SCIENTIFIC RESEARCH METHODS

HENOK FIKRE (Dr.-Ing.)

May 2024
Unit 4

Process in Conducting Research

 Lesson 1. The Research Process

• Stages in the research process:

Conceptualization – idea on the research process
Identifying a Problem
Literature review
Specifying a purpose

Contextualization – putting your research in the context of others

–(unit 3)

Data collection and analysis – (this unit addresses)

Reporting – writing up of your research and presentation - (unit 6)

 Research methods – Data collection and Analysis

• To collect data, choose the most suitable research method for your
study according to the type of research/approaches used.

Quantitative research – involving numerical and statistical data.

The emphasis is on quantitative observations.

Qualitative research – gathering non-numerical data. The

emphasis is on qualitative results.

Example:
Effect of 1mg/day folic acid to pregnant women on the birth
weight of their babies.– qualitative or quantitative?
 Research methods – Common Types

• Observational studies
• Questionnaires
• Interviews Survey
• Focus groups
• Document analysis
• Mathematical modeling Correlational study
• The experimental method
 Research methods – Common Types

• Observation studies- the process of observing and recording events.

Especially useful for studying human or animal behavior
Two types – participant (observer as participant) and non-
participant
E.g. Study on weight gain of selected sheep breeds which are
exposed to the same environment.
Study on social norms of Awera Amba community.
Morphological processes of lower Awash river channel

Data collection:
no perfect example; varies with the type of problem
often through writing up of notes
may also involve taping or filming
graphs, charts
 Research methods – Common Types

• Questionnaires – a tool where respondents answers to questions.

It could be open or closed/fixed.
It is flexible and can be applied on almost any topic of research.

Data collection:
Questionnaire forms (hard copies), web based questionnaires.

E.g. Why do you apply for graduate program? – closed

1 – to expand my knowledge
2 - to earn a better salary after graduation
3 – to get promotion
4 – no specific reason
 Research methods – Common Types

• Interviews – tools where questions are delivered in a face to face

encounter.
It is limited to cases where the subjects of study are human.
It can be approached in pure quantitative (structured) and pure
qualitative (not structured) angle as of questionnaire.
Mainly interviews are semi-structured

Data collection:
Structured one – ticking/writing on a form
Less structured data – taping and taking notes
 Research methods – Common Types

• Focus groups – a type of interview but targeting only carefully selected

individuals usually who do not know each other.

It is useful in providing qualitative data.

E.g. Study on identification of corrupted politicians.

 Research methods – Common Types

• Document analysis/content analysis – the process of using any kind of

document, films, photographs, books, etc, for analysis for a particular
research interest.

It is an indirect form of research wherein original data is not

generated.

It is a non-reactive method.

Reliability and validity are the central concerns

Typical example: The Da Vinci Code

 Research methods – Common Types

• Mathematical modeling – used to analyze relationships between

different variables and to predict possible outcomes, or causal effects.
• Can be developed analytically or through conducting experiment.

E.g.
Development of a modified universal Soil Loss Equation for
Andit Tsed woreda, North Shewa, Ethiopia.

Development of Intensity-Duration-frequency curves for

Southern Ethiopia.
 Research methods – Common Types

• The experimental method – involves setting up an experiment in order

to test a particular theory or hypothesis.

laboratory experiments – small scale study and subjects are

studied in a controlled environment.

E.g. bio-technology, chemistry, medical studies

field experiments – research conducted outside the laboratory

and researcher control of the env’t is reduced.

E.g. agricultural studies, hydrological studies

 Analyzing and Interpreting Quantitative Data

Steps in quantitative analysis and interpretation:

data preparation

Data analysis

Reporting the results

Discussion of the results

 Analyzing and Interpreting Quantitative Data

Preparing the data for analysis:

Arrange the data according to your need
If need be, score data first by assigning numeric code
Create data file in data grid
Clean database, missing values

• Then, Select a statistical program as a tool for analysis:

Statistical Package for Social Sciences -SPSS is most popular
Other programs: Mini-tab, Statview, SAS
Use mainframe, PC or other platforms
 Analyzing and Interpreting Quantitative Data

How do you analyze the data?

