Skip to content
phdguide

Statistics & Data Analysis

Statistics for researchers, in plain English — descriptive statistics, hypothesis tests, correlation and regression, factor analysis, SEM, p-values and effect sizes — and how to choose and interpret the right test.

All Statistics & Data Analysis guides

15 articles

Intermediate

Convergent & Discriminant Validity: AVE, HTMT and Fornell-Larcker Thresholds

The exact thresholds examiners check: AVE ≥ 0.50, loadings ≥ 0.708, HTMT below 0.85/0.90, and the Fornell-Larcker criterion — what each means, and what to do when a construct fails.

3 min19 Jul 2026
Intermediate

How to Interpret SmartPLS Bootstrapping Results (t-Values, p-Values, CIs)

You've run bootstrapping in SmartPLS — now what do the t-values, p-values and confidence intervals actually mean? A path-by-path reading guide, with the reporting format reviewers expect.

3 min19 Jul 2026
Beginner

How to Choose the Right Statistical Test: A Decision Guide

Every statistical test answers three questions: what are you testing, how many groups, and what type of data? Answer those and the right test chooses itself — here's the complete decision map.

2 min18 Jul 2026
Guide

How to Analyse Likert Scale Data in SPSS (Without Getting It Wrong)

Mean or median? Parametric or not? Item vs summated scale? The practical, defensible way to analyse Likert data in SPSS — the workflow, the tests and the classic examiner objections.

2 min9 Jul 2026
Guide

Mediation vs Moderation Analysis: What They Mean and How to Run Them

Mediators explain *how* an effect happens; moderators explain *when* it's stronger or weaker. Plain-English definitions, how to test each (PROCESS, AMOS, SmartPLS), and how to report them.

2 min9 Jul 2026
Beginner

What Is Jamovi? The Free SPSS Alternative, Honestly Reviewed

Jamovi is free, open-source statistics software with an SPSS-like interface built on R. What it does well, where it can replace SPSS for a thesis, and where it can't.

2 min9 Jul 2026
Advanced

What is Meta-Analysis? Pooling Evidence the Right Way

Meta-analysis pools effect sizes from many studies into one weighted estimate. The core concepts — effect sizes, fixed vs random effects, heterogeneity, forest and funnel plots — explained without the algebra.

2 min4 Jul 2026
Advanced

Model Fit Indices in AMOS Explained (CFI, RMSEA, CMIN/df & More)

CMIN/df, CFI, TLI, RMSEA, SRMR — what each fit index actually measures, the thresholds examiners expect, and what to do (and not do) when your model doesn't fit.

2 min4 Jul 2026
Beginner

How to Use SPSS for Thesis Analysis: A Practical Roadmap

From raw questionnaires to reportable results: the seven-step SPSS workflow every thesis analysis follows — data entry, cleaning, reliability, descriptives, testing and reporting.

2 min4 Jul 2026
Intermediate

What is SmartPLS? PLS-SEM Explained for Thesis Research

SmartPLS runs PLS-SEM — the variance-based cousin of structural equation modelling. What it is, when it's the right choice, and the full analysis workflow with the thresholds reviewers check.

2 min4 Jul 2026
Guide

SPSS vs R vs Python: Which Should You Learn for Your Research?

Point-and-click ease, statistical depth or full flexibility? A practical comparison of SPSS, R and Python to help you pick the right tool for your thesis.

1 min24 Jun 2026
Guide

Reliability and Validity Explained (With Examples)

If your measures aren't reliable and valid, your results mean nothing. A plain-English guide to both — and how to report them in your thesis.

1 min22 Jun 2026

Frequently asked

How do I choose the right statistical test?+

Three questions decide it: what type of data do you have (categorical/continuous), how many groups or variables are involved, and what are you testing — difference, relationship or prediction? Answer those and the test usually chooses itself.

What matters more — p-value or effect size?+

Both, together. The p-value says whether an effect is likely real; the effect size says whether it is big enough to matter. Journals and examiners increasingly expect effect sizes and confidence intervals alongside significance.

Not sure where to start?

Book a free 15-minute consult. We'll map your next three steps — no obligation.

Ethical, compliant guidance

We provide academic support, mentoring, analysis, editing and structuring — not authorship. Your work stays compliant with university policies.