CHAPTER 5: UNDERSTANDING and SYSTEMATIZING DATA

Lesson 1: QUANTITATIVE RESEARCH DESIGNS

QUANTITATIVE RESEARCH involves the collection of data to establish the relationship between and among variables using
statistical analysis.
It aims to establish or validate relationships and to develop generalizations from the relationships.
QUANTITATIVE RESEARCH DESIGNS
1. DESCRIPTIVE RESEARCH uses questionnaires and interviews to gather data about a group of people.
Example: A study on the attitude of parent/s toward the “No Homework Policy” for grades 1 and 2 pupils.
2. CORRELATIONAL RESEARCH looks into the degree of association between variables.
Example: A study on how the absences of a grade 11 student may affect his/her performance in Statistics.
3. EXPERIMENTAL RESEARCH a group of respondents are randomly selected to undergo a particular researcher-
imposed treatment.
Example: A group of students may be subjected to learning using technology, while the regular class uses the
ordinary way of learning.
4. HISTORICAL RESEARCH makes use of historical data to predict the behavior of a variable.
Historical research is a process of collecting and interpreting data about past events or ideas in order to find how
they affected the present events and ideas. It studies possible reasons behind certain events to explain their
influence on the events that followed.
Example: A study on the sales of a particular type of milk tea over a six-month period to predict the probable
amount of sales in the next period.
5. CAUSAL RESEARCH looks into the cause-and-effect relationship between variables.
Example: As price increases, the demand decreases

Methods of Collecting Data

1. INTERVIEW METHOD data is obtained through oral exchange of questions and answers by the researcher and the
respondents.
2. QUESTIONNAIRE METHOD data is provided by the respondents in a set of questions provided by the researcher.
Questionnaire is usually resorted to if the study needs a large sample size, or a cross-sectional analysis is needed.
3. DOCUMENT METHOD where data previously gathered and stored may be availed by the researcher.
A researcher may be interested to use existing information found in records. These may be HISTORICAL DATA or
data that were stored by other individuals or institutions.
4. OBSERVATION METHOD where data is acquired on an actual situation and recorded through the direct observation
by the researcher. To look into a particular behavioral aspect, a researcher may use this method.
5. EXPERIMENT METHOD where data is gathered by the researcher through the experimentation process. It is used
when the cause/s of the phenomenon being studied is being scrutinized.

Lesson 2: LOCUS IDENTIFICATION

DATA is a body of information or observations that is provided to a researcher. It is a response or reaction given to a
particular situation.
CLASSIFICATION OF DATA
1. PRIMARY DATA refers to first-hand information gathered by the person who needs them.
2. SECONDARY DATA refers to second-hand information. They are taken from observations of others or responses to
queries in researches done earlier.
DATA MEASUREMENT
Data in quantitative researches should be measurable. Measurement is not limited to the use of rulers or other similar
instruments. It may take the form of scales used to measure a behavior, an instrument that assesses the awareness of
people toward a particular product.
DATA MEASUREMENT SCALES
1. NOMINAL SCALE is one where specific values are assigned to a particular group. The values assigned have no
significant value, and is used just for labelling purposes.
To illustrate, if the students in grade 11 of a particular school are to be used as respondents, the students may be
divided into two groups: male and female. The male group may be assigned the number 1, and the female group
the number 2.
Another example would be – if respondents are grouped according to employment status, the number 1 may be
assigned to students, 2 for employees, 3 for employer, and 4 for retirees.
The numbers assigned have no bearing to the discussion, and are assigned simply to separate one from another.
Nominal scale is the lowest level of data measurement.
2. ORDINAL SCALE the numbers obtained provide the rank or order of the values.
If birth order is the characteristic under study, we may assign a value of 1 to first-born, 2 to middle-child, and 3 to
youngest child. From the numbers assigned, the order is clear.
3. INTERVAL SCALE is a scale where intervals are consistent but it does not have a true zero point.
If a scale of 1 to 8 is used, with 1 as the least frequent and 8 as the most frequent, we can notice that the interval is
consistently 1. However, we notice that the number 0 is not used to mean absence of frequency. Most survey
instruments use interval scale, with some researchers preferring a scale of 1 to 10 to allow flexibility of responses.
 4. RATIO SCALE is similar to the interval scale, except for the presence of an absolute zero point which means absence
of whatever is being measured. It expresses values in terms of multiples or fractional parts. This, together with the
interval scale, belongs to the highest level of data measurement.

