Сравнение на методи

	Методи за събиране на данни	Валидност и надеждност в изследванията
Област	Методология на изследванията	Методология на изследванията
Семейство	Process / pipeline	Process / pipeline
Година на възникване	1980	1950
Създател	Floyd Fowler (surveys); John Creswell, Robert DeVellis (qualitative and scale methodology)	Lee Cronbach, Paul Meehl (1950s); Donald Campbell, Julian Stanley (1960s); Samuel Messick (1990s)
Тип	Framework	Framework
Основополагащ източник	Fowler, F. J. (2014). Survey Research Methods (5th ed.). SAGE Publications.	Shadish, W. R., Cook, T. D., & Campbell, D. T. (2002). Experimental and Quasi-Experimental Designs for Generalized Causal Inference. Houghton Mifflin.
Други названия	data gathering, measurement instruments	measurement validity, test-retest reliability, internal and external validity
Свързани	3	2
Резюме	Data collection methods are the specific techniques and instruments used to gather information from research participants or sources. Common quantitative methods include surveys (questionnaires, interviews), physiological measurements (blood pressure, lab assays), behavioral observations, and administrative/secondary data (e.g., medical records, national registers). Qualitative methods include in-depth interviews, focus groups, observations, and document analysis. Selection and design of data collection instruments directly affect data quality, validity, and reliability. Floyd Fowler's work on survey methodology (1980s–2010s), Robert DeVellis's scale development approach, and John Creswell's frameworks for qualitative data collection provide systematic guidance.	Validity and reliability are two foundational concepts in research quality. Reliability refers to the consistency and reproducibility of measurements: do repeated applications of an instrument yield the same results? Validity refers to the truthfulness of inferences: does an instrument measure what it claims to measure, and do study findings answer the research question appropriately? Cronbach and Meehl (1955) distinguished construct validity from other validity types; Campbell and Stanley (1963) categorized internal and external validity threats in experimental designs; and Messick (1995) unified validity concepts as 'the degree to which evidence and theory support the intended interpretations of test scores.' Contemporary frameworks encompass multiple validity types (construct, criterion, content, internal, external) and reliability estimates tailored to measurement context.