- Количество слайдов: 36
Scientific Methods for Management Science Alexander Settles Higher School of Economics [email protected] ru
Course Objectives Learn how to use the scientific method ¡ Discuss your topic with fellow students ¡ Find literature sources on management ¡ Develop scholarly writing skills ¡ Develop critical thinking skills ¡ Instill research ethics ¡
Course Objectives Investigate professors that are potential dissertation advisors ¡ Learn about human subjects issues ¡ Develop bibliographic organization and citation skills ¡ Prepare dissertation proposal ¡
Purpose of this Seminar Introduction to international research practices ¡ Improve results of your dissertation work and encourage you take an entire year to work on your papers ¡ Gain a working knowledge of methods of scientific analysis ¡
Common mistakes of HSE students in pursuing research Making the blanket statement that things in Russia are different so social science practices do not apply ¡ Poor literature reviews ¡ No methods – summaries of work experiences or essay format ¡ No data to support or reject hypotheses ¡ No conclusions ¡
Terms ¡ ¡ ¡ ¡ applied research basic research belief-based explanation circular explanation (or tautology) commonsense explanations confirmation bias deductive reasoning ¡ ¡ ¡ ¡ hypothesis pseudoscience rational method research Science scientific method variable
Is Management a Science?
Language of Research Concepts ¡ Constructs ¡ Definitions ¡ Variables ¡ Propositions and Hypotheses ¡ Theory ¡ Models ¡
Methodology Qualitative ¡ Secondary Data Analysis ¡ Surveys ¡ Observation Studies ¡ Experiments ¡ Naturalistic Experiments ¡
Contents of a typical research paper Title page : abstract, contents ¡ Introduction ¡ Literature Review ¡ Description of work done and methods. ¡ Results and Discussion. ¡ Conclusions and Recommendations. ¡ References and Bibliography. ¡ Appendices. ¡
Introduction Define what the problem is ¡ The questions you are addressing ¡ Outline personal/specific considerations that lead to this investigation ¡ How it differs from previous work ¡ What the report will contain ¡ Perhaps some (hint) of the conclusions ¡
Methods ¡ ¡ Describe the method or approach. Justify that it is appropriate. Establish constraints or assumptions. Enable others to repeat the work and check the conclusions. ¡ ¡ ¡ Link with the research question. Motivate the work - what is its importance? Establish approaches used in previous research - the literature search.
Errors in inquiry ¡ Inaccurate observations l l ¡ Overgeneralization l l ¡ Assuming that a few similar events are evidence of a general pattern Scientists guard against this by REPLICATION of inquiry Selective observation l ¡ Most daily observations are casual… not precise Scientific observation is a conscious activity We assume a pattern exists then focus on future events that fit the pattern Illogical reasoning l “Exception that proves the rule”
Independent, Dependent and Control Variables ¡ Two concepts are implicit in causal or deterministic models ¡ A dependent variable “depends” on an independent variable ¡ That is, a change in the independent variable will produce a change in the dependent variable ¡ Control variables
Dialectics of Social Research: Quantitative and Qualitative Data ¡ Most simply put, difference is the distinction between numerical and non-numerical data ¡ Every observation is qualitative at the outset l ¡ We quantify it to make it easier to aggregate, compare and summarize the data Both types of data are useful and legitimate in management research
Elements of Social Theory ¡ Law: universal generalization about classes of facts l l ¡ Ex: law of gravity—bodies are attracted to each other in proportion to their mass and in inverse proportion to their distance No (or almost no) social scientific laws that claim universal certainty Theory: a systematic explanation for observations that relate to a particular aspect of social life. . . l For example someone might offer a theory of strategy, firm competitiveness, organization, etc.
Elements of Social Theory ¡ Proposition: specific conclusions about the relationships among concepts that are derived from axiomatic groundwork ¡ Hypothesis: a specified testable expectation about empirical reality that follows from a more general proposition l l Research is designed to test hypotheses Null hypothesis suggests that there is NO relationship among the variables under study
Traditional model of science ¡ Theory ¡ Operationalization l l For the researcher testing an hypothesis, the meaning of variables is exactly and only what the operational definition specifies l ¡ Specification of the exact operations involved in measuring a variable Must be specified with clarity in a way to make observation precise and rigorous Observation l Systematic and rigorous gathering of data to test the hypothesis
Research Design Purposes of Research ¡ Exploration: typically done for three purposes: l l l ¡ Description: describe situations and events l ¡ to satisfy the researcher’s curiosity and desire for better understanding to test the feasibility of undertaking a more extensive study to develop the methods to be employed in a subsequent study Census is good example of descriptive research Explanation: the “why? ” of events, situations, behavior, attitudes, etc.
