Transforming Concepts into Variables, Lecture notes of Research Methodology

Download Transforming Concepts into Variables and more Lecture notes Research Methodology in PDF only on Docsity!

Transforming Concepts into

Transforming Concepts into

Variables

Variables

Operationalization and

Measurement

Issues of Validity and Reliability

Concepts

What is a concept?

• A mental image that summarizes a set of

similar observations, feelings, or ideas.

• All theories, ideas, are based on concepts

Introduction: normal science vs.

Introduction: normal science vs.

social science

social science

On the contrary, social sciences oftenuse concepts that are more abstractand therefore the standardization inmeasurement varies or there is littleagreement (e.g. social class,development, poverty, etc.)

• Thus, our goal is that our measurements

of the different concepts are valid or

match

as much as possible the “real” world

The case of development

The case of development

According to Michael Todaro (1994:18)development is both a physical reality and astate of mind in which society has, throughsome combination of social, economic, andinstitutional processes, secure the means forobtaining a better life, development in allsocieties must have a least the following threeobjectives:

To increase the availability and widen thedistribution of basic life sustaining goods

To rise levels of living

To expand the range of economic and socialchoices

Creating Variables

Creating Variables

• Our goal is to create measurable variables

out of our concepts.

• We first must nominally define our

concepts.

• We are moving from the abstract to the

concrete.

Creating Variables

Creating Variables

• We must be able to observe our variables! • We link our variables to data. • When we link our variables to data, this is

operationalization

. (a word that always

comes up as misspelled in a spell check)

Development and Deadly Conflicts

MID is acronym for Militarized Interstate Dispute

Figure 3: The Effect of Development on a State's Involvement in

a Fatal MID

0.003000.002500.002000.001500.001000.00050 0.

0

2

4

6

Logged Development

Probability of Fatal MID

Measurement

Measurement

If our studies do not allow us to measurevariation in the dependent variable asrelated to variation in our X variables,then we cannot do any scientific testing.

We measure whether certain variables aremeaningful – individually significant.

We measure the variation in our variables.

We also measure the significance andexplanatory power of our models and therelationships between variables.

If it can be quantified, then you should do so.

Some Definitions

Gender

Gender Gender

Variable

Variable Variable

Attribute

Attribute Attribute

Attribute

Attribute Attribute

Female

Female Female

Male

Male Male

What Is Level of Measurement?

The relationship of the values that are The relationship of the values that are

assigned to the attributes assigned to the attributes

for a variable for a variable

1 1

2 2

3 3

Variable VariableAttributes AttributesValues ValuesRelationship Relationship

Republican Republican

Independent Independent

Democrat Democrat

Party Affiliation Party Affiliation

Nominal Measurement

• The values “name” the attribute

uniquely (classification).

• The value does not imply any

ordering of the cases, for example,jersey numbers in football.

• Even though player 32 has higher

number than player 19, you can’t sayfrom the data that he’s greater than ormore than the other.

Nominal continued

Nominal continued

• Nominal

: These variables consist of

categories that are non-ordered. Forexample, race or ethnicity is one variableused to classify people.

• A simple categorical variable is binary or

dichotomous (1/0 or yes/no). For example, dida councilwomen vote for the ordinance changeor not?

• When used as an independent variable, it is

often referred to as a “dummy” variable.

• When used as a dependent variable, the

outcome of some phenomenon is eitherpresent or not.

Ordinal Measurement

When attributes can be rank-ordered…• Distances between attributes do not

have any meaning, for example, codeEducational Attainment as 0=lessthan H.S.; 1=some H.S.; 2=H.S.degree; 3=some college; 4=collegedegree; 5=post college

Is the distance from 0 to 1 the same as

3 to 4?

Types of Variable Constructions

• Interval

: Variables of this type are called

scalar or index variables in the sense theyprovide a scale or index that allows us tomeasure between levels. We can not onlymeasure which is higher or lower, but howmuch so.

• Distance is measured between points on a

scale with even units.

• Good example is temperature based on

Fahrenheit or his evil twin Celsius.