larsen jsm2003

Information about larsen jsm2003

Published on October 29, 2007

Author: Arley33

Source: authorstream.com

Content

Comparison of Alternative Latent Class Clusterings of Survey Data:  Comparison of Alternative Latent Class Clusterings of Survey Data Michael D. Larsen University of Chicago/ Iowa State University Outline:  Outline Survey and variables Latent class models Comparing clusterings Some comparisons Conclusions and future plans Survey:  Survey 1997 Survey of Doctoral Recipients NSF survey every 2 years 1 of 3 surveys in SESTAT database Respondents PhDs 1990-1996 Physical (n=2216) and biological (n=1019) sciences, engineering (n=516) Work in higher educational institutions Variables:  Variables Demographics: Sex, Race, Ethnicity, Age, etc. %F: biology (49%), physical (33%), eng. (23%) Several sets on career preparation Limitations on career path job searches Work activities Job search resources (which used?) Adequacy of PhD program career preparation Assorted other questions (e.g., postdoc?) One set of variables example:  One set of variables example Adequacy of career preparation Very adequate vs. Somewhat or not adeq. 11 areas (211 table) Biology, 3 significant differences, F vs. M Communication (F>M) z= 2.73 Ethics (F>M) z= 2.48 Computer (M>F) z= -2.58 Why cluster?:  Why cluster? Interest in clusters themselves Are there identifiable groups? Are clusters stable over time? Are the clusters related to demographic subpopulations? How do outcomes vary across clusters? Latent Class Models:  Latent Class Models G latent classes (subpopulations) K categorical variables define contingency table, each person in one cell of table Observed pattern of responses in table is mixture of patterns from latent classes. Response probability on each variable (conditionally) independent within each class (prob’s differ across classes). Latent Class Models, cont.:  Latent Class Models, cont. P(response pattern) = sum over classes of [ P(class) P(response pattern | class) ] EM algorithm (Dempster, Laird, Rubin 1977) Compute P(class | response pattern). Comparing clusterings:  Comparing clusterings Different sets of variables will group respondents differently. Cross tabulations Adjusted Rand Index (ARI) Rand Index = # of pairs in same cluster ARI = (Rand – Exp.)/(Max –Exp.) -- assumes hyper geometric distribution Calibrating the ARI (or other):  Calibrating the ARI (or other) Simulation Generate 1000 samples from the hyper geometric distribution, which corresponds to null of no association Compute ARI for 1000 samples Report # of samples >= ARIobserved A comparison:  A comparison Biology, Adequacy of Career Preparation Communication, ARI = 0.002, tail = 0.015 Ethics, ARI = 0.039, tail = 0.039 Computer, ARI = 0.002, tail = 0.021 4 latent classes (interesting patterns) ARI value is lower, tail area is larger Comments:  Comments ARI values are not large (not near 1) for tables with large n Simulated values are similar to P-values from standard tests Small ARI values can be significant in the way that small log odds (near 0) can be significant for large n Latent classes fit better than simple classifications, but ARI doesn’t increase. More on comment 4.:  More on comment 4. Two classes (females, males) and CI. vs. Four latent classes (based on BCI) and CI. Latter fits (much) better. ARI not larger than largest on individual variables. Future plans:  Future plans 1. Repeat on next waves (1999, 2001) 2. Additional comparison methods: Diversity measures Slight modification of ARI Machine Learning, Stats, Discovery, 2003, Marina Meila, U of Washington 3. Missing data (DK, RF, Missing) References:  References Larsen, Statistics in Transition, 2003 Larsen, submitted to “Retaining Women in Early Academic SMET Careers,” 2002, under revision Hubert and Arabie, 1985, J. of Classification NSF, EIA-0089930, ITWF Contact Information:  Contact Information Mike Larsen, U of Chicago, Statistics [email protected] http://galton.uchicago.edu/~larsen/jsm03 Email for contact at Iowa State University, Statistics

