Quantitative Analysis That Stands Up to Rigorous Review
StatForge helps MBA, Master's, Doctoral, and academic researchers advance and de-risk their quantitative work with defensible methods, clean data, reproducible analysis, and report-ready tables — so the analysis is clear, traceable, and easier to defend.
Defensible methods
Diagnostics, assumptions, robustness, and clear justification.
Examiner and publication-ready outputs
Clean data, code, tables/figures, and interpretation notes.
Clear execution
Clear scope, fixed deliverables, and transparent timelines.
Ethical support only: we provide analysis, coaching, and reproducible outputs — not writing/ghostwriting.
Supporting candidates from leading institutions: WBS, GIBS, UCT GSB, Stellenbosch, Henley, Milpark, UNISA SBL
We align analyses to your programme requirements and examiner expectations.
What you’ll receive
Concrete deliverables — not vague “analysis done” claims
Methods memo
Detailed, plain-English justification of method choice, key assumptions, risks, and how to address them.
Report-ready tables & figures
APA/Harvard-ready tables and clean visuals with clear labels — structured so you can write the Results section efficiently.
Reproducible code + clean dataset
A clean analysis dataset and reproducible R/Python scripts or notebooks, with outputs aligned to SPSS, AMOS, SmartPLS, or supervisor/journal requirements where relevant.
What clients say
Feedback from researchers who have used our services.
“I really appreciated the guidance [Michael] provided on the steps I needed to take to ensure that I present and communicate my research and results properly. No amount of reading prepared me for the complexity of what I had to do. I appreciated the assistance in showing me how to set everything up for success.”
“At proposal stage, if you are in doubt about quantitative analysis or mixed-methods, Michael is able to guide you to make the right decision. The research methodology you choose will support a high-performance dissertation and may have a meaningful impact on your future career.”
Deborah
Master’s in Organisational Psychology, UNICAF
“I appreciated the detailed and in-depth engagement [from Michael]. [Michael] didn't just run the statistical analysis for me, [he] handled everything with such care that I had complete confidence in the results. What really stood out for me though was how [he] caught a few critical weaknesses in my survey. Not only did [he] flag the issues, but [he] also identified possible solutions that I would've never considered. I would recommend [him] without hesitation to anyone doing high-level postgraduate research.”
Aaron
Master of Business Administration, SBS
Engagement Options
Start with the Risk Review, then scale up to full analysis only if it’s justified.
Research Design & Analysis Risk Review
Fixed-fee, senior review to de-risk your approach before you invest in full analysis.
- 60–90 minute structured call
- Pre-read: proposal + data description (sent beforehand)
- Identify fatal flaws and methodological risks
- Clarify model choice, measurement strategy, and identification issues where relevant
- Written memo: risks, fixes, and next steps
Analysis Execution
Clean, correct results and deliverables you can write up confidently.
- Data quality review (missingness, outliers, coding issues)
- Cleaning + analysis-ready dataset
- Assumptions & diagnostics (fit for purpose)
- Core model(s) aligned to your research questions
- Report-ready tables/figures (APA/Harvard-ready)
- Reproducible R / Python scripts and notebooks, with support for SPSS / AMOS / SmartPLS-style analyses where relevant
- Support for supervisor feedback and targeted revisions
Research Pro (Advanced + Robust)
For complex research where robustness, measurement quality, and deeper back-and-forth are required.
- SEM/CFA (incl. reliability/validity + measurement notes)
- Panel methods / GMM where appropriate
- Robustness aligned to your context (not checkbox stats)
- Walkthrough session + optional recording for revision support
- Extended support for supervisor feedback cycles
Best for: supervisor-driven iterations, complex measurement models, or projects where the methods section needs to withstand detailed challenge.
Extensions & Revisions
When you already have results but need improvements, additional tests, or supervisor-requested changes.
- Model refinement and re-specification
- Additional variables, interactions, or robustness checks
- SEM multi-group / invariance (where relevant)
- Updated tables/figures + clean write-up notes
- Supervisor feedback response support (methods-focused)
Not sure what you need? Book a Risk Review first — it’s the quickest way to get clarity and avoid wasted analysis.
How We Work
A deliberate process designed for robust research outcomes
Scope
You share your thesis. we arrange a brief meeting to discuss your study and thereafter we confirm the right approach and deliverables.
Prepare
Data checks, cleaning, and a clear analysis plan aligned to examiner and peer review expectations.
Analyse + Validate
Models, diagnostics, and robustness — focused on conclusions you can defend.
Handover
Examiner- and publication-ready outputs + support for feedback cycles and targeted revisions.
What good methodological support actually looks like
Brief examples of the methodological judgement, interpretation support, and reproducible code typically provided as part of a StatForge engagement.
All examples below use a synthetic topic and simulated data — not client work. They reflect the format and depth of materials typically produced in a StatForge engagement.
Methodological guidance
Example memo excerpt
The proposed model treats psychological safety as a mediator between transformational leadership and turnover intention. Before estimating the model, three issues should be resolved.
