IxDF Certificate of Completion

Make the case for quantitative UX research as a complement to qualitative methods, and weigh the strengths and limits of each.

Fit surveys, early-design tests, analytics, and A/B/multivariate tests into the appropriate phase of a project lifecycle, with clear judgment about which methods belong at the start, middle, or end of development.

Use triangulation to combine qualitative depth with quantitative scale before committing resources to a design direction.

Write strong survey questions using short words, vertical response formats, randomized order, neutral language, and opt-outs like "Don't know" and "Prefer not to say."

Recruit, screen, and size studies for quantitative UX research, including writing effective screeners, targeting behaviors and needs over demographics, and spotting failing participants like straightliners and speed-runners.

Design and deploy survey research end-to-end, from framing research questions and recruiting participants to choosing between custom questionnaires and standardized instruments like SUS (System Usability Scale) and WAMMI (web-specific, paid).

Test navigation early with tree tests to isolate terminology and information architecture from visual design distractions.

Test layout and visual hierarchy with first-click tests on wireframes or screenshots to predict task success.

Set up early-design tests with user-language goals, interpret pietree reports and first-click heatmaps, and confirm results with Chi-Square tests.

Use Google Analytics to define conversion goals, read core reports, analyze landing pages and referral paths, and build stable KPI dashboards.

Design, plan, and interpret A/B, redirect, and multivariate (A/B/n) tests on live sites or apps, sizing tests appropriately, confirming results with Chi-Square, and interpreting inconclusive results honestly.

Run Chi-Square and Fisher's exact tests on categorical data using raw counts rather than percentages.

Analyze Likert scale data correctly with weighted approaches and Chi-Square, avoiding the trap of treating ordinal data as interval.

Frame UX studies using the null and alternative hypotheses, conduct hypothesis tests, interpret p-values against the UX-standard 0.05 threshold, and explain results in language stakeholders understand.

Identify the four data types (nominal, ordinal, interval, ratio), distinguish within-subjects from between-subjects designs, and choose between parametric tests (t-test, ANOVA) and non-parametric alternatives (Mann-Whitney U, Wilcoxon, Kruskal-Wallis) based on the data.

Apply core statistical concepts to UX datasets, including descriptive statistics (minimum, maximum, range, mean, median, standard deviation, variance) and distributions (histograms, normal distribution, QQ plots), using Excel, Google Sheets, or free online calculators.

Recognize and minimize survey bias (social desirability, conformity, yea-saying, stereotype) using Jeff Sauro's framework, and spot disengaged respondents (straightliners, speed-runners) before analyzing the data.

Conduct ad hoc analyses with a five-step method (question, gather, transform, analyze, answer) and use advanced features like custom segmentation, page value, and goal flow to investigate UX problems.

Run Jansen's four-step web analytics process (identify stakeholders, define primary goals, pinpoint key visitors, and set KPIs) to align analytics with business priorities.

Apply correlation (Pearson vs. Spearman), effect size, statistical power, and confidence intervals to make richer claims about UX data.

Build a UX analytics practice that reveals what users do (not what they say), and understand the mechanics and limits of cookies, web beacons, and event tracking.