Efficient Cause Analysis - Paired Orderings


Generic Questions: Do two variables (orderings) change consistently over time or across multiple occasions? Do changes in one ordering follow changes in another ordering in time (a lagged effect over time). More generally, do changes in one ordering cause changes in the second ordering? 

Data Type: Two or more qualitative or quantitative orderings (variables). Longitudinal / repeated measures / within-subjects / dependent observations

Hypotheses
: The pattern of change in one ordering across time or occasions will match (or be opposite of) the pattern in a second ordering

Traditional analogs
: Hierarchical linear modeling examining person-level "effects"

Summary
: This analysis can be used when you wish to compare pairs of observations made over time or across occasions on the same persons or entities (e.g., examine simultaneous changes in attitudes and emotions across time or examine simultaneous changes in attitudes and emotions when exposed to a series of images). The observations for this analysis can be qualitative or quantitative in nature. For instance, attitudes and emotions are often assessed using rating scales which represent categorical or ordinal judgments. Patterns in these judgments can be examined across time or occasions. Example quantitative variables could be daily caloric intake and weight measured in pounds. Do these two quantitative orderings increase or decrease simultaneously over time? If caloric intake is considered as the cause, and weight as the effect, then changes in weight may be lagged in time as the impact of dietary changes may not be immediate. With regard to traditional statistics, this analysis can be used instead of a hierarchical linear model or mixed-effects (fixed and random effects) ANOVA.

Software Access: The Efficient Cause Analysis -- Paired Orderings procedure can be found by selecting "Analyses --> Efficient Cause Analysis --> Paired Orderings" from the Main Menu. The procedure window appears as:


Videos and Files: The following videos and files describe the procedure and its various options. Be sure to set the video quality to High Definition (1080p) if the browser does not automatically do so. If you wish to follow along with the analyses on your own computer, download and open the data set(s) linked at the bottom of this page.


Reporting Results

 


Data