Types of question and types of variable

1
Types of question and types of variable
GAP Toolkit 5
Training in basic drug abuse data
management and analysis

• Training session 4

2
Objectives

• Define a range of classifications for questions
  and variables
• Discuss the use of levels of measurement in
  defining variables in SPSS

3
Types of question

• Closed, open
• Factual and attitudinal

4
Closed questions

• The respondent selects from a list of mutually
  exclusive and collectively exhaustive answers
• The answers are pre-coded

5
Example

• Has the patient been in treatment prior to this
  episode?
• Yes (1)
• No (0)

6
Example

• In the last 30 days, how many times (if any) have
  you had 5 or more drinks in a row?
• None
• 1
• 2
• 3-5
• 6-9
• 10 or more

7
Other Category

• An option on all but the simplest closed
  questions
• Ensures the list of options are exhaustive
• Allows flexibility in response
• Post-coded rather than pre-coded

8
Example

• Type of centre
• Specialized treatment centre
• Therapeutic community
• General hospital
• Psychiatric hospital/unit
• Other (specify) ..

9
Dichotomous questions

• A subset of closed questions
• There are only two possible answers
• The answers are mutually exclusive and
  collectively exhaustive

10
Examples

• 1. Gender
• Male
• Female
• 2. Has the patient been in treatment prior to
  this episode?
• Yes
• No

11
Multiple-response questions

• The question allows more than one response
• The categories are not mutually exclusive
• Frequently, a grouping of dichotomous closed
  questions

12
Example

• Mode of ingestion of primary substance(X all
  that apply)
• Swallow
• Smoke
• Snort
• Inject
• Other (specify) .

13
Likert Scales

• A type of closed question
• Designed to measure attitudes

14
Example

• Do you disapprove of people doing each of the
  following
• Trying marijuana once or twice
• Dont approve
• Disapprove
• Strongly disapprove
• Dont know
• Smoking marijuana occasionally
• (options repeated)

15
Open questions

• There are no constraints on the respondents
  answer
• The answers cannot be predicted before the
  questionnaires are presented
• The answers must be coded after the
  questionnaires are collected

16
Examples

• Q30. Which new drugs or new patterns of use have
  been reported?
• Q13. Indicate primary substance of abuse, that
  is, the most frequently used
• Other (specify) ..

17
Exercise discussion

• Do Open or Closed questions appear more
  frequently in the questionnaires used by your
  specific focal group? Give reasons/possible
  explanations for these choices.

18
Response types

• Factual/attitudinal
• Direct/indirect

19
Types of variable

• Levels of measurement
• Types of variation
• Categorical vs. continuous

20
Levels of measurement

• Nominal
• Ordinal
• Interval
• Ratio

21
Nominal

• The data describe an attribute
• The set of possible values the variable can
  contain are mutually exclusive and collectively
  exhaustive categories
• The categories cannot be objectively measured
  against each other

22
Examples nominal data

• Gender male and female
• Location urban and rural
• Religion Christian, Hindu, Muslim, Jew
• Race white, black, coloured, mixed
• Referral source self, employer, court

23
Ordinal

• The data are broken into categories that can be
  ranked
• It is not possible to quantify the difference
  between the categories

24
Example ordinal

• Level of education
• None
• Primary
• Secondary
• Tertiary

25
Interval

• The data are measured on a continuous scale, not
  simply ranked
• The units of measurement are constant
• There is no absolute 0

26
Example interval

• Temperature
• Fahrenheit or Celsius
• Measured on a continuous scale
• No absolute 0

27
Ratio

• The data are measured on a continuous scale, not
  simply ranked
• The units of measurement are constant
• There is an absolute 0

28
Examples ratio

• Age
• Income
• Temperature on the Kelvin Scale

29
Types of variation

• Nominal equal categories
• Ordinal ordered categories
• Interval and ratio a continuous scale

30
Types of variation

• Qualitative nominal
• Quantitative interval and ratio
• Quantitative and qualitative ordinal

31
Exercise identify the levels of measurement

• Name of treatment centre
• Referral source
• Gender
• Age
• Home language
• Region of permanent residence

• Highest level of education completed
• Employment status
• Current marital status
• How old was the patient when they first began
  using drugs regularly?

32
Level of measurement in SPSS

• Nominal
• Ordinal
• Scale

33
Exercise measure

• Return to Ex1.sav and set the level of
  measurement for the variables ID, DRUG, AGE and
  COND
• Save the file

34
Summary

• Question types
• Closed/Open
• Factual/Attitudinal

• Variable types
• Levels of measurement
• Discrete (categorical)/continuous
• Quantitative/qualitative