Last visit was: 18 Nov 2025, 18:42 It is currently 18 Nov 2025, 18:42
Close
GMAT Club Daily Prep
Thank you for using the timer - this advanced tool can estimate your performance and suggest more practice questions. We have subscribed you to Daily Prep Questions via email.

Customized
for You

we will pick new questions that match your level based on your Timer History

Track
Your Progress

every week, we’ll send you an estimated GMAT score based on your performance

Practice
Pays

we will pick new questions that match your level based on your Timer History
Not interested in getting valuable practice questions and articles delivered to your email? No problem, unsubscribe here.
Close
Request Expert Reply
Confirm Cancel
User avatar
almirab
Joined: 24 Oct 2022
Last visit: 12 May 2024
Posts: 11
Own Kudos:
859
 [96]
Location: Turkey
Posts: 11
Kudos: 859
 [96]
11
Kudos
Add Kudos
85
Bookmarks
Bookmark this Post
Most Helpful Reply
User avatar
chetan2u
User avatar
GMAT Expert
Joined: 02 Aug 2009
Last visit: 15 Nov 2025
Posts: 11,238
Own Kudos:
43,696
 [18]
Given Kudos: 335
Status:Math and DI Expert
Location: India
Concentration: Human Resources, General Management
GMAT Focus 1: 735 Q90 V89 DI81
Products:
Expert
Expert reply
GMAT Focus 1: 735 Q90 V89 DI81
Posts: 11,238
Kudos: 43,696
 [18]
10
Kudos
Add Kudos
8
Bookmarks
Bookmark this Post
User avatar
rahul_patnaik
Joined: 28 Jun 2023
Last visit: 18 Nov 2025
Posts: 3
Own Kudos:
7
 [6]
Given Kudos: 26
Posts: 3
Kudos: 7
 [6]
3
Kudos
Add Kudos
3
Bookmarks
Bookmark this Post
General Discussion
User avatar
Edoua
Joined: 18 Feb 2024
Last visit: 31 Oct 2025
Posts: 103
Own Kudos:
55
 [2]
Given Kudos: 638
Posts: 103
Kudos: 55
 [2]
2
Kudos
Add Kudos
Bookmarks
Bookmark this Post
Classify the data from 2009 to 2013

1- positively correlated

2-Not positively correlated

3- positively correlated

For the 3rd question we have to observe what can be the general trend and not only focus on the first point…..

Posted from my mobile device
User avatar
whatsarc
Joined: 26 Aug 2023
Last visit: 18 Nov 2025
Posts: 109
Own Kudos:
102
 [1]
Given Kudos: 78
Products:
Posts: 109
Kudos: 102
 [1]
1
Kudos
Add Kudos
Bookmarks
Bookmark this Post
Positive correlation (aka directly related): If one increases, the other also increases
Negative correlation (aka inversely related): If one increases, the other decreases

6–10, 11–15
movement from 4-14%, corresponding movement 39-47%
Both show increasing trend, hence positive correlation

6–10, 16-20
movement from 4-14%, corresponding movement 37-31%
One increasing, another decreasing. hence not positive

