Descriptive and inferential statistics, tests, regression, effect sizes, analysis tools and reading results correctly.
Statistics & Data
Moderation asks when an effect is stronger or weaker; mediation asks through which pathway it works. Interactions, simple slopes, bootstrapped indirect effects
Statistics & Data
Bayesian statistics answers the question many people think a p-value answers: given these data, how believable is the hypothesis? Priors, posteriors, credible i
Statistics & Data
The ordinal-versus-interval argument about Likert data has run for decades. The practical answer lies in separating a single item from a multi-item scale, and i
Statistics & Data
When your question is “how long until it happens”, such as time to PhD completion or to dropout, the average time is the wrong number. Censoring, Kaplan–Meier c
Statistics & Data
Surveying 800 pupils in 20 classes does not give you 800 independent observations. Ignoring nesting makes standard errors falsely small. ICC, the design effect,
Statistics & Data
Many errors in quantitative papers sit in the data file, not the model: unreversed items, duplicates, an age of 250. A logged cleaning routine that lets you exp
Statistics & Data
The chi-square test is the most-run test in survey theses and among the most misread. Expected counts, when to use Fisher, reading residuals to find which cells
Statistics & Data
Shapiro–Wilk gives p < 0.05 and many researchers jump to Mann–Whitney. But normality tests usually answer the wrong question, and Mann–Whitney does not compare
Statistics & Data
A meta-analysis turns 20 small studies into one estimate, or pools apples with oranges and reports a very confident number. Weights, fixed versus random effects
Statistics & Data
When the outcome is pass or fail, dropped out or stayed, linear regression no longer fits. How to read logistic coefficients, convert them to odds ratios, avoid
Statistics & Data
Six months on, a reviewer asks about a number in Table 3 and you cannot remember which buttons produced it. Comparing R, Python, SPSS, Stata, jamovi and JASP, a
Statistics & Data
Two groups with the same mean and error bar can have completely different distributions. Choosing charts by question, showing raw data, labelling error bars, co
Leave your details and our team will contact you within 24 hours. The first consultation is completely free.
