Hi all,
I have two questions relating to QAP in UCINET.
1. MR-QAP and LR-QAP application in binary network
After reading the chapter8 of ASN, I am wondering that the relationship between MR-QAP and LR-QAP is the same as between their analogues in logit and ordinary regression; and MR-QAP is more suitable for valued dependent variable and LR-QAP is more suitable for binary dependent variable? However, I find that some binary cases like the high-tec example is analysed by MR-QAP. Or may MR-QAP works in both cases? ??
2.coefficient comparison
I have two different undirected collaborative networks: N1(35*35) and N2(41*41). And I want to run QAP to (1) examine factors predicting collaboration (homophily, sender effect, and transitivity; the identical model specification, but the outcome objects are different); (2) explore the relative contribution of above effects within network; (3) and compare the strength of certain effect across QAPs (e.g. is the homophily effect in N1 stronger than N2). Could I ues MR-QAP and compare the standardized coefficient of N1 model and N2 model and run T-test?
Any information would be appreciated. Thank you!
Best,
Longxia Huo
Ph.D. Student
|
Thanks. I only have a few days to do this, so ideally, really looking for some 1 to 1.
|
There is an amazing book that will help you understand SNA.
Analyzing Social Networks by Stephen Borgatti, Martin Everett and Jeffrey C Johnson
best!
On Monday, June 13, 2022, 07:15:37 AM EDT, Dr. Tariq Ahmad PhD <tariqnahmad@...> wrote:
hi
?
I am a newbie to UCINET and need some one-to-one help on some seemingly basic tasks, e.g. extract data from a network, compare graphs. Happy to pay for your time.
?
Thank you.
|
hi
?
I am a newbie to UCINET and need some one-to-one help on some seemingly basic tasks, e.g. extract data from a network, compare graphs. Happy to pay for your time.
?
Thank you.
|
Age, CSS performance data set
Dear Networkers
?i am looking for a publicly available data set (like Krackhardt, 1990) that includes the following
1) demographics data
2) CSS (friendship and advice)
3) Performance ratings.
Any guidance on how to get such a dataset or the performance measures for Krackhardt's dataset would be greatly appreciated.
Thank you in advance?
Prasad Balkundi
SUNY Buffalo
|
On Fri, Jun 10, 2022 at 07:50 AM, Steve Borgatti wrote:
滨苍蝉迟补濒濒.辫补肠办补驳别蝉(“蝉苍补”)
Looks this is working know, tnx? p? ? ?(-:
|
|
|
Hi,
I've got this?xUCINET_0.0.1.0022.zip from:
|
In general with R, if you are installing something and it says something like
?
“there is no package called ‘sna’”
?
Then you can just install the missing package, as in :
?
滨苍蝉迟补濒濒.辫补肠办补驳别蝉(“蝉苍补”)
?
Then do the library command again.
?
Btw, which version of xucinet is this?
?
steve
?
toggle quoted message
Show quoted text
From: [email protected] < [email protected]> On Behalf Of
Paulo Matui via groups.io
Sent: Friday, June 10, 2022 10:40
To: [email protected]
Subject: Re: [ucinet] xUCINET installation
?
?
Hi,
I'm trying to install xUCINET, and it is returnig:
?install.packages("blockmodeling")
Installing package into ‘C:/Users/paulo/AppData/Local/R/win-library/4.2’
(as ‘lib’ is unspecified)
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.2/blockmodeling_1.0.5.zip'
Content type 'application/zip' length 415153 bytes (405 KB)
package ‘blockmodeling’ successfully unpacked and MD5 sums checked
The downloaded binary packages are in
C:\Users\paulo\AppData\Local\Temp\RtmpG0UAUC\downloaded_packages
Error: package or namespace load failed for ‘xUCINET’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]):
?there is no package called ‘sna’
I'm doing this on
RStudio 2022.02.3+492 "Prairie Trillium" Release (1db809b8323ba0a87c148d16eb84efe39a8e7785, 2022-05-20) for Windows
Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) QtWebEngine/5.12.8 Chrome/69.0.3497.128 Safari/537.36
Should I fall back to a previous version?
saluti
p
|
Hi, I'm trying to install xUCINET, and it is returnig:
?install.packages("blockmodeling")
Installing package into ‘C:/Users/paulo/AppData/Local/R/win-library/4.2’
(as ‘lib’ is unspecified)
trying URL 'https://cran.rstudio.com/bin/windows/contrib/4.2/blockmodeling_1.0.5.zip'
Content type 'application/zip' length 415153 bytes (405 KB)
downloaded 405 KB
?
package ‘blockmodeling’ successfully unpacked and MD5 sums checked
?
