Understanding Data Types and Collection Methods

Data are individual facts, observations, statistics, characteristics, symbols, images, numbers.
Data out of context have no meaning and are difficult to understand.
Raw data are frequently referred to as data.
Research data can be classified as quantitative or qualitative.

Data collection is a crucial part of any research.
The conclusion of a study is dependant on the data.
Observation, Questionnaire, Interview, Surveys, and Experimental devices are essential methods.

Observational research, also known as field research, directly observes phenomena in their natural settings.
Types of observation include non-controlled, participant observation, non-controlled, non-participant observation, and systematic, controlled observation.
In participant observation, the observer actively becomes a member of the group under study.
A disadvantage of participant observation is that the researcher may lose objectivity.
Non-participant observation involves observation from a distance without participating in the group activities.
Controlled observation involves pre-determining and controlling variables, location, time, participants, and tools used for the study.

A questionnaire is a series of written questions that researchers present to subjects.
Questionnaires are a tool for gathering information.
Questionnaires have structured (closed) and unstructured (open) types.

An interview is more than just a conversation, it is a conservation with a purpose.
There are many types of interviews, including non-directive, directive, repeated, focused, and depth interviews.
A non-directive interview is unstructured.
A directive interview has a specific set of predetermined questions that are followed by the interviewer.
A repeated interview focuses on changes in a phenomenon over a period of time.
A focused interview is limited by relevant theory and evidence.
A depth interview involves conducting intensive interviews with participants to explore particular perspectives on an idea or program.

A survey is a research method where subjects respond to questions in a questionnaire or interview.
Surveys are used to collect data from entire populations, or sample populations.
Random sampling is usually used to collect sample data representative of an entire population.

Information is a set of processed data.
Information is structured or presented for a specific given requirement.
Information becomes meaningful and useful based on its context.
Data processing follows a cycle of collection, preparation, input, processing, output, and storage.

Raw data are not useful in their original form.
Data processing translates raw data into usable information.
Data processing involves data collection, validation, sorting, input, processing (analysis), and storage.
Computer processing, including data output/interpretation, is usually used for large amounts of data.

Batch processing collects and processes data in batches.
Real-time processing processes data within seconds.
Online processing automatically transmits data to the central processing unit immediately upon availability.
Time-sharing computer resources to accommodate many users simultaneously, allocating limited resources to individual users.

Statistical analysis is a scientific tool that helps identify patterns and trends in large datasets.
Statistical analysis converts data into meaningful information.
Statistical analysis and software include: Descriptive statistics (distribution, measures of central tendency, measures of variability), measures of central tendency (mean, median, mode), and measures of variability (range, standard deviation, variance, interquartile range).
Inferential statistics (hypothesis testing, regression analysis).
Associative or relative statistics identify meaningful interrelationships between data.
Major statistical data analysis software includes SPSS, Microsoft Excel, Matlab, OriginPro, Minitab, and GraphPad Prism.

A database is a structured collection of organized information accessible, manageable and updatable digitally.
Database types include: relational, document-oriented, graph, hypertext, operational, distributed and flat file.
Relational databases are comprised of tables with rows and columns.
Rows (tuples) store data, and columns (attributes) categorize data.
A primary key uniquely identifies rows.
A foreign key in one table points to the primary key in another.
Document-oriented databases store data in JSON-like documents.
Graph databases use graph structures, nodes, edges, and properties.
Hypertext databases link objects such as text, pictures, music, programs.

Knowledge combines information, experience, and insight, enabling understanding for individuals or organizations.
Information provides answers to questions of who, what, where, when, and how.
Knowledge provides answers to questions of why and how.

Three main types for acquiring knowledge include unscientific sources, scientific sources, and divine books.
Unscientific sources include empiricism, trial and error, tradition (local knowledge), tenacity, rationalism, and authority.
Scientific sources include empirical evidence to understand the natural world.
Scientific knowledge is durable, strong, and open to change.

Research is an investigation process to identify solutions and new knowledge and information.
The word "Research" is formed from "RE" (again, new, or over again) and "SEARCH" (examine, closely, and carefully, test, or probe).

Research is classified based on application, objectives and enquiry mode.
By application, research categories are Pure research (basic) and Applied research.
By objectives, research categories are Exploratory, Descriptive, Correlational and Explanatory.
By enquiry mode, research categories are Qualitative and Quantitative research.