Overview
We tutor probability and statistics at every stage: school statistics (for example in IB Math AI, A-Level Mathematics or AP Statistics), introductory university courses in business, psychology, health and social sciences, mathematical statistics for math and economics majors, and research methods modules at master's and doctoral level. The sessions look different at each level, but the core aim is the same: to help you understand what a procedure assumes, what it tells you and what it does not.
Probability is taught with concrete models first (tree diagrams, two-way tables, simulations) before formulas, which makes conditional probability and Bayes' theorem far less slippery. Inference is taught through simulation and visualization: we generate many samples, watch the sampling distribution form, and only then connect it to standard errors, confidence intervals and test statistics.
When your course uses software, sessions include hands-on practice in the tool you're assessed in, such as R, SPSS, jamovi, JASP, Excel, Stata or a graphing calculator, so you learn to set up an analysis, read the output and describe it in words. If you need an analysis for your own research project run and reported, our data analysis services are the better fit; tutoring is for building your own skill.
Who it’s for and the problems it solves
This is for you if you are…
- Secondary students taking statistics in IB Math AI or AA, A-Level Mathematics or AP Statistics
- Undergraduates in required statistics courses for psychology, business, nursing, biology or social sciences
- Math, economics and data science students in probability theory or mathematical statistics modules
- Master's and doctoral students who must learn statistics for their own research, often under time pressure
- Professionals preparing for courses or roles that use data analysis
Common problems we help with
- Conditional probability and Bayes' theorem produce answers that feel wrong
- You can compute a test statistic but can't explain what the p-value or confidence interval means
- You don't know which test to use for a given design and variable types
- Assumptions such as normality, independence and equal variances are a checklist you don't understand
- Software output (SPSS tables, R summaries) is overwhelming and you don't know which numbers matter
- Regression interpretation, such as coefficients, R², dummy variables and interactions, is confusing
What’s included — and what isn’t
Included
- Diagnostic session covering probability reasoning, descriptive statistics and your comfort with software
- Probability: sample spaces, conditional probability, independence, Bayes' theorem, expected value and variance
- Distributions: binomial, Poisson, normal, t, chi-square and F, and when each arises
- Sampling distributions, the central limit theorem, standard error and confidence intervals
- Hypothesis testing: null and alternative hypotheses, test statistics, p-values, Type I and II errors, power and effect sizes
- Common tests: t-tests, ANOVA, chi-square tests, correlation and their nonparametric alternatives
- Linear and logistic regression interpretation, including assumptions and diagnostics
- Software walkthroughs in R, SPSS, jamovi, JASP, Excel, Stata or a graphing calculator, matched to your course
- Practice problems with worked solutions and short 'explain in words' exercises
- For researchers: using your own anonymized or example dataset to practice choosing and interpreting analyses
Not included
- Completing graded statistics assignments, online quizzes or take-home exams for submission
- Running and writing up the analysis for your thesis or dissertation as tutoring; that is a separate, disclosed analysis service
- Choosing analyses to reach a desired p-value or advising on selective reporting
What you receive
- Learning plan
- Topics ordered from probability foundations to the inference methods your course or project requires, with target dates.
- Session notes and concept maps
- Plain-language summaries of each concept, including common misinterpretations to avoid (for example what a 95% confidence interval does and doesn't mean).
- Test-selection guide
- A decision chart built with you, linking research questions and variable types to appropriate tests, tailored to what your course covers.
- Annotated software walkthroughs
- Step-by-step notes or scripts for running analyses in your software, with the key output highlighted and explained.
- Practice sets
- Problems with worked solutions, including interpretation questions that ask you to state conclusions in context.
How it works
Share your course or project
Send the syllabus, lecture slides or research plan, the software you use and any upcoming exam or deadline.
Diagnose foundations
We check probability, descriptive statistics and graph reading, because weak foundations are the most common hidden cause of later confusion.
Build intuition, then formulas
Simulation and visuals come first, then notation and calculation, then software, so each layer has meaning.
Practice interpretation
Every session includes writing a conclusion in words, because exams and supervisors assess interpretation as much as calculation.
Review and consolidate
Progress reviews use mixed practice where you choose the method yourself, followed by timed questions before exams.
Teaching approaches and tools
- Simulation-based inference
- Resampling and simulation (for example in R or online applets) to show sampling variability before introducing theoretical distributions.
- Two-way tables and natural frequencies
- Representing conditional probability as counts ('out of 1,000 people…') to make Bayes' theorem intuitive.
- Design-first test selection
- Starting from the research question, number of groups, paired or independent data and variable types, then choosing the test.
