دانلود رایگان مقاله انگلیسی کلان داده: برخی از مسائل آماری - الزویر 2018

عنوان فارسی
کلان داده: برخی از مسائل آماری
عنوان انگلیسی
Big data: Some statistical issues
صفحات مقاله فارسی
0
صفحات مقاله انگلیسی
11
سال انتشار
2018
نشریه
الزویر - Elsevier
فرمت مقاله انگلیسی
PDF
کد محصول
E8254
رشته های مرتبط با این مقاله
آمار
مجله
آمار و احتمال نامه ها - Statistics and Probability Letters
دانشگاه
Medical Research Council Population Health Research Unit - University of Oxford - UK
چکیده

ABSTRACT


A broad review is given of the impact of big data on various aspects of investigation. There is some but not total emphasis on issues in epidemiological research.

نتیجه گیری

7 Concluding remarks


Big data enable investigations to be conducted and reliable conclusions to be drawn that would otherwise be difficult or impossible. An example is their use in pharmacoepidemiology to evaluate treatment effects (Smeeth et al, 2009; Hernan & Robins, 2016).


We have highlighted some of the challenges that arise in the use of big data. One main theme has been to emphasise the potential for overconfidence in results obtained from analyses of large data sets, due to superficially highly precise but potentially biased estimates, or due to under-estimated standard errors. The size of the data does not remove the need for appropriate study design and statistical analysis (e.g. Welch et al, 2014, Lin et al, 2004, Pullenayegum & Lim, 2016). The potential impact of unobserved and unaccounted-for dependencies must not be ignored.


We have focused primarily on big data in the biomedical field. Even within that field there are many sources of big data that we have not mentioned. Each may present special challenges and opportunities.


In summary, while the availability of big data offers many possibilities for improved understanding, the need for careful and productive use of statistical concepts is pervasive and raises many challenges.


بدون دیدگاه