The 5 Basic Statistics Concepts Data Scientists Need to Know · Statistical Features · Probability Distributions · Dimensionality Reduction · Over and Under Sampling.GetstartedOpeninappSigninGetstartedFollow551KFollowers·Editors'PicksFeaturesDeepDivesGrowContributeAboutGetstartedOpeninappThe5BasicStatisticsConceptsDataScientistsNeedtoKnowGeorgeSeifOct22,2018·9minreadIrecentlystartedabook-focusededucationalnewsletter.BookDivesisabi-weeklynewsletterwhereforeachnewissuewediveintoanon-fictionbook.You’lllearnaboutthebook’scorelessonsandhowtoapplytheminreallife.Youcansubscribeforithere.StatisticscanbeapowerfultoolwhenperformingtheartofDataScience(DS).Fromahigh-levelview,statisticsistheuseofmathematicstoperformtechnicalanalysisofdata.Abasicvisualisationsuchasabarchartmightgiveyousomehigh-levelinformation,butwithstatisticswegettooperateonthedatainamuchmoreinformation-drivenandtargetedway.Themathinvolvedhelpsusformconcreteconclusionsaboutourdataratherthanjustguesstimating.Usingstatistics,wecangaindeeperandmorefinegrainedinsightsintohowexactlyourdataisstructuredandbasedonthatstructurehowwecanoptimallyapplyotherdatasciencetechniquestogetevenmoreinformation.Today,we’regoingtolookat5basicstatisticsconceptsthatdatascientistsneedtoknowandhowtheycanbeappliedmosteffectively!Justbeforewejumpin,checkouttheAISmartNewslettertoreadthelatestandgreatestonAI,MachineLearning,andDataScience!StatisticalFeaturesStatisticalfeaturesisprobablythemostusedstatisticsconceptindatascience.It’softenthefirststatstechniqueyouwouldapplywhenexploringadatasetandincludesthingslikebias,variance,mean,median,percentiles,andmanyothers.It’sallfairlyeasytounderstandandimplementincode!Checkoutthegraphicbelowforanillustration.AbasicboxplotThelineinthemiddleisthemedianvalueofthedata.Medianisusedoverthemeansinceitismorerobusttooutliervalues.Thefirstquartileisessentiallythe25thpercentile;i.e25%ofthepointsinthedatafallbelowthatvalue.Thethirdquartileisthe75thpercentile;i.e75%ofthepointsinthedatafallbelowthatvalue.Theminand