Related presentations


Other presentations created by Arley33

Cold Weather Safety
02. 01. 2008
0 views

Cold Weather Safety

TEN RULES OF FIREARM SAFETY
26. 02. 2008
0 views

TEN RULES OF FIREARM SAFETY

How to succeed
02. 10. 2007
0 views

How to succeed

The Internet Motion Sensor
07. 10. 2007
0 views

The Internet Motion Sensor

Xraydiffraction 2007
12. 10. 2007
0 views

Xraydiffraction 2007

CHM1222Chromatograph yTheory
16. 10. 2007
0 views

CHM1222Chromatograph yTheory

student chap21
17. 10. 2007
0 views

student chap21

Imperialism and World War I
22. 10. 2007
0 views

Imperialism and World War I

kr spam hacking status
11. 09. 2007
0 views

kr spam hacking status

tiger
11. 09. 2007
0 views

tiger

019
11. 09. 2007
0 views

019

tsg0502 10
09. 10. 2007
0 views

tsg0502 10

atomsmoleculesandions
16. 10. 2007
0 views

atomsmoleculesandions

wipo ip mct 05 3
25. 10. 2007
0 views

wipo ip mct 05 3

Adam Smith Krestinskiy
26. 10. 2007
0 views

Adam Smith Krestinskiy

ROK CP
11. 09. 2007
0 views

ROK CP

R LANQUAR FEMIP
23. 10. 2007
0 views

R LANQUAR FEMIP

rmode potsdam04
15. 11. 2007
0 views

rmode potsdam04

how to spot a turkey
26. 11. 2007
0 views

how to spot a turkey

052407 Gascon
14. 12. 2007
0 views

052407 Gascon

15 whiteCWppt
22. 11. 2007
0 views

15 whiteCWppt

PPA724 queries
28. 09. 2007
0 views

PPA724 queries

IPv6 Forum World Congress Europe
07. 01. 2008
0 views

IPv6 Forum World Congress Europe

v short lcg
17. 10. 2007
0 views

v short lcg

click construct
02. 11. 2007
0 views

click construct

symp apr 02 page e
15. 10. 2007
0 views

symp apr 02 page e

Model PÃster horitzontal
16. 11. 2007
0 views

Model PÃster horitzontal

NTS 101
16. 02. 2008
0 views

NTS 101

ENG 40B DR Mathias P Point
20. 02. 2008
0 views

ENG 40B DR Mathias P Point

Nichols Schwartz 05 Bowenian
24. 02. 2008
0 views

Nichols Schwartz 05 Bowenian

swartz
17. 10. 2007
0 views

swartz

ON VECTOR 022707 final
19. 10. 2007
0 views

ON VECTOR 022707 final

EducationalPowerpoint
19. 11. 2007
0 views

EducationalPowerpoint

lectures256p3
07. 12. 2007
0 views

lectures256p3

W03 Late Ming 3 Lives b
26. 03. 2008
0 views

W03 Late Ming 3 Lives b

germany 1 27 05
07. 04. 2008
0 views

germany 1 27 05

EH HL3 MP TWG1
30. 03. 2008
0 views

EH HL3 MP TWG1

ustrans
10. 04. 2008
0 views

ustrans

CAP12PP2
13. 04. 2008
0 views

CAP12PP2

Dr Jongkon
14. 04. 2008
0 views

Dr Jongkon

WEBS0104
16. 04. 2008
0 views

WEBS0104

Deb Tairas presentation
17. 04. 2008
0 views

Deb Tairas presentation

silverman 06
19. 02. 2008
0 views

silverman 06

SAB EPEAT 050608
28. 04. 2008
0 views

SAB EPEAT 050608

Macsim Mihai
18. 03. 2008
0 views

Macsim Mihai

martes manyana 5a presentacion
28. 12. 2007
0 views

martes manyana 5a presentacion

korea otonwu06
11. 09. 2007
0 views

korea otonwu06

PHYCS 199B Oct 29 2002
15. 10. 2007
0 views

PHYCS 199B Oct 29 2002

Ryan Henry
23. 12. 2007
0 views

Ryan Henry

ewilaya eforumALAMI 2007
23. 10. 2007
0 views

ewilaya eforumALAMI 2007

ELAN
05. 10. 2007
0 views

ELAN

BELIZE
22. 10. 2007
0 views

BELIZE

Sheena Kim
11. 09. 2007
0 views

Sheena Kim

moscow11
15. 10. 2007
0 views

moscow11

Gavrilova PAA 2005
12. 10. 2007
0 views

Gavrilova PAA 2005

mirror darts
29. 12. 2007
0 views

mirror darts

bruxelles dd
17. 10. 2007
0 views

bruxelles dd

EC Baron DCC abridged
11. 03. 2008
0 views

EC Baron DCC abridged

Image53967
07. 01. 2008
0 views

Image53967

GSA dlese teaching boxes
30. 10. 2007
0 views

GSA dlese teaching boxes

Illarionovs Projections
26. 10. 2007
0 views

Illarionovs Projections