LOCUS OF THE RESEARCH is the place where data is to be gathered.

RESPONDENTS the people who are the subject of the study.

Lesson 3: SAMPLES and SAMPLE SIZE

POPULATION is the totality of individuals or objects that are the focus of the study.
TARGET POPULATION is the population used by the researcher in generalizing the conclusion of the study.
SAMPLING FRAME lists all individuals or objects included in the target population.
Drawn from the sampling frame, SAMPLE is a subset of the population chosen to participate in a study. Those chosen are
known as the subjects or RESPONDENTS of the study.
SAMPLE SIZE is the number of elements in the sample set.
RESPONSE RATE is determined by dividing the number of usable responses by the total number of questionnaires fielded.

Lesson 4: SAMPLING TECHNIQUES

CENSUS is the systematic recording of information of each member of a population.
SAMPLING TECHNIQUE is the process of selecting samples from a target population.
PROBABILITY SAMPLING is the method of drawing samples where every member of the target population has an equal
chance of being selected.
NONPROBABILITY SAMPLING does not ensure that every member of the target population is given an equal chance of
being selected.
This is not a scientific way of selecting respondents. Neither does it offer a valid or an objective way of detecting sampling
errors. The subjects are chosen based on their availability or the purpose of the study, and in some cases, on the sole
discretion of the researcher.

DIFFERENT PROBABILITY SAMPLING TECHNIQUES

1. SIMPLE RANDOM SAMPLING It is the best type of probability sampling through which you can choose sample from
a population.
Using a pure-chance selection, you assure every member the same opportunity to be in the sample.
>Have a list of all members of the population; write each name on a card, and choose cards through a pure-chance
selection.
2. SYSTEMATIC SAMPLING is an improvement of the random sampling process where a pre-selection system is in
place to complement the randomness of the selection process.
For this kind of probability sampling, chance and system are the ones to determine who should compose the
sample.
For instance, if you want to have a sample of 150, you may select a set of numbers like 1 to 15, and out of a list of
1,500 students, take every 15th name on the list until you complete the total number of respondents to constitute
your sample.
3. STRATIFIED SAMPLING the target population is first divided into strata according to certain predefined
characteristics.
4. CLUSTER SAMPLING TECHNIQUE is used when the population is dispersed over a wide geographic region.
For example, if you want to have a sample of 120 out of 1,000 students, you can randomly select three sections
with 40 students each to constitute the sample.

TYPES OF NON-PROBABILITY SAMPLING

1. QUOTA SAMPLING. You resort to quota sampling when you think you know the characteristics of the target
population very well. In this case, you tend to choose sample members possessing or indicating the characteristics
of the target population.
Using a quota or a specific set of persons whom you believe to have the characteristics of the target population
involved in the study is your way of showing that the sample you have chosen closely represents the target
population as regards such characteristics.
2. VOLUNTARY SAMPLING occurs when researchers seek volunteers to participate in studies. Volunteers can be
solicited in person, over the internet, via public postings, and a variety of other methods.
3. PURPOSIVE or JUDGMENTAL SAMPLING. You choose people whom you are sure could correspond to the
objectives of your study, like selecting those with rich experience or interest in your study.
This strategy is used in situations where a researcher believes some respondents may be more knowledgeable than
others, and requires an expert to use their judgment in selecting cases with that purpose in mind.
4. AVAILABILITY SAMPLING is used quite frequently. It involves selecting a sample from the population because it is
accessible. That is to say, individuals are selected for the research not because they meet some statistical criterion,
but because they are readily available.
If during the data-collection time, you encounter people walking on a school campus, along corridors, and along the
park or employees lining up at an office, and these people show willingness to respond to your questions, then you
automatically consider them as your respondents.
 CONVENIENCE SAMPLING is a non-probability sampling method where units are selected for inclusion in the
sample because they are the easiest for the researcher to access. This can be due to geographical proximity,
availability at a given time, or willingness to participate in the research.
5. SNOWBALL SAMPLING or CHAIN-REFERRAL SAMPLING is defined as a non-probability sampling technique in which
the samples have rare traits. This is a sampling technique, in which existing subjects provide referrals to recruit
samples required for a research study.
Free to obtain data from any group just like snow freely expanding and accumulating at a certain place, you tend to
increase the number of people you want to form the sample of your study. (Harding 2013)

SAMPLING BIAS
Getting responses only from those who are interested or those who are available is one of the causes of sampling bias.
Overrepresentation or underrepresentation can also result to sampling bias.
SAMPLING ERROR results when there is sampling bias or samples taken are not representative of the target population.
Normally, the problem may be corrected by increasing the sample size.
NONSAMPLING ERROR is usually caused by problems in data collection or processing.
A typical non-sampling error occurs when the response rate is low, thereby leading to sampling bias.
Another error could be error in the instrument used in data collection.
Mistakes in data encoding may also lead to error when the data are processed.
Response rate may be increased by making follow-up after questionnaires are sent.

Lesson 5: RESEARCH TECHNIQUES OR INSTRUMENTS

An INSTRUMENT is a measuring device. It may be used to gather data of the study.

Interview as a Tool to Gather Data

INTERVIEW SCHEDULE contains a set of questions that the interviewer will ask the interviewees.

Questionnaire as a tool to Gather Data

TWO BASIC TYPES OF QUESTIONS
1. OPEN-ENDED QUESTIONS are used when there are many possible responses to a particular problem. Respondents
may answer freely and provide a detailed responses to a query.
2. CLOSED-ENDED QUESTIONS have limited responses which are pre-determined.
TYPES OF CLOSED-ENDED QUESTIONS
1. DICHOTOMOUS QUESTIONS require respondents to answer two-point questions such as “yes” or “no,” “satisfied”
or “unsatisfied.”
2. MULTIPLE CHOICE QUESTIONS require respondents to choose one among the different choices enumerated.
3. RANK ORDER QUESTIONS require respondents to indicate their order of preference from a list of options.
4. RATING SCALE require the respondents to rate their agreement or disagreement with a particular statement.
5. SEMANTIC DIFFERENTIAL SCALE requires respondents to check their responses between two extreme values at the
opposite ends of the scale.
6. STAPLE SCALE is a unipolar rating scale without a neutral or zero point.
7. CONSTANT SUM QUESTIONS require respondents to enter numeric data expressing the importance allocated by
the respondent to the said option.

Validity of Questionnaire
VALIDITY of an instrument is the extent to which an instrument measures what it is intended to measure.
TABLE OF SPECIFICATIONS serves as a guide on the completeness of the questionnaire relative to the listed behavior.
FORMS OF VALIDITY
1. CONTENT VALIDITY An instrument that adequately contains the characteristics being measured.
Experts in the particular content area are requested to review the questionnaire to establish content validity.
2. CRITERION VALIDITY useful in predicting a person’s behavior in a specified situation. Experts will have to check on
the criteria used in measuring characteristics being studied.
3. CONSTRUCT VALIDITY used to measure characteristics which are not directly observable or measurable.

Reliability of Questionnaire
RELIABILITY of an instrument measures the degree of consistency with which the instrument measures what it is intended
to measure.
FORMS OF RELIABILITY
1. TEST-RETEST RELIABILITY is the extent to which a questionnaire is administered to the same group of people on
two different occasions and yield the same results.
2. EQUIVALENT FORMS RELIABILITY is the extent to which two different questionnaires administered to the same
group of people yield similar results.
3. INTERNAL CONSISTENCY RELIABILITY is the extent to which all items within a questionnaire yield similar results.
Data Collection
DATA GATHERING OR COLLECTION is a process of collecting information.
VARIABLES are the characteristics of interest of the study.

STATISTICAL TREATMENT OF DATA

It is important to use the appropriate STATISTICAL TOOL in answering the objective of the study. The researcher can use
correlation, covariance, t-test, chi-test, z-test, analysis of variance (ANOVA), or regression in the study.

STATISTICAL TOOL PURPOSE

Correlation To show the degree of relationship between two variables
Covariance To show the relationship between two variables
T-test To examine if there is a significant difference between two variables or to your
hypothesis (less than 30 observations)
Chi-test To examine if there is a significant difference between the expected frequencies and the
observed frequencies of one or more categories
Z-test To examine if there is a significant difference between two variables or to your
hypothesis (more than 30 observations)
ANOVA To examine if there is a significant difference of the means of three or more variables or
categories
Regression To examine the relationship of the independent variable to the dependent variable

ORGANIZATION OF DATA refers to the process of classifying data collected for ease of presentation.