Scribd
Upload
99 views7 pages

Correlation PDF

Uploaded by

ecobalas7

Correlation is when two sets of data are strongly linked together we say they have a High correlation. Linear correlations (correlations that follow a line) show how good the correlation is (not how steep the line is) 0 is no correlation (the values don't seem linked at all) 1 is a perfect negative correlation.

Copyright:

© All Rights Reserved
Download as PDF, TXT or read online from Scribd
Download as pdf or txt

Correlation PDF

Uploaded by

ecobalas7
99 views7 pages
Correlation is when two sets of data are strongly linked together we say they have a High correlation. Linear correlations (correlations that follow a line) show how good the correlation is (not how steep the line is) 0 is no correlation (the values don't seem linked at all) 1 is a perfect negative correlation.

Original Title

Correlation.pdf

Copyright

© © All Rights Reserved

Available Formats

PDF, TXT or read online from Scribd

Did you find this document useful?

Is this content inappropriate?

Correlation is when two sets of data are strongly linked together we say they have a High correlation. Linear correlations (correlations that follow a line) show how good the correlation is (not how steep the line is) 0 is no correlation (the values don't seem linked at all) 1 is a perfect negative correlation.

Copyright:

© All Rights Reserved
Download as PDF, TXT or read online from Scribd
Download as pdf or txt
99 views7 pages

Correlation PDF

Uploaded by

ecobalas7
Correlation is when two sets of data are strongly linked together we say they have a High correlation. Linear correlations (correlations that follow a line) show how good the correlation is (not how steep the line is) 0 is no correlation (the values don't seem linked at all) 1 is a perfect negative correlation.

Copyright:

© All Rights Reserved
Download as PDF, TXT or read online from Scribd
Download as pdf or txt
You are on page 1/ 7

Correlation

WhentwosetsofdataarestronglylinkedtogetherwesaytheyhaveaHigh
Correlation.

ThewordCorrelationismadeofCo(meaning"together"),and
Relation

CorrelationisPositivewhenthevaluesincreasetogether,and
CorrelationisNegativewhenonevaluedecreasesastheotherincreases
Herewelookatlinearcorrelations(correlationsthatfollowaline).

Correlationcanhaveavalue:

1isaperfectpositivecorrelation
0isnocorrelation(thevaluesdon'tseemlinkedatall)
1isaperfectnegativecorrelation
Thevalueshowshowgoodthecorrelationis(nothowsteepthelineis),andifitis
positiveornegative.

Example: Ice Cream Sales


https://www.mathsisfun.com/data/correlation.html

1/7

Thelocalicecreamshopkeepstrackofhowmuchicecreamtheysellversusthe
temperatureonthatday,herearetheirfiguresforthelast12days:

IceCreamSalesvsTemperature
TemperatureC IceCreamSales
14.2

$215

16.4

$325

11.9

$185

15.2

$332

18.5

$406

22.1

$522

19.4

$412

25.1

$614

23.4

$544

18.1

$421

22.6

$445

17.2

$408

Andhereisthesamedataasa ScatterPlot :

Wecaneasilyseethatwarmerweatherleadstomoresales,therelationshipisgoodbut
notperfect.

https://www.mathsisfun.com/data/correlation.html

2/7

Infactthecorrelationis0.9575...seeattheendhowIcalculatedit.

Correlation Is Not Good at Curves


Thecorrelationcalculationonlyworkswellforrelationshipsthatfollowastraightline.

OurIceCreamExample:therehasbeenaheatwave!
Itgetssohotthatpeoplearen'tgoingneartheshop,andsalesstart
dropping.
Hereisthelatestgraph:

Thecorrelationvalueisnow0:"NoCorrelation"...!
Thecalculatedcorrelationvalueis0(Iworkeditout),whichmeans"no
correlation".
Butwecanseethedatadoeshaveacorrelation:itfollowsanicecurve
thatreachesapeakaround25C.
Butthelinearcorrelationcalculationisnot"smart"enoughtoseethis.

Moralofthestory:makea ScatterPlot ,andlookatit!


Youmayseeacorrelationthatthecalculationdoesnot.

Correlation Is Not Causation

https://www.mathsisfun.com/data/correlation.html

3/7

Correlation Is Not Causation


"CorrelationIsNotCausation"...whichsaysthatacorrelationdoesnotmeanthatone
thingcausestheother(therecouldbeotherreasonsthedatahasagoodcorrelation).

Example:SunglassesvsIceCream
OurIceCreamshopfindshowmanysunglassesweresoldbyabigstorefor
eachdayandcomparesthemtotheiricecreamsales:

ThecorrelationbetweenSunglassesandIceCreamsalesishigh
Doesthismeanthatsunglassesmakepeoplewanticecream?

Example:ARealCase!
Afewyearsagoasurveyofemployeesfounda
strongpositivecorrelationbetween"Studying
anexternalcourse"andSickDays.
Doesthismean:
Studyingmakesthemsick?
Sickpeoplestudyalot?
Ordidtheylieaboutbeingsicktostudy
more?
Withoutfurtherresearchwecan'tbesurewhy.
https://www.mathsisfun.com/data/correlation.html

4/7

How To Calculate
HowdidIcalculatethevalue0.9575atthetop?
Iused"Pearson'sCorrelation".Thereissoftwarethatcancalculateit,suchasthe
CORREL()functioninExcelorLibreOfficeCalc...

...buthereishowtocalculateityourself:
Letuscallthetwosetsofdata"x"and"y"(inourcaseTemperatureisxandIceCream
Salesisy):
Step1:Findthemeanofx,andthemeanofy
Step2:Subtractthemeanofxfromeveryxvalue(callthem"a"),dothesame
fory(callthem"b")
Step3:Calculate:ab,a2andb2foreveryvalue
Step4:Sumupab,sumupa2andsumupb2
Step5:Dividethesumofabbythesquarerootof[(sumofa2)(sumof
b2)]
HereishowIcalculatedthefirstIceCreamexample(valuesroundedto1or0decimal
places):

https://www.mathsisfun.com/data/correlation.html

5/7

Asaformulaitis:

Where:

isSigma,thesymbolfor"sumup"
iseachxvalueminusthemeanofx(called"a"above)
iseachyvalueminusthemeanofy(called"b"above)
Youprobablywon'thavetocalculateitlikethat,butatleastyouknowitisnot"magic",
butsimplyaroutinesetofcalculations.

NoteforProgrammers
https://www.mathsisfun.com/data/correlation.html

6/7

Youcancalculateitinonepassthroughthedata.Justsumupx,y,x2,y2
andxy(noneedforaorbcalculationsabove)thenusetheformula:

OtherMethods
Thereareotherwaystocalculateacorrelationcoefficient,suchas"Spearman'srank
correlationcoefficient",butIpreferusingaspreadsheetlikeabove.

Question1Question2Question3Question4
Question5Question6Question7Question8
Question9Question10

Search::Index::About::Contact::Contribute::CiteThisPage::Privacy

Copyright2016MathsIsFun.com

https://www.mathsisfun.com/data/correlation.html

7/7

You might also like