BASIC STATISTICS

Chapter 2. Collection of Data

Collection of Data refers to the process of obtaining numerical measurements.

Any statistical investigations must necessarily be based on accurate data. To ensure

the accuracy of data the researcher or investigator must know the right source and methods
of collecting them.
Two Sources of Data
1. Documentary Sources
The information contained in published or unpublished reports, statistics, letters,
magazines, diaries, and so on. These are taken from primary and secondary data.
a. Primary Data - refers to the information gathered directly from an original source
or based on the direct or first-hand experience.
b. Secondary Data - refers to the information which are previously gathered by
previous individual. Data were previously gathered from an original source, which
are computed and compiled.
Advantages of primary data over secondary data
• Primary data frequently give detailed definition of terms and accurate
statistical units in the survey.
• Primary data lend more relevance to the researcher’s study.
• Primary data are more reliable because of their first-hand nature.
2. Field Sources
This includes individuals who have sufficient knowledge and experience regarding
the study under investigation.
Methods of Collecting Data
1. Direct Method – this method is often referred to as interview method.
- This is a face-to-face encounter between the interviewer and the
interviewee.
Advantages:
- It provides consistent and precise information
- Questions may be repeated or modified to suit each interviewee’s level of
understanding
Disadvantages
- Time consuming
- Expensive
- Has limited coverage.
 2. Indirect Method – Popularly known as the questionnaire method
- This method is done by giving prepared relevant questionnaires to the
respondents of the study from which one would like to get the needed
information
Questionnaire – a list of questions, which are intended to elicit answers to the
problems under investigation.
Advantages:
- Questionnaires may be mailed or hand-held.
- It is inexpensive and can cover a wide area in a short period of time
Disadvantages:
- There is a strong probability of no response, especially if questionnaires
are mailed
- Questions not easily understood will also probably not be answered.

3. Registration Method – a method of gathering information or data enforced by the

law.
- It is a method of utilizing the existing data or fact or information, which is
kept systematized by the office concerned such as registrations of birth,
death, motor vehicles, and marriage licenses because these are being
enforced by certain laws.

4. Observation Method - the investigator observes the behavior of the subject and their
outcomes. The subject usually cannot talk or write and it requires a proper
recording of the behavior at the appropriate time and situation.
- This method is used to collect data pertaining attitudes, behaviors, values,
and cultural patterns of the samples under investigation. Subjects may be
taken individually or collectively. It is usually used when the subjects
cannot talk. This can be done directly or indirectly.

5. Experiment Method - it is a method of gathering data when the objective is to

determine the cause and effect relationship of a phenomena under
controlled conditions.
- This is used in making scientific inquiry.
Example: When a researcher wants to determine the different factors affecting the
academic performance of students such as IQ or approaches in teaching, and
others.

Types of Questions
1. Structured Questions
- This is a type of question that leaves only one way or few alternative ways
of answering it.
- The questions asked are clear, simple and objective. Structured questions
are easy to answer and tabulate.
 2. Unstructured or Open-ended Questions
- These are questions that can be answered in many ways – probing
questions or questions that want elicit reasons.

Features of a Good Questionnaire

1. Make questions short and clear.
2. Avoid leading questions.
3. Always state the precise units in which you require them to answer in order to
facilitate tabulation later on.
4. As much as possible, ask questions which can only be answered by just checking
slots or stating simple names or brands.
5. Arrangement of questions should be carefully planned.
6. Limit questions to essential information.

Planning the Study

1. Estimate the number of items in the population.
2. Assess resources such as time and money factors, which are available to pursue the
research.
3. Determine the sample size needed in the study using the Slovin’s formula.
𝑁
𝑛=
1 + 𝑁𝑒 2
Where: n = sample size
N = population size
e = margin of error
4. Pick the sample by using the appropriate sampling technique.
5. Prepare the questions to be asked in the interview or in the questionnaire.

Probability Sampling Techniques

- Popularly known as the simple random sampling technique
- A sampling procedure of selecting a sample size (n) from a universe/population(N)
such that each member of the population is given a non-zero chance of being
included in the sample and all possible combinations of size (n) have an equal
chance of being selected as a sample.
a. Random Sampling
• Lottery Sampling – carried out by assigning numbers to each member of the
population
• Table of Random Numbers – the selection of each member of the population is
left adequately to chance, and every member of the population has an equal
chance of being chosen
- Picking numbers in the calculator or computer.

b. Systematic Sampling – process of selecting the sample when units are obtained by
drawing every nth element of the population.
 𝑁
𝑛𝑡ℎ =
𝑛
Where, N = total number of elements in the population
n = desired sample size

• Stratified Sampling – the population is divided into groups based on

homogeneity to avoid the possibility of drawing samples whose
members came from one stratum.
- The distribution of sampling units is proportional to the total
number of units in each stratum. The bigger the population, the
more sample units are drawn; the lesser the population, the less
sample units.
Steps:
a. Identify the N and its different strata.
b. Divide the members of the population into percent shares.
c. Multiply each percent share by n sample units to get the actual number of
sample units for each stratum.
Example:
Strata Population Distribution % n*(%share) Number
of share of
population Sample
units
High 500 500/10000 0.05 1000*.05 50
income
Middle 2500 2500/10000 0.25 1000*.25 250
Income
Low 7000 7000/10000 0.7 1000*.7 700
Income
N 10000 1000
N(at e = 1000
10%)

• Cluster Sampling – An area sample

- Frequently applied on a geographical basis
- Districts/blocks constitute the cluster
- This is useful in selecting the sample when heterogenous groups
occupy blocks in a community/city
For instance, if a community has a lower, middle and upper income residents
living side by side, we may use this community as a source of a sample to
study the different socio-economic status. By concentrating on this particular
area, we can save time, effort and money.
• Multi-stage Sampling – uses several stages or phrases in getting the samples
from the general population.
 - Useful in conducting a nationwide survey or any survey involving a
large population.

Non-Probability/Non-Random Sapling Techniques

- Not all members are given equal chances to be chosen
- The researcher states his/her prejudice in the choice of the sample
- It finds its greatest use in fields like market research or in employment
department of companies.
• Purposive Sampling – a non-random sampling of choosing samples which is
based on a certain criteria and rules laid down by the researcher.
Ex. A researcher may want to find out the central bank circular, instead of
interviewing the executives of all banks, he purposely can choose to interview the
key executives of only five biggest banks in the country.
• Quota Sampling – the researcher limits the number of his samples based on the
required number of the subject under investigation.
- this is relatively quick and inexpensive method to operate. Each
interviewer is given definite instruction about the section of the
public he is to question, but the final choice of the actual person is
left to his own convenience or preference
Ex. A researcher wants to determine the favorite teams of the PBA. His quota is
say 100 basketball fans. The researcher may reach his quota by going to the
ARANETA coliseum to enjoy watching the game at the same time interview thrilled
viewers during the game.
• Convenience Sampling – The researcher conducts a study at his convenient time,
preferred place or venue. He specifies the place and time where he can gather
his data.