Mixed Effects Models - Effect Size

Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
Follow-Up on Autocorrelation
• Autocorrelation: An empirical phenomenon in
longitudinal data where the value of a variable
at time t correlates with its value at time t+1
• Could test this with a Pearson correlation
Correlation
of
time
t
with
time
t+1
(lag
1)
Correlation
of
time
t
with
time
t+2
(lag
2)
Correlation
of
time
t
with
time
t+3
(lag
3)
• acf.fnc() plot
shows pairwise
correlations
Correlation
of
time
t
with
itself
(always
1)
Follow-Up on Autocorrelation
• Autocorrelation: An empirical phenomenon in
longitudinal data where the value of a variable
at time t correlates with its value at time t+1
• We can incorporate into a mixed-effects model
• Unlike a pairwise correlation, accounts for nested
structure and other variables
• model.auto <- lmer(WarmthToday ~
1 + Day + WarmthYesterday +
(1 + Day + WarmthYesterday|Couple),
data=relationship)
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
Cross-Lagged Models
• Our diary study also includes records of
emotional support attempts from the partner
• Do these cause
increased
warmth towards
the partner?
Cross-Lagged Models
• Our diary study also includes records of
emotional support attempts from the partner
• Do these cause
increased
warmth towards
the partner?
Wait just a darn minute! Correlation does
not imply causation!
You didn’t experimentally manipulate these
support attempts, so you don’t know which
caused which!
I’VE FINALLY GOT YOU, FRAUNDORF!!
Cross-Lagged Models
• Problem: Relation between support attempts &
warmth is ambiguous
• What could cause this?
• Support attempts could increase warmth towards partner
• Warmth towards partner could motivate support attempts
• A third variable could explain both
Perceived
warmth
Support
attempt
TIME t
?
Relationship
commitment
Cross-Lagged Models
• Problem: Relation between support attempts &
warmth is ambiguous
• But: Causes precede effects in time
• Support attempt on a previous day should
influence warmth now
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
Duckworth, Tsukayama,
& May, 2010
Cross-Lagged Models
• Use lags.fnc() to create a SupportYesterday variable
• relationship %>% mutate(SupportYesterday=
lags.fnc(relationship, time='Day', group='Couple',
depvar='PartnerSupport', lag=1)) -> relationship
• Then, use that in a model:
• model.lagged <- lmer(WarmthToday ~ 1 + Day +
SupportYesterday + (1|Couple), data=relationship)
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
Duckworth, Tsukayama,
& May, 2010
Cross-Lagged Models
• model.lagged <- lmer(WarmthToday ~ 1 + Day +
SupportYesterday + (1|Couple), data=relationship)
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
Duckworth, Tsukayama,
& May, 2010
Cross-Lagged Models
• Warmth at t can’t be the cause of support at t-1
• Helps clarify which is the cause and which is the
effect
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Duckworth, Tsukayama,
& May, 2010
Cross-Lagged Models
• Warmth at t can’t be the cause of support at t-1
• But, warmth at time t-1 could still function as
a 3rd variable
• Causes support attempts at time t-1
• Leads to greater warmth at time t (autocorrelation)
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
Duckworth, Tsukayama,
& May, 2010
X
Cross-Lagged Models
• To rule this out, we need to include the
autocorrelative effect of perceived warmth (our DV)
• model.lagged2 <- lmer(WarmthToday ~ 1 + Day
+ SupportYesterday + WarmthYesterday +
(1|Couple), data=relationship)
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
Duckworth, Tsukayama,
& May, 2010
Cross-Lagged Models
• model.lagged2 <- lmer(WarmthToday ~ 1 + Day
+ SupportYesterday + WarmthYesterday +
(1|Couple), data=relationship)
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
Duckworth, Tsukayama,
& May, 2010
Cross-Lagged Models
• Now, we are seeing a time-lagged effect of support
attempts over and above what can predicted by
previous warmth
• No way to explain this in a model where the causation only
works in reverse
• Strong evidence against the reverse direct of causation
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
X
Duckworth, Tsukayama,
& May, 2010
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
Establishing Causality
• Between-person variation in support attempts
predicts within-couple change in warmth
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
X
Duckworth, Tsukayama,
& May, 2010
Establishing Causality
• But, there’s still the possibility of a third variable that
really drives this between-person difference
• e.g., relationship commitment could explain variation in
previous support attempts and increase in warmth
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
X
Relationship
commitment
Duckworth, Tsukayama,
& May, 2010
Establishing Causality
• If relationship is driven by an underlying 3rd variable,
then warmth & support don’t have a cause/effect
relation
• Should see the same relation regardless of their order
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
X
Relationship
commitment
Duckworth, Tsukayama,
& May, 2010
Establishing Causality
• To establish causality, show that the direction of the
relationship matters
• Run the inverse model where support attempts are the DV
and previous warmth is the predictor
• model.lagged3 <- glmer(PartnerSupport ~ 1 + Day +
WarmthYesterday + SupportYesterday + (1|Couple),
data=relationship, family=binomial)
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
Perceived
warmth
X X
Establishing Causality
• model.lagged3 <- glmer(PartnerSupport ~ 1 + Day +
WarmthYesterday + SupportYesterday + (1|Couple),
data=relationship, family=binomial)
• No significant effects
• Earlier support attempts predict later warmth
(model.lagged2)
• But earlier warmth doesn’t predict later support
attempts (model.lagged3)
• Evidence for directionality of effect
Establishing Causality
• This kind of evidence is called Granger causality
• Still one kind of 3rd variable not ruled out: One with immediate
effect on support attempts & a delayed effect on warmth
• However, much less likely
• So, not quite as good as randomized experiment
• But, effective when experimental control not
possible (e.g., economics, neuroscience)
Perceived
warmth
Support
attempt
TIME t
TIME t-1
Support
attempt
X
Perceived
warmth
X
???
Establishing Causality
• This kind of evidence is called Granger causality
• Still one kind of 3rd variable not ruled out: One with immediate
effect on support attempts & a delayed effect on warmth
• However, much less likely
• So, not quite as good as randomized experiment
• But, effective when experimental control not
possible (e.g., economics, neuroscience)
Adapted from
Kaminski et al., 2011
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
Effect Size
• Revisiting lifexpectancy.csv, let’s run a model
predicting Lifespan from fixed effects of
YrsEducation and IncomeThousands, and a random
intercept of Family
• Two variables related to socioeconomic status
• Does each matter, when controlling for the other?
Which is the most important?
Effect Size
• Revisiting lifexpectancy.csv, let’s run a model
predicting Lifespan from fixed effects of
YrsEducation and IncomeThousands, and a random
intercept of Family
• Two variables related to socioeconomic status
• Which significantly predict the number of years that
people live?
• model.life <- lmer(Lifespan ~ 1 +
YrsEducation + IncomeThousands + (1|Family),
data=lifeexpectancy) They
both do!
Which is
bigger?
Effect Size
• Remember that t statistics and p-values
tell us about whether there’s an effect in
the population
• Is the effect statistically reliable?
• A separate question is how big the effect
is
• Effect size
Bigfoot: Little
evidence he
exists, but he’d
be large if he
did exist
Pygmy hippo: We know it exists and it’s
small
LARGE EFFECT SIZE,
LOW RELIABILITY
[-.20, 1.80]
SMALL EFFECT SIZE,
HIGH RELIABILITY
[.15, .35]
• Is bacon really this
bad for you??