Criteria for Causality ¡ Correlation: the variables must be correlated ¡ Time order: the cause takes place before the effect ¡ Non-spurious: the variables are non-spurious l Spurious relationship: a coincidental statistical correlation between two variables, shown to be caused by some third variable
Correlation ¡ Some relationship---or correlation—between the variables must exist before we can consider causality ¡ Correlation: empirical relationship between two variables such that… l Changes in one are associated with changes in the other l Particular attributes of one variable are associated with particular attributes of the other
Necessary and Sufficient Causes ¡ Necessary cause represents a condition that must be present for the effect to follow l Ex: must be female to become pregnant l Ex: must take college courses to get a degree…but… ¡ ¡ Simply taking courses is not a sufficient cause Must take the right ones
Necessary and Sufficient Causes ¡ Sufficient cause represents a condition that, if it is present, guarantees the effect in question ¡ Not saying that sufficient cause is only possible cause for effect l Ex: skipping exam in course would be sufficient cause for failing, but students could fail in other ways, too l So, cause can be sufficient but not necessary
Units of Analysis ¡ No limit to what or whom can be studied ¡ Common social science units of analysis: l l ¡ Individuals Groups Organizations Social artifacts. Important: what you “call” a given unit of analysis is almost irrelevant—but you must be clear what that unit “is” l l l Country level effects or the firms that operate in that country? Firm level strategy or country level strategy? Efficiency of the hotel or the satisfaction of customers?
Conceptualization, Operationalization & Measurement ¡ Conceptualization l l ¡ The refinement and specification of abstract concepts A specific agreed-upon meaning of the concept under study Operationalization l The development of specific research procedures (operations) that will result in empirical observations representing those concepts in the real world
Indicators and Dimensions ¡ Indicator l l ¡ An observation that we consider as a reflection of the variable under study Ex: attending church as an indicator or religiosity Dimension l l A specific aspect of a concept Ex: action aspects of religiosity (attending church, giving money) and contemplative aspects (prayer, etc)
Basic Research Outline* ¡ The Problem l Present a clear, brief statement of the problem, with concepts defined where necessary l Show that the problem is limited to bounds amenable to treatment or test l Describe the significance of the problem with reference to specific criteria Source: Miller, Delbert C. 1991. Handbook of Research Design and Social Measurement, 5 th Edition. Newbury Park: Sage Publications, pp. 15 -16. Edition
Basic Research Outline ¡ Theoretical Framework l Describe the relationship of the problem to a theoretical framework l Demonstrate the relationship of the problem to previous research l Present alternate hypotheses considered feasible within the framework of theory.
Basic Research Outline ¡ The Research Question/Hypotheses l Clearly state the research questions or the hypotheses selected for test. (Null and alternate) l Indicate the significance of test hypotheses to the advancement of research and theory. l Define concepts or variables (preferably in operational terms). l Describe possible mistakes and their consequences. l Note seriousness of possible mistakes.
Basic Research Outline ¡ Design of the Experiment or Inquiry l Describe ideal design or designs with particular attention to the control of interfering variables l Describe selected operational design l Specify statistical tests including dummy variables
Basic Research Outline ¡ Sampling Procedures l Describe experimental and control samples l Specify method of drawing or selecting sample
Basic Research Outline ¡ Methods of Gathering Data l Describe measures of quantitative variables showing reliability and validity when these are known. Describe means of identifying qualitative variables l Include descriptions of questionnaires or schedules l Describe interview procedure l Describe use made of pilot study, pretest, trial run.
Basic Research Outline ¡ Working Guide l Prepare working guide with time and budget estimates l Estimate total person-hours and cost
Basic Research Outline ¡ Analysis l of Results Specify methods of analysis
Basic Research Outline ¡ Interpretation of Results l Discuss how conclusions will be fed back into theory…OR… l Inform practice.
Basic Research Outline ¡ Publication or Reporting Plans. . . Communication Plans l Monograph, Executive summary Monograph l Testimony to policy makers. l Presentations to institutions, nongovernmental agencies, media, public. l Journal publication