Title: Cultural Nuances, Assumptions and the Butterfly Effect: A Prelude
1Cultural Nuances, Assumptions and the Butterfly
EffectA Prelude
- A Brief Introduction
- to
- Generalizability Theory
- for the
- Uninitiated
2What is Generalizability Theory?
-
- Generalizability Theorythe theory that deals
with the degree to which one can say that
conclusions drawn on the basis of data collected
from sampling different domains can be applied
with confidence to those domains.
3Still Lost?
- What were talking about you best know as
instrument reliability. Commonly known examples - inter-rater reliability,
- test-retest reliability,
- split-halves reliability,
- Kuder-Richardson reliabilities,
- Hoyt reliability, and
- Cronbachs alpha
4Test (True) Score Theory
- Observed scores are composed of true scores and
error. - The variance of the observed scores is
partitioned. - Then estimates are combined to produce a
coefficient.
- Xo Xt Xe Xscore,
- ttrue, oobserved, eerror
- So2 St2 Se2
- S2 variance
- r11 St2/So2
5True Score Theory and Generalizability
- Generalizabilty is an extension of true-score
theory. - Sources of Variation are viewed from different
perspectives. - S2O S2LG S2TG S2LS S2TS
- Llong term, Ttemporary Ggeneral,
Sspecific
6So what does this have to do with Multivariate
Analysis?
- All techniques we have studied deals with the
degree of overlap of variance (information) for
sets of variables (Tabachnick Fidell, 2001). In
the present case the overlap of interest is
between observed variance for evaluators
opinions about the spheres involved and the
actual underlying dimensions influencing
interpersonal interactions perceived by the
evaluators--true-score variance. - S2TOT S2E S2V S2Sc S2e
- Eevaluator, Vvignette,Scscale, eerror
7Relationship of Gerneralizability to Multivariance
- To produce the variance estimates needed ANOVA
is used. In this situation a 6 x 7 x 46
Evaluator (E) x Sphere Primary Category (S) x
Vignette (V) Mixed Effects Repeated Measures
ANOVA is used. Evaluator and Vignette are
considered random, Sphere fixed.
8ANOVA DESIGNDoubly Repeated MeasuresScale and
Vignette WithinEvaluator Between
9Table 1 Variance Components Derived from the SPSS
GLM repeated Measures Calculation for Overall
Evaluations  Source of Variation SS
df MS Â Vignette (V) 29.220
45 .649 Â Sphere (S) 639.865
6 106.644 Â Evaluator (E) 61.972
5 12.394 Â V x S
185.516 270 .687 V x E
96.528 225 .429 S x E
340.184 30
11.339 V x S x E Â Error
(e) Â Residual
648.149 1350
.480
10- Table 2
- Variance Components and Expected Mean Squares for
Overall Evaluations - Â
- Source of Variation Means Square (MS) Expected
Mean Square (EMS) Estimated Variance - Â
- Vignette (V) .649 ?2e
?2VE ?2V .220 - Â
- Sphere (S) 106.644 ?2e
?2VS ?2SE ?2S 94.618 - Â
- Evaluator (E) 12.394 ?2e
?2VE ?2E 11.965 - Â
- V x S .687 ?2e ?2VS
.207 - Â
- V x E .429 ?2e ?2VE
-.059 - Â
- S x E 11.339 ?2e ?2SE
10.859 - Â
- V x S x E ?2e ?2VSE .480
- Â
11Table 3 Variance Components Derived from the SPSS
GLM repeated Measures Calculation for
Spheres  Source of Variation SS df
MS Â Vignette (V) 12.426 45
.276 Â Sphere (S) 22.575 5
4.515 Â Evaluator (E) 16.996
5 3.399 Â V x S 73.730 225
.328 V x E 27.643 225 .123 Â S x
E 24.769 25 .991 Â V x S x E
 Error (e)
 Residual 168.092
1125 .149
12- Table 4
- Variance Components and Expected Mean Squares for
Spheres - Â
- Source of Variation Means Square (MS) Expected
Mean Square (EMS) Estimated Variance - Â
- Vignette (V) .276 ?2e
?2VE ?2V .153 - Â
- Sphere (S) 4.515 ?2e
?2VS ?2SE ?2S 3.345 - Â
- Evaluator (E) 3.399 ?2e
?2VE ?2E 3.276 - Â
- V x S .328 ?2e
?2VS .179 - Â
- V x E .123 ?2e
?2VE -.026 - Â
- S x E .991 ?2e
?2SE .842 - Â
- V x S x E ?2e ?2VSE .149
- Â
13A Sample Calculation
As an interesting example of how the ?s are
calculated here is one (see Table 2 for the
data) Â Sphere (MS) 106.644 ?2e
?2VS ?2SE ?2S -V x S (MS)
.687 ?2e ?2VS -S x E (MS)
11.339 ?2e ?2SE Error (MS)
.480 ?2e Sphere (Variance)
95.094 ?2S -Error (MS)
.480 ?2e Sphere (Variance)
94.618 Â Total (TOT) 107.763 ?2e
?2S ?2V ?2E 107.283 ? S2S /
S2TOT 94.618 / 107.763 0.879 95.094 /
107.283 0.886 Â 0.879 ? 0.882
14The Conclusion
- What we get is three little numbers that are not
as simple as they look - Primary Influence
- ? .966
- Spheres
- ? .473
- Overall
- ? .879