Table of Contents


Basic process

  • It starts with an observation.
  • Deduce hypothesis from observation and asking 5W questions. ("an educated guess" or possible solution for the research question) Hypothesis can be generated be deduction or induction.
  • Conduct an experiment to proove or reject the hypothesis.
  • Analyze the test results and seek evidence.
  • Is a iterative process. Depending on whether the hypothesis is confirmed or rejected, it needs to be refined or replaced.
  • Once there is a conclusion, publish and present the results.


(Image source: Wikipedia - ArchonMagnus - CC BY-SA 4.0)

While theses steps are the greatest common denominator, each field of science uses its own version of the scientific method as the nature of the subject and its goals vary. The differences manifest themselves in the emphasis on the individual steps and the required formality.



hypothesis - a testable proposition explaining the occurrence of a phenomenon or phenomena, often asserted as a conjecture to guide further investigation. (…) One important word in the definition of "hypothesis" is "testable". If a proposition contains some component that defies testing or detection, the proposition is not a scientific hypothesis. (…) –

  • Types
    • Null-hypothesis: Negation of the hypothesis in order to test it.
    • Wenn-dann-Hyptothese
    • Je-desto-Hypotheses
    • Individual-Hypothese: eine Person betreffend
    • Kollektivhypothese: mehrere Personen betreffend
    • Kontexthypothesen: Kombination verschiedener Faktoren
    • Probabilistische Hypothese: Abhängigkeit von Wahrscheinlichkeiten
    • Deterministische Hypothese: Hypothesen mit 100% Wahrscheinlichkeit
  • Generation




Research Methods

Criteria for scientific work

Science follows certain standards which should be verified by peer reviews.


  • Observations and conclusions
  • Be truthful to yourself and to others.
  • Questions seriously whether the criteria described above have been applied.
  • Be open for critique.
  • Don't steal the intellectual property of others, e.g. unpublished conclusions, hypotheses, research approaches.


  • Neutral and based on facts opposed to opinions.
  • Not based on personal preferences, prejudices, feelings, politics and wishes.
  • Know about your biases (preferences, tempers, goals, hopes, narrow mindedness)
  • Don't try to manipulate
  • Let the reader to his/her own judgements


  • See "Methode der Falsifikation" from Karl Popper
  • Lost of our ideas and assumtions are wrong.
  • It should be possible to falsify the hypothesis.
  • Search for indicators which would proove the hypothesis wrong.
  • Search for indicators which would proove the hypothesis right.
  • Document the setup and steps in a way that others can reproduce the experiment.
  • Save and store the primary result data.
  • Check conclusions and forms of knowledge before forwarding them to others.
  • Describe experiments to enable their reproduction.
  • Describe all sources of information
  • Describe intermediary results, used tools and methods, graphical data models


  • When the experiment is repeated, it will lead to the same result.
  • Know and apply current best practices but questions the methods and (intermediary) results.
  • Possibility to check sources and references