Analyzing cyclic patterns in psychological data: A tutorial

Abstract

A growing number of studies on psychological phenomena employ the Ecological Momentary Assessment (EMA) method for obtaining intensive longitudinal data in daily life. Whereas cyclic processes may underlie different psychological and physiological outcomes, the cyclic model that describes such processes is rarely used for fitting EMA data. The aim of this paper is to introduce the cyclic model to researchers, and to demonstrate its use in an empirical data set. It is shown how the cyclic terms can be incorporated in multilevel models. Based on secondary analyses on an existing EMA data set, it can be concluded that adding cyclic terms in EMA analyses may improve model fit and may help understanding the dynamic processes.

Forecasting the number of dengue fever based on weather conditions using ensemble forecasting method

“…In the independent variable forecasting process, the methods used are different depending on the data pattern. Based on observations, the variables of air temperature, air humidity, and wind speed have cyclical data patterns, where the data patterns are repeated over a long period of time [23]. Therefore, the three variables can be predicted using the multiplicative decomposition method [24].…”

Why and How to Deal With Diurnal Cyclic Patterns in Ambulatory Assessment of Emotions

“…The cyclic modeling approach uses sine and cosine functions to model (diurnal) cycles (Flury & Levri, 1999; Huh, Kaysen, & Atkins, 2015). While this approach balances adequately capturing cyclic patterns with simplicity of application (Huh et al., 2015; Liu & West, 2016; Verboon & Leontjevas, 2018; West & Hepworth, 1991), it has so far been scarcely used in AA research. Therefore, in addition to discussing the rationale for considering cyclic models to analyze AA data on emotions ( why ), we aim to describe and give researchers easy to use instructions on how cyclic models can be used to observe and address diurnal cyclic patterns in an empirical AA dataset, together with an evaluation of potential benefits and drawbacks of this approach compared to other (conventional) approaches for observing and addressing cyclicity.…”

“…The cyclic modeling approach allows to accurately capture and estimate increases and decreases of a variable over time, and has been suggested as a practical alternative to the methods mentioned above (Huh et al, 2015; Verboon & Leontjevas, 2018). Below we illustrate and evaluate the use of this approach in an AA context.…”

“…To estimate the amplitude and the horizontal shift from the data, the cyclic model has to be rewritten using a number of basic trigonometric transformations and elementary algebra (Verboon & Leontjevas, 2018). Using our example data with positive affect as criterion variable the cyclic model will look like: …”

“…The original parameters b 1 (amplitude), and b 2 (horizontal shift), can be obtained from the parameter estimates a 1 and a 2 (see Verboon & Leontjevas, 2018).…”