CS701 Research Methodology in Computer Science: Lesson 3: Tools of Research

CS701 Research Methodology in Computer Science
Lesson 3: Tools of Research
Tools of Research
Six general tools of research
The library and its resources The computer and its software Techniques of measurement Statistics The human mind Languages
Measurement as a Tool of Research

Measurement is limiting the data of any phenomenon substantial or insubstantialso that those data may be interpreted and, ultimately, compared to an acceptable qualitative or quantitative standard. (Leedy & Ormrod, 2004)

Substantial measurements: things being measured have an obvious basis in the physical world. Insubstantial measurements: things existing only as concepts, ideas, opinions, feeling, or other intangible entities.
Measuring insubstantial phenomena: An Example

To measuring the interpersonal dynamics of the group
A group of nine people work together in the personnel department of a large corporation. They attend a recognition dinner at an exclusive hotel. The interpersonal dynamics within the group
Who greets whom with enthusiasm or with indifference? Who joins in conversation with whom? Who seems to be a relative outsider
Measuring insubstantial phenomena: An Example

If there were personal magnetic fields among the guests, we might easily detect the presence of personal attraction, indifference, or rejection among various individuals within the group. No such objective sensors of interpersonal relationship exists. Sociogram of interpersonal dynamics, sociometric matrix
Four scales of measurement

Any form of measurements falling into one of four categories, or scales
Nominal scale of measurement Ordinal scale of measurement Interval scale of measurement Ratio scale of measurement

Nominal scale of measurement
Assigning names to data Divide data into discrete categories Names can be numbers, but they have no quantitative meaning. Statistic analysis
Mode, percentage Chi-square test

Ordinal scale of measurement
Rank-order data Comparing data in terms of one being greater or higher than another
Ex: Ranking the important factors (class size, instructors, lab, homework, etc.) that affect to learning programming
Statistical techniques
Median Spearmans rank order correlation

Interval scale of measurement
Two characteristics
Equal units of measurement Zero point established arbitrarily
Example
Rating the availability of your professor
Statistical analysis
Means Standard deviation Pearson product moment correlations Etc.

Ratio scale of measurement
Two characteristics
Equal measurement units An absolute zero point (can be expressed in terms of multiples and fractional parts)
Example
Absolutely unavailable
Statistic analysis
All

You can say that
One object is different from another,
You have a nominal scale
One object is bigger or more of anything than another,

You have an ordinal scale
One object is so many units (degrees, inches) more than another,

You have an interval scale
One object is so many times as big or tall or heavy as another,

You have a ratio scale

Validity and Reliability of Measurement
Validity of a measurement instrument
The extent to which the instrument measures what it is supposed to measure
Thinking of a personality test Does it really measure the personality trait?
Reliability
The consistency with which a measuring instrument yields a certain result when the entity being measured hasnt changed.
Scale for measuring professor availability 1st : 70 yesterday, 2nd : 90 today
Reliability is a necessary but inefficient condition for validity.

Validity and reliability reflect the degree to which we may have error in our measurements. They are essential particularly in measuring insubstantial phenomena (measuring characteristics).
Statistics as a Tool of Research

Statistics are powerful tools. Whenever we use statistics,
Remember that the statistical values are not the end of a research endeavor nor the final answer to a research problem. Statistics give use information about the data The final question in research is:
What do the data indicate? A conscientious researcher is not satisfied until the meaning of the information is revealed.
The Lure of Statistics

The entire body of data collected,
Not any single statistic calculated, is what ultimately must be used to resolve the research problem. Not only calculation of a few numbers can interpret the data
The task the researcher ultimately faces:

To discover the meaning of the data and its relevance to the research problem.
Primary Functions of Statistics

Statistics have two principal functions to help the research:
Describe the data Draw inference from the data
Both of these functions ultimately involve summarizing the data in some way.
Statistics help the human mind comprehend disparate data as an organized whole.
The Human Mind as a Tool of Research

Statistics cannot interpret those data and arrive at a logical conclusion as to their meaning. Only the mind of the researcher can do that.

Deductive logic
Begin with one or more premises. If they are accepted truths, reasoning then proceeds logically from those premises toward conclusions that must also be true. Example:
If all tulips are plants, (premise 1) And if all plants produce energy through photosynthesis, (premise 2) Then all tulips must produce energy through photosynthesis. (conclusion)

Deductive logic
is extremely valuable for generating research hypothesis and test theories. Example:
Learning theory:
forming association among two or more pieces of information results in more effective learning than does trying to learn each piece of information separately from the others
Research literature:
the kinds of the questions people ask themselves (mentally) and try to answer as they learn (e.g. as they sit in class or read a textbook) affect what they learn and how effectively they remember Compare these two questions: What do I need to remember for the test? How might I apply this information to my own life?

