Practical Research 2

Descriptive – Survey

A research design using surveys to gather data without making judgments.

Descriptive – Normative Survey

An extension of the descriptive survey that critiques gathered data for improvement.

Descriptive – Status Survey

A design that answers questions about real-life situations, assuming change may occur.

Descriptive - Analysis Survey

Separates an object into parts to identify or discover its nature.

Descriptive – Classification Survey

A design to classify plants and animals based on traits.

Descriptive – Evaluative Survey

Seeks to judge or assess the value of the topic being studied.

Longitudinal Study

An evaluative survey examining changes over time with the same group of subjects.

Cross-sectional Study

An evaluative survey examining different subjects from various grade levels simultaneously.

Descriptive – Comparative Study

Establishes a procedure to compare variables to determine significant differences.

Correlational Study

Describes and measures the degree of association between two or more variables.

Experimental Research Design

Accurately describes facts and characteristics of a population or situation.

True Experimental

Includes manipulation, control, and randomization in research design.

Manipulation

Using an independent variable to cause an effect on a dependent variable.

Control

A group that does not receive treatment in a true experimental design.

Randomization

Every member of the population has an equal chance to be selected.

Post-test only control group design

Involves two randomly assigned groups with no pre-test.

Pre-test post-test control group design

Involves pre-test and post-test for both experimental and control groups.

Solomon four group design

Includes four groups to minimize threats to validity in research.

Quasi Experimental Research Design

Involves independent variable manipulation but lacks one essential characteristic of true experiments.

Nonrandomized control group design

Similar to pre-test post-test control group design but participants are not selected randomly.

Time series design

Ideal for measuring treatment effects over a long duration.

Pre-experimental Research Design

The weakest experimental design with no control over validity.

One shot case study

A design with no randomization or control group, only a post-test after treatment.

One group pre-test - post-test design

A design with a pre-test followed by treatment and a post-test.

Static group comparison study

Compares two groups with only a post-test after treatment.

Population

The entire group that the researcher wishes to study.

Population size

The number of subjects in a population, represented by 'N'.

Sample

A specific group chosen to represent the entire population.

Sample size

The number of subjects included in a study, represented by 'n'.

Sampling technique

The process by which samples are selected.

Subject

An individual participating in a research study, also called a case or respondent.

Probability Sampling

A technique where all population members have equal chances of being selected.

Simple Random Sampling

Subjects are selected randomly through methods like drawing lots.

Systematic Random Sampling

Uses intervals to select subjects from a list.

Stratified Random Sampling

Divides the population into groups to obtain a representative sample.

Cluster Sampling

Divides the population into subgroups and selects clusters for the study.

Convenience Sampling

Participants are chosen based on their availability to the researcher.

Snowball Sampling

Participants are recruited through referrals from other participants.

Purposive Sampling

Participants are selected based on specific criteria set by the researcher.

Quota Sampling

Proportionate representation of subjects based on preferable variables.

Margin of Error

The allowable error margin in research indicating difference from the real population value.

Confidence Interval

Shows actual low and high limits of the estimate at a significance level.

Confidence Level

Indicates how confident the researcher is in the study's results.

Descriptive Research Design

This design aims to accurately describe the facts and characteristics of a given population, situation, or phenomenon.

Questionnaire

A list of planned, written questions related to a particular topic, with space provided for indicating the response to each question, intended for submission for a number of persons for reply.

Tests

These are used to measure the knowledge, intelligence, or aptitude of a respondent. It can also assess feeling or skills. According to Gay (1996), tests are used to “identify, classify, or evaluate test takers”

Validity

refers to the accuracy of an instrument to measure what it intends to measure.

Face Validity

It answers the question, “does the content of the test match the objectives of the study?”

• It is an informal and subjective type of assessment and is the simplest and easiest type of validity.

• The validator just skims the surface of the instrument to form an opinion.

Content Validity

It answers the question, “does the test represent all aspects of the study?”

• It often includes people who are expert in the field or are familiar to the topic being studied.

• For example, an English teacher constructs a summative test for the topic discussed for the week which is parts of speech. If there were parts of speech not included in the instrument or topics included in the test which was not discussed, then the test does not represent the students’ understanding of the topic.

Criterion Validity

It answers the question, “do the results of this instrument similar to the result of a different test?”

• For example, a Filipino teacher constructs a new test to measure student’s literacy skills. To assess the validity of the test, the teacher finds an established test considered to be a valid measurement of students’ literacy skills, let the same group of students take both tests, and if results are very similar, then it means that the new test has a high criterion validity.

Construct Validity

It answers the question, “does the test represent what is intended to measure?”

• For example, if there is a new phenomenon that occurred and there were no existing tests to measure it, the researcher may choose to use a test using current knowledge about the topic to answer identified questions.

Reliability

refers to how accurate and precise an instrument is.

Stability or Test-retest reliability.

• It is considered as the simplest type of reliability.

• The same questionnaire is administered twice.

Interrater

It is where the same test is conducted by different people.

• For example, two (2) doctors are conducting a study to the same set of patients. If after the results of the two doctors are compared and it was found out that there is a high correlation between the two (2), then there is a high interrater reliability.

Parallel forms

• It is the use of one set of questionnaires that are administered to two (2) equivalent sets.

• For example, give test A to a group A on Monday and test B on group B on Monday then correlate the results

Internal Consistency

It refers to a single form of test administered on a single occasion.

• For example, if the statements, “I love research” and “I like conducting research” both received positive results, then it is an indicative of a good internal consistency.

Intervention

is a strategy, a combination of strategies, element, or a combination of elements that are designed to produce changes

Measures of Central Tendency 

It is a way to describe the center of a data set and is also called measures of location, central location, or simply, center. 

Mean

It is defined as the average of a set of numbers. It is considered as the most widely used and simplest measure of central tendency. It is calculated by getting the summation of all observation divided by the number of observations

Median

It is the middle value on a given set of numbers. It is considered as the most appropriate measure of central tendency for ordinal data

Mode

The _____ is the number which appears most often in a set of given numbers.

Measures of Dispersion/Measure of Variability

It is a way of describing how spread out a set of data is. The measures to be considered are the range, average or mean deviation, standard deviation, and the variance. 

Range

To find the _____, we must compute for the difference between the highest and lowest values.

Mean Deviation

It tells how averagely far all values are from the middle.

Standard Deviation

This is used to measure how spread out the numbers are. Its symbol is σ which is the Greek letter sigma. 

Inferential Statistics

This is where data were taken from a sample and makes inferences about the larger population from which the sample was drawn. These are some common statistical measures to measure significant differences and relationships between variables.

T-test

A ____is used to determine if there is a significant difference between the means of two groups, which may be related in certain features (Kenton, 2019). 

Independent t-test

It is used to determine if there is a significant difference between the means of two groups, the means of two interventions, or the means of changed scores.

It is important to note that this can only compare the means for two groups.

Dependent t-test

It compares the means between two related groups on the same variable.

ANOVA

An ______ is used to test multiple groups to see if there is a difference to any of the variable

Spearman Rho

It is used when data gathered are expressed in ranks