How the smoking-behaviour dataset is structured

In Copy of Smoking Data 2(1), the workbook is organised into three relevant sheets: Rawdata, ListVariables, and Source. Reading these together helps you understand both the data values and the variable dictionary.

1. The three worksheet tabs

• Rawdata: contains the actual case-by-case dataset.
• ListVariables: gives a compact variable dictionary, including measurement scales and coded labels.
• Source: gives fuller source-style documentation, including value ranges and coded meanings.

2. What is on the Rawdata sheet?

According to Copy of Smoking Data 2(1), the first row of Rawdata lists the variables:

• Age
• Alcohol
• AgeOnset
• Gender
• Smoking

The second row adds labels for some variables, such as Alcohol consumption, Age of Onset of smoking, and Smoking behaviour. The rows below are individual observations. For example, row 3 shows one record with values for Age, Alcohol, AgeOnset, Gender, and Smoking.

This means Rawdata is the sheet you use to see the actual participant data.

3. What is on the ListVariables sheet?

In Copy of Smoking Data 2(1), the ListVariables sheet works like a short codebook. It shows:

• the variable names,
• the question or label for some variables,
• the measurement scale,
• and the coded values and labels.

For the measurement scales, row 4 shows:

• Age = Scale
• Alcohol = Nominal
• AgeOnset = Nominal
• Gender = Nominal
• Smoking = Scale

4. What is on the Source sheet?

The Source sheet in Copy of Smoking Data 2(1) provides more detailed documentation. It lists each variable with its content, value labels, and in some cases numeric ranges.

For example, it shows:

• Age as a quantity with range 16 to 68.83.
• Alcohol with coded values 0 and 2.
• AgeOnset with coded values 1 and 2.
• Gender with coded values 1 and 2.
• Smoking as a quantity with range 1.7729 to 9.9717.

5. The variables and how they are coded

Age

From Copy of Smoking Data 2(1), Age is measured on a scale. The Source sheet describes it as a quantity, with values ranging from 16 to 68.83.

• Variable name: Age
• Measurement scale: Scale
• Range: 16 to 68.83

Alcohol

Alcohol is listed as nominal in the ListVariables sheet. Its label is Alcohol consumption. The coded values shown in Copy of Smoking Data 2(1) are:

• 0 = None to low levels
• 2 = Moderate to High levels

• Variable name: Alcohol
• Label: Alcohol consumption
• Measurement scale: Nominal

AgeOnset

AgeOnset is also nominal in the ListVariables sheet, with the label Age of Onset of smoking. The coded values are:

• 1 = 0 to 30 yrs age
• 2 = 31 and older

• Variable name: AgeOnset
• Label: Age of Onset of smoking
• Measurement scale: Nominal

Gender

Gender is marked as nominal in Copy of Smoking Data 2(1). Its coded values are:

• 1 = Male
• 2 = Female

• Variable name: Gender
• Measurement scale: Nominal

Smoking

Smoking is measured on a scale. Its label is Smoking behaviour. The Source sheet describes it as a quantity with values ranging from 1.7729 to 9.9717.

• Variable name: Smoking
• Label: Smoking behaviour
• Measurement scale: Scale
• Range: 1.7729 to 9.9717

6. Quick summary

Using Copy of Smoking Data 2(1), you can read the workbook structure like this:

• Rawdata = the actual participant records.
• ListVariables = the short variable dictionary with scales and value labels.
• Source = the fuller documentation with ranges and coded meanings.

The key variables for this lesson are:

• Age: Scale
• Alcohol: Nominal; 0 = None to low levels, 2 = Moderate to High levels
• AgeOnset: Nominal; 1 = 0 to 30 yrs age, 2 = 31 and older
• Gender: Nominal; 1 = Male, 2 = Female
• Smoking: Scale