Joost will present a useful overview for different kinds of statistics that can be used in cognitice semiotics studies. Welcome to the room, or else on zoom!

The focus of an experimental study (as in the third-person perspective of phenomenological triangulation) is to establish whether or not there is a causal relationship between two variables. To establish this kind of relationship, one variable is varied in a controlled way by the experimenter, and the effect that this variation has on another variable is measured. Everything else is being kept constant as much as possible, so that potential effects that other variables may have is minimized. This variable measurement in experiments in most behavioural disciplines is carried out on groups consisting of limited numbers of participants (typically 20 to 30), which brings about a risk of sampling error. This means that in addition to not knowing in advance whether a relationship between the variables of interest exists in the first place, the relationship in the selected sample of participants may not be quite the same as that in the population. Taken together, there are a great deal of factors that can cast a shadow on the results of the experiment. Observed effects may be a consequence of researcher luck while the absence of observed effects may be a consequence of researcher bad luck. To put the findings in a greater perspective, a statistical analysis of the experimental results is usually required. As we will see, this analysis can assist the researcher in providing estimates of effect sizes given the strength of the effect and the size of the sample in which the effect was found, and can help researchers in convincing their audience was not just a matter of good or bad luck.