In: Statistics and Probability
1. Avoiding Plagiarism
Instead of rewriting an entire passage of a paper, it may be possible to cut and paste selected parts, stringing them together in a way that presents the gist of the passage and still sounds natural. But this is not paraphrasing. This is plagiarism. If you copy from another work, you must cite the author and then place the copied parts in quotation marks. This generally proves to be a clumsy and intrusive method in a research paper, which is why paraphrasing is so useful.
Use Your Own Words
In a paraphrased passage, you should still start out by referring to the original author, then summarize the relevant passage of the author’s work in your own words and in your own style. For example, “In his 1989 paper, Robinson concluded that . . .“ There should be nothing in the paraphrased passage that was obviously lifted from the original.
Give Credit where Due
Although the original authors should be given credit for the gist of the paraphrased passage, don’t give them more credit that they deserve. If a previous work supports your own there is a temptation to oversell the earlier work, as in the authors “proved” this or that. But scientific experiments cannot prove anything; they can only support a hypothesis or disprove alternatives. Better to use a more neutral statement such as “Robinson’s 1989 paper strongly supports the proposed mechanism, since it reports that . . .”
Don’t Overuse
When I began freelance writing, I found that the issue of “fair use” was of great concern to authors. In an original work of your own, you are allowed to quote a certain amount from a previously written copyrighted work, but if you quote too much you can get in trouble for copyright infringement. How much is too much? Nobody knows. Only the haziest guidelines exist. The situation is somewhat similar in the use of paraphrases. Paraphrases are supposed to be a small proportion of an original work. If the paraphrased material is a major portion, the new work risks being seen as derivative of the original, a weak paper riding on the back of a stronger one. A good paper stands on its own, and any paraphrased passages should be there only to clarify and support it.
2. Primary data means the raw data (data without fabrication or not tailored data) which has just been collected from the source and has not gone any kind of statistical treatment like sorting and tabulation. The term primary data may sometimes be used to refer to first hand information.