October 26, 2015
• Is bacon really this
bad for you??
• True that we have
as much evidence
that bacon causes
cancer as smoking
causes cancer!
• Same level of
statistical
reliability
• Is bacon really this
bad for you??
• True that we have
as much evidence
that bacon causes
cancer as smoking
causes cancer!
• Same level of
statistical
reliability
• But, effect size is
much smaller for
bacon
Effect Size
• Our model results tell us both
Parameter estimate
tells us about effect
size
t statistic and p-value
tell us about statistical
reliability
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
Effect Size: Parameter Estimate
• Simplest measure: Parameter estimates
• Effect of 1-unit change in predictor on outcome
variable
• “Each additional $1,000 of annual income predicts
another 0.25 years of life”
• “Each minute of exercise increases life expectancy
by about 7 minutes.” (Moore et al., 2012, PLOS ONE)
• “People with a college diploma earn around
$24,000 more per year.” (Bureau of Labor Statistics, 2018)
• Concrete! Good for “real-world” outcomes
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
Effect Size: Standardization
• Which is the bigger effect?
• 1 year of education = 0.57 years of life expectancy
• $1,000 of annual income = 0.25 years of life
expectancy
• Problem: These are measured in
different, non-comparable units
• Years of education vs. (thousands of) US dollars
Effect Size: Standardization
• Which is the bigger effect?
• 1 year of education = 0.57 years of life expectancy
• $1,000 of annual income = 0.25 years of life
expectancy
• Problem: These are measured in
different, non-comparable units
• Years of education vs. (thousands of) US dollars
• Convert to z-scores: # of standard
deviations from the mean
• This scale applies to anything!
• Standardized scores
Effect Size: Standardization
• scale() puts things in terms of z-scores
• New z-scored version of our predictors:
• lifeexpectancy %>% mutate(
YrsEducation.z = scale(YrsEducation)[,1],
IncomeThousands.z = scale(IncomeThousands)[,1]) ->
lifeexpectancy
• # of standard deviations above/below mean
income
Effect Size: Standardization
• scale() puts things in terms of z-scores
• New z-scored version of our predictors:
• lifeexpectancy %>% mutate(
YrsEducation.z = scale(YrsEducation)[,1],
IncomeThousands.z = scale(IncomeThousands)[,1]) ->
lifeexpectancy
• # of standard deviations above/below mean
income
• Then use these in a new model
• model.life <- lmer(Lifespan ~ 1 +
YrsEducation.z + IncomeThousands.z +
(1|Subject), data=lifeexpectancy)
Effect Size: Standardization
• New results:
• 1 SD increase in education = +2.1 years of
life expectancy
• 1 SD increase in income = +2.4 years of life
expectancy
• Income effect is bigger in this dataset
Effect Size: Standardization
• Old results:
• New results:
No change in
statistical reliability
Effect size is now
estimated differently
Effect Size: Standardization
• Standardized effects
make effect sizes more
reliant on our data
• Effect of 1 SD relative to
the mean depends on
what the M and SD are!
• e.g., Effect of cigarette
smoking on life
• Smoking rates vary a lot
from country to country!
• Might get different
standardized effects
even if unstandardized
is the same
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
Overall Variance Explained
• How well can we explain this DV?
• In the linear model context:
• R2=
• But in mixed-effect context: Which variance are
we talking about?
Model-explained variance
Model-explained variance + Error variance
Level-1 error variance
Variance from level-2 clustering
Jaeger, Edwards, Das, & Sen, 2017;
Rights & Sterba, 2019
• One R2 we can compute in mixed-effects context:
• R2
c=
• Obtain with the squared correlation between
model-predicted and observed values
• cor(fitted(model.life),
lifeexpectancy$Lifespan)^2
• Here, 46%!
Variance explained by fixed & random effects
Conditional R2
All variance
Jaeger, Edwards, Das, & Sen, 2017;
Rights & Sterba, 2019
70 75 80 85
50
60
70
80
90
100
PREDICTED lifespan
ACTUAL
lifespan
• One R2 we can compute in mixed-effects context:
• R2
c=
Variance explained by fixed & random effects
Conditional R2
All variance
• One R2 we can compute in mixed-effects context:
• R2
c=
• But, are random effects really “explaining” the
variance?
Variance explained by fixed & random effects
Conditional R2
All variance
Some families have
longer average lifespans
Some subjects have
faster RTs than others
• One R2 we can compute in mixed-effects context:
• R2
c=
• Summary:
• Conditional R2 counts both fixed and random effects
as explained variance
• Preserves R2 as square of the correlation between
observed & predicted data
• Evaluates model’s ability to make good predictions
• But, may overstate scientific/theoretical explanatory
power
Variance explained by fixed & random effects
Conditional R2
All variance
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
• Another R2 that may be more helpful:
• R2
β*=
• library(r2glmm)
• r2beta(model.life)
Variance explained by fixed effects only
Marginal R2
All variance
Variance
explained by all
fixed effects
combined (14%)
Partial R2 for each
fixed effect
Jaeger, Edwards, Das, & Sen, 2017
• Another R2 that may be more helpful:
• R2
β*=
• library(r2glmm)
• r2beta(model.life)
• r2dt(model1, model2) to test
R2 difference between two models
Variance explained by fixed effects only
Marginal R2
All variance
Jaeger, Edwards, Das, & Sen, 2017
• plot(r2beta(model.life))
Marginal R2
• Another R2 that may be more helpful:
• R2
β*=
• Summary:
• Marginal R2 counts only fixed effects as explained
variance
• Evaluates model’s scientific/theoretical explanatory
ability
• Probably more useful in most purposes
Variance explained by fixed effects only
Marginal R2
All variance
Week 12.1: Effect Size
! Finish Longitudinal Designs
! Follow-Up on Autocorrelation
! Cross-Lagged Designs
! Cross-Lagged Models
! Establishing Causality
! Effect Size
! Effect Size vs. Statistical Significance
! Unstandardized
! Standardized
! Variance Explained (R2)
! Conditional
! Marginal
! Interpreting Effect Size
• Some conventional interpretations of R2 and
partial R2:
• But, take these with several grains of salt
• Cohen (1988) just made them up
• Unclear why we care about variance
explained (R2) rather than standard
deviations (r), in original units
• Even small effects can accumulate
over time (Funder & Ozer, 2019)
Cohen (1988)
“Small” .01
“Medium” .06
“Large” .15
Interpreting Effect Size
• Some conventional interpretations of R2 and
partial R2: Cohen (1988)
Funder &
Ozer (2019)
“Small” .01
“Medium” .06
“Large” .15
Interpreting Effect Size
.001
.04
.09
.0025
“Very Small”
.16
“Very Large”
• Consider in context of other effect sizes in
this domain:
• vs:
• For interventions: Consider cost,
difficulty of implementation, etc.
• Aspirin’s effect in reducing heart attacks:
r = .03, R2 < .01, but cheap! (Rosenthal, 1990)
Our
effect:
.10
Other
effect 1:
.20
Other
effect 2:
.30
Our
effect:
.10
Other
effect 1:
.01
Other
effect 2:
.05
Effect Size: Interpretation
• For theoretically guided research, compare
to predictions of competing theories
• The lag effect in memory:
• Is this about intervening items or time?
Study
RACCOON
5 sec.
Study
WITCH
5 sec.
Study
VIKING
5 sec.
Study
RACCOON
5 sec.
1 sec 1 sec 1 sec 1 day
Study
RACCOON
5 sec.
Study
WITCH
5 sec.
Study
VIKING
5 sec.
Study
RACCOON
5 sec.
1 sec 1 sec 1 sec 1 day
POOR
recall of
RACCOON
GOOD
recall of
RACCOON
Effect Size: Interpretation
Effect Size: Interpretation
• Is lag effect about intervening items or time?
• Intervening items hypothesis predicts A > B
• Time hypothesis predicts B > A
• Goal here is to use direction of the effect to
adjudicate between competing hypotheses
• Not whether the lag effect is “small” or “large”
Study
RACCOON
5 sec.
Study
WITCH
5 sec.
Study
VIKING
5 sec.
Study
RACCOON
5 sec.
1 sec 1 sec 1 sec 1 day TEST
A:
Study
RACCOON
5 sec.
Study
WITCH
5 sec.
Study
RACCOON
5 sec.
10 sec 10 sec 1 day TEST
B:
1 of 60

Recommended

Mixed Effects Models - Orthogonal Contrasts by
Mixed Effects Models - Orthogonal ContrastsMixed Effects Models - Orthogonal Contrasts
Mixed Effects Models - Orthogonal ContrastsScott Fraundorf
359 views68 slides
Mixed Effects Models - Fixed Effects by
Mixed Effects Models - Fixed EffectsMixed Effects Models - Fixed Effects
Mixed Effects Models - Fixed EffectsScott Fraundorf
222 views58 slides
Mixed Effects Models - Model Comparison by
Mixed Effects Models - Model ComparisonMixed Effects Models - Model Comparison
Mixed Effects Models - Model ComparisonScott Fraundorf
152 views58 slides
Mixed Effects Models - Growth Curve Analysis by
Mixed Effects Models - Growth Curve AnalysisMixed Effects Models - Growth Curve Analysis
Mixed Effects Models - Growth Curve AnalysisScott Fraundorf
200 views62 slides
Mixed Effects Models - Random Slopes by
Mixed Effects Models - Random SlopesMixed Effects Models - Random Slopes
Mixed Effects Models - Random SlopesScott Fraundorf
262 views73 slides
Mixed Effects Models - Random Intercepts by
Mixed Effects Models - Random InterceptsMixed Effects Models - Random Intercepts
Mixed Effects Models - Random InterceptsScott Fraundorf
185 views79 slides

More Related Content

What's hot

Logistic regression sage by
Logistic regression sageLogistic regression sage
Logistic regression sagePakistan Gum Industries Pvt. Ltd
1.5K views21 slides
Đánh giá bằng chứng khoa học tìm được (Bác sĩ. Nguyễn Văn Hùng) by
Đánh giá bằng chứng khoa học tìm được (Bác sĩ. Nguyễn Văn Hùng)Đánh giá bằng chứng khoa học tìm được (Bác sĩ. Nguyễn Văn Hùng)
Đánh giá bằng chứng khoa học tìm được (Bác sĩ. Nguyễn Văn Hùng)Friendship and Science for Health
3.5K views40 slides
Part 2 Cox Regression by
Part 2 Cox RegressionPart 2 Cox Regression
Part 2 Cox RegressionBhaswat Chakraborty
5.9K views38 slides
Manova Report by
Manova ReportManova Report
Manova ReportAshutosh Kumar Jha
18.5K views13 slides
Luận án: Điều trị tăng áp lực nội sọ bằng dd NACl 3% ở bệnh nhân by
Luận án: Điều trị tăng áp lực nội sọ bằng dd NACl 3% ở bệnh nhânLuận án: Điều trị tăng áp lực nội sọ bằng dd NACl 3% ở bệnh nhân
Luận án: Điều trị tăng áp lực nội sọ bằng dd NACl 3% ở bệnh nhânDịch vụ viết bài trọn gói ZALO 0909232620
983 views211 slides
Luận án: Phẫu thuật cắt đầu tụy tá tràng điều trị ung thư bóng vater by
Luận án: Phẫu thuật cắt đầu tụy tá tràng điều trị ung thư bóng vaterLuận án: Phẫu thuật cắt đầu tụy tá tràng điều trị ung thư bóng vater
Luận án: Phẫu thuật cắt đầu tụy tá tràng điều trị ung thư bóng vaterDịch vụ viết bài trọn gói ZALO: 0917.193.864
92 views24 slides

