Analysis of team size on team cohesion scores

[Hannah State-Davey]

All,

I would like to run an analysis to investigate the impact of team size on
team cohesion scores.

For each participant I have collected the number of members they have in
their team.

Should I run a simple ANOVA where the quantitative variables are number of
members in team and total cohesion score; and use a dummy variable where I
assign number of members in team to groups based on some assigned cut-off
value to denote say small, medium, large teams. I can then determine if
there is a significant difference between the means of these groups.

Any thoughts?

Hannah

=====================
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

[Swank, Paul R]

You can determine the relation between team size and cohesion scores but not the impact unless you can randomly assign to team size. I would not categorize the data first. I would do a scatter plot of the variables and if the relation is monotonic, I would use a rank order correlation. If it is fairly linear, you might get by with a simple Pearson's r.

Dr. Paul R. Swank,
Professor and Director of Research
Children's Learning Institute
University of Texas Health Science Center-Houston


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Hannah State-Davey
Sent: Wednesday, April 15, 2009 5:03 AM
To: [hidden email]
Subject: Analysis of team size on team cohesion scores

All,

I would like to run an analysis to investigate the impact of team size on
team cohesion scores.

For each participant I have collected the number of members they have in
their team.

Should I run a simple ANOVA where the quantitative variables are number of
members in team and total cohesion score; and use a dummy variable where I
assign number of members in team to groups based on some assigned cut-off
value to denote say small, medium, large teams. I can then determine if
there is a significant difference between the means of these groups.

Any thoughts?

Hannah

=====================
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

[statisticsdoc]

Hannah,

Are you measuring team cohesion with a survey that you administer to
individual team members (rather than, say, an observational coding of team
interaction),   If the dependent variable is measured at the level of the
individual team member, rather than the team, then I suggest that you
utilize Hierarchical Linear Modeling to investigate the association between
team-level variations in size and between-team variance in cohesion ratings.
This approach will respect the nested nature of the data (i.e., individual
team members are nested within teams).  Within SPSS, hierachical linear
modeling can be carried out using the Mixed Models module.

Hope This Helps,

Stephen Brand

www.StatisticsDoc.com


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]]On Behalf Of
Hannah State-Davey
Sent: Wednesday, April 15, 2009 6:03 AM
To: [hidden email]
Subject: Analysis of team size on team cohesion scores


All,

I would like to run an analysis to investigate the impact of team size on
team cohesion scores.

For each participant I have collected the number of members they have in
their team.

Should I run a simple ANOVA where the quantitative variables are number of
members in team and total cohesion score; and use a dummy variable where I
assign number of members in team to groups based on some assigned cut-off
value to denote say small, medium, large teams. I can then determine if
there is a significant difference between the means of these groups.

Any thoughts?

Hannah

=====================
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

[Hannah State-Davey]

Thank you Stephen for this suggestion - I will definately look further into using Hierarchical Linear Modeling.
 
I have collected data via a survey for each individual team member but what I don't have is a balanced number of people against team size. Knowing nothing (as yet) about hierarchical linear modeling is this a problem? Also is there an alternative technique if my data violates the assumptions - e.g. linearity?
 
 

> From: [hidden email]
> To: [hidden email]; [hidden email]
> Subject: RE: Analysis of team size on team cohesion scores
> Date: Thu, 16 Apr 2009 23:46:01 -0400
>
> Hannah,
>
> Are you measuring team cohesion with a survey that you administer to
> individual team members (rather than, say, an observational coding of team
> interaction), If the dependent variable is measured at the level of the
> individual team member, rather than the team, then I suggest that you
> utilize Hierarchical Linear Modeling to investigate the association between
> team-level variations in size and between-team variance in cohesion ratings.
> This approach will respect the nested nature of the data (i.e., individual
> team members are nested within teams). Within SPSS, hierachical linear
> modeling can be carried out using the Mixed Models module.
>
> Hope This Helps,
>
> Stephen Brand
>
> www.StatisticsDoc.com
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]]On Behalf Of
> Hannah State-Davey
> Sent: Wednesday, April 15, 2009 6:03 AM
> To: [hidden email]
> Subject: Analysis of team size on team cohesion scores
>
>
> All,
>
> I would like to run an analysis to investigate the impact of team size on
> team cohesion scores.
>
> For each participant I have collected the number of members they have in
> their team.
>
> Should I run a simple ANOVA where the quantitative variables are number of
> members in team and total cohesion score; and use a dummy variable where I
> assign number of members in team to groups based on some assigned cut-off
> value to denote say small, medium, large teams. I can then determine if
> there is a significant difference between the means of these groups.
>
> Any thoughts?
>
> Hannah
>
> =====================
> 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
>

---

Share your photos with Windows Live Photos – Free. Try it Now!