Deductive Theory Building and Inductive Theory Building

Developing Theory from Observations - Creativity in Inductive Thinking - Research Methodology


Scientific Research is theory building.

Theory is developed for the set of observations. The process involved is inductive thinking. There is creativity involved in theory building. The concrete or specific observations are to be described by general concepts. Theory connects the concepts.

In developing the concept from a practical instance or observation some assumptions are employed and a rigorous description of the concept is developed. Further assumptions are used to develop theory. Model building is also theory development only. Model building used to solve practical problems also involves assumptions that bring the reality to close to the existing problem solving theories. From the set of assumptions, the theory is developed. This is termed as deductive approach to theory building.

In grounded theory method, Glaser and Strauss recommend theory building from the evidence only without building any model and then developing theory. They criticize model based theory building as too distant from the evidence on which it was supposed to be based. Hence, the likelihood of the theory failing in test is high.


Illustrations of Assumptions and Theory Building

Modigliani and Miller Capital Structure Theory

Assumptions

1. Perfect capital market: Information is freely available, there is no asymmetry, transactions are costless; there are no bankruptcy costs, securities are infinitely divisible.
2. Rational Investors and Managers: Investors rationally choose a combination of risk and return that is most advantageous to them. Managers act in the interests of shareholders.
3. Homogeneous expectations: Investors hold identical expecations about future operating earnings.
4. Equivalent risk classes: Firms can be grouped into 'equivalent risk classes' on the basis of their business risk.
5. Absence of Taxes: There is no corporate income tax.

MM Proposition I
The value of a firm is equal to its expected operating income divided by the discount rate appropriate to its risk class. It is independent of its capital structure.

MM Proposition II
The expected return on equity is equal to the expected rate of return on assets, plus a premium. The premium is equal to the debt-equity ratio times the difference between the expected return on assets and the expected return on debt.

(Source: Prasanna Chandra, Financial Management: Theory and Practice, Fifth Edition, Tata McGraw-Hill Pub. Co. Ltd, New Delhi, 2001. pp.417-24.)


Theory of Collisions (Physics)

Assumptions

The masses are moving on a frictionless surface.
The masses are perfectly elastic bodies (or they are connected by massless springs).

(Reference: H.C. Verma, Concepts of Physics Part 1, Bharati Bhawan, New Delhi, 1993 (Second reprint of revised edition 2007), p.145.


Article originally published at Knol 2657

List of Articles on the Topic


Volume 14, No. 1, Art. 25 – January 2013
Theory Building in Qualitative Research: Reconsidering the Problem of Induction

Pedro F. Bendassolli

Abstract: The problem of induction refers to the difficulties involved in the process of justifying experience-based scientific conclusions. More specifically, inductive reasoning assumes a leap from singular observational statements to general theoretical statements. It calls into question the role of empirical evidence in the theory-building process. In the philosophy of science, the validity of inductive reasoning has been severely questioned since at least the writings of David HUME. At the same time, induction has been lauded as one of the main pillars of qualitative research methods, and its identity as such has consolidated to the detriment of hypothetical-deductive methods. This article proposes reviving discussion on the problem of induction in qualitative research. It is argued that qualitative methods inherit many of the tensions intrinsic to inductive reasoning, such as those between the demands of empiricism and of formal scientific explanation, suggesting the need to reconsider the role of theory in qualitative research.
http://www.qualitative-research.net/index.php/fqs/article/view/1851/3497

Full paper available


Updated   14 September 2016,  24 August 2016,  10 December 2012

StatSoft Statistics Textbook - Book Information

The book is available for free access since 1995. Now Statsoft is part of Dell.

_______________________

_______________________

•  Elementary Concepts
• 
  
•  Statistics Glossary
• 
  
•  Basic Statistics
• 
  
•  ANOVA / MANOVA
• 
  
•  Association Rules
• 
  
•  Boosting Trees
• 
  
•  Canonical Analysis
• 
  
•  CHAID Analysis
• 
  
•  C & R Trees
• 
  
•  Classification Trees
• 
  
•  Cluster Analysis
• 
  
•  Correspondence Analysis
• 
  
•  Data Mining Techniques
• 
  
•  Discriminant Analysis

Discriminant analysis classifies the given subjects into two categories like "likely to be successful" and "likely to be failures" based on the data that is given for each subject. The decision maker can select the subjects likely to be successful for say, investment.

•  Distribution Fitting
• 
  
•  Experimental Design
• 
  
•  Factor Analysis

Factor analysis converts the given data on various subjects into less number of variables termed as factors. The factors can be used for further data analysis.

•  General Discrim. Analysis
• 
  
•  General Linear Models
•  Generalized Additive Mod.
•  Generalized Linear Mod.
•  General Regression Mod.
•  Graphical Techniques
•  Ind.Components Analysis
• 
  
•  Linear Regression
•  Log-Linear Analysis
•  MARSplines
•  Machine Learning
• 
  
•  Multidimensional Scaling
• 
  
•  Neural Networks
• 
  
•  Nonlinear Estimation
• 
  
•  Nonparametric Statistics
•  Partial Least Squares
•  Power Analysis
•  Process Analysis
• 
  
•  Quality Control Charts
• 
  
•  Reliability / Item Analysis
•  SEPATH (Structural eq.)
•  Survival Analysis
•  Text Mining
• 
  
•  Time Series / Forecasting
•  Variance Components
•  Statistical Advisor
•  Distribution Tables
•  References Cited
•  Send Comments
•  Business Solutions
•  Free Resources
•  About Textbook

_______________________

_______________________

Summer Undergraduate Research Program at Purdue University College of Engineering

https://engineering.purdue.edu/Engr/Research/SURF/ModulePages/Mod1



Research Notebook
https://engineering.purdue.edu/Engr/Research/SURF/ModulePages/Mod2


Literature Review
https://engineering.purdue.edu/Engr/Research/SURF/ModulePages/Mod3

An Introduction to Logic - Cohen and Nagel - Book Information

https://books.google.co.in/books?id=U09MjwDSZ0kC&printsec=frontcover#v=onepage&q&f=false

Glaser and Strauss - Grounded Theory - Chapter 2 - Generating Theory - Quotations and Summary

From the data based on coding, categories (conceptual categories or concepts) have to identified. From the data only properties of categories are also identified. Then relations among categories are identified. The theory developed that can be expressed as a descriptive note or proposition. Glaser and Strauss prefer descriptive note. They say descriptive note provides an indication that theory needs to be further developed. A proposition indicates finality.   But they stated that from descriptive note, propositions can be created as necessary say for testing purpose.


Quotations

Comparative analysis is a general method, just as are the experimental and statistical methods. (All use the logic of comparison.)


A concept may be generated from one fact, which then becomes merely one of a universe of many possible diverse indicators for, and data on, the concept. These indicators are then sought for the comparative analysis.

In discovering theory, one generates conceptual categories or their properties from evidence; then the evidence from which the category emerged is used to illustrate the concept. The evidence may not necessarily be accurate beyond a doubt (nor is it even in studies concerned only with accuracy), but
the concept is undoubteclly a relevant theoretical abstraction about what is going on in the area studied. Furthermore, the concept itself will not change, while even the most accurate facts change. Concepts only have their meanings respecified at times because other theoretical and research purposes have evolved.

Our goal of generating theory also subsumes this establishing of empirical generalizations, for the generalizations not only help delimit a grounded theory's boundaries of applicability; more important, they help us broaden the theory so that it is more generally applicable and has greater explanatory and
predictive power. By comparing where the facts are similar or different, we can generate properties of categories that increase the categories' generality and explanatory power.

While verifYing is the researcher's principal and vital task for existing theories, we suggest that his main goal in developing new theories is their purposeful systematic generation from the data of social research.

A grounded theory can be used as a fuller test of a logico-deductive theory pertaining to the same area by comparison of both theories than an accurate description used to verify a few propositions would provide. ·whether or not there is a previous speculative theory, discovery gives us a theory
that "fits or works" in a substantive or formal area (though further testing, clarification, or reformulation is still necessary), since the theory has been derived from data, not deduced from
logical assumptions. . .

The sociologist with theoretical generation ·as his major aim need not know the concrete situation better than the people involved in it (an impossible task anyway). His job and his training are to do what these laymen cannot do-generate general categories and their properties for general and specific situations and problems. Thesevcan provide theoretical guides to the layman's action

Grounded theory can be presented either as a wellcodified set of propositions or in a running theoretical discussion, using conceptual categories and their properties.

If necessary for verillcational studies, parts of the theoretical discussion can at any point be rephrased
as a set of propositions. This repht:asing is simply a formal exercise, though, since the concepts are already related in the discussion. Also, with either a propositional or discussional grounded theory, the sociologist can then logically deduce further hypotheses. Indeed, deductions from grounded theory, as it develops, are the method by which the researcher directs his theoretical sampling

Our approach, allowing substantive concepts and hypotheses to emerge first, on their own, enables the analyst to ascertain which, if any, existing formal theory may help him generate his substantive theories. He can then be more faithful to his data, rather than forcing it to fit a theory. He can be
more objective and less theoretically biased. Of course, this also means that he cannot merely apply Parsonian or Mertonian categories at the start, but must wait to see whether they are linked to the emergent substantive theory concerning the issue in focus.

the elements of theory that are generated by comparative analysis are, first, conceptual categories and their conceptual properties; and second, hypotheses or generalized relations among the categories and their properties.

A category stands by itself as a conceptual element of the theory. A property, in turn, is a conceptual aspect or element of a category. We have, then, both categories and their properties.

It must be kept in mind that both categories and properties are concepts indicated by the data (and not the data itself); also that both vary in degree of conceptual abstraction. Once a category or property is conceived, a change in the evidence that indicated it will not necessarily alt~r, clarify or destroy it.
It takes much more evidence-usually from different substantive areas-as well as the creation of a better category to achieve such changes in the original category. In short, conceptual categories
and properties have a life apart from the evidence that gave rise to them.

Lower level categories emerge rather quickly during the early phases of data collection. Higher level,
overridLllg and integrating, conceptualizations-and the properties that elaborate them-tend to come later during the joint collection, coding and analysis of the data.

The comparison of differences and similarities among groups not only generates categories, but also rather speedily generates generalized relations among them. It must be emphasized that these hypotheses have at first the status of suggested, not tested, relations among categories and !heir properties, though they are verified as much as possible in the course of research.

Joint collection, coding, and analysis of data is the underlying operation. The generation of theory,
coupled with the notion of theory as process, requires that all three operations be done together as much as possible. They should blur and intertwine continually, from the beginning of an investigation to its end.


Summary of Glaser, Barney G & Strauss, Anselm L., 1967. The Discovery of Grounded Theory: Strategies for Qualitative Research,
http://faculty.babson.edu/krollag/org_site/craft_articles/glaser_strauss.html

Research Methods in Education - Cohen, Manion, and Morrison - Book Information

Research Methods in Education

7th Edition

Louis Cohen, Lawrence Manion, Keith Morrison
Routledge, 2011 - Education - 758 pages

7th edition of the long-running bestseller Research Methods in Education encompasses the whole range of methods currently employed by educational research at all stages. It offers plentiful and rich practical advice, underpinned by clear theoretical foundations, research evidence and up-to-date references.

Chapters new to this edition cover:

Causation, critical educational research, evaluation and the politics of research, including material on cross-cultural research, mixed methods and participatory research

Choosing and planning a research project, including material on sampling, research questions, literature reviews and ethical issues

Meta-analysis, research syntheses and systematic reviews

Virtual worlds and internet research

Using and analysing visual media and data in educational research

Organizing and presenting qualitative data, content analysis, coding and computer analysis, themes, narratives, conversations and discourses, grounded theory

Understanding and choosing statistical tests, descriptive and inferential statistics, multi-dimensional measurement and factor analysis

Research Methods in Education is essential reading for both the professional researcher and students of education at postgraduate level and Phd level, who need to understand how to plan, conduct, analyse and use research.

The textbook is accompanied by a website: www.routledge.com/textbooks/cohen7e. PowerPoint slides for every chapter contain an outline of the chapter structure followed by a thorough summary of the key points, ideal for both lecturers and students. Within the book a variety of internet resources are referred to and these references have been included here, with links to the websites. A wide range of supplementary documents are available for many chapters, providing additional guidance and examples. They range from guidelines for the contents of a research proposal with a worked example, to screen-print manuals for using SPSS and QSR N6 NUD*IST (exportable to N-Vivo) plus data files.

Dictionary of the History of Science - Bynum, Browne and Porter - Book Information

Dictionary of the History of Science


William F. Bynum, E. Janet Browne, Roy Porter
Princeton University Press, 14-Jul-2014 - Science - 530 pages

For readers interested in the development of major scientific concepts and the role of science in the western world, here is the first conceptually organized historical dictionary of scientific thought. The purpose of the dictionary is to illuminate this history by providing a concise, single volume reference book of short historical accounts of the important themes, ideas, and discoveries of science. Its conceptual approach differentiates the dictionary from previous reference works such as books of scientific biography and makes it a convenient manual both for the general reader and for scientists interested in the origin of concepts in their own and other scientific fields.

Originally published in 1982.

https://books.google.co.in/books/p/princeton?id=Ian_AwAAQBAJ