# Using a two-part mixed-effects model for understanding daily, individual-level media behavior

- 7 Downloads

## Abstract

This study supports a strategic analytics proposal, namely that there is conceptual and practical utility in applying a two-part mixed-effects model for understanding individual differences in daily media use. Individual-level daily diary measures of media use typically contain information about a person’s likeliness to use media, extent of usage, and variation in use across days that, taken together, can provide data for evaluating media behavior that is otherwise masked by using aggregate measures. The statistical framework developed and demonstrated here focuses on these three metrics. The approach, applied to daily diary measures of television use in a large, representative U.S. sample, yields results that add value when weighing media strategies centered on the twin tactics of reach and frequency. The implications for the proposed analytic strategy are discussed.

## Keywords

Media TV Mixed-effects models Diary data Repeated measures Frequency versus reach## Notes

## References

- AdAge. 2017. Marketing Fact Pack 2018 http://adage.com/d/resources/resources/whitepaper/marketing-fact-pack-2018.
- Aitkin, M. 1987. Modelling variance heterogeneity in normal regression using GLIM.
*Applied Statistics*36 (3): 332–339.Google Scholar - Beal, V., J. Romaniuk, and B. Sharp. 2018. Television advertising television: measuring the ability of television promos to deliver ratings for new programs using single-source data.
*International Journal of Advertising*3 (3): 463–481.Google Scholar - Carroll, R.J., and D. Ruppert. 1988.
*Transformation and Weighting in Regression*. New York: Chapman & Hall.Google Scholar - Cheon, H.J., F.R. Fraser, and T.K. Nguyen. 2018. Family-based treatment for obesity in tweens: A three-year longitudinal follow-up study.
*International Journal of Advertising*37 (4): 548–567.Google Scholar - Cook, R.D., and S. Weisberg. 1983. Diagnostics for heteroscedasticity in regression.
*Biometrika*70 (1): 1–10.Google Scholar - Danaher, P.J., and T.S. Dagger. 2013. Comparing the relative effectiveness of advertising channels: a case study of a multimedia blitz campaign.
*Journal of Marketing Research*50 (4): 517–534.Google Scholar - Duan, N., W.G. Manning, Jr., C.N. Morris, and J.P. Newhouse. 1983. A comparison of alternative models for the demand for medical care.
*Journal of Business & Economic Statistics*1 (2): 115–126.Google Scholar - Gottard, A., E. Stanghellini, and R. Capobianco. 2013. Semicontinuous regression models with skew distribution. In
*Complex Models and Computational Methods in Statistics*, ed. M. Grigoletto, L. Francesco, and S. Petrone, 149–160. Verlag-Mailand: Springer.Google Scholar - Hallward, J. 2008. Make measurable what is not so: consumer mix modeling for the evolving media world.
*Journal of Advertising Research*44 (3): 339–351.Google Scholar - Harvey, A.C. 1976. Estimating regression models with multiplicative heteroscedasticity.
*Econometrica*44 (3): 461–465.Google Scholar - Kazakova, S., V. Cauberghe, L. Hudders, and C. Labyt. 2016. The impact of media multitasking on the cognitive and attitudinal response to television commercials: The moderating role of type of advertising appeal.
*Journal of Advertising*45 (4): 403–416.Google Scholar - Kelly, J.S., and S.K. Jones. 2012.
*The IMC Handbook: Readings & Cases in Integrated Marketing Communications*. Chicago: Ramcom Communications.Google Scholar - La Ferle, C., and W.N. Lee. 2005. Can English language media connect with ethnic audiences? Ethnic minorities’ media use and representation perceptions.
*Journal of Advertising Research*45 (1): 140–153.Google Scholar - Laird, N.M., and J.H. Ware. 1982. Random-effects models for longitudinal data.
*Biometrics*38 (4): 963–974.Google Scholar - Larsen, K., J.H. Petersen, E. Budtz-Jorgensen, and L. Endahl. 2000. Interpreting parameters in the logistic regression model with random effects.
*Biometrics*56 (3): 909–914.Google Scholar - Lin, C., S. Venkataraman, and S.D. Jap. 2013. Media multiplexing behaviour: implications for targeting and media planning.
*Marketing Science*32 (2): 310–324.Google Scholar - Liu, L., R.L. Strawderman, M.E. Cowen, and Y.C. Shih. 2010. A flexible two-part random effects model for correlated medical costs.
*Journal of Health Economics*29: 110–123.Google Scholar - Min, Y., and A. Agresti. 2002. Modeling nonnegative data with clumping at zero: a survey.
*Journal of the Iranian Statistical Society*1 (1–2): 7–33.Google Scholar - McDonal, C., and Ehrenberg, A.S.C. 2003. What happens when brands gain or lose share? Customer acquisition or increased loyalty?: Report 31 for Corporate Members. Adelaide, Australian: Ehrenberg-Bass Institute for Marketing Science.Google Scholar
- Molenberghs, G., and M. Kenward. 2007.
*Missing Data in Clinical Studies*. West Sussex: Wiley.Google Scholar - Mora, J.D. 2016. Social context and advertising effectiveness: a dynamic study.
*International Journal of Advertising*35 (2): 325–344.Google Scholar - Nelson-Field, K., E. Riebe, and B. Sharp. 2012. What’s not to “like?”: Can Facebook fan base give a brand the advertising reach it needs?
*Journal of Advertising Research*52 (2): 262–269.Google Scholar - O’Guinn, T.C., C.T. Allen, A. Close Scheinbaum, and R.J. Semenik. 2019.
*Advertising and Integrated Brand Promotion*. Boston: Cengage Learning Inc.Google Scholar - Olsen, M.K., and J.L. Schafer. 2001. A two-part random effects model for semicontinuous longitudinal data.
*Journal of the American Statistical Association*96 (454): 730–745.Google Scholar - Precourt, G. 2017. Why tv still matters.
*Journal of Advertising Research*57 (1): 1–2.Google Scholar - Ryff, C.D., and Almeida, D. Midlife in the United States (MIDUS Refresher): Daily Diary Project, 2012-2014. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2018-06-06.Google Scholar
- Schmidt, S., and M. Eisend. 2015. Advertising repetition: a meta-analysis on effective frequency in advertising.
*Journal of Advertising*44 (4): 415–428.Google Scholar - Tobin, J. 1958. Estimation of relationships for limited dependent variables.
*Econometrica*26 (1): 24–36.Google Scholar - Wolfinger, R.D. 1999. Fitting nonlinear mixed models with the new NLMIXED procedure. Paper 287, SUGI Proceedings. Cary: SAS Institute Inc.Google Scholar
- Wolfinger, R.D. 2000. Fitting nonlinear mixed models with the new NLMIXED procedure, Paper 287, SAS Institute Inc., Proceedings of the Twenty-Fifth Annual SAS Users Group International Conference Cary, NC: SAS Institute Inc.Google Scholar
- Xing, D., Y. Huang, H. Chen, Y. Zhu, G.A. Dagne, and J. Baldwin. 2017. Bayesian inference for two-part mixed-effects model using skew distributions, with application to longitudinal semicontinuous alcohol data.
*Statistical Methods in Medical Research*26 (4): 1838–1853.Google Scholar - Xu, S., and S.A. Blozis. 2011. Sensitivity analysis of mixed models for incomplete longitudinal data.
*Journal of Educational and Behavioral Statistics*36 (2): 237–256.Google Scholar - Xu, S., S.A. Blozis, and E. Vandewater. 2014. On fitting a multivariate two-part latent growth model.
*Structural Equation Modeling*21 (1): 131–148.Google Scholar