`1. What is Data?
Data refers to various types of information formatted for use in scientific and business
applications. It plays a crucial role in decision-making and strategy formulation.
2. Types of Data
• Qualitative Data (Categorical) – Describes characteristics and cannot be
measured numerically.
o Nominal (e.g., colors, gender, smartphone brand) – No specific order.
o Ordinal (e.g., clothing sizes, grades) – Follows a natural order.
• Quantitative Data (Numerical) – Represents measurable quantities.
o Discrete (e.g., number of speakers in a phone, number of students) – Whole
numbers.
o Continuous (e.g., temperature, weight, frequency) – Includes
fractions/decimals.
3. Data Collection
A systematic approach to gathering and analyzing data to find solutions, test hypotheses,
and make predictions.
• Primary Data Collection – First-hand data collected for a specific purpose.
o Qualitative Methods – Focus on opinions and feelings (e.g., open-ended
surveys, interviews).
o Quantitative Methods – Focus on numerical analysis (e.g., structured
surveys, statistical methods).
• Secondary Data Collection – Uses existing data from sources like books,
journals, and online databases.
4. Methods of Data Collection
1. Literature Sources – Books, reports, articles.
2. Surveys – Questionnaires (web-based or paper).
3. Interviews – Structured, semi-structured, or unstructured discussions.
4. Observations – Monitoring behaviors or environments.
5. Documents & Records – Analyzing logs, emails, reports.
6. Experiments – Testing causal relationships between variables.
5. Planning and Conducting Surveys
1. Define the purpose of the survey.
2. Identify the target group.
3. Choose the best distribution method (e.g., email, QR codes).
4. Limit the scope to avoid low response rates.
5. Write clear, valuable questions.
6. Review and refine the survey for accuracy.
6. Bias in Surveys
• Questionnaire Bias – Poor wording affecting responses.
• Sampling Bias – Targeting the wrong audience.
• Interpretation Bias – Misleading or unclear questions.
7. Sampling Methods
• Simple Random Sampling – Equal chance for all individuals.
• Stratified Sampling – Dividing the population into subgroups.
• Cluster Sampling – Grouping people based on proximity.
8. Planning and Conducting Experiments
• An experiment is designed to discover new knowledge and explain why
phenomena occur. For valid results, experiments must maintain internal and
external validity and follow the scientific method, which includes hypothesis
formulation, controlled testing, and statistical analysis.
• Stages of Conducting an Experiment:
1. Defining Sample Groups – After forming a hypothesis, researchers select a
sample group large enough for statistical validity but practical for study.
Random selection is preferred to generalize findings, though some fields (e.g.,
medical trials) may rely on volunteers, limiting randomization.
2. Dividing into Control and Test Groups – The sample is split into a control
group (no treatment) and a test group (receives treatment). Assignments
should be blind or double-blind to minimize bias. Ethical considerations must
be addressed if deviations occur.
3. Determining Time Scale & Sampling Frequency – The duration and
frequency of data collection should align with the study. Short-term studies
(e.g., cold treatment) require frequent sampling, whereas long-term studies
(e.g., Parkinson’s research) span months or years.
4. Conducting the Experiment – The researcher manipulates the
independent variable while measuring its effect on the dependent
variable using predetermined methods.
5. Data Collection & Analysis – Raw data is statistically analyzed to determine
relationships between variables, leading to the acceptance or rejection of the
null hypothesis.
9. Planning and Conducting Experiments; introduction to design experiment
• Observational Studies – No intervention, only observation.
• Experimental Studies – Manipulation of variables to study effects.