1. Causal language
Because the data is cross-sectional, the analysis can test a theoretical mediation pathway, but it cannot demonstrate a causal mediation effect. The Results chapter should describe paths as associations rather than effects, and the Discussion should foreground this as a primary limitation. This is one of the most common framing errors examiners flag in mediation studies.
2. Measurement quality
Two items on the psychological safety scale load below 0.50 in the CFA. Three options are defensible: remove the items and re-run the CFA; retain them and report the lower loadings as a limitation; or test both versions and report the more conservative model as primary. The third option is the strongest defensibility strategy.
3. Theoretical justification
Statistical mediation is only meaningful if the theoretical ordering is well-grounded: leadership influences safety, which then influences turnover intention. The proposal should briefly address alternative explanations, such as turnover-prone employees perceiving leadership more negatively, before the model is tested.
Report-ready output
Example mediation table
| Path | Description | β | p | 95% CI | Result |
|---|---|---|---|---|---|
| a | Leadership → Psych. Safety | 0.52 | <.001 | [.41, .63] | Supported |
| b | Psych. Safety → Turnover | -0.34 | <.001 | [-.45, -.23] | Supported |
| c′ | Leadership → Turnover | -0.11 | .087 | [-.24, .02] | Not supported |
| a × b | Indirect effect | -0.18 | — | [-.26, -.10] | Supported |
Interpretation note
The pattern shows full mediation: the indirect effect through psychological safety is significant (β = -0.18, 95% CI [-.26, -.10]), while the direct path from leadership to turnover intention is not. Substantively, this suggests that transformational leadership is associated with lower turnover intention primarily by creating environments where employees feel safe, rather than through a direct association of leadership style itself.
Key Insight
Psychological safety appears to be a key mechanism linking leadership to turnover intention.
Anticipated examiner challenge
The cross-sectional design is the primary vulnerability. The assumed ordering — leadership → psychological safety → turnover intention — should be defended theoretically and presented as an associational pathway, not a causal sequence proven by the data.
Reproducible code
# ============================================================
# Mediation analysis:
# Leadership → Psychological Safety → Turnover Intention
# Synthetic cross-sectional survey example
# ============================================================
library(lavaan)
# Define structural model with labelled paths
model <- '
# Direct and indirect paths
psych_safety ~ a * leadership
turnover_int ~ b * psych_safety + c_prime * leadership
# Derived effects
indirect_eff := a * b
total_eff := c_prime + indirect_eff
'
# Fit model with bootstrap standard errors
fit <- sem(
model,
data = analysis_data,
se = "bootstrap",
bootstrap = 5000
)
# Report standardized estimates and confidence intervals
summary(
fit,
standardized = TRUE,
fit.measures = TRUE,
ci = TRUE
)Analyses are documented line by line so outputs can be checked, reproduced, and defended.
Request a Quote
Tell us what you’re working on. We’ll respond with scope, deliverables, timeline, and pricing.
FAQs
Clear answers — no ambiguity
What do you actually deliver?
Clean analysis-ready data, reproducible code, report-ready tables/figures, and plain-English interpretation notes you can confidently defend. We also support revisions when your supervisor or reviewers asks for changes.
Do you write dissertations or do assignments?
No. We provide ethical analysis and coaching support only. You remain responsible for the writing and academic submission.
How fast can you turn work around?
Typical timelines for the initial analysis phase: Analysis Execution is often ~1–2 weeks, and Research Pro is typically 2–4+ weeks depending on complexity and data readiness. Complex projects commonly require multiple feedback cycles with your supervisor/reviewers and can run over several weeks to a few months. Rush work (48-72 hours) is possible for tightly scoped tasks where capacity allows.
Which tools do you use?
We primarily use open-source, script-based tools such as R and Python, with specialist support for methods such as regression, econometrics, CFA, SEM, mediation, moderation, and PLS-SEM. For covariance-based SEM and CFA, we typically use lavaan in R; for PLS-SEM, we use packages such as SEMinR or cSEM. We are familiar with SPSS, AMOS, and SmartPLS-style workflows, and can align the analysis and outputs with your programme requirements where feasible.
Who leads the work?
All work is led by Dr. Michael Pietersen (PhD, University of Pretoria), specialising in quantitative methods and SEM. You can view academic background and publications on Google Scholar.
How does payment work?
Payment terms depend on the scope. Smaller fixed-scope engagements, Risk Reviews, and rush work are generally payable upfront to reserve capacity. For larger analysis projects, we may split payment into a deposit and final balance, with the balance due before release of final deliverables. All pricing and payment terms are confirmed upfront before work begins.
Do you offer editing or language support?
StatForge focuses exclusively on quantitative analysis and methodological support. For thesis editing or language refinement, we recommend the professional editors listed below. View our recommended editors →
Editing & Language Support
StatForge focuses exclusively on quantitative analysis and methodological support. For thesis editing or language refinement, we recommend the professional editors listed below.
OneStopSolution.co.za provide professional editing services for dissertations and theses, and have the resources, experience, and skills to ensure that your document exceeds the required style and language standards for examination.
Email: Wynand@OneStopSolution.co.za
Website: OneStopSolution.co.za