Training module

Jamovi for descriptive statistics and hypothesis testing

Jamovi para sa descriptive statistics at hypothesis testing

Jamovi is a free, point-and-click statistics program. Learn to install it, compute descriptive statistics, and run and interpret a t-test with Grade 11 data.

Time: 60 minutes
For: Grade 11 General Mathematics teachers (Term 2, Week 2; Term 3, Weeks 5–7)
Tools: Jamovi, Spreadsheet

You will be able to

Install Jamovi on a school computer and import a spreadsheet of class data.
Produce descriptive statistics (mean, median, standard deviation) and a histogram or box plot.
Run an independent-samples t-test and explain the p-value in learner-friendly language.

Module

What Jamovi is

Jamovi (jamovi.org) is an open-source statistics program built on R, with a spreadsheet-like interface and menus instead of code. It is free for Windows, macOS, Linux and ChromeOS, and once installed it needs no internet. A cloud version exists for occasional use. It is lighter than SPSS and far easier for learners than MATLAB.

Install and import

Download the current version from jamovi.org/download.html; the installer is about 300 MB, so download once and copy by USB to other computers.
Open Jamovi; the left pane is the data sheet, the right pane shows results.
Import a CSV or Excel file via the menu (☰) → Open → This PC. A class data set of heights, daily allowance or quiz scores works well.
Double-click a column header to set its measure type: Continuous, Ordinal or Nominal.

Descriptive statistics

Explore

Analyses → Exploration → Descriptives. Move the variable to Variables; tick Mean, Median, Mode, Standard deviation, Minimum and Maximum. Under Plots, tick Histogram and Box plot. Results update live; learners can compare two sections by adding a 'Split by' variable.

A t-test walkthrough

Explain

Question: do learners who review with practice sets score higher on the quiz than learners who do not? Data: Score (continuous) and Group (nominal: review / no review). Analyses → T-Tests → Independent Samples T-Test. Move Score to Dependent Variables and Group to Grouping Variable. Tick Descriptives and Effect size.

t = \frac{\bar{x}_1-\bar{x}_2}{\sqrt{\frac{s_1^2}{n_1}+\frac{s_2^2}{n_2}}}

State hypotheses first: H₀: μ₁ = μ₂ (no difference in mean scores); H₁: μ₁ ≠ μ₂.
Read the t statistic, degrees of freedom and p-value from the table.
Decision at α = 0.05: if p < 0.05, reject H₀.
Interpretation stem for learners: 'If there were really no difference, a gap this large would appear in about p×100 % of samples. Because that is (less / more) than 5 %, we (reject / do not reject) the claim of no difference.'

Common misconceptions to address

A small p-value does not mean a large or important difference; show the effect size (Cohen's d) too.
'Not rejecting H₀' is not 'proving H₀'.
Statistical significance depends on sample size; try the same means with n = 5 and n = 50.

Correlation and regression

Extend

Analyses → Regression → Correlation Matrix for r, and Linear Regression for the line of best fit. Pair it with a scatter plot (Exploration → Scatterplot). This covers the Term 3 correlation competencies with the same data set.

Try it

Install Jamovi and import a CSV with at least 30 rows of class data (anonymised; no learner names).
Produce a descriptives table and a box plot split by section, and write two sentences comparing them.
Run the t-test on your data and write a learner-friendly interpretation using the stem above.