Module 1 — Opening data & the two Views

Question: what does a dataset look like in ChakataStat, and how does data get in and out?

Open the sample

File → Open Sample Dataset (Ctrl+Shift+O). The status bar reports 600 cases; the title shows an unsaved document — the bundled sample can never be overwritten, so you can experiment freely.

The two Views

The bottom-left tabs switch between two faces of the same dataset:

• Data View (Ctrl+1) — one row per participant, one column per variable. Click a cell: its full row and column tint so you can trace a case; type to edit; Ctrl+F finds values. Hover a column header for the variable's description.
• Variable View (Ctrl+2) — one row per variable, holding everything ChakataStat knows about it: name, type, label, value labels, missing values, measure. Module 2 lives here.

Round trip: export, then import

The sample opened fully dressed — labels and codes all set. To see what raw data looks like, push it out and bring it back:

1. File → Export…, format CSV, save as mystudy.csv.
2. File → Import Data…, choose mystudy.csv, accept the header-row prompt.

Same values — but check Variable View: EducationLevel's value labels and FastingGlucose_mmolL's missing code are gone. A CSV carries values only; the metadata lives in the .ckd document. That is why the last step of any session is File → Save (Ctrl+S) — it keeps data and definitions.

Not every format loses the labels

CSV loses the labels because a CSV has nowhere to put them — not because importing does. File → Import Data… also reads SPSS (.sav, .zsav), Stata (.dta), SAS (.sas7bdat, .xpt), Parquet and Excel, and the statistical formats bring their metadata across with the values:

• SPSS carries the most — variable labels, value labels, measurement level and declared missing values. A .sav opens fully dressed, the way the sample did, and module 2's work is already done for you.
• Stata carries variable labels and value labels.
• SAS carries variable labels, and value labels too when the .sas7bcat catalog sits beside the data file.

A CSV from the same colleague carries none of it. When you get a choice of format, that is the reason to ask for one of these instead. Importing data has the full table of what each format keeps.

Re-open the dressed original with File → Open Sample Dataset before the next module.

Exercise

1. In Data View, find participant P1234 (Ctrl+F). What is their BMI?
2. Export to CSV and re-import. Which columns import as String and which as Numeric? Why did the importer decide that way? (The importer has only the values to go on — no format that carries types would need to guess.)
3. Save your imported copy as mystudy.ckd, close and reopen it. Did it remember anything the CSV did not? (Not yet — you have added no metadata. Module 2 fixes that.)

The syntax trail

Open the Syntax tab: even this module left commands (the export). From here on, every module ends with the commands it generated — the growing, re-runnable record of your session.