1

DATA AND INFORMATION

GATHERING

2

Definitions

A population consists of all elements – individuals, items, or objects – whose characteristics are being studied. The population that is being studied is also called the target population.

3

Population versus sample

A portion of the population selected for study is referred to as a sample.

4

Figure 1.1 Population and sample.

Population

Sample

5

Population vs sample conti…

A survey that includes every number of the population is called a census. The technique of collecting information from a portion of the population is called a sample survey.

6

Population vs sample conti…

A sample that represents the characteristics of the population as closely as possible is called a representative sample.

7

Population vs sample conti…

A sample drawn in such a way that each element of the population has a chance of being selected is called a random sample

8

Reasons for use of samples

These are easier, faster, cheaper and more convenient than a census.

A good sample is almost as reliable as a census.

They analyse a representative from the population.

9

BASIC TERMS Table 1.1 2001 Sales of Seven Ghana Companies

Company2001 Sales

(millions of dollars)

Wal-Mart StoresIBMGeneral MotorsDell ComputerProcter & GambleJC PenneyHome Depot

217,79985,866

177,26031,16839,26232,00453,553

An element or a

member

An observation or

measurement

Variable

10

BASIC TERMS cont.

Definition An element or member of a sample

or population is a specific subject or object (for example, a person, firm, item, state, or country) about which the information is collected.

11

BASIC TERMS cont.

Definition A variable is a characteristic under

study that assumes different values for different elements. In contrast to a variable, the value of a constant is fixed.

12

BASIC TERMS cont.

Definition The value of a variable for an element

is called an observation or measurement.

13

BASIC TERMS cont.

Definition A data set is a collection of

observations on one or more variables.

14

Classification of data (Nature)

Quantitative Variables or data Discrete Variables Continuous Variables

Qualitative/Categorical Variables or data

15

Quantitative Variables

Definition A variable that can be measured

numerically is called a quantitative variable. The data collected on a quantitative variable are called quantitative data.

16

Quantitative Variables cont.

Definition Discrete variable are variables that

can assume only certain values with no intermediate values.

17

Quantitative Variables cont.

Definition A variable that can assume any

numerical value over a certain interval or intervals is called a continuous variable.

18

Qualitative or Categorical Variables

Definition A variable that cannot assume a

numerical value but can be classified into two or more nonnumeric categories is called a qualitative or categorical variable. The data collected on such a variable are called qualitative data.

19

Figure 1.2 Types of variables.

Variable

Quantitative Qualitative orcategorical (e.g.,

make of a computer,hair color, gender)

Continuous(e.g., length,age, height,weight, time)

Discrete (e.g.,number of

houses, cars,accidents)

20

Types of Qualitative data collection methods

In-depth interview with: individual respondent key informant General respondent

Good for exploratio

n research

21

Types of Qualitative data collection methods

Group interview in the form of: Community meeting Focus group discussion

Participant Observation – Direct extensive observation of an

activity, behaviour or relationship

22

Qualitative interviews

Qualitative interviews can be; Informal conversational Topic focused Semi-structured open ended

questionnaire

Usually guided by a checklist

23

Limitations of qualitative interviews

No quantitative data can be generated in a way that can provide general estimate

Cannot use these methods with probability samples

Findings are susceptible to biases which can arise out of inaccurate judgments of interviewers and interviewees

24

Quantitative methods Most widely used method is structured

survey. Structured Survey entails administering a written questionnaire to a sample of respondents.

Structured survey conducted: At a point in time

OR At regular intervals (useful for tracking

change and for collecting flow data)

25

Advantages of Structured Surveys

Standardized mode of interview & construction of questions implies biases introduced by the enumerator’s style or respondent’s misunderstanding is controlled / minimized

Sample is usually drawn according to sampling theory therefore Sample results can be used to derive estimates for the whole population

Quantitative data may be obtained from secondary sources such as records, publications …..

26

Constraints on options for data collections

Available resources – funding & skills

Time Nature of research (objectives)

27

Classification of data (range)

Several ways of classifying data Nominal Data (Difficult to quantify with

meaningful units, more qualitative) Ordinal Data (measurement is achieved by

ranking e.g. the use of a 1 to 5 rating scale from ‘strongly agree’ to ‘strongly disagree’)

Cardinal Data (Attributes can be measured ie more quantitaive eg weight of potatoes)

28

Classification (Time span)

Cross-Section Data Time-Series Data Panel data

29

Cross-Section Data

Definition Data collected on different elements

for the same variables for the same period of time are called cross-section data.

30

Time-Series Data Definition Data collected on the same element for

the same variables at different points in time or for different periods of time are called time-series data.

31

Panel data

Definition Data collected on different

elements for the same variable at different points in time periods are called panel data.

32

Classification of data (Source) Primary data – it is new data

collected by an organisation or individual for a specific purpose.

Secondary data – is existing data collected by other organisations or for other purposes.

We have to balance the costs and benefits of collecting primary data.

33

Sampling Techniques

Probability Sampling This is where every item has a

calculable chance of selection e.i. random sampling

4

34

Non-probability Sampling This is where someone has some

choice in who or what is selected This would mean that some people

or organisations had a zero chance of selection

4

35

Sampling Techniques

Informal/non-probability Sampling Purposive Snow balling Systematic Stratified Quota Multi-stage Cluster

4

36

SAMPLING ERRORS

Two sources of error Non-Sampling error due to:

Enumeration Data input Measurement inaccuracy Refusal to respond

Sampling error due to: Sample is part of a population and cannot

perfectly represent the population Different samples may produce difference

results

37

SAMPLING ERRORS Sampling error is unavoidable If Sampling is based on probability theory,

the sampling error can be calculated.

- Total Error Sampling error Non sampling error

SD

Std error of sample estimates SEn n

38

SAMPLING ERRORS

Since

SE can be reduced by increasing n Suppose we want to decrease SE by ½

(50%)

SEn

39

SAMPLING ERRORS

This implies sample size should be increased 4x! but the larger the sample, the higher the non-sampling error.

Therefore there is always a trade-off between sampling error and non-sampling error.

1 1 2 2 2 4

Then SEn n n

40

Steps in data collection

1. Define the purpose of the data.

2. Describe the data you need to achieve this purpose.

3. Check available secondary data and see how useful it is.

4. Define the population and sampling frame to give primary data.

5. Choose the best sampling method and sample size.

6. Identify an appropriate sample.

7. Design a questionnaire or other method of data collection.

8. Run a pilot study and check for problems.

9. Train interviewers, observers or experimenters.

10. Do the main data collection.

11. Do follow-up, such as contacting non-respondents.

12. Analyse and present the results.