lOMoARcPSD|266586 02
Scientific Research
Primarily, the goal of scientific research, among others, is to describe how
scientific study is carried out in practical terms. More so it aims at explaining why a
given scientific research succeeds in terms of producing some knowledge at the end
of the inquiry. In other words, scientific research aims or strives to draw inferences
by explaining or describing within the scope of “empirical information about the
world” (King, Keohane, and Verb 1994). Thus, in an effort to attain its primary
objective, Gary King and his colleagues further point out that all scientific researches
should be distinguished by the following four features: the goal of inference, the use
of “explicit, codified, and public methods to generate and analyze data whose
reliability can therefore be assessed” and reaching conclusions which tend to
premise on uncertainty, as well as paying close attention to a body of rules with
regard to “inference on which its validity depends” (King et al, 1994).
Regarding the key differences among experimental, statistical, and comparative
methods, one preeminent political science researcher had explained that, in so many
ways, the three scientific research designs share some fundamental commonalities,
one which borders on the “establishment of general empirical relationships among
two or more variables” (Lijphart 1971, 683). Notwithstanding the similarities, the late
Professor Arend Lijphart goes on to underscore or explain some crucial differences
pertaining to experimental, comparative, and statistical research methods. He
implies or points out that unlike in experimental study where the subjects are not
normally known beforehand, and hence the variables/subjects within the groups are
randomly selected, comparative research, on the other hand, uses or compare the
subjects in the group that are already known. This is because in the case of
comparative design one is dealing with an issues or phenomenon/event already
happened; that is to say, one cannot feasibly compare two unknown quantities or
actions.
For Lijphart, statistical method, unlike experimental and comparative methods,
is mostly predicated on theoretical control of verifiable data/numbers, “which cannot
be manipulated situationally as in experimental design—in order to controlled
relationships among variables” (Lijphart 1971, 684). These “situational
manipulations” probably explain the basis of Lijphart’s worldview that experimental
method maybe the beau ideal for “scientific explanation, but unfortunately it can only
rarely be used” (683-684) in the method suffers from pragmatic and moral
constraints.
The logic of inference can be explained as a process of drawing deducible
conclusion from assumptions/premises that are considered to be true or have some
elements of truth to them. King and his colleagues extensively highlighted on
the logic of inference probably because of their understanding that “All good
research can be understood—indeed, is best understood—to derive from the same
underlying logic of inference” (King et al, 1994). In other words, the significance or
pervasive application of logical inferences toward almost all research designs—
whether quantitative or qualitative—calls for more in-depth discussion on logic of
inference on the part of King and others.
In another development, King et al (1994) admit that although it may not
necessarily yield the expected outcome in all cases, nonetheless many research
designs, especially in the social science domain, “often begin research with a
considered design, collect some data, and draw conclusions” (12-13). Stated
differently, the key elements of research design, according to Professor King and his
lOMoARcPSD|266586 02
other co-researchers include developing the research question, the theory, the data,
and the use of the data (13). Clearly, based on King and colleagues’ assessment,
what plays the “leading role” in the determination of an appropriateness of research
design would be providing considerable attention to the “rules of scientific
inference…though certainty is unattainable, we can improve the reliability, validity,
certainty, and honesty of our conclusions” (7). Finally, research design decision may
greatly enhance each phase/stage of the research project, and it may also go a long
way to assist the investigator(s) in terms of taking relevant steps or ensuring correct
approach regarding how the research process should proceed. In many cases, the
design decision helps to underscore the main focus of the research study (Pedhazur,
and Schmelkin 1991).
References
King, Gary., Robert O. Keohane., and Sidney Verb. 1994. Designing Social Inquiry:
Scientific Inference in Qualitative Research. Princeton University Press.
Lijphart, Arend. 1971. “Comparative Politics and the Comparative Method.” The
American Political Science Review, 65(3): 682-693
Pedhazur, Elazar J., & Liora P. Schmelkin. 1991. Measurement, design, and
analysis: An integrated approach. Hillsdale, NJ: Lawrence Erlbaum Associates
Publications.
