ChakataStat
Download

Quick Start

From install to your first result in about ten minutes — one linear pass, no choices to make. Every step names the exact menu item. When you finish, the User Guide has the depth, and the tutorial workbook turns this walk into a full course.

1. Install and launch

  • Windows — install ChakataStat from the Microsoft Store and launch it from the Start menu.
  • Ubuntu / Linux — snap install chakatastat, then launch ChakataStat from your applications, or run chakatastat.

You land in the Data View: an empty spreadsheet-style editor (cases will be rows, variables columns), with the menu bar above and the AI assistant panel on the right — ignore that panel for now (Ctrl+Shift+A hides it).

2. Open the sample dataset

File → Open Sample Dataset (Ctrl+Shift+O).

That loads the bundled teaching dataset: a synthetic health study of 600 participants and 21 variables — age, sex, blood pressure, glucose, cholesterol, smoking, and more (the codebook describes every variable). It opens as a new, unsaved document, so nothing you do here can damage the sample.

3. Read the two views

Look at the bottom-left tabs:

  • Data View — the values, one row per participant. Click any cell and notice its whole row and column tint, so you can trace a case across the sheet.
  • Variable View (Ctrl+2) — one row per variable: its name, type, label, value labels (open EducationLevel's — the codes 0–3 mean None/Primary/Secondary/Tertiary), missing values (FastingGlucose_mmolL declares 99 = "Not measured"), and measure (Scale/Ordinal/Nominal).

That metadata is what turns a grid of numbers into a dataset.

4. Run Frequencies on a categorical variable

Analyze → Descriptive Statistics → Frequencies… Move SmokingStatus into the Variables list and click Run.

The app switches to the Output View with a frequency table: each smoking category with its count, percent and cumulative percent.

5. Run Descriptives on scale variables

Analyze → Descriptive Statistics → Descriptives… Move Age, BMI and SystolicBP across, Run.

You get valid N, minimum, maximum, mean and standard deviation for each — your first numeric summary of the study.

6. Compare two groups with a t test

Analyze → Compare Means → Independent-Samples T Test… Test variable SystolicBP; grouping variable Sex; Run.

The output shows each group's mean and the test: t, degrees of freedom and the p value ("Sig."). A small p (below .05, say) means the difference between men's and women's mean systolic pressure is unlikely to be chance.

7. Draw a chart

Graphs → Histogram… (Ctrl+Shift+H), pick BMI, Run. A histogram card appears in the output right under your tables — tick the normal-curve overlay in the dialog if you want a shape reference.

8. Keep your work

  • File → Save (Ctrl+S) saves the dataset as a .ckd document — data and every variable definition together.
  • Right-click any output card to copy it, or File → Export Output… writes the whole log to HTML/Markdown/LaTeX.
  • Switch to the Syntax tab: every step you just took was also recorded as an editable, re-runnable command — select them all and Run to reproduce your session. That command trail is how work in ChakataStat stays reproducible.

Where to go next