Deductive logic
If learning information in an integrative fashion is more effective than learning information piecemeal, (premise 1) If the kinds of questions learners ask themselves during a learning activity influence how they learn, (premise 2) If training in self-questioning techniques influences the kinds of questions that students ask themselves, (premise 3) And if learning is reflected in the kinds of notes that learners take during class, (premise 4) Then teaching students to ask themselves integrative questions as they study class material should lead to class notes that are more integrative in nature. (conclusion)
What should be a hypothesis?

Inductive Reasoning
People use specific instances or occurrences to draw conclusions about entire classes of objects or events. In other words, people observe a sample and then draw conclusions about the population from which the sample comes.
All the data point to the same conclusion. From the data observed, the conclusion reached was that.
The scientific Method

Application of the scientific method often involves both deductive and inductive reasoning. Researchers may develop a hypothesis either from a theory (deductive logic) or from observations of specific events (inductive reasoning).
Using deductive logic, make predictions about the patterns which are likely to be seen in the data if the hypothesis is true. Using inductive reasoning, generalize from data taken from a sample to describe the characteristics of a larger population.
Critical Thinking
Good researchers engage in critical thinking.
Evaluating information or arguments in terms of accuracy an worth
Verbal reasoning: evaluating persuasive techniques found in oral and written language Argument analysis: discriminating between reasons that do and do not support a particular conclusion Decision making: identifying and judging several alternatives and selecting the best alternative Critical analysis of prior research: evaluating the value of data and research design to obtain the data
Was an appropriate method used to measure a particular outcome? Are the data and results derived from relatively large number of people, objects or events? Have other possible explanations or conclusion been eliminated? Can the results obtained in one situation be reasonably generalized to other situations?
Collaboration with others

Two heads are better than one.
Language as a Tool of Research

The value of knowing two or more languages
Many doctoral programs require that students demonstrate a reading competency in one or two foreign languages in addition to proficiency in English.
The importance of writing

When you write your ideas down on paper, you do several things:
Identify the specific idea you do and do not know Clarify and organize your thoughts sufficiently to communicate them to your readers You may detect gaps and logical flaws in your thinking
Guidelines: Writing to Communicate

Guidelines for effective writing
Say what you mean to say Keep your primary objective in writing your paper in mind at all times, and focus your discussion accordingly Provide an overview of what you will be talking about Organize your ideas into general and more specific categories, and use heading and subheading to guide your readers through your discussion of these categories
Guidelines: Writing to Communicate

Guidelines for effective writing (continued)
Provide transition phases, sentences, or paragraphs that help your readers follow your train of thought. Use concrete examples to make abstract ideas more understandable Use appropriate punctuation Use figures and tables when such mechanisms can more effectively present or organize your ideas and findings At the conclusion of a chapter or major section, summarize what you have said Anticipate that you will almost certainly have to write multiple drafts.
The procedure of great research are identical to those every student follows in doing a dissertation, a thesis, or a research report. All research begins with a problem, an observation, a questions. Curiosity is the germinal seed. Hypotheses are formulated. Data are gathered. Conclusions are researched.

CS701 Research Methodology in Computer Science: Lesson 3: Tools of Research

Uploaded by

Copyright:

Available Formats

CS701 Research Methodology in Computer Science: Lesson 3: Tools of Research

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

CS701 Research Methodology in Computer Science: Lesson 3: Tools of Research

Uploaded by

Copyright:

Available Formats

CS701 Research Methodology in Computer Science

Lesson 3: Tools of Research

Measurement as a Tool of Research

Measurement as a Tool of Research

Measuring insubstantial phenomena: An Example

Measuring insubstantial phenomena: An Example

Four scales of measurement

Four scales of measurement

Four scales of measurement

Four scales of measurement

Four scales of measurement

Four scales of measurement

One object is bigger or more of anything than another,

One object is so many units (degrees, inches) more than another,

One object is so many times as big or tall or heavy as another,

Measurement as a Tool of Research

Reliability is a necessary but inefficient condition for validity.

Statistics as a Tool of Research

The Lure of Statistics

The task the researcher ultimately faces:

Primary Functions of Statistics

The Human Mind as a Tool of Research

The Human Mind as a Tool of Research

The Human Mind as a Tool of Research

The Human Mind as a Tool of Research

The Human Mind as a Tool of Research

The scientific Method

Collaboration with others

Language as a Tool of Research

The importance of writing

Guidelines: Writing to Communicate

Guidelines: Writing to Communicate

You might also like