze multiple-item, multiple-method data required for reliability and validity assessment. Currently archived time-series data generally include at best single-item measures infrequently available for a restricted period of time. Increased attention to measurement issues in time-series research should result in renewed emphasis on the design, measurement, and archiving of multiple "focal local indicators" (Campbell 1976) of marketing phenomena. It also should contribute to further research in the limitations of currently available time-series statistical models and causality tests and to the development of promising alternative procedures.

Кодировка UTF-8 Кодировка WIN-1251 Кодировка KOI8-R

BiBTeX

/text/biblio/16553321/bib

RIS

/text/biblio/16553321/ris