from web site
In this case scientists resort to natural experiments or quasi-experiments. Natural experiments rely solely on observations of the variables of the system under research study, instead of adjustment of simply one or a few variables as happens in regulated experiments. To the degree possible, they attempt to collect information for the system in such a way that contribution from all variables can be identified, and where the impacts of variation in certain variables remain around continuous so that the impacts of other variables can be determined.
When these variables are not well associated, natural experiments can approach the power of controlled experiments. Typically, nevertheless, there is some correlation between these variables, which minimizes the dependability of natural experiments relative to what might be concluded if a controlled experiment were performed. Likewise, A Good Read to the fact that natural experiments generally occur in unchecked environments, variables from undetected sources are neither determined nor held consistent, and these might produce illusory correlations in variables under research study.
For instance, in astronomy it is clearly difficult, when testing the hypothesis "Stars are collapsed clouds of hydrogen", to begin with a giant cloud of hydrogen, and after that perform the experiment of waiting a couple of billion years for it to form a star. Nevertheless, by observing numerous clouds of hydrogen in different states of collapse, and other implications of the hypothesis (for example, the existence of various spectral emissions from the light of stars), we can gather information we need to support the hypothesis.
Observation of the appearance of the moons of Jupiter were somewhat delayed when Jupiter was farther from Earth, rather than when Jupiter was closer to Earth; and this phenomenon was utilized to show that the distinction in the time of appearance of the moons was consistent with a measurable speed.
Typically utilized in the social sciences, and particularly in financial analyses of education and health interventions, field experiments have the benefit that outcomes are observed in a natural setting rather than in a contrived laboratory environment. For this factor, field experiments are in some cases viewed as having higher external validity than laboratory experiments.