- Output reading drills
- Annotating real SPSS, jamovi or R output to identify the test statistic, degrees of freedom, p-value, effect size and confidence interval.
- Reporting practice
- Writing results in the conventions of your field, such as APA style, with effect sizes and intervals rather than p-values alone.
- Calculator fluency
- For school exams, efficient use of the statistics functions on permitted graphing calculators.
The misconceptions we target first
A few misunderstandings cause a large share of lost marks and confused research write-ups. We check for them early and revisit them often.
- Treating a p-value as the probability that the null hypothesis is true
- Reading 'not significant' as 'no effect' without considering power or the confidence interval
- Confusing P(A|B) with P(B|A), the error behind many medical-testing puzzles
- Assuming a correlation or regression coefficient shows causation
- Checking normality of raw data when a test's assumption concerns residuals or sampling distributions
Statistics at school level
School courses combine calculation with interpretation in context. IB Math AI places heavy weight on statistics and on technology use; A-Level Mathematics includes a statistics component built around a pre-released large data set; AP Statistics asks students to communicate conclusions in context in its free-response questions and, according to College Board's current information, is moving to a fully digital exam. We practice exactly the question styles of your course and the calculator or software it allows.
Statistics for your own research
Master's and doctoral students often need to learn methods their undergraduate degree never covered. Tutoring can use a public dataset or your own anonymized data so you learn by doing: screening data, checking assumptions, running the analysis and interpreting it. You remain the analyst and author. If your timeline means you need an analysis carried out and documented instead, we'll say so and point you to the relevant service, with the reminder to acknowledge any assistance according to your institution's rules.
What the work can look like
Illustrative example — fictional data
Sample session plan: hypothesis testing for a psychology student
A fictional second-year psychology student could run independent t-tests in SPSS but couldn't explain the output or choose between tests. This plan is invented to show how a session might be structured.
Warm-up (10 minutes)
Retrieval questions from the last session: what the standard error measures, and why a larger sample narrows a confidence interval.
Core concept (25 minutes)
Simulate two groups drawn from the same population many times to see how often a difference this large appears by chance. Connect that to the p-value, then to the t statistic in the SPSS output.
Application and write-up (25 minutes)
The student chooses between independent, paired and Welch t-tests for three short scenarios, runs one in SPSS and writes a two-sentence APA-style result including Cohen's d and a 95% CI. Practice set: four mixed scenarios with worked solutions.
Illustrative session plan with an invented student. Actual plans follow your course content and pace.
What you’ll need to provide
- Course syllabus or module outline, lecture notes and any assigned textbook
- Past papers, practice tests or feedback on previous work
- Access to the software your course uses (we can help with installation in the first session)
- For researchers: your research questions and a description or anonymized sample of your data
- Exam dates or project deadlines
You don’t need everything ready to ask for a quote — tell us what you have and we’ll say what’s missing.
What affects price and turnaround
Price depends on
- Level: school statistics, introductory university statistics or advanced and mathematical statistics
- Whether software instruction is needed and in which package
- Session length and frequency, including intensive pre-exam scheduling
- Amount of custom practice material or dataset-based exercises between sessions
Turnaround depends on
- How quickly you can share course materials and software details
- Tutor availability for the software or advanced topic you need
- Exam or deadline proximity
Every project is quoted individually. How we price our work.
Questions people ask before starting
Which software can you teach?
Commonly R (including RStudio), SPSS, jamovi, JASP, Excel and Stata, plus graphing calculators for school exams. Tell us what your course or supervisor uses; if a package is less common, we'll confirm tutor availability before starting.
I need to use statistics for my thesis but I've forgotten everything. Where do we start?
We start with a brief diagnostic and your research questions, then build only the foundations you need for your planned analysis, using practice data. This is usually faster than working through a full textbook, and you end up able to explain your own analysis in a viva or defense.
Can you check whether I chose the right test for my assignment?
We can teach the principles of test selection and work through similar scenarios so you can decide yourself. For graded assignments we don't confirm or supply answers; if your course allows feedback on drafts, follow its rules about what help is permitted.
Is probability theory included, or only applied statistics?
Both. We tutor calculus-based probability (random variables, joint distributions, moment generating functions, limit theorems) and mathematical statistics (estimation, likelihood, hypothesis testing theory) for students in math, economics or data science programs.
Do you teach Bayesian statistics?
Yes, at an introductory level: priors, likelihoods and posteriors, Bayesian estimation, and tools such as JASP or R packages when a course or project requires them. Tell us your course so we can match depth.