16–20, 21+
movement from 37-31%, corresponding movement 20-08%
Both show decreasing trend, hence positive correlation­
User avatar
yipmewmew
Joined: 26 May 2021
Last visit: 15 Jul 2025
Posts: 230
Own Kudos:
Given Kudos: 792
Location: India
GMAT 1: 640 Q44 V33
GMAT 2: 730 Q48 V42
Products:
GMAT 2: 730 Q48 V42
Posts: 230
Kudos: 83
Kudos
Add Kudos
Bookmarks
Bookmark this Post
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
User avatar
KarishmaB
Joined: 16 Oct 2010
Last visit: 18 Nov 2025
Posts: 16,265
Own Kudos:
76,982
 [4]
Given Kudos: 482
Location: Pune, India
Expert
Expert reply
Active GMAT Club Expert! Tag them with @ followed by their username for a faster response.
Posts: 16,265
Kudos: 76,982
 [4]
2
Kudos
Add Kudos
2
Bookmarks
Bookmark this Post
sv2023
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
­
There is no such rule, but the general trend would be obvious. Otherwise we would get confused whether the data is correlated at all.
There are 4 increases/decreases so  1 change in the opposite direction would be ok. After all, they are not "directly varying". They are positively correlated and the correlation coefficient could be any positive value less than 1 so there is a fair margin. 
But if 2 changes were in same direction and 2 in opposite, then we cannot extablish any correlation between them. 
User avatar
nust2017
Joined: 04 Sep 2018
Last visit: 29 Oct 2025
Posts: 129
Own Kudos:
Given Kudos: 54
GPA: 3.33
Posts: 129
Kudos: 32
Kudos
Add Kudos
Bookmarks
Bookmark this Post
Hi Karishma. Can you please explain why we we are looking at correlation in part A from 2013-2009? Should it not be from 2009-2013 which clearly shows negative correlation i.e. from 2009-2013, as the percentage in 6-10 increases, the 11-15 age ranges are decreasing.
KarishmaB
sv2023
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
­
There is no such rule, but the general trend would be obvious. Otherwise we would get confused whether the data is correlated at all.
There are 4 increases/decreases so 1 change in the opposite direction would be ok. After all, they are not "directly varying". They are positively correlated and the correlation coefficient could be any positive value less than 1 so there is a fair margin.
But if 2 changes were in same direction and 2 in opposite, then we cannot extablish any correlation between them.
User avatar
KarishmaB
Joined: 16 Oct 2010
Last visit: 18 Nov 2025
Posts: 16,265
Own Kudos:
Given Kudos: 482
Location: Pune, India
Expert
Expert reply
Active GMAT Club Expert! Tag them with @ followed by their username for a faster response.
Posts: 16,265
Kudos: 76,982
Kudos
Add Kudos
Bookmarks
Bookmark this Post
nust2017
Hi Karishma. Can you please explain why we we are looking at correlation in part A from 2013-2009? Should it not be from 2009-2013 which clearly shows negative correlation i.e. from 2009-2013, as the percentage in 6-10 increases, the 11-15 age ranges are decreasing.
KarishmaB
sv2023
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
­
There is no such rule, but the general trend would be obvious. Otherwise we would get confused whether the data is correlated at all.
There are 4 increases/decreases so 1 change in the opposite direction would be ok. After all, they are not "directly varying". They are positively correlated and the correlation coefficient could be any positive value less than 1 so there is a fair margin.
But if 2 changes were in same direction and 2 in opposite, then we cannot extablish any correlation between them.


Positive correlation means that when one quantity increases, the other increases too. When one quantity decreases, the other decreases too.
For part A, From 2009 to 2013, values for both ranges are decreasing. So as one is decreasing, other is decreasing too. Hence there is positive correlation between them..
User avatar
saurvan
Joined: 09 Oct 2014
Last visit: 28 Oct 2025
Posts: 17
Own Kudos:
21
 [1]
Given Kudos: 198
Posts: 17
Kudos: 21
 [1]
1
Kudos
Add Kudos
Bookmarks
Bookmark this Post
so as per this, what is the permissible amount of outliers that we need to ignore? Lets say in a set of 5, there are two outliers and 3 are in trend. will that count to be in trend?
KarishmaB
sv2023
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
­
There is no such rule, but the general trend would be obvious. Otherwise we would get confused whether the data is correlated at all.
There are 4 increases/decreases so 1 change in the opposite direction would be ok. After all, they are not "directly varying". They are positively correlated and the correlation coefficient could be any positive value less than 1 so there is a fair margin.
But if 2 changes were in same direction and 2 in opposite, then we cannot extablish any correlation between them.
User avatar
KarishmaB
Joined: 16 Oct 2010
Last visit: 18 Nov 2025
Posts: 16,265
Own Kudos:
Given Kudos: 482
Location: Pune, India
Expert
Expert reply
Active GMAT Club Expert! Tag them with @ followed by their username for a faster response.
Posts: 16,265
Kudos: 76,982
Kudos
Add Kudos
Bookmarks
Bookmark this Post
saurvan
so as per this, what is the permissible amount of outliers that we need to ignore? Lets say in a set of 5, there are two outliers and 3 are in trend. will that count to be in trend?
KarishmaB
sv2023
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
­
There is no such rule, but the general trend would be obvious. Otherwise we would get confused whether the data is correlated at all.
There are 4 increases/decreases so 1 change in the opposite direction would be ok. After all, they are not "directly varying". They are positively correlated and the correlation coefficient could be any positive value less than 1 so there is a fair margin.
But if 2 changes were in same direction and 2 in opposite, then we cannot extablish any correlation between them.


You don't have 2 outliers in a set of 5 here. Both positively correlated series have only 1 outlier. The other 4 are as per trend.
2 out of 5 becomes debatable. Then I would like to see what their graphs looks like. Small increase/decrease but overall same trend would indicate positive correlation.
User avatar
Sanjanaad
Joined: 19 Sep 2021
Last visit: 11 Nov 2025
Posts: 7
Own Kudos:
Given Kudos: 5
Location: India
GMAT Focus 1: 655 Q85 V86 DI76
GPA: 7/7
GMAT Focus 1: 655 Q85 V86 DI76
Posts: 7
Kudos: 6
Kudos
Add Kudos
Bookmarks
Bookmark this Post
Hi Karishma,

