This guide covers the statistical methods most relevant to interpreting Implicitify assessment data and conducting psychological research. It is a practical reference — focused on application rather than derivation.
Effect Sizes
Cohen's d for mean differences, Pearson's r for correlations, and eta-squared for variance explained. Why effect sizes matter more than p-values for interpreting research findings, and how to compute them from Implicitify's standardized output.
Reliability
Internal consistency (Cronbach's alpha, McDonald's omega), test-retest reliability, inter-rater reliability (ICC), and standard error of measurement. How to evaluate whether a score is precise enough to support the interpretation you want to make.
Normative Comparisons
IQ-scale transformation (M=100, SD=15), T-score transformation (M=50, SD=10), percentile ranks, and qualitative classifications. How Implicitify converts raw scores to standardized scores and what those scores mean.
Change Detection
Reliable Change Index (RCI), clinically significant change, and Jacobson-Truax criteria. How to determine whether a change in scores from pre- to post-treatment exceeds measurement error and reflects genuine change.
Power Analysis
Sample size estimation for common designs in psychological research. How many participants you need to detect effects of various sizes with adequate statistical power.