What's hot(20)

Epidemiology And Public Health Part II for Graduate and Postgraduate students by Tauseef Jawaid
Epidemiology And Public Health Part II for Graduate and Postgraduate studentsEpidemiology And Public Health Part II for Graduate and Postgraduate students
Epidemiology And Public Health Part II for Graduate and Postgraduate students
Tauseef Jawaid946 views
ĐÁI THÁO ĐƯỜNG THAI KỲ ĐIỀU TRỊ BẰNG THUỐC by SoM
ĐÁI THÁO ĐƯỜNG THAI KỲ ĐIỀU TRỊ BẰNG THUỐCĐÁI THÁO ĐƯỜNG THAI KỲ ĐIỀU TRỊ BẰNG THUỐC
ĐÁI THÁO ĐƯỜNG THAI KỲ ĐIỀU TRỊ BẰNG THUỐC
SoM5.1K views
Survival Analysis Using SPSS by Nermin Osman
Survival Analysis Using SPSSSurvival Analysis Using SPSS
Survival Analysis Using SPSS
Nermin Osman921 views
Case-crossover study by Jinseob Kim
Case-crossover studyCase-crossover study
Case-crossover study
Jinseob Kim3K views
đIều trị sỏi đường mật chính by Định Ngô
đIều trị sỏi đường mật chínhđIều trị sỏi đường mật chính
đIều trị sỏi đường mật chính
Định Ngô4.7K views
Multinomial Logistic Regression by Dr Athar Khan
Multinomial Logistic RegressionMultinomial Logistic Regression
Multinomial Logistic Regression
Dr Athar Khan351 views
LÂY TRUYỀN HIV/AIDS TỪ MẸ SANG CON by SoM
LÂY TRUYỀN HIV/AIDS TỪ MẸ SANG CONLÂY TRUYỀN HIV/AIDS TỪ MẸ SANG CON
LÂY TRUYỀN HIV/AIDS TỪ MẸ SANG CON
SoM459 views
Introduction to Analysis of Variance by jasondroesch
Introduction to Analysis of VarianceIntroduction to Analysis of Variance
Introduction to Analysis of Variance
jasondroesch8.4K views
Statistical tests for data involving quantitative data by Rizwan S A
Statistical tests for data involving quantitative dataStatistical tests for data involving quantitative data
Statistical tests for data involving quantitative data
Rizwan S A2.1K views
CHUYỂN DẠ SINH NON by SoM
CHUYỂN DẠ SINH NONCHUYỂN DẠ SINH NON
CHUYỂN DẠ SINH NON
SoM3.4K views
What is Binary Logistic Regression Classification and How is it Used in Analy... by Smarten Augmented Analytics
What is Binary Logistic Regression Classification and How is it Used in Analy...What is Binary Logistic Regression Classification and How is it Used in Analy...
What is Binary Logistic Regression Classification and How is it Used in Analy...

Similar to Mixed Effects Models - Effect Size

Mixed Effects Models - Centering and Transformations by
Mixed Effects Models - Centering and TransformationsMixed Effects Models - Centering and Transformations
Mixed Effects Models - Centering and TransformationsScott Fraundorf
144 views45 slides
Topic 5 (multiple regression) by
Topic 5 (multiple regression)Topic 5 (multiple regression)
Topic 5 (multiple regression)Ryan Herzog
125 views19 slides
Scientific method and si units UPDATED by
Scientific method and si units UPDATEDScientific method and si units UPDATED
Scientific method and si units UPDATEDMaria Donohue
829 views45 slides
Week 4 Interpreting Longitudinal Models (1).pptx by
Week 4 Interpreting Longitudinal Models (1).pptxWeek 4 Interpreting Longitudinal Models (1).pptx
Week 4 Interpreting Longitudinal Models (1).pptxOyebayo Ridwan Olaniran
9 views35 slides
Mixed Effects Models - Fixed Effect Interactions by
Mixed Effects Models - Fixed Effect InteractionsMixed Effects Models - Fixed Effect Interactions
Mixed Effects Models - Fixed Effect InteractionsScott Fraundorf
119 views29 slides
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx by
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docxnovabroom
5 views98 slides

Similar to Mixed Effects Models - Effect Size(20)

Mixed Effects Models - Centering and Transformations by Scott Fraundorf
Mixed Effects Models - Centering and TransformationsMixed Effects Models - Centering and Transformations
Mixed Effects Models - Centering and Transformations
Scott Fraundorf144 views
Topic 5 (multiple regression) by Ryan Herzog
Topic 5 (multiple regression)Topic 5 (multiple regression)
Topic 5 (multiple regression)
Ryan Herzog125 views
Scientific method and si units UPDATED by Maria Donohue
Scientific method and si units UPDATEDScientific method and si units UPDATED
Scientific method and si units UPDATED
Maria Donohue829 views
Mixed Effects Models - Fixed Effect Interactions by Scott Fraundorf
Mixed Effects Models - Fixed Effect InteractionsMixed Effects Models - Fixed Effect Interactions
Mixed Effects Models - Fixed Effect Interactions
Scott Fraundorf119 views
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx by novabroom
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx
novabroom5 views
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx by hyacinthshackley2629
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx
11 T(EA) FOR TWO TESTS BETWEEN THE MEANS OF DIFFERENT GROUPS11 .docx
Experimental design techniques- why experimental design needed? by Dr-Jitendra Patel
Experimental design techniques- why experimental design needed?Experimental design techniques- why experimental design needed?
Experimental design techniques- why experimental design needed?
Dr-Jitendra Patel324 views
Foundations of Statistics in Ecology and Evolution. 8. Bayesian Statistics by Andres Lopez-Sepulcre
Foundations of Statistics in Ecology and Evolution. 8. Bayesian StatisticsFoundations of Statistics in Ecology and Evolution. 8. Bayesian Statistics
Foundations of Statistics in Ecology and Evolution. 8. Bayesian Statistics
Unit one presentation by mrcoyleteach
Unit one presentationUnit one presentation
Unit one presentation
mrcoyleteach610 views
PhD Research Proposal - Qualifying Exam by Paramita Mirza
PhD Research Proposal - Qualifying ExamPhD Research Proposal - Qualifying Exam
PhD Research Proposal - Qualifying Exam
Paramita Mirza3.5K views
BUS 308 Week 5 Lecture 3 A Different View Effect Sizes .docx by curwenmichaela
BUS 308 Week 5 Lecture 3 A Different View Effect Sizes .docxBUS 308 Week 5 Lecture 3 A Different View Effect Sizes .docx
BUS 308 Week 5 Lecture 3 A Different View Effect Sizes .docx
curwenmichaela2 views
FE3.ppt by asde13
FE3.pptFE3.ppt
FE3.ppt
asde132 views

More from Scott Fraundorf

Mixed Effects Models - Signal Detection Theory by
Mixed Effects Models - Signal Detection TheoryMixed Effects Models - Signal Detection Theory
Mixed Effects Models - Signal Detection TheoryScott Fraundorf
280 views61 slides
Mixed Effects Models - Power by
Mixed Effects Models - PowerMixed Effects Models - Power
Mixed Effects Models - PowerScott Fraundorf
126 views60 slides
Mixed Effects Models - Missing Data by
Mixed Effects Models - Missing DataMixed Effects Models - Missing Data
Mixed Effects Models - Missing DataScott Fraundorf
88 views67 slides
Mixed Effects Models - Empirical Logit by
Mixed Effects Models - Empirical LogitMixed Effects Models - Empirical Logit
Mixed Effects Models - Empirical LogitScott Fraundorf
121 views30 slides
Mixed Effects Models - Logit Models by
Mixed Effects Models - Logit ModelsMixed Effects Models - Logit Models
Mixed Effects Models - Logit ModelsScott Fraundorf
127 views71 slides
Mixed Effects Models - Post-Hoc Comparisons by
Mixed Effects Models - Post-Hoc ComparisonsMixed Effects Models - Post-Hoc Comparisons
Mixed Effects Models - Post-Hoc ComparisonsScott Fraundorf
679 views33 slides

More from Scott Fraundorf(13)

Mixed Effects Models - Signal Detection Theory by Scott Fraundorf
Mixed Effects Models - Signal Detection TheoryMixed Effects Models - Signal Detection Theory
Mixed Effects Models - Signal Detection Theory
Scott Fraundorf280 views
Mixed Effects Models - Missing Data by Scott Fraundorf
Mixed Effects Models - Missing DataMixed Effects Models - Missing Data
Mixed Effects Models - Missing Data
Scott Fraundorf88 views
Mixed Effects Models - Empirical Logit by Scott Fraundorf
Mixed Effects Models - Empirical LogitMixed Effects Models - Empirical Logit
Mixed Effects Models - Empirical Logit
Scott Fraundorf121 views
Mixed Effects Models - Logit Models by Scott Fraundorf
Mixed Effects Models - Logit ModelsMixed Effects Models - Logit Models
Mixed Effects Models - Logit Models
Scott Fraundorf127 views
Mixed Effects Models - Post-Hoc Comparisons by Scott Fraundorf
Mixed Effects Models - Post-Hoc ComparisonsMixed Effects Models - Post-Hoc Comparisons
Mixed Effects Models - Post-Hoc Comparisons
Scott Fraundorf679 views
Mixed Effects Models - Simple and Main Effects by Scott Fraundorf
Mixed Effects Models - Simple and Main EffectsMixed Effects Models - Simple and Main Effects
Mixed Effects Models - Simple and Main Effects
Scott Fraundorf618 views
Mixed Effects Models - Crossed Random Effects by Scott Fraundorf
Mixed Effects Models - Crossed Random EffectsMixed Effects Models - Crossed Random Effects
Mixed Effects Models - Crossed Random Effects
Scott Fraundorf294 views
Mixed Effects Models - Level-2 Variables by Scott Fraundorf
Mixed Effects Models - Level-2 VariablesMixed Effects Models - Level-2 Variables
Mixed Effects Models - Level-2 Variables
Scott Fraundorf119 views
Mixed Effects Models - Data Processing by Scott Fraundorf
Mixed Effects Models - Data ProcessingMixed Effects Models - Data Processing
Mixed Effects Models - Data Processing
Scott Fraundorf100 views
Mixed Effects Models - Descriptive Statistics by Scott Fraundorf
Mixed Effects Models - Descriptive StatisticsMixed Effects Models - Descriptive Statistics
Mixed Effects Models - Descriptive Statistics
Scott Fraundorf147 views
Mixed Effects Models - Introduction by Scott Fraundorf
Mixed Effects Models - IntroductionMixed Effects Models - Introduction
Mixed Effects Models - Introduction
Scott Fraundorf194 views

Recently uploaded

AI Tools for Business and Startups by
AI Tools for Business and StartupsAI Tools for Business and Startups
AI Tools for Business and StartupsSvetlin Nakov
101 views39 slides
231112 (WR) v1 ChatGPT OEB 2023.pdf by
231112 (WR) v1  ChatGPT OEB 2023.pdf231112 (WR) v1  ChatGPT OEB 2023.pdf
231112 (WR) v1 ChatGPT OEB 2023.pdfWilfredRubens.com
144 views21 slides
Class 10 English lesson plans by
Class 10 English  lesson plansClass 10 English  lesson plans
Class 10 English lesson plansTARIQ KHAN
257 views53 slides
Narration lesson plan.docx by
Narration lesson plan.docxNarration lesson plan.docx
Narration lesson plan.docxTARIQ KHAN
104 views11 slides
Google solution challenge..pptx by
Google solution challenge..pptxGoogle solution challenge..pptx
Google solution challenge..pptxChitreshGyanani1
98 views18 slides
The Open Access Community Framework (OACF) 2023 (1).pptx by
The Open Access Community Framework (OACF) 2023 (1).pptxThe Open Access Community Framework (OACF) 2023 (1).pptx
The Open Access Community Framework (OACF) 2023 (1).pptxJisc
85 views7 slides

Recently uploaded(20)

AI Tools for Business and Startups by Svetlin Nakov
AI Tools for Business and StartupsAI Tools for Business and Startups
AI Tools for Business and Startups
Svetlin Nakov101 views
Class 10 English lesson plans by TARIQ KHAN
Class 10 English  lesson plansClass 10 English  lesson plans
Class 10 English lesson plans
TARIQ KHAN257 views
Narration lesson plan.docx by TARIQ KHAN
Narration lesson plan.docxNarration lesson plan.docx
Narration lesson plan.docx
TARIQ KHAN104 views
The Open Access Community Framework (OACF) 2023 (1).pptx by Jisc
The Open Access Community Framework (OACF) 2023 (1).pptxThe Open Access Community Framework (OACF) 2023 (1).pptx
The Open Access Community Framework (OACF) 2023 (1).pptx
Jisc85 views
Drama KS5 Breakdown by WestHatch
Drama KS5 BreakdownDrama KS5 Breakdown
Drama KS5 Breakdown
WestHatch71 views
American Psychological Association 7th Edition.pptx by SamiullahAfridi4
American Psychological Association  7th Edition.pptxAmerican Psychological Association  7th Edition.pptx
American Psychological Association 7th Edition.pptx
SamiullahAfridi482 views
Class 10 English notes 23-24.pptx by TARIQ KHAN
Class 10 English notes 23-24.pptxClass 10 English notes 23-24.pptx
Class 10 English notes 23-24.pptx
TARIQ KHAN107 views
7 NOVEL DRUG DELIVERY SYSTEM.pptx by Sachin Nitave
7 NOVEL DRUG DELIVERY SYSTEM.pptx7 NOVEL DRUG DELIVERY SYSTEM.pptx
7 NOVEL DRUG DELIVERY SYSTEM.pptx
Sachin Nitave58 views
Lecture: Open Innovation by Michal Hron
Lecture: Open InnovationLecture: Open Innovation
Lecture: Open Innovation
Michal Hron96 views
Sociology KS5 by WestHatch
Sociology KS5Sociology KS5
Sociology KS5
WestHatch64 views
Solar System and Galaxies.pptx by DrHafizKosar
Solar System and Galaxies.pptxSolar System and Galaxies.pptx
Solar System and Galaxies.pptx
DrHafizKosar85 views
Use of Probiotics in Aquaculture.pptx by AKSHAY MANDAL
Use of Probiotics in Aquaculture.pptxUse of Probiotics in Aquaculture.pptx
Use of Probiotics in Aquaculture.pptx
AKSHAY MANDAL89 views
The basics - information, data, technology and systems.pdf by JonathanCovena1
The basics - information, data, technology and systems.pdfThe basics - information, data, technology and systems.pdf
The basics - information, data, technology and systems.pdf
JonathanCovena188 views

Mixed Effects Models - Effect Size

  • 1. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 2. Follow-Up on Autocorrelation • Autocorrelation: An empirical phenomenon in longitudinal data where the value of a variable at time t correlates with its value at time t+1 • Could test this with a Pearson correlation
  • 4. Follow-Up on Autocorrelation • Autocorrelation: An empirical phenomenon in longitudinal data where the value of a variable at time t correlates with its value at time t+1 • We can incorporate into a mixed-effects model • Unlike a pairwise correlation, accounts for nested structure and other variables • model.auto <- lmer(WarmthToday ~ 1 + Day + WarmthYesterday + (1 + Day + WarmthYesterday|Couple), data=relationship)
  • 5. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 6. Cross-Lagged Models • Our diary study also includes records of emotional support attempts from the partner • Do these cause increased warmth towards the partner?
  • 7. Cross-Lagged Models • Our diary study also includes records of emotional support attempts from the partner • Do these cause increased warmth towards the partner? Wait just a darn minute! Correlation does not imply causation! You didn’t experimentally manipulate these support attempts, so you don’t know which caused which! I’VE FINALLY GOT YOU, FRAUNDORF!!
  • 8. Cross-Lagged Models • Problem: Relation between support attempts & warmth is ambiguous • What could cause this? • Support attempts could increase warmth towards partner • Warmth towards partner could motivate support attempts • A third variable could explain both Perceived warmth Support attempt TIME t ? Relationship commitment
  • 9. Cross-Lagged Models • Problem: Relation between support attempts & warmth is ambiguous • But: Causes precede effects in time • Support attempt on a previous day should influence warmth now Perceived warmth Support attempt TIME t TIME t-1 Support attempt Duckworth, Tsukayama, & May, 2010
  • 10. Cross-Lagged Models • Use lags.fnc() to create a SupportYesterday variable • relationship %>% mutate(SupportYesterday= lags.fnc(relationship, time='Day', group='Couple', depvar='PartnerSupport', lag=1)) -> relationship • Then, use that in a model: • model.lagged <- lmer(WarmthToday ~ 1 + Day + SupportYesterday + (1|Couple), data=relationship) Perceived warmth Support attempt TIME t TIME t-1 Support attempt Duckworth, Tsukayama, & May, 2010
  • 11. Cross-Lagged Models • model.lagged <- lmer(WarmthToday ~ 1 + Day + SupportYesterday + (1|Couple), data=relationship) Perceived warmth Support attempt TIME t TIME t-1 Support attempt Duckworth, Tsukayama, & May, 2010
  • 12. Cross-Lagged Models • Warmth at t can’t be the cause of support at t-1 • Helps clarify which is the cause and which is the effect Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Duckworth, Tsukayama, & May, 2010
  • 13. Cross-Lagged Models • Warmth at t can’t be the cause of support at t-1 • But, warmth at time t-1 could still function as a 3rd variable • Causes support attempts at time t-1 • Leads to greater warmth at time t (autocorrelation) Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth Duckworth, Tsukayama, & May, 2010 X
  • 14. Cross-Lagged Models • To rule this out, we need to include the autocorrelative effect of perceived warmth (our DV) • model.lagged2 <- lmer(WarmthToday ~ 1 + Day + SupportYesterday + WarmthYesterday + (1|Couple), data=relationship) Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth Duckworth, Tsukayama, & May, 2010
  • 15. Cross-Lagged Models • model.lagged2 <- lmer(WarmthToday ~ 1 + Day + SupportYesterday + WarmthYesterday + (1|Couple), data=relationship) Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth Duckworth, Tsukayama, & May, 2010
  • 16. Cross-Lagged Models • Now, we are seeing a time-lagged effect of support attempts over and above what can predicted by previous warmth • No way to explain this in a model where the causation only works in reverse • Strong evidence against the reverse direct of causation Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth X Duckworth, Tsukayama, & May, 2010
  • 17. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 18. Establishing Causality • Between-person variation in support attempts predicts within-couple change in warmth Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth X Duckworth, Tsukayama, & May, 2010
  • 19. Establishing Causality • But, there’s still the possibility of a third variable that really drives this between-person difference • e.g., relationship commitment could explain variation in previous support attempts and increase in warmth Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth X Relationship commitment Duckworth, Tsukayama, & May, 2010
  • 20. Establishing Causality • If relationship is driven by an underlying 3rd variable, then warmth & support don’t have a cause/effect relation • Should see the same relation regardless of their order Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth X Relationship commitment Duckworth, Tsukayama, & May, 2010
  • 21. Establishing Causality • To establish causality, show that the direction of the relationship matters • Run the inverse model where support attempts are the DV and previous warmth is the predictor • model.lagged3 <- glmer(PartnerSupport ~ 1 + Day + WarmthYesterday + SupportYesterday + (1|Couple), data=relationship, family=binomial) Perceived warmth Support attempt TIME t TIME t-1 Support attempt Perceived warmth X X
  • 22. Establishing Causality • model.lagged3 <- glmer(PartnerSupport ~ 1 + Day + WarmthYesterday + SupportYesterday + (1|Couple), data=relationship, family=binomial) • No significant effects • Earlier support attempts predict later warmth (model.lagged2) • But earlier warmth doesn’t predict later support attempts (model.lagged3) • Evidence for directionality of effect
  • 23. Establishing Causality • This kind of evidence is called Granger causality • Still one kind of 3rd variable not ruled out: One with immediate effect on support attempts & a delayed effect on warmth • However, much less likely • So, not quite as good as randomized experiment • But, effective when experimental control not possible (e.g., economics, neuroscience) Perceived warmth Support attempt TIME t TIME t-1 Support attempt X Perceived warmth X ???
  • 24. Establishing Causality • This kind of evidence is called Granger causality • Still one kind of 3rd variable not ruled out: One with immediate effect on support attempts & a delayed effect on warmth • However, much less likely • So, not quite as good as randomized experiment • But, effective when experimental control not possible (e.g., economics, neuroscience) Adapted from Kaminski et al., 2011
  • 25. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 26. Effect Size • Revisiting lifexpectancy.csv, let’s run a model predicting Lifespan from fixed effects of YrsEducation and IncomeThousands, and a random intercept of Family • Two variables related to socioeconomic status • Does each matter, when controlling for the other? Which is the most important?
  • 27. Effect Size • Revisiting lifexpectancy.csv, let’s run a model predicting Lifespan from fixed effects of YrsEducation and IncomeThousands, and a random intercept of Family • Two variables related to socioeconomic status • Which significantly predict the number of years that people live? • model.life <- lmer(Lifespan ~ 1 + YrsEducation + IncomeThousands + (1|Family), data=lifeexpectancy) They both do! Which is bigger?
  • 28. Effect Size • Remember that t statistics and p-values tell us about whether there’s an effect in the population • Is the effect statistically reliable? • A separate question is how big the effect is • Effect size
  • 29. Bigfoot: Little evidence he exists, but he’d be large if he did exist Pygmy hippo: We know it exists and it’s small LARGE EFFECT SIZE, LOW RELIABILITY [-.20, 1.80] SMALL EFFECT SIZE, HIGH RELIABILITY [.15, .35]
  • 30. • Is bacon really this bad for you?? October 26, 2015
  • 31. • Is bacon really this bad for you?? • True that we have as much evidence that bacon causes cancer as smoking causes cancer! • Same level of statistical reliability
  • 32. • Is bacon really this bad for you?? • True that we have as much evidence that bacon causes cancer as smoking causes cancer! • Same level of statistical reliability • But, effect size is much smaller for bacon
  • 33. Effect Size • Our model results tell us both Parameter estimate tells us about effect size t statistic and p-value tell us about statistical reliability
  • 34. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 35. Effect Size: Parameter Estimate • Simplest measure: Parameter estimates • Effect of 1-unit change in predictor on outcome variable • “Each additional $1,000 of annual income predicts another 0.25 years of life” • “Each minute of exercise increases life expectancy by about 7 minutes.” (Moore et al., 2012, PLOS ONE) • “People with a college diploma earn around $24,000 more per year.” (Bureau of Labor Statistics, 2018) • Concrete! Good for “real-world” outcomes
  • 36. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 37. Effect Size: Standardization • Which is the bigger effect? • 1 year of education = 0.57 years of life expectancy • $1,000 of annual income = 0.25 years of life expectancy • Problem: These are measured in different, non-comparable units • Years of education vs. (thousands of) US dollars
  • 38. Effect Size: Standardization • Which is the bigger effect? • 1 year of education = 0.57 years of life expectancy • $1,000 of annual income = 0.25 years of life expectancy • Problem: These are measured in different, non-comparable units • Years of education vs. (thousands of) US dollars • Convert to z-scores: # of standard deviations from the mean • This scale applies to anything! • Standardized scores
  • 39. Effect Size: Standardization • scale() puts things in terms of z-scores • New z-scored version of our predictors: • lifeexpectancy %>% mutate( YrsEducation.z = scale(YrsEducation)[,1], IncomeThousands.z = scale(IncomeThousands)[,1]) -> lifeexpectancy • # of standard deviations above/below mean income
  • 40. Effect Size: Standardization • scale() puts things in terms of z-scores • New z-scored version of our predictors: • lifeexpectancy %>% mutate( YrsEducation.z = scale(YrsEducation)[,1], IncomeThousands.z = scale(IncomeThousands)[,1]) -> lifeexpectancy • # of standard deviations above/below mean income • Then use these in a new model • model.life <- lmer(Lifespan ~ 1 + YrsEducation.z + IncomeThousands.z + (1|Subject), data=lifeexpectancy)
  • 41. Effect Size: Standardization • New results: • 1 SD increase in education = +2.1 years of life expectancy • 1 SD increase in income = +2.4 years of life expectancy • Income effect is bigger in this dataset
  • 42. Effect Size: Standardization • Old results: • New results: No change in statistical reliability Effect size is now estimated differently
  • 43. Effect Size: Standardization • Standardized effects make effect sizes more reliant on our data • Effect of 1 SD relative to the mean depends on what the M and SD are! • e.g., Effect of cigarette smoking on life • Smoking rates vary a lot from country to country! • Might get different standardized effects even if unstandardized is the same
  • 44. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 45. Overall Variance Explained • How well can we explain this DV? • In the linear model context: • R2= • But in mixed-effect context: Which variance are we talking about? Model-explained variance Model-explained variance + Error variance Level-1 error variance Variance from level-2 clustering Jaeger, Edwards, Das, & Sen, 2017; Rights & Sterba, 2019
  • 46. • One R2 we can compute in mixed-effects context: • R2 c= • Obtain with the squared correlation between model-predicted and observed values • cor(fitted(model.life), lifeexpectancy$Lifespan)^2 • Here, 46%! Variance explained by fixed & random effects Conditional R2 All variance Jaeger, Edwards, Das, & Sen, 2017; Rights & Sterba, 2019
  • 47. 70 75 80 85 50 60 70 80 90 100 PREDICTED lifespan ACTUAL lifespan • One R2 we can compute in mixed-effects context: • R2 c= Variance explained by fixed & random effects Conditional R2 All variance
  • 48. • One R2 we can compute in mixed-effects context: • R2 c= • But, are random effects really “explaining” the variance? Variance explained by fixed & random effects Conditional R2 All variance Some families have longer average lifespans Some subjects have faster RTs than others
  • 49. • One R2 we can compute in mixed-effects context: • R2 c= • Summary: • Conditional R2 counts both fixed and random effects as explained variance • Preserves R2 as square of the correlation between observed & predicted data • Evaluates model’s ability to make good predictions • But, may overstate scientific/theoretical explanatory power Variance explained by fixed & random effects Conditional R2 All variance
  • 50. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 51. • Another R2 that may be more helpful: • R2 β*= • library(r2glmm) • r2beta(model.life) Variance explained by fixed effects only Marginal R2 All variance Variance explained by all fixed effects combined (14%) Partial R2 for each fixed effect Jaeger, Edwards, Das, & Sen, 2017
  • 52. • Another R2 that may be more helpful: • R2 β*= • library(r2glmm) • r2beta(model.life) • r2dt(model1, model2) to test R2 difference between two models Variance explained by fixed effects only Marginal R2 All variance Jaeger, Edwards, Das, & Sen, 2017
  • 54. • Another R2 that may be more helpful: • R2 β*= • Summary: • Marginal R2 counts only fixed effects as explained variance • Evaluates model’s scientific/theoretical explanatory ability • Probably more useful in most purposes Variance explained by fixed effects only Marginal R2 All variance
  • 55. Week 12.1: Effect Size ! Finish Longitudinal Designs ! Follow-Up on Autocorrelation ! Cross-Lagged Designs ! Cross-Lagged Models ! Establishing Causality ! Effect Size ! Effect Size vs. Statistical Significance ! Unstandardized ! Standardized ! Variance Explained (R2) ! Conditional ! Marginal ! Interpreting Effect Size
  • 56. • Some conventional interpretations of R2 and partial R2: • But, take these with several grains of salt • Cohen (1988) just made them up • Unclear why we care about variance explained (R2) rather than standard deviations (r), in original units • Even small effects can accumulate over time (Funder & Ozer, 2019) Cohen (1988) “Small” .01 “Medium” .06 “Large” .15 Interpreting Effect Size
  • 57. • Some conventional interpretations of R2 and partial R2: Cohen (1988) Funder & Ozer (2019) “Small” .01 “Medium” .06 “Large” .15 Interpreting Effect Size .001 .04 .09 .0025 “Very Small” .16 “Very Large”
  • 58. • Consider in context of other effect sizes in this domain: • vs: • For interventions: Consider cost, difficulty of implementation, etc. • Aspirin’s effect in reducing heart attacks: r = .03, R2 < .01, but cheap! (Rosenthal, 1990) Our effect: .10 Other effect 1: .20 Other effect 2: .30 Our effect: .10 Other effect 1: .01 Other effect 2: .05 Effect Size: Interpretation
  • 59. • For theoretically guided research, compare to predictions of competing theories • The lag effect in memory: • Is this about intervening items or time? Study RACCOON 5 sec. Study WITCH 5 sec. Study VIKING 5 sec. Study RACCOON 5 sec. 1 sec 1 sec 1 sec 1 day Study RACCOON 5 sec. Study WITCH 5 sec. Study VIKING 5 sec. Study RACCOON 5 sec. 1 sec 1 sec 1 sec 1 day POOR recall of RACCOON GOOD recall of RACCOON Effect Size: Interpretation
  • 60. Effect Size: Interpretation • Is lag effect about intervening items or time? • Intervening items hypothesis predicts A > B • Time hypothesis predicts B > A • Goal here is to use direction of the effect to adjudicate between competing hypotheses • Not whether the lag effect is “small” or “large” Study RACCOON 5 sec. Study WITCH 5 sec. Study VIKING 5 sec. Study RACCOON 5 sec. 1 sec 1 sec 1 sec 1 day TEST A: Study RACCOON 5 sec. Study WITCH 5 sec. Study RACCOON 5 sec. 10 sec 10 sec 1 day TEST B: