Please kindly advice

[maggieho]

Hi,

I am analyzing the relationship between HbA1c (measure in %) and skin thickness (measure in mm) using pearson's correlation but I would also like to know whether gender(nominal data) and diabetic duration(years) are covariate.  Can you please advise on which test I should use to control for gender and diabetic duration in this case? Thank you for your time.

Regards,
Maggie

[Bruce Weaver]

Assuming one of those variables is seen as dependent on the other, you can use REGRESSION with values of 0 and 1 for gender.  Focus on the coefficient for the explanatory variable of interest rather than the correlation.

Out of curiosity, what is your sample size?  I.e., is it large enough to support a model with 3 explanatory variables?

HTH.

maggieho wrote

Hi,

I am analyzing the relationship between HbA1c (measure in %) and skin thickness (measure in mm) using pearson's correlation but I would also like to know whether gender(nominal data) and diabetic duration(years) are covariate.  Can you please advise on which test I should use to control for gender and diabetic duration in this case? Thank you for your time.

Regards,
Maggie

[maggieho]

Thank you for your prompt reply.

My sample consists of 99 subjects.
I would like to see the whether there is a correlation between HbA1c level and soft tissues thickness after controlling the effects for both "Diabetic Duration" and "gender".  If only controlling diabetic duration (years), I can run partial correlation.  However, if I added gender into the analysis, how shall I do this on spss?  Thank you very mcuh.

[parisec]

Hi Maggieho,

Assuming that soft tissue thickness is a continuous variable, this sounds like a perfect candidate for linear regression analysis using soft tissue thickness as the DV and HbA1c, diabetic duration, and gender as your predictor variables.

Carol

________________________________________
From: SPSSX(r) Discussion [[hidden email]] On Behalf Of maggieho [[hidden email]]
Sent: Saturday, July 09, 2011 12:34 AM
To: [hidden email]
Subject: Re: Please kindly advice

Thank you for your prompt reply.

My sample consists of 99 subjects.
I would like to see the whether there is a correlation between HbA1c level
and soft tissues thickness after controlling the effects for both "Diabetic
Duration" and "gender".  If only controlling diabetic duration (years), I
can run partial correlation.  However, if I added gender into the analysis,
how shall I do this on spss?  Thank you very mcuh.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Please-kindly-advice-tp4537676p4567609.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

[John F Hall]

Partial corr allows for up to 5 levels,so there's no reason why you can't
use "by sex".  Being dichotomous it can be treated as a scale variable.


John F Hall

[hidden email]
www.surveyresearch.weebly.com





Partial corr /variables duration HbA1c by duration by sex.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
maggieho
Sent: 09 July 2011 09:35
To: [hidden email]
Subject: Re: Please kindly advice

Thank you for your prompt reply.

My sample consists of 99 subjects.
I would like to see the whether there is a correlation between HbA1c level
and soft tissues thickness after controlling the effects for both "Diabetic
Duration" and "gender".  If only controlling diabetic duration (years), I
can run partial correlation.  However, if I added gender into the analysis,
how shall I do this on spss?  Thank you very mcuh.

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Please-kindly-advice-tp4537676
p4567609.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD