How many days was that? We're still not sure, but we're asking the question better!

Abstract

Unreliable measures limit the ability to detect relationships with other variables. Day-to-day variability in measurement is a source of unreliability. Studies vary substantially in numbers of days needed to reliably assess physical activity. The required numbers of days has probably been underestimated due to violations of the assumption of compound symmetry in using the intraclass correlation. Collecting many days of data become unfeasible in real-world situations. The current dilemma could be solved by adopting distribution correction techniques from nutrition or gaining more information on the measurement model with generalizability studies. This would partition the variance into sources of error that could be minimized. More precise estimates of numbers of days to reliably assess physical activity will likely vary by purpose of the study, type of instrument, and characteristics of the sample. This work remains to be done.

FIGURE 1

Pattern in days of physical activity by levels of consistency.

FIGURE 2

Venn diagram of a study including the people’s (P), days (D), and number of devices (T) facets. The interactions of people and days are represented by P × D, the interaction between people and number of devices are represented by P × T, the interaction between days and number of devices is D × T, and people, days, and the number of devices include undefined error (P × D × T, e).