The downloaded binary packages are in
C:\Users\paulo\AppData\Local\Temp\RtmpG0UAUC\downloaded_packages
> library("xUCINET")
Error: package or namespace load failed for ‘xUCINET’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]):
?there is no package called ‘sna’
I'm doing this on
RStudio 2022.02.3+492 "Prairie Trillium" Release (1db809b8323ba0a87c148d16eb84efe39a8e7785, 2022-05-20) for Windows
Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) QtWebEngine/5.12.8 Chrome/69.0.3497.128 Safari/537.36
Should I fall back to a previous version?
saluti
p
|
Re: Component Ratio calculation to a node adjacent matrix
#help
Professor, Great, which means that, if I multiply the result?over a subgraph?by (Nsub-1), I'll get the number of eulerian cycles where it is not isolated or strong by itself - the digraph case where the node has only in-degree or out-degree. So, it is feasible?to calculate the number of eulerian cycles that a node is part in its directional adjacent matrix,?including ties among the adjacent nodes. Then, the point is how to generate the adjacent subgraph? I can generate subgraph from a partition vector, but the best for my research is if there is a way to extract the adjacent submatrix of a node.
The theoretical approach of this model comes from Padgett, J. F. (1997) - The emergence of simple ecologies of skills. The organizational learning process is treated as cycles. From the field side, some of the informants confirmed they use multiple allocation practices to induce results in quality, productivity?and relevance in the HEI research?community, some not. I want to triangulate objective?data, and perhaps correlates individual categories.? Em qua., 8 de jun. de 2022 às 09:03, Steve Borgatti < sborgatti@...> escreveu:
Yes, it uses the Tarjan depth-first search algorithm
Steve Borgatti
LINKS Center for Social Network Analysis
?
Hi Professor,
I know, I?did this analysis?with this metric in the figure attached. Actually, reading my?research notes I have a question about the CR metric. It is the number of components minus 1 divided?by the number of
nodes minus 1. To achieve the number of strong components in a digraph, does UCINET?use the in-depth research from Robert Tarjan (1972)?
This is the population of Administration and Industrial Engineer??research departments in Brazilian HEIs, the ties are teachers who teach?in more?than 1 research department.?
paulo
Paulo, the component ratio is something you calculate for the whole network. It measures the extent to which the network is broken up into fragments. In UCINET you can calculate it by going to network|whole
networks|multiple measures. For your directed data, you need to decide whether to respect direction or ignore it. I ran it both ways and got the below. First column is ignoring direction and the second is respecting direction.
?
?
?????????????????????????????????? 1????????? 2
??????????????????????????000_2020_C 000_2020_C
??????????????????????????ONS_ACAD_t ONS_ACAD_t
??????????????????????????o_PROF-coh o_PROF-coh
???????????????????????????????????u????????? d
??????????????????????????---------- ----------
????1???????? # of nodes???? 317.000??? 317.000
????2????????? # of ties???? 740.000??? 416.000
????3???????? Avg Degree?????? 2.334????? 1.312
????4????? Indeg H-Index?????? 7.000????? 5.000
????5?????? K-core index?????? 4.000????? 4.000
????6 Deg Centralization?????? 0.075????? 0.075
????7 Out-Centralization?????? 0.075????? 0.021
????8? In-Centralization?????? 0.075????? 0.066
????9???????? Indeg Corr?????? 0.062????? 0.056
???10??????? Outdeg Corr?????? 0.062????? 0.027
???11??????????? Density?????? 0.007????? 0.004
???12???????? Components????? 54.000??? 241.000
???13??? Component Ratio?????? 0.168????? 0.759
???14????? Connectedness?????? 0.513????? 0.062
???15????? Fragmentation?????? 0.487????? 0.938
???16??????????? Closure?????? 0.186????? 0.135
???17?????? Avg Distance?????? 6.021????? 4.506
???18????? Prop within 3?????? 0.074????? 0.019
???19?????????? # w/in 3??? 7390.000?? 1861.000
???20??????? SD Distance?????? 2.408????? 1.884
???21?????????? Diameter????? 16.000???? 11.000
???22?????? Wiener Index? 309716.000? 28206.000
???23???? Dependency Sum? 258280.000? 21947.000
???24??????????? Breadth?????? 0.894????? 0.982
???25??????? Compactness?????? 0.106????? 0.018
???26??? Small Worldness???????????????????????
???27??????????? Mutuals?????? 0.007????? 0.001
???28??????? Asymmetrics?????? 0.000????? 0.006
???29????? ????????Nulls?????? 0.993????? 0.993
???30??? Arc Reciprocity?????? 1.000????? 0.221
???31?? Dyad Reciprocity?????? 1.000????? 0.124
?
Having looked at your data, I’m not sure the component ratio would be very useful. If we ignore direction, your data consist of a single large component containing 72% of all nodes, and many many tiny
components that are just isolates or dyads.
?
?
The picture seems more valuable than the statistic.
?
steve
?
?
?
Hi all,
I have the directional networks from 1990 to 2020 - the files attached belongs to 2020, and I'm trying to calculate the component ratio of each node adjacent matrix, icluding the ties among adjacent nodes. Does any one have an idea how to generate automatically
the sub-digraphs for the calculation?
Saluti?
matui
--
Paulo Matui
12 98122 6600
|
Re: Component Ratio calculation to a node adjacent matrix
#help
Yes, it uses the Tarjan depth-first search algorithm
Steve Borgatti
LINKS Center for Social Network Analysis
toggle quoted message
Show quoted text
On Jun 8, 2022, at 07:59, Paulo Matui <paulo.matui@...> wrote:
?
Hi Professor,
I know, I?did this analysis?with this metric in the figure attached. Actually, reading my?research notes I have a question about the CR metric. It is the number of components minus 1 divided?by the number of
nodes minus 1. To achieve the number of strong components in a digraph, does UCINET?use the in-depth research from Robert Tarjan (1972)?
This is the population of Administration and Industrial Engineer??research departments in Brazilian HEIs, the ties are teachers who teach?in more?than 1 research department.?
paulo
Paulo, the component ratio is something you calculate for the whole network. It measures the extent to which the network is broken up into fragments. In UCINET you can calculate it by going to network|whole
networks|multiple measures. For your directed data, you need to decide whether to respect direction or ignore it. I ran it both ways and got the below. First column is ignoring direction and the second is respecting direction.
?
?
?????????????????????????????????? 1????????? 2
??????????????????????????000_2020_C 000_2020_C
??????????????????????????ONS_ACAD_t ONS_ACAD_t
??????????????????????????o_PROF-coh o_PROF-coh
???????????????????????????????????u????????? d
??????????????????????????---------- ----------
????1???????? # of nodes???? 317.000??? 317.000
????2????????? # of ties???? 740.000??? 416.000
????3???????? Avg Degree?????? 2.334????? 1.312
????4????? Indeg H-Index?????? 7.000????? 5.000
????5?????? K-core index?????? 4.000????? 4.000
????6 Deg Centralization?????? 0.075????? 0.075
????7 Out-Centralization?????? 0.075????? 0.021
????8? In-Centralization?????? 0.075????? 0.066
????9???????? Indeg Corr?????? 0.062????? 0.056
???10??????? Outdeg Corr?????? 0.062????? 0.027
???11??????????? Density?????? 0.007????? 0.004
???12???????? Components????? 54.000??? 241.000
???13??? Component Ratio?????? 0.168????? 0.759
???14????? Connectedness?????? 0.513????? 0.062
???15????? Fragmentation?????? 0.487????? 0.938
???16??????????? Closure?????? 0.186????? 0.135
???17?????? Avg Distance?????? 6.021????? 4.506
???18????? Prop within 3?????? 0.074????? 0.019
???19?????????? # w/in 3??? 7390.000?? 1861.000
???20??????? SD Distance?????? 2.408????? 1.884
???21?????????? Diameter????? 16.000???? 11.000
???22?????? Wiener Index? 309716.000? 28206.000
???23???? Dependency Sum? 258280.000? 21947.000
???24??????????? Breadth?????? 0.894????? 0.982
???25??????? Compactness?????? 0.106????? 0.018
???26??? Small Worldness???????????????????????
???27??????????? Mutuals?????? 0.007????? 0.001
???28??????? Asymmetrics?????? 0.000????? 0.006
???29????? ????????Nulls?????? 0.993????? 0.993
???30??? Arc Reciprocity?????? 1.000????? 0.221
???31?? Dyad Reciprocity?????? 1.000????? 0.124
?
Having looked at your data, I’m not sure the component ratio would be very useful. If we ignore direction, your data consist of a single large component containing 72% of all nodes, and many many tiny
components that are just isolates or dyads.
?
?
The picture seems more valuable than the statistic.
?
steve
?
?
?
Hi all,
I have the directional networks from 1990 to 2020 - the files attached belongs to 2020, and I'm trying to calculate the component ratio of each node adjacent matrix, icluding the ties among adjacent nodes. Does any one have an idea how to generate automatically
the sub-digraphs for the calculation?
Saluti?
matui
--
Paulo Matui
12 98122 6600
|
Re: Component Ratio calculation to a node adjacent matrix
#help
Hi Professor,
I know, I?did this analysis?with this metric in the figure attached. Actually, reading my?research notes I have a question about the CR metric. It is the number of components minus 1 divided?by the number of nodes minus 1. To achieve the number of strong components in a digraph, does UCINET?use the in-depth research from Robert Tarjan (1972)? This is the population of Administration and Industrial Engineer??research departments in Brazilian HEIs, the ties are teachers who teach?in more?than 1 research department.?
paulo
Paulo, the component ratio is something you calculate for the whole network. It measures the extent to which the network is broken up into fragments. In UCINET you can calculate it by going to network|whole networks|multiple measures. For your directed data, you need to decide whether to respect direction or ignore it. I ran it both ways and got the below. First column is ignoring direction and the second is respecting direction. ? ? ?????????????????????????????????? 1????????? 2 ??????????????????????????000_2020_C 000_2020_C ??????????????????????????ONS_ACAD_t ONS_ACAD_t ??????????????????????????o_PROF-coh o_PROF-coh ???????????????????????????????????u????????? d ??????????????????????????---------- ---------- ????1???????? # of nodes???? 317.000??? 317.000 ????2????????? # of ties???? 740.000??? 416.000 ????3???????? Avg Degree?????? 2.334????? 1.312 ????4????? Indeg H-Index?????? 7.000????? 5.000 ????5?????? K-core index?????? 4.000????? 4.000 ????6 Deg Centralization?????? 0.075????? 0.075 ????7 Out-Centralization?????? 0.075????? 0.021 ????8? In-Centralization?????? 0.075????? 0.066 ????9???????? Indeg Corr?????? 0.062????? 0.056 ???10??????? Outdeg Corr?????? 0.062????? 0.027 ???11??????????? Density?????? 0.007????? 0.004 ???12???????? Components????? 54.000??? 241.000 ???13??? Component Ratio?????? 0.168????? 0.759 ???14????? Connectedness?????? 0.513????? 0.062 ???15????? Fragmentation?????? 0.487????? 0.938 ???16??????????? Closure?????? 0.186????? 0.135 ???17?????? Avg Distance?????? 6.021????? 4.506 ???18????? Prop within 3?????? 0.074????? 0.019 ???19?????????? # w/in 3??? 7390.000?? 1861.000 ???20??????? SD Distance?????? 2.408????? 1.884 ???21?????????? Diameter????? 16.000???? 11.000 ???22?????? Wiener Index? 309716.000? 28206.000 ???23???? Dependency Sum? 258280.000? 21947.000 ???24??????????? Breadth?????? 0.894????? 0.982 ???25??????? Compactness?????? 0.106????? 0.018 ???26??? Small Worldness??????????????????????? ???27??????????? Mutuals?????? 0.007????? 0.001 ???28??????? Asymmetrics?????? 0.000????? 0.006 ???29????? ????????Nulls?????? 0.993????? 0.993 ???30??? Arc Reciprocity?????? 1.000????? 0.221 ???31?? Dyad Reciprocity?????? 1.000????? 0.124 ? Having looked at your data, I’m not sure the component ratio would be very useful. If we ignore direction, your data consist of a single large component containing 72% of all nodes, and many many tiny components that are just isolates or dyads. ? 
? The picture seems more valuable than the statistic. ? steve ? ? ? Hi all,
I have the directional networks from 1990 to 2020 - the files attached belongs to 2020, and I'm trying to calculate the component ratio of each node adjacent matrix, icluding the ties among adjacent nodes. Does any one have an idea how to generate automatically the sub-digraphs for the calculation?
Saluti?
matui
|
Re: Component Ratio calculation to a node adjacent matrix
#help
Paulo, the component ratio is something you calculate for the whole network. It measures the extent to which the network is broken up into fragments. In UCINET you can calculate it by going to network|whole networks|multiple measures. For your directed data, you need to decide whether to respect direction or ignore it. I ran it both ways and got the below. First column is ignoring direction and the second is respecting direction. ? ? ?????????????????????????????????? 1????????? 2 ??????????????????????????000_2020_C 000_2020_C ??????????????????????????ONS_ACAD_t ONS_ACAD_t ??????????????????????????o_PROF-coh o_PROF-coh ???????????????????????????????????u????????? d ??????????????????????????---------- ---------- ????1???????? # of nodes???? 317.000??? 317.000 ????2????????? # of ties???? 740.000??? 416.000 ????3???????? Avg Degree?????? 2.334????? 1.312 ????4????? Indeg H-Index?????? 7.000????? 5.000 ????5?????? K-core index?????? 4.000????? 4.000 ????6 Deg Centralization?????? 0.075????? 0.075 ????7 Out-Centralization?????? 0.075????? 0.021 ????8? In-Centralization?????? 0.075????? 0.066 ????9???????? Indeg Corr?????? 0.062????? 0.056 ???10??????? Outdeg Corr?????? 0.062????? 0.027 ???11??????????? Density?????? 0.007????? 0.004 ???12???????? Components????? 54.000??? 241.000 ???13??? Component Ratio?????? 0.168????? 0.759 ???14????? Connectedness?????? 0.513????? 0.062 ???15????? Fragmentation?????? 0.487????? 0.938 ???16??????????? Closure?????? 0.186????? 0.135 ???17?????? Avg Distance?????? 6.021????? 4.506 ???18????? Prop within 3?????? 0.074????? 0.019 ???19?????????? # w/in 3??? 7390.000?? 1861.000 ???20??????? SD Distance?????? 2.408????? 1.884 ???21?????????? Diameter????? 16.000???? 11.000 ???22?????? Wiener Index? 309716.000? 28206.000 ???23???? Dependency Sum? 258280.000? 21947.000 ???24??????????? Breadth?????? 0.894????? 0.982 ???25??????? Compactness?????? 0.106????? 0.018 ???26??? Small Worldness??????????????????????? ???27??????????? Mutuals?????? 0.007????? 0.001 ???28??????? Asymmetrics?????? 0.000????? 0.006 ???29????? ????????Nulls?????? 0.993????? 0.993 ???30??? Arc Reciprocity?????? 1.000????? 0.221 ???31?? Dyad Reciprocity?????? 1.000????? 0.124 ? Having looked at your data, I’m not sure the component ratio would be very useful. If we ignore direction, your data consist of a single large component containing 72% of all nodes, and many many tiny components that are just isolates or dyads. ? 
? The picture seems more valuable than the statistic. ? steve ? ?
toggle quoted message
Show quoted text
From: [email protected] < [email protected]> On Behalf Of Paulo Matui Sent: Tuesday, June 7, 2022 15:01 To: [email protected]Subject: [ucinet] Component Ratio calculation to a node adjacent matrix #help ? Hi all,
I have the directional networks from 1990 to 2020 - the files attached belongs to 2020, and I'm trying to calculate the component ratio of each node adjacent matrix, icluding the ties among adjacent nodes. Does any one have an idea how to generate automatically the sub-digraphs for the calculation?
Saluti?
matui
|
Component Ratio calculation to a node adjacent matrix
#help
Hi all,
I have the directional networks from 1990 to 2020 - the files attached belongs to 2020, and I'm trying to calculate the component ratio of each node adjacent matrix, icluding the ties among adjacent nodes. Does any one have an idea how to generate automatically the sub-digraphs for the calculation?
Saluti?
matui
|
Re: Drawing graphs without alter-to-alter ties
Thank you for the video and the quick answer with a change to UCINET. Very clearly explained.? I will try this, thanks again appreciate this help, Prof. Borgatti.
|
Re: Drawing graphs without alter-to-alter ties
I made a quick change to UCINET to let you visualize those ego networks. You need to
, 6.750, and then run Transform|Egotize. Here’s a video on how to do it:
?
?
steve
?
toggle quoted message
Show quoted text
From: [email protected] < [email protected]> On Behalf Of
ozlemozkok via groups.io
Sent: Wednesday, June 1, 2022 06:10
To: [email protected]
Subject: Re: [ucinet] Drawing graphs without alter-to-alter ties
?
?
Thanks, Prof Borgatti. I can do this, great idea. My data has all the ties in a square matrix (all 1s as having a tie, 0 for no tie), I don't know how to differentiate and code them actually. Any guidance for this is appreciated :) Thanks.
|
Re: Drawing graphs without alter-to-alter ties
Thanks, Prof Borgatti. I can do this, great idea. My data has all the ties in a square matrix (all 1s as having a tie, 0 for no tie), I don't know how to differentiate and code them actually. Any guidance for this is appreciated :) Thanks.
|
Re: Drawing graphs without alter-to-alter ties
Hard to say without knowing more about your data. One obvious thing that may or may not be practical is to code alter-alter ties 1, and code ego-alter ties 2. Then in Netdraw, you can set the filter to show only
ties with strength > 1
?
steve
?
toggle quoted message
Show quoted text
From: [email protected] < [email protected]> On Behalf Of
ozlemozkok via groups.io
Sent: Tuesday, May 31, 2022 09:00
To: [email protected]
Subject: [ucinet] Drawing graphs without alter-to-alter ties
?
?
Hi Everyone,
I am trying to show some ego connections to different alters in NetDraw, is there a way to model only ego's ties? Thanks for your time :)
Ozzie
|
Hi Reut, sorry your email got stuck in the queue. If you are still having a problem, feel free to send me the data (sborgatti@...). You can send either the ucinet files
(don’t forget to include both the ##h and ##d files) or Excel.
?
steve
?
toggle quoted message
Show quoted text
From: [email protected] < [email protected]> On Behalf Of
Reut Liraz via groups.io
Sent: Thursday, May 19, 2022 06:49
To: [email protected]
Subject: [ucinet] E-I index calculation - Ego Networks. #egonetworks
?
?
Hello,?
I am trying to calculate ego-alter similarity via UCINET, however, although my net and attribute data are completely symmetrical on the Excell sheet? (both contain 192 rows), on the UCINET I receive different rows' sizes.
When I input the files into Netdraw it works smoothly, without any warning.
However, trying to calculate the E-I index, I receive an "Attribute vector must be the same size as matrix rows" notice.
Maybe someone can help solve this issue,
Thank you
Reut Liraz
|
Paulo Matui
