ShmoopTube

00:00

Finance Allah Shmoop What is inverse correlation All right It's

00:07

the relationship between two variables where we can expect an

00:10

increase in one variable to be paired with a decrease

00:13

in another variable Alright in plain English correlation When it

00:17

rains you get wet Inverse correlation When it rains you

00:22

get dry Correlation You have a big brain So your

00:26

smart inverse correlation like we're thinking dinosaurs Maybe they had

00:30

big brains all of it But if they had big

00:32

brains the bigger their brain Well the dumber thing God

00:35

Well that would be an inverse correlation right Correlation You

00:38

drive a fast flashy cars so you probably have a

00:41

small garage Alright Inverse correlation You drive a fast flashy

00:45

car and everything else about you is enormous Yeah So

00:49

in a word in versus just opposite check out inverse

00:52

correlations in this table showing to data sets Note how

00:55

the returns on investment in gold increase while the returns

00:58

on investment in Pat's for cats decrease over the same

01:02

timeframe And instead of hats for cats you could have

01:05

seen the stock market because people typically retreat into gold

01:08

when they're nervous about equities So this is really not

01:10

a bad inverse correlation right Okay So let's take a

01:13

look at a scatter plot of the same two data

01:14

sets See how the data points get lower and lower

01:17

as we go farther to the right Yeah that's because

01:19

the X values or the returns on the gold investment

01:22

increase or go farther to the right Well then the

01:25

Y values or returns on the hats for cats equities

01:28

investment decrease or go closer to the Y axis Well

01:31

sometimes we want to put a number on how strong

01:34

or weak The inverse correlation is between any two pairs

01:38

of variables So basically we're trying to determine if the

01:40

inverse correlation is one that follows a very steady amount

01:44

of decrease in one variable for a fixed amount of

01:47

increase in the other or if the amount of decrease

01:50

in one variable fluctuates for a fixed increase in the

01:53

other or more simply how closely the points on the

01:56

scatter plot are to an imaginary line like this thing

01:59

that best represents them Right That's an r squared correlation

02:02

there we'll get to it So the measure of how

02:04

strong the correlation is between these two variables is called

02:08

yes the correlation coefficient or our value Well a strong

02:13

inverse correlation would have the data points all cozied up

02:17

to the best fitting line coincidently called the line of

02:21

best fit Kind of like all of your new you

02:23

know friends after you win the ninety million dollars Powerball

02:27

lottery Well a week inverse correlation would have the data

02:32

spread out away from the line and best fit So

02:34

there's really no clustering here It's just a whole bunch

02:36

of dots on a graph that don't really tell you

02:39

much of anything you know like the location of kids

02:41

at a middle school dance compared to the location of

02:44

the dance floor So how do we find the our

02:46

value to determine how strong our correlation is inverse or

02:50

otherwise Well typically people use some sort of technological gadgets

02:53

such as a graphing calculator spreadsheet or a nap Let's

02:56

take that investment data from before comparing Gold returns to

02:59

returns on equity and hats for cats and walked through

03:02

how you'd find the R value using a spreadsheet So

03:05

open your favour like Excel or Google sheets or OpenOffice

03:08

Cal Core sells for days or and whatever you use

03:11

We're using Excel for this demo but they all work

03:13

in basically the same Put the data for the gold

03:15

returns without the presented signs in the first column Put

03:18

the data from hats for cats also without the presented

03:20

signs In the second column like that go to any

03:22

blank cell like the top selling the third column C

03:25

one there Then click on the formula's tab Choose the

03:28

Mohr Functions button and Anju Statistical See the coral option

03:32

there you selected Once we choose correlation we'll get a

03:35

pop up asking us to define the two sets of

03:37

data highlight on ly the first column of data It

03:40

should load that set of cells in the top row

03:42

of the pop up All right now left Click in

03:44

the second row of the pop up Highlight on ly

03:46

the second column of data and well should slide those

03:50

cells right into place Got it Okay So click okay

03:52

and boom instant our value Well it should show up

03:55

in the cell you picked to enter the Correlation Command

03:58

See one If you followed our Russians to et You

04:01

know t looks like our correlation has the strength of

04:03

negative point eight four Oh one Okay But like what

04:06

does that mean Is that strong or weak Positive Negative

04:10

Well for inverse correlations there's a range of values between

04:14

zero and negative one that we consider strong medium and

04:17

weak Inverse correlations like strong inverse correlation is generally run

04:21

from about negative point seven The negative one These will

04:23

be scatter plots where the points are quite close to

04:26

the best fit line like they're extremely counter or inversely

04:30

correlated Like if you found that every guy over forty

04:34

who drove a red convertible portion wore a gold chain

04:37

necklace there had a really big garage well then it

04:40

would be negatively correlated to our expectations Okay medium inverse

04:45

correlation is generally run from about negative point For the

04:48

negative point seven seas will be scattered plots with points

04:50

group less closely around the line A best fit Think

04:53

about it like well maybe half to two thirds of

04:55

all the guys have a small garage versus a big

04:58

garage Yeah something like that Weak inverse correlation is generally

05:01

run from well zero toe negative point for easily scatter

05:04

plots with almost no riel tight grouping Maybe there's some

05:07

trend if you really study it hard and think about

05:10

Roar Shack But there's really no correlation between the size

05:13

of your garage and when you're driving a convertible red

05:15

portion you wear a gold chain necklace All right one

05:18

thing we have to be careful about With the inverse

05:19

correlation XYZ thie implied value judgments that mistakenly get applied

05:22

to the two variables that are inversely correlated like in

05:25

our correlation calculation on returns we saw the gold investment

05:28

rise while the equity in hats for cats investment had

05:31

decreasing returns and basically was saying that people retreated putting

05:36

there cash into gold when they were nervous about the

05:38

equity markets Well that doesn't mean gold will always be

05:41

the one to increase While hats for cats decreases Beyond

05:44

the obvious changes in the market that might make gold

05:47

suddenly tank an inverse correlation means that gold could be

05:50

the investment with decreasing returns While hats for cat shows

05:54

increasing returns right the correlation thing is just showing that

05:57

they're inversely correlated When one goes up the other goes

06:00

down It could be that well when one goes down

06:02

the other one goes up Got it by the biggest

06:04

takeaway smelling That inverse correlation means that as one variable

06:08

increases in general the other variable decreases particularly when you

06:12

have high R squared correlations there Also we can calculate

06:15

how strong the correlation is by finding the R value

06:18

which we typically do using some technological do Dad Yeah

06:21

thank you Google Sheets and excel in all that stuff

06:23

Inverse correlation Czar values run from zero to negative one

06:27

with strong being in close to negative one in week

06:30

being close to zero And we're hoping there's an infamous

06:33

correlation between the number of matches we get on tinder

06:35

and the number of dates when we get that in

06:37

badly But well so far the data is not backing 00:06:41.135 --> [endTime] us up Change our picture what Oh

Full Transcript