SPSS - create histogram of Pearson correlations

Watch
Papayaa
Badges: 1
Rep:
?
#1
Report Thread starter 2 years ago
#1
Hello,

I need to make a histogram with the Pearson correlations I calculated with SPSS to see how the correlations are distributed. When I click on the output table I am somewhat able to make one, but this includes also the correlation of Variable1 with Variable1 (=1) which I of course do not need.

Is there any other possibility? Can I make a new variable with the Pearson correlations for the datas? In case someone wants to suggest it: A scatterplot won't do the job for me, I want to be able to see easily how many correlations are between 0.3 - 0.5 or -.3, -.5 etc.

I appreciate any help, as even google fails to help me with this problem!
0
reply
Magdatrix >_<
Badges: 17
Rep:
?
#2
Report 2 years ago
#2
(Original post by Papayaa)
Hello,

I need to make a histogram with the Pearson correlations I calculated with SPSS to see how the correlations are distributed. When I click on the output table I am somewhat able to make one, but this includes also the correlation of Variable1 with Variable1 (=1) which I of course do not need.

Is there any other possibility? Can I make a new variable with the Pearson correlations for the datas? In case someone wants to suggest it: A scatterplot won't do the job for me, I want to be able to see easily how many correlations are between 0.3 - 0.5 or -.3, -.5 etc.

I appreciate any help, as even google fails to help me with this problem!
How many variables do you have? What hypotheses are you testing?

You're right in saying you do not need the V1=V1 correlations - these should form a diagonal line across the table, and you can also disregard either everything above that or everything below that as it is repeated information.

It will probably be more meaningful to find and report which of the correlations are significant than how many of each strength.
0
reply
Papayaa
Badges: 1
Rep:
?
#3
Report Thread starter 2 years ago
#3
(Original post by Magdatrix >_<)
How many variables do you have? What hypotheses are you testing?

You're right in saying you do not need the V1=V1 correlations - these should form a diagonal line across the table, and you can also disregard either everything above that or everything below that as it is repeated information.

It will probably be more meaningful to find and report which of the correlations are significant than how many of each strength.
Oh I thought those informations are unnecessary, sorry!
I have 4 variables, 2 for timeframe a and 2 for timeframe b, which I correlate with another variable for both times frames. I therefore do 4 correlations, split by 40 participants. I want to test the hypothesis if the majority of correlations will be moderately positive.

In my written report I do exactly what you suggested: mention the significant ones, how many, of which strength. I nevertheless wanted to make a graph (honestly just because my supervisor asked for this specific graph) where I highlight the significant ones.
Or would you suggest to omit the insignificant results completely? Because then I do not have many correlations left, with which I can either make a graph manually or for which a graph is of no value.
0
reply
X

Quick Reply

Attached files
Write a reply...
Reply
new posts
Back
to top
Latest
My Feed

See more of what you like on
The Student Room

You can personalise what you see on TSR. Tell us a little about yourself to get started.

Personalise

Have you experienced financial difficulties as a student due to Covid-19?

Yes, I have really struggled financially (22)
14.01%
I have experienced some financial difficulties (42)
26.75%
I haven't experienced any financial difficulties and things have stayed the same (65)
41.4%
I have had better financial opportunities as a result of the pandemic (23)
14.65%
I've had another experience (let us know in the thread!) (5)
3.18%

Watched Threads

View All