To establish a correlation in these questions, is it necessary to sort the data as per the first data set e.g. 6-10 years age group in the first case? Or should we go by the default sorting given (in this case sequence of years)
KarishmaB
sv2023
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
­
There is no such rule, but the general trend would be obvious. Otherwise we would get confused whether the data is correlated at all.
There are 4 increases/decreases so 1 change in the opposite direction would be ok. After all, they are not "directly varying". They are positively correlated and the correlation coefficient could be any positive value less than 1 so there is a fair margin.
But if 2 changes were in same direction and 2 in opposite, then we cannot extablish any correlation between them.
User avatar
KarishmaB
Joined: 16 Oct 2010
Last visit: 18 Nov 2025
Posts: 16,265
Own Kudos:
76,982
 [1]
Given Kudos: 482
Location: Pune, India
Expert
Expert reply
Active GMAT Club Expert! Tag them with @ followed by their username for a faster response.
Posts: 16,265
Kudos: 76,982
 [1]
1
Kudos
Add Kudos
Bookmarks
Bookmark this Post
This is time series data so there is a natural sequence to it. Stick to it.
If you plot the two data series with time on x axis, the lines should move in a similar manner is all you require for them to have positive correlation.

A question on correlation is discussed here: https://youtu.be/Zx-PysHlhGM
I have a video and topic discussion on correlation - exactly how it works for time series data and paired data. You can check it out by using the 3 day free trial on my platform.


Sanjanaad
Hi Karishma,

To establish a correlation in these questions, is it necessary to sort the data as per the first data set e.g. 6-10 years age group in the first case? Or should we go by the default sorting given (in this case sequence of years)
KarishmaB
sv2023
KarishmaB can you please weigh in on the 3rd option? I understand that just one data point is going against the trend but where would we follow this 'rule' of looking at the general trend while determining the correlation? Here's there's just one data point going opposite, what if there were two? What would the ans be then?­
­
There is no such rule, but the general trend would be obvious. Otherwise we would get confused whether the data is correlated at all.
There are 4 increases/decreases so 1 change in the opposite direction would be ok. After all, they are not "directly varying". They are positively correlated and the correlation coefficient could be any positive value less than 1 so there is a fair margin.
But if 2 changes were in same direction and 2 in opposite, then we cannot extablish any correlation between them.
User avatar
Batka
Joined: 21 May 2025
Last visit: 20 Sep 2025
Posts: 3
Given Kudos: 64
Posts: 3
Kudos: 0
Kudos
Add Kudos
Bookmarks
Bookmark this Post
KarishmaB Hey, Karishma
I understand how you approached this problem (general trend was focused), while Chetan2U paid attention to differences between each year. I did take the same way you took, and I see both of you're experts. But whose strtgy is more correct here? Please clarify. I thought that we need a general trend, which can be seen by looking at the 1st and the last year numbers (if in the 1st year it was 10% and in the last year it was 15%, then there was an in crease), so if this is the case with both age groups, then a positive correlation is chosen.

Thank you
User avatar
KarishmaB
Joined: 16 Oct 2010
Last visit: 18 Nov 2025
Posts: 16,265
Own Kudos:
Given Kudos: 482
Location: Pune, India
Expert
Expert reply
Active GMAT Club Expert! Tag them with @ followed by their username for a faster response.
Posts: 16,265
Kudos: 76,982
Kudos
Add Kudos
Bookmarks
Bookmark this Post
Batka
KarishmaB Hey, Karishma
I understand how you approached this problem (general trend was focused), while Chetan2U paid attention to differences between each year. I did take the same way you took, and I see both of you're experts. But whose strtgy is more correct here? Please clarify. I thought that we need a general trend, which can be seen by looking at the 1st and the last year numbers (if in the 1st year it was 10% and in the last year it was 15%, then there was an in crease), so if this is the case with both age groups, then a positive correlation is chosen.

Thank you

There is nothing called "more correct" strategy. There are various strategies people use to evaluate a question based on what works better for them. You use whatever you feel is more intuitive to you - the answer is correct in either case. Also, if looking at a general trend, you cannot focus on only the first and last year numbers - you see whether usually numbers are moving in one direction. Since technically every case with an r > 0 is positive correlation (even if it is low), "no positive correlation" will typically be a case of "negative correlation" on GMAT since we need to get the answer with observation. There won't be any confusion.
User avatar
elainejames
Joined: 26 Dec 2024
Last visit: 14 Nov 2025
Posts: 1
Given Kudos: 8
Posts: 1
Kudos: 0
Kudos
Add Kudos
Bookmarks
Bookmark this Post
KishoreSuravarapu
Is the positive correlation mean generic?? I see if we go for specific comparison for every year- there are cases of negative relation also.
Positive/Negative correlation also comes with an anomaly. As long as the majority or overall data points to one direction, it is okay to have one or 2 small deviations
Moderators:
Math Expert
105355 posts
496 posts