If statistics is involved, either conduct descriptive analysis:

Measures of central tendency
Measures of relative standing
Descriptive Statistics

Central Tendency Variability Relative standing

Mean Variance Z-Score

Median Standard Deviation Percentile Ranks
Mode Range
 Analyzing and Interpreting Quantitative Data

Or, Conduct inferential analysis:

Hypothesis testing
Confidence interval

Identify a null and alternative hypothesis

Set the level of significance (alpha level) for rejecting the null
hypothesis

Compute the sample statistic

Make a decision about rejecting/failing to reject

 Analyzing and Interpreting Quantitative Data

Parametric inferential analysis:

Correlation coefficient and regression coefficient

T-test, analysis of variance, analysis of covariance

Chi-square analysis, etc.

Analyzing and Interpreting Qualitative Data

Codes the Text for Codes the Text for

Description to be Used Themes to be Used
in the Research Report in the Research Report

The Researcher Codes the Data (i.e., locates text

segments and assigns a code to label them)

The Researcher Reads Through Data

( i.e., obtains general sense of material)

The Researcher Prepares Data for analysis

( e.g., transcribes field notes)

The Researcher Collects Data (i.e., a text file, such as

fieldnotes, transcriptions, optically scanned material)
 The coding process for qualitative data

Divide text Reduce

Initially read
into segments Overlap and
through data
of information redundancy
of codes

Many Many Codes

Pages Segments 30-40 reduced
codes Reduce Codes to
of Text of Text to 20 5-7 Themes
Interpreting Qualitative Data

Interpretation is not neutral

Reflect about the personal meaning of the data

Compare and contrast personal viewpoints with the literature

Address limitations of the study

Make suggestions for future research

 Summary of a research process

Steps in the Research Process Two Approaches Research Designs

Quantitative
Identifying a Problem
Qualitative

Reviewing the Literature Quantitative

Qualitative •Experimental

Specifying a Purpose Quantitative •Correlational

Qualitative •Survey

Collecting Data Quantitative

Qualitative
•Mixed

Analyze and Interpret Data Quantitative

Qualitative

Report and Evaluate Quantitative

•Narrative
Qualitative
 Sampling Terms and Procedures

• Population - inclusive group defined by researcher

• Sample - representative subset of population
should contain essential elements of population
Samples are only estimates
The difference between the sample estimate and the true population is the
“sampling error.”

Population Population
• All teachers in high schools in one city • All high school biology teachers
• College students in all community colleges • Students in one community college
 Sampling Terms and Procedures

Precision: the range within which the population average (or other
parameter) will lie in accordance with the reliability specified in the
confidence level as a percentage of the estimate ± or as a numerical quantity.

Confidence level and significance level: The confidence level or

reliability is the expected percentage of times that the actual value will fall
within the stated precision limits.
 Sampling Terms and Procedures

Quantitative Sampling Strategies

Probability Sampling Non-Probability Sampling

Simple Stratified Systematic Convenience Snowball

Random Sampling Sampling Sampling Sampling
 Sampling Terms and Procedures

Types of Sampling:
1. Probability Sampling - the selection of individuals from the population
so that they are representative of the population

Random Sampling-process of sampling which assures that any

subject in the population has an equal probability of being in the
sample
Systematic counting-uses list to choose every nth person from the
population
Stratified Random-used when researcher believes the population
has distinct subgroups.
E.g. if population has 45% men, then we make sure sample is
45% men
 Sampling Terms and Procedures

2. Non-Probability Sampling - the selection of participants because they

are available, convenient, or represent some characteristic the
investigator wants to study.

Convenience Sampling - participants are selected because they are

willing and available to be studied
Snowball Sampling - the researcher asks participants to identify
other participants to become members of the sample.
Thank you