template script for analyses
Dani Grant
2023-03-09
1. does condition predict donations?
a. raw donated
summary(m1 <- lmer(donate ~ indiv_1 + charity_1 + (indiv_1 + charity_1 | participant) + (1 | stimulus),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 100000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ indiv_1 + charity_1 + (indiv_1 + charity_1 | participant) +
## (1 | stimulus)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
##
## REML criterion at convergence: -6459
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.0574 -0.4435 -0.0785 0.2429 5.7846
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 9.628e-03 0.098123
## indiv_1 7.087e-03 0.084183 0.77
## charity_1 7.300e-03 0.085441 0.67 0.91
## stimulus (Intercept) 4.279e-05 0.006541
## Residual 2.633e-02 0.162251
## Number of obs: 9828, groups: participant, 378; stimulus, 21
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.115520 0.008937 9.028766 12.926 3.95e-07 ***
## indiv_1 0.072178 0.009186 8.337363 7.857 3.95e-05 ***
## charity_1 0.066646 0.009217 8.448168 7.231 6.81e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1
## indiv_1 -0.458
## charity_1 -0.480 0.848summary(m2 <- lmer(donate ~ pract_1 + charity_1 + (pract_1 + charity_1 | participant) + (1 | stimulus),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 100000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ pract_1 + charity_1 + (pract_1 + charity_1 | participant) +
## (1 | stimulus)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
##
## REML criterion at convergence: -6459
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.0574 -0.4435 -0.0785 0.2429 5.7846
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 2.942e-02 0.171515
## pract_1 7.087e-03 0.084183 -0.93
## charity_1 1.257e-03 0.035452 -0.21 0.17
## stimulus (Intercept) 4.279e-05 0.006541
## Residual 2.633e-02 0.162251
## Number of obs: 9828, groups: participant, 378; stimulus, 21
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.187698 0.009438 303.975061 19.888 < 2e-16 ***
## pract_1 -0.072178 0.009186 8.337351 -7.857 3.95e-05 ***
## charity_1 -0.005532 0.005080 23.050532 -1.089 0.287
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1
## pract_1 -0.540
## charity_1 -0.304 0.270summary(m3 <- lmer(donate ~ pract_1 + indiv_1 + (indiv_1 + pract_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 100000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ pract_1 + indiv_1 + (indiv_1 + pract_1 | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
##
## REML criterion at convergence: -6456.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.0330 -0.4495 -0.0798 0.2411 5.7928
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.028166 0.16783
## indiv_1 0.001250 0.03536 0.00
## pract_1 0.007291 0.08539 -0.90 0.24
## Residual 0.026359 0.16235
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.182167 0.009027 393.417752 20.180 <2e-16 ***
## pract_1 -0.066646 0.006155 409.930194 -10.828 <2e-16 ***
## indiv_1 0.005532 0.004154 393.417998 1.332 0.184
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1
## pract_1 -0.741
## indiv_1 -0.186 0.348tab_model(m1, m2, m3)| donate | donate | donate | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.12 | 0.10 – 0.13 | <0.001 | 0.19 | 0.17 – 0.21 | <0.001 | 0.18 | 0.16 – 0.20 | <0.001 |
| indiv_1 | 0.07 | 0.05 – 0.09 | <0.001 | 0.01 | -0.00 – 0.01 | 0.183 | |||
| charity_1 | 0.07 | 0.05 – 0.08 | <0.001 | -0.01 | -0.02 – 0.00 | 0.276 | |||
| pract_1 | -0.07 | -0.09 – -0.05 | <0.001 | -0.07 | -0.08 – -0.05 | <0.001 | |||
| Random Effects | |||||||||
| σ2 | 0.03 | 0.03 | 0.03 | ||||||
| τ00 | 0.01 participant | 0.03 participant | 0.03 participant | ||||||
| 0.00 stimulus | 0.00 stimulus | ||||||||
| τ11 | 0.01 participant.indiv_1 | 0.01 participant.pract_1 | 0.00 participant.indiv_1 | ||||||
| 0.01 participant.charity_1 | 0.00 participant.charity_1 | 0.01 participant.pract_1 | |||||||
| ρ01 | 0.77 participant.indiv_1 | -0.93 participant.pract_1 | -0.00 | ||||||
| 0.67 participant.charity_1 | -0.21 participant.charity_1 | -0.90 | |||||||
| ICC | 0.48 | 0.48 | 0.48 | ||||||
| N | 378 participant | 378 participant | 378 participant | ||||||
| 21 stimulus | 21 stimulus | ||||||||
| Observations | 9828 | 9828 | 9828 | ||||||
| Marginal R2 / Conditional R2 | 0.017 / 0.490 | 0.017 / 0.490 | 0.017 / 0.489 | ||||||
b. proportion donated
singular random intercepts for stimulus
summary(m4 <- lmer(propDonate ~ indiv_1 + charity_1 + (indiv_1 + charity_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 100000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ indiv_1 + charity_1 + (indiv_1 + charity_1 | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
##
## REML criterion at convergence: -3361.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7629 -0.3035 -0.0273 0.2403 5.0872
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.04671 0.2161
## indiv_1 0.03234 0.1798 0.16
## charity_1 0.03400 0.1844 0.10 0.82
## Residual 0.03240 0.1800
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.22262 0.01174 376.99978 18.960 <2e-16 ***
## indiv_1 0.10333 0.01041 377.00014 9.924 <2e-16 ***
## charity_1 0.09376 0.01062 377.00049 8.828 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1
## indiv_1 0.016
## charity_1 -0.028 0.780summary(m5 <- lmer(propDonate ~ pract_1 + charity_1 + (pract_1 + charity_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 100000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ pract_1 + charity_1 + (pract_1 + charity_1 | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
##
## REML criterion at convergence: -3361.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7629 -0.3035 -0.0273 0.2403 5.0872
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.09129 0.3021
## pract_1 0.03234 0.1798 -0.71
## charity_1 0.01189 0.1091 -0.22 0.26
## Residual 0.03240 0.1800
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.325947 0.015814 376.999200 20.611 <2e-16 ***
## pract_1 -0.103330 0.010412 376.999394 -9.924 <2e-16 ***
## charity_1 -0.009566 0.006972 376.999890 -1.372 0.171
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1
## pract_1 -0.670
## charity_1 -0.249 0.304summary(m6 <- lmer(propDonate ~ pract_1 + indiv_1 + (indiv_1 + pract_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 100000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ pract_1 + indiv_1 + (indiv_1 + pract_1 | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 1e+05))
##
## REML criterion at convergence: -3361.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7629 -0.3035 -0.0273 0.2403 5.0872
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.08892 0.2982
## indiv_1 0.01189 0.1091 -0.15
## pract_1 0.03400 0.1844 -0.69 0.34
## Residual 0.03240 0.1800
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.316381 0.015615 376.999713 20.262 <2e-16 ***
## pract_1 -0.093764 0.010621 376.999985 -8.828 <2e-16 ***
## indiv_1 0.009566 0.006972 376.999948 1.372 0.171
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1
## pract_1 -0.660
## indiv_1 -0.194 0.358tab_model(m4, m5, m6)| propDonate | propDonate | propDonate | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.22 | 0.20 – 0.25 | <0.001 | 0.33 | 0.29 – 0.36 | <0.001 | 0.32 | 0.29 – 0.35 | <0.001 |
| indiv_1 | 0.10 | 0.08 – 0.12 | <0.001 | 0.01 | -0.00 – 0.02 | 0.170 | |||
| charity_1 | 0.09 | 0.07 – 0.11 | <0.001 | -0.01 | -0.02 – 0.00 | 0.170 | |||
| pract_1 | -0.10 | -0.12 – -0.08 | <0.001 | -0.09 | -0.11 – -0.07 | <0.001 | |||
| Random Effects | |||||||||
| σ2 | 0.03 | 0.03 | 0.03 | ||||||
| τ00 | 0.05 participant | 0.09 participant | 0.09 participant | ||||||
| τ11 | 0.03 participant.indiv_1 | 0.03 participant.pract_1 | 0.01 participant.indiv_1 | ||||||
| 0.03 participant.charity_1 | 0.01 participant.charity_1 | 0.03 participant.pract_1 | |||||||
| ρ01 | 0.16 | -0.71 | -0.15 | ||||||
| 0.10 | -0.22 | -0.69 | |||||||
| ICC | 0.71 | 0.71 | 0.71 | ||||||
| N | 378 participant | 378 participant | 378 participant | ||||||
| Observations | 9828 | 9828 | 9828 | ||||||
| Marginal R2 / Conditional R2 | 0.015 / 0.716 | 0.015 / 0.716 | 0.015 / 0.716 | ||||||
2. do people donate more when allocated more money?
a. raw donated
singular with money.c random slopes
summary(m7 <- lmer(donate ~ (indiv_1 + charity_1) * money.c + (indiv_1 + charity_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (indiv_1 + charity_1) * money.c + (indiv_1 + charity_1 |
## participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -9297.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.0659 -0.5861 -0.0534 0.4791 5.7562
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.010854 0.10418
## indiv_1 0.009049 0.09513 0.52
## charity_1 0.009262 0.09624 0.44 0.85
## Residual 0.018968 0.13772
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.253e-01 6.109e-03 3.818e+02 20.507 < 2e-16 ***
## indiv_1 5.819e-02 6.129e-03 3.820e+02 9.493 < 2e-16 ***
## charity_1 5.275e-02 6.175e-03 3.820e+02 8.543 3.17e-16 ***
## money.c 2.224e-01 1.111e-02 8.691e+03 20.014 < 2e-16 ***
## indiv_1:money.c 9.999e-02 1.383e-02 8.691e+03 7.228 5.32e-13 ***
## charity_1:money.c 9.250e-02 1.383e-02 8.691e+03 6.686 2.44e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 mony.c in_1:.
## indiv_1 0.132
## charity_1 0.080 0.772
## money.c 0.080 -0.079 -0.079
## indv_1:mny. -0.064 0.053 0.063 -0.803
## chrty_1:mn. -0.064 0.064 0.053 -0.803 0.645summary(m8 <- lmer(donate ~ (pract_1 + charity_1) * money.c + (pract_1 + charity_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (pract_1 + charity_1) * money.c + (pract_1 + charity_1 |
## participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -9297.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.0659 -0.5861 -0.0534 0.4791 5.7562
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.030153 0.17365
## pract_1 0.009049 0.09513 -0.86
## charity_1 0.002728 0.05223 -0.22 0.25
## Residual 0.018968 0.13772
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.835e-01 9.209e-03 3.771e+02 19.922 < 2e-16 ***
## pract_1 -5.819e-02 6.129e-03 3.820e+02 -9.493 < 2e-16 ***
## charity_1 -5.433e-03 4.157e-03 3.780e+02 -1.307 0.192
## money.c 3.224e-01 8.241e-03 8.691e+03 39.119 < 2e-16 ***
## pract_1:money.c -9.999e-02 1.383e-02 8.691e+03 -7.228 5.32e-13 ***
## charity_1:money.c -7.497e-03 1.166e-02 8.691e+03 -0.643 0.520
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 mony.c pr_1:.
## pract_1 -0.753
## charity_1 -0.269 0.328
## money.c -0.012 0.018 0.026
## prct_1:mny. 0.007 0.053 -0.016 -0.596
## chrty_1:mn. 0.008 -0.013 -0.037 -0.707 0.421tab_model(m7, m8)| donate | donate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.13 | 0.11 – 0.14 | <0.001 | 0.18 | 0.17 – 0.20 | <0.001 |
| indiv_1 | 0.06 | 0.05 – 0.07 | <0.001 | |||
| charity_1 | 0.05 | 0.04 – 0.06 | <0.001 | -0.01 | -0.01 – 0.00 | 0.191 |
| money.c | 0.22 | 0.20 – 0.24 | <0.001 | 0.32 | 0.31 – 0.34 | <0.001 |
| indiv_1 * money.c | 0.10 | 0.07 – 0.13 | <0.001 | |||
| charity_1 * money.c | 0.09 | 0.07 – 0.12 | <0.001 | -0.01 | -0.03 – 0.02 | 0.520 |
| pract_1 | -0.06 | -0.07 – -0.05 | <0.001 | |||
| pract_1 * money.c | -0.10 | -0.13 – -0.07 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.01 participant | 0.03 participant | ||||
| τ11 | 0.01 participant.indiv_1 | 0.01 participant.pract_1 | ||||
| 0.01 participant.charity_1 | 0.00 participant.charity_1 | |||||
| ρ01 | 0.52 | -0.86 | ||||
| 0.44 | -0.22 | |||||
| ICC | 0.57 | 0.57 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9828 | 9828 | ||||
| Marginal R2 / Conditional R2 | 0.144 / 0.632 | 0.144 / 0.632 | ||||
b. proportion donated
summary(m9 <- lmer(propDonate ~ (indiv_1 + charity_1) * money.c + (indiv_1 + charity_1 + money.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (indiv_1 + charity_1) * money.c + (indiv_1 + charity_1 +
## money.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -3360.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7916 -0.3035 -0.0321 0.2403 5.1241
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.046946 0.21667
## indiv_1 0.032676 0.18076 0.15
## charity_1 0.034262 0.18510 0.10 0.82
## money.c 0.005801 0.07616 0.11 -0.15 -0.10
## Residual 0.031937 0.17871
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.225e-01 1.178e-02 3.787e+02 18.891 <2e-16 ***
## indiv_1 1.036e-01 1.046e-02 3.789e+02 9.901 <2e-16 ***
## charity_1 9.399e-02 1.066e-02 3.788e+02 8.819 <2e-16 ***
## money.c -3.551e-03 1.494e-02 3.891e+03 -0.238 0.812
## indiv_1:money.c -1.497e-03 1.795e-02 8.314e+03 -0.083 0.934
## charity_1:money.c -1.661e-03 1.795e-02 8.314e+03 -0.093 0.926
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 mony.c in_1:.
## indiv_1 0.008
## charity_1 -0.034 0.782
## money.c 0.080 -0.093 -0.080
## indv_1:mny. -0.043 0.041 0.048 -0.775
## chrty_1:mn. -0.043 0.049 0.040 -0.775 0.645summary(m10 <- lmer(propDonate ~ (pract_1 + charity_1) * money.c + (pract_1 + charity_1 + money.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (pract_1 + charity_1) * money.c + (pract_1 + charity_1 +
## money.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -3360.6
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.7916 -0.3035 -0.0321 0.2403 5.1241
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.091341 0.30223
## pract_1 0.032676 0.18076 -0.71
## charity_1 0.011988 0.10949 -0.22 0.26
## money.c 0.005801 0.07616 -0.01 0.15 0.08
## Residual 0.031937 0.17871
## Number of obs: 9828, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.260e-01 1.581e-02 3.770e+02 20.614 <2e-16 ***
## pract_1 -1.036e-01 1.046e-02 3.789e+02 -9.901 <2e-16 ***
## charity_1 -9.564e-03 6.975e-03 3.776e+02 -1.371 0.171
## money.c -5.048e-03 1.139e-02 1.651e+03 -0.443 0.658
## pract_1:money.c 1.497e-03 1.795e-02 8.314e+03 0.083 0.934
## charity_1:money.c -1.642e-04 1.512e-02 8.314e+03 -0.011 0.991
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 mony.c pr_1:.
## pract_1 -0.668
## charity_1 -0.249 0.305
## money.c -0.011 0.058 0.042
## prct_1:mny. 0.005 0.041 -0.012 -0.559
## chrty_1:mn. 0.006 -0.010 -0.029 -0.664 0.421tab_model(m9, m10)| propDonate | propDonate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.22 | 0.20 – 0.25 | <0.001 | 0.33 | 0.30 – 0.36 | <0.001 |
| indiv_1 | 0.10 | 0.08 – 0.12 | <0.001 | |||
| charity_1 | 0.09 | 0.07 – 0.11 | <0.001 | -0.01 | -0.02 – 0.00 | 0.170 |
| money.c | -0.00 | -0.03 – 0.03 | 0.812 | -0.01 | -0.03 – 0.02 | 0.658 |
| indiv_1 * money.c | -0.00 | -0.04 – 0.03 | 0.934 | |||
| charity_1 * money.c | -0.00 | -0.04 – 0.03 | 0.926 | -0.00 | -0.03 – 0.03 | 0.991 |
| pract_1 | -0.10 | -0.12 – -0.08 | <0.001 | |||
| pract_1 * money.c | 0.00 | -0.03 – 0.04 | 0.934 | |||
| Random Effects | ||||||
| σ2 | 0.03 | 0.03 | ||||
| τ00 | 0.05 participant | 0.09 participant | ||||
| τ11 | 0.03 participant.indiv_1 | 0.03 participant.pract_1 | ||||
| 0.03 participant.charity_1 | 0.01 participant.charity_1 | |||||
| 0.01 participant.money.c | 0.01 participant.money.c | |||||
| ρ01 | 0.15 | -0.71 | ||||
| 0.10 | -0.22 | |||||
| 0.11 | -0.01 | |||||
| ICC | 0.72 | 0.72 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9828 | 9828 | ||||
| Marginal R2 / Conditional R2 | 0.015 / 0.720 | 0.015 / 0.720 | ||||
5. do people donate more when stimluli are in greater need?
a. raw donated
singular with need.c random slopes
summary(m11 <- lmer(donate ~ (indiv_1 + charity_1) * need.c + (indiv_1 + charity_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (indiv_1 + charity_1) * need.c + (indiv_1 + charity_1 |
## participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -7466.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3677 -0.5030 -0.0963 0.3431 5.4545
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.006651 0.08156
## indiv_1 0.004793 0.06923 0.90
## charity_1 0.005180 0.07198 0.90 0.93
## Residual 0.024062 0.15512
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.473e-01 5.782e-03 4.498e+02 25.468 < 2e-16 ***
## indiv_1 3.144e-02 5.929e-03 4.595e+02 5.303 1.77e-07 ***
## charity_1 1.788e-02 6.059e-03 4.775e+02 2.952 0.00332 **
## need.c 3.060e-02 2.204e-03 5.439e+02 13.883 < 2e-16 ***
## indiv_1:need.c 1.212e-02 2.647e-03 9.194e+02 4.580 5.30e-06 ***
## charity_1:need.c 1.073e-02 2.680e-03 9.478e+02 4.005 6.68e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 need.c in_1:.
## indiv_1 -0.071
## charity_1 -0.058 0.788
## need.c 0.395 -0.391 -0.388
## indv_1:nd.c -0.306 0.265 0.286 -0.775
## chrty_1:nd. -0.303 0.292 0.221 -0.765 0.673summary(m12 <- lmer(donate ~ (pract_1 + charity_1) * need.c + (pract_1 + charity_1 | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (pract_1 + charity_1) * need.c + (pract_1 + charity_1 |
## participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -7466.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3677 -0.5030 -0.0963 0.3431 5.4545
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.0216369 0.14709
## pract_1 0.0047931 0.06923 -0.97
## charity_1 0.0007369 0.02715 0.00 0.09
## Residual 0.0240625 0.15512
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.787e-01 7.983e-03 3.735e+02 22.385 < 2e-16 ***
## pract_1 -3.144e-02 5.929e-03 4.596e+02 -5.303 1.77e-07 ***
## charity_1 -1.356e-02 3.901e-03 3.892e+02 -3.477 0.000565 ***
## need.c 4.272e-02 1.681e-03 3.715e+03 25.410 < 2e-16 ***
## pract_1:need.c -1.212e-02 2.647e-03 9.194e+02 -4.580 5.30e-06 ***
## charity_1:need.c -1.390e-03 2.156e-03 1.685e+03 -0.645 0.519223
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 need.c pr_1:.
## pract_1 -0.691
## charity_1 -0.207 0.295
## need.c -0.044 0.095 0.054
## prct_1:nd.c 0.025 0.265 -0.041 -0.559
## chrty_1:nd. 0.027 -0.037 -0.174 -0.617 0.392tab_model(m11, m12)| donate | donate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.15 | 0.14 – 0.16 | <0.001 | 0.18 | 0.16 – 0.19 | <0.001 |
| indiv_1 | 0.03 | 0.02 – 0.04 | <0.001 | |||
| charity_1 | 0.02 | 0.01 – 0.03 | 0.003 | -0.01 | -0.02 – -0.01 | 0.001 |
| need.c | 0.03 | 0.03 – 0.03 | <0.001 | 0.04 | 0.04 – 0.05 | <0.001 |
| indiv_1 * need.c | 0.01 | 0.01 – 0.02 | <0.001 | |||
| charity_1 * need.c | 0.01 | 0.01 – 0.02 | <0.001 | -0.00 | -0.01 – 0.00 | 0.519 |
| pract_1 | -0.03 | -0.04 – -0.02 | <0.001 | |||
| pract_1 * need.c | -0.01 | -0.02 – -0.01 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.01 participant | 0.02 participant | ||||
| τ11 | 0.00 participant.indiv_1 | 0.00 participant.pract_1 | ||||
| 0.01 participant.charity_1 | 0.00 participant.charity_1 | |||||
| ρ01 | 0.90 | -0.97 | ||||
| 0.90 | -0.00 | |||||
| ICC | 0.43 | 0.43 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.118 / 0.501 | 0.118 / 0.501 | ||||
################################
mplot <- lmer(donate ~ condition * need.c + (condition | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d)
(p <- plot_model(mplot, type = "pred",
terms = c("need.c", "condition")) +
ggtitle("") +
ylab("proportion donated") +
xlab("mean-centered need rating") +
theme_minimal() +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.line = element_line(colour = "black"),
legend.position = c(.5, .8),
legend.direction = "horizontal",
legend.box = "horizontal",
legend.background = element_rect(fill = "white", color = "white"),
legend.title = element_blank()) +
scale_color_manual(
labels = c("charity","individual", "practice"),
values = c("blue", "red", "purple")) +
scale_fill_manual(values = c("blue", "red", "purple")) +
scale_x_continuous(breaks = c(-2.5, -2, -1.5, -1, -.5, 0, .5, 1, 1.5, 2, 2.5),
limits = c(-2.5, 3)) +
scale_y_continuous(breaks = c(0, .10, .20, .30, .40),
limits = c(0, .4)))## Scale for 'colour' is already present. Adding another scale for 'colour',
## which will replace the existing scale.## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.## Warning: Removed 3 row(s) containing missing values (geom_path).
b. proportion donated
summary(m13 <- lmer(propDonate ~ (indiv_1 + charity_1) * need.c + (indiv_1 + charity_1 + need.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (indiv_1 + charity_1) * need.c + (indiv_1 + charity_1 +
## need.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -7239.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.0469 -0.3095 -0.0332 0.2562 6.3841
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.052873 0.22994
## indiv_1 0.015099 0.12288 -0.09
## charity_1 0.019118 0.13827 -0.16 0.75
## need.c 0.003384 0.05817 0.62 0.06 -0.11
## Residual 0.020328 0.14258
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.666e-01 1.283e-02 4.056e+02 20.781 < 2e-16 ***
## indiv_1 3.416e-02 8.381e-03 3.852e+02 4.076 5.58e-05 ***
## charity_1 1.093e-02 9.035e-03 3.931e+02 1.210 0.227
## need.c 5.003e-02 4.610e-03 9.271e+02 10.852 < 2e-16 ***
## indiv_1:need.c 2.157e-02 3.779e-03 1.205e+03 5.707 1.45e-08 ***
## charity_1:need.c 2.492e-02 3.871e-03 1.337e+03 6.437 1.70e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 need.c in_1:.
## indiv_1 -0.275
## charity_1 -0.312 0.766
## need.c 0.579 -0.300 -0.365
## indv_1:nd.c -0.247 0.359 0.348 -0.660
## chrty_1:nd. -0.249 0.370 0.303 -0.650 0.800summary(m14 <- lmer(propDonate ~ (pract_1 + charity_1) * need.c + (pract_1 + charity_1 + need.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (pract_1 + charity_1) * need.c + (pract_1 + charity_1 +
## need.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -7239.2
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.0469 -0.3095 -0.0332 0.2562 6.3841
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.063153 0.25130
## pract_1 0.015099 0.12288 -0.41
## charity_1 0.008767 0.09363 -0.21 0.21
## need.c 0.003384 0.05817 0.60 -0.06 -0.25
## Residual 0.020328 0.14258
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.008e-01 1.326e-02 3.695e+02 22.687 < 2e-16 ***
## pract_1 -3.416e-02 8.381e-03 3.852e+02 -4.076 5.58e-05 ***
## charity_1 -2.323e-02 5.988e-03 3.821e+02 -3.879 0.000123 ***
## need.c 7.159e-02 3.539e-03 4.699e+02 20.230 < 2e-16 ***
## pract_1:need.c -2.157e-02 3.779e-03 1.205e+03 -5.707 1.45e-08 ***
## charity_1:need.c 3.352e-03 2.419e-03 3.796e+03 1.386 0.165935
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 need.c pr_1:.
## pract_1 -0.366
## charity_1 -0.237 0.244
## need.c 0.470 0.008 -0.145
## prct_1:nd.c 0.012 0.359 -0.023 -0.208
## chrty_1:nd. 0.008 -0.031 -0.134 -0.311 0.281tab_model(m13, m14)| propDonate | propDonate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.27 | 0.24 – 0.29 | <0.001 | 0.30 | 0.27 – 0.33 | <0.001 |
| indiv_1 | 0.03 | 0.02 – 0.05 | <0.001 | |||
| charity_1 | 0.01 | -0.01 – 0.03 | 0.226 | -0.02 | -0.03 – -0.01 | <0.001 |
| need.c | 0.05 | 0.04 – 0.06 | <0.001 | 0.07 | 0.06 – 0.08 | <0.001 |
| indiv_1 * need.c | 0.02 | 0.01 – 0.03 | <0.001 | |||
| charity_1 * need.c | 0.02 | 0.02 – 0.03 | <0.001 | 0.00 | -0.00 – 0.01 | 0.166 |
| pract_1 | -0.03 | -0.05 – -0.02 | <0.001 | |||
| pract_1 * need.c | -0.02 | -0.03 – -0.01 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.05 participant | 0.06 participant | ||||
| τ11 | 0.02 participant.indiv_1 | 0.02 participant.pract_1 | ||||
| 0.02 participant.charity_1 | 0.01 participant.charity_1 | |||||
| 0.00 participant.need.c | 0.00 participant.need.c | |||||
| ρ01 | -0.09 | -0.41 | ||||
| -0.16 | -0.21 | |||||
| 0.62 | 0.60 | |||||
| ICC | 0.78 | 0.78 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.149 / 0.812 | 0.149 / 0.812 | ||||
mplot <- lmer(propDonate ~ condition * need.c + (condition + need.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d)
(p <- plot_model(mplot, type = "pred",
terms = c("need.c", "condition")) +
ggtitle("") +
ylab("proportion donated") +
xlab("mean-centered need rating") +
theme_minimal() +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.line = element_line(colour = "black"),
legend.position = c(.5, .2),
legend.direction = "horizontal",
legend.box = "horizontal",
legend.background = element_rect(fill = "white", color = "white"),
legend.title = element_blank()) +
scale_color_manual(
labels = c("charity","individual", "practice"),
values = c("blue", "red", "purple")) +
scale_fill_manual(values = c("blue", "red", "purple")) +
scale_x_continuous(breaks = c(-2.5, -2, -1.5, -1, -.5, 0, .5, 1, 1.5, 2, 2.5),
limits = c(-2.5, 3)) +
scale_y_continuous(breaks = c(0, .10, .20, .30, .40, .50, .6),
limits = c(0, .6)))## Scale for 'colour' is already present. Adding another scale for 'colour',
## which will replace the existing scale.## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.## Warning: Removed 3 row(s) containing missing values (geom_path).
6. do people donate more when givig makes a greater difference?
a. raw donated
summary(m15 <- lmer(donate ~ (indiv_1 + charity_1) * diff.c + (indiv_1 + charity_1 + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (indiv_1 + charity_1) * diff.c + (indiv_1 + charity_1 +
## diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -7523.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.4161 -0.4084 -0.0702 0.2069 6.2214
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.008878 0.09423
## indiv_1 0.005802 0.07617 0.76
## charity_1 0.005556 0.07454 0.69 0.95
## diff.c 0.001508 0.03883 0.58 0.04 0.03
## Residual 0.023000 0.15166
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.450e-01 6.368e-03 3.428e+02 22.774 < 2e-16 ***
## indiv_1 4.627e-02 5.929e-03 3.717e+02 7.804 6.14e-14 ***
## charity_1 3.469e-02 5.901e-03 3.600e+02 5.878 9.45e-09 ***
## diff.c 4.483e-02 3.242e-03 3.937e+02 13.827 < 2e-16 ***
## indiv_1:diff.c 2.307e-03 2.797e-03 8.196e+02 0.825 0.410
## charity_1:diff.c 1.509e-03 2.792e-03 7.640e+02 0.541 0.589
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 diff.c in_1:.
## indiv_1 0.028
## charity_1 -0.015 0.793
## diff.c 0.530 -0.165 -0.175
## indv_1:dff. -0.183 0.171 0.172 -0.509
## chrty_1:df. -0.190 0.186 0.157 -0.529 0.738summary(m16 <- lmer(donate ~ (pract_1 + charity_1) * diff.c + (pract_1 + charity_1 + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (pract_1 + charity_1) * diff.c + (pract_1 + charity_1 +
## diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -7523.8
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.4161 -0.4084 -0.0702 0.2069 6.2214
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.0255249 0.15977
## pract_1 0.0058021 0.07617 -0.92
## charity_1 0.0005883 0.02425 -0.26 0.23
## diff.c 0.0015079 0.03883 0.36 -0.04 -0.04
## Residual 0.0229995 0.15166
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 0.191283 0.008822 367.611031 21.682 < 2e-16 ***
## pract_1 -0.046269 0.005929 371.687500 -7.804 6.14e-14 ***
## charity_1 -0.011582 0.003803 378.111539 -3.046 0.00248 **
## diff.c 0.047139 0.003017 353.629492 15.623 < 2e-16 ***
## pract_1:diff.c -0.002307 0.002797 819.576123 -0.825 0.40975
## charity_1:diff.c -0.000798 0.002023 735.736810 -0.395 0.69331
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 diff.c pr_1:.
## pract_1 -0.692
## charity_1 -0.270 0.328
## diff.c 0.276 0.019 -0.014
## prct_1:dff. 0.017 0.171 -0.001 -0.380
## chrty_1:df. 0.007 -0.020 -0.065 -0.366 0.364tab_model(m15, m16)| donate | donate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.15 | 0.13 – 0.16 | <0.001 | 0.19 | 0.17 – 0.21 | <0.001 |
| indiv_1 | 0.05 | 0.03 – 0.06 | <0.001 | |||
| charity_1 | 0.03 | 0.02 – 0.05 | <0.001 | -0.01 | -0.02 – -0.00 | 0.002 |
| diff.c | 0.04 | 0.04 – 0.05 | <0.001 | 0.05 | 0.04 – 0.05 | <0.001 |
| indiv_1 * diff.c | 0.00 | -0.00 – 0.01 | 0.410 | |||
| charity_1 * diff.c | 0.00 | -0.00 – 0.01 | 0.589 | -0.00 | -0.00 – 0.00 | 0.693 |
| pract_1 | -0.05 | -0.06 – -0.03 | <0.001 | |||
| pract_1 * diff.c | -0.00 | -0.01 – 0.00 | 0.410 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.01 participant | 0.03 participant | ||||
| τ11 | 0.01 participant.indiv_1 | 0.01 participant.pract_1 | ||||
| 0.01 participant.charity_1 | 0.00 participant.charity_1 | |||||
| 0.00 participant.diff.c | 0.00 participant.diff.c | |||||
| ρ01 | 0.76 | -0.92 | ||||
| 0.69 | -0.26 | |||||
| 0.58 | 0.36 | |||||
| ICC | 0.53 | 0.53 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.139 / 0.598 | 0.139 / 0.598 | ||||
####################################################
mplot <- lmer(donate ~ condition * diff.c + (condition + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d)
(p <- plot_model(mplot, type = "pred",
terms = c("condition")) +
ggtitle("") +
ylab("donated") +
xlab("condition") +
theme_minimal() +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.line = element_line(colour = "black"),
legend.position = c(.5, .2),
legend.direction = "horizontal",
legend.box = "horizontal",
legend.background = element_rect(fill = "white", color = "white"),
legend.title = element_blank()) +
scale_fill_manual(values = c("blue", "red", "purple")) +
scale_y_continuous(breaks = c(0, .10, .20, .30, .40, .5),
limits = c(0, .5)))## Scale for 'colour' is already present. Adding another scale for 'colour',
## which will replace the existing scale.## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.
b. proportion donated
summary(m17 <- lmer(propDonate ~ (indiv_1 + charity_1) * diff.c + (indiv_1 + charity_1 + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (indiv_1 + charity_1) * diff.c + (indiv_1 + charity_1 +
## diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -6224.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.4664 -0.3022 -0.0244 0.2402 6.2612
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.051698 0.22737
## indiv_1 0.028345 0.16836 0.11
## charity_1 0.028681 0.16936 0.06 0.84
## diff.c 0.007507 0.08664 0.50 0.07 0.06
## Residual 0.022087 0.14862
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.734e-01 1.281e-02 3.562e+02 21.349 < 2e-16 ***
## indiv_1 6.820e-02 9.917e-03 3.880e+02 6.877 2.45e-11 ***
## charity_1 4.757e-02 9.989e-03 3.806e+02 4.762 2.73e-06 ***
## diff.c 6.390e-02 5.980e-03 4.739e+02 10.684 < 2e-16 ***
## indiv_1:diff.c 2.640e-02 4.132e-03 1.493e+03 6.389 2.23e-10 ***
## charity_1:diff.c 2.413e-02 4.162e-03 1.499e+03 5.797 8.20e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 diff.c in_1:.
## indiv_1 -0.040
## charity_1 -0.079 0.811
## diff.c 0.508 -0.090 -0.094
## indv_1:dff. -0.144 0.175 0.178 -0.484
## chrty_1:df. -0.149 0.186 0.168 -0.495 0.790summary(m18 <- lmer(propDonate ~ (pract_1 + charity_1) * diff.c + (pract_1 + charity_1 + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (pract_1 + charity_1) * diff.c + (pract_1 + charity_1 +
## diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -6224.4
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -5.4664 -0.3022 -0.0244 0.2402 6.2612
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.088465 0.29743
## pract_1 0.028345 0.16836 -0.65
## charity_1 0.009191 0.09587 -0.22 0.27
## diff.c 0.007507 0.08664 0.42 -0.07 -0.01
## Residual 0.022087 0.14862
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.416e-01 1.588e-02 3.655e+02 21.514 < 2e-16 ***
## pract_1 -6.820e-02 9.917e-03 3.880e+02 -6.877 2.45e-11 ***
## charity_1 -2.064e-02 6.114e-03 3.798e+02 -3.375 0.000814 ***
## diff.c 9.030e-02 5.379e-03 3.242e+02 16.786 < 2e-16 ***
## pract_1:diff.c -2.640e-02 4.132e-03 1.493e+03 -6.389 2.23e-10 ***
## charity_1:diff.c -2.270e-03 2.688e-03 1.482e+03 -0.844 0.398612
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 diff.c pr_1:.
## pract_1 -0.592
## charity_1 -0.237 0.296
## diff.c 0.388 -0.035 -0.005
## prct_1:dff. 0.007 0.175 -0.007 -0.230
## chrty_1:df. 0.004 -0.019 -0.053 -0.266 0.314tab_model(m17, m18)| propDonate | propDonate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.27 | 0.25 – 0.30 | <0.001 | 0.34 | 0.31 – 0.37 | <0.001 |
| indiv_1 | 0.07 | 0.05 – 0.09 | <0.001 | |||
| charity_1 | 0.05 | 0.03 – 0.07 | <0.001 | -0.02 | -0.03 – -0.01 | 0.001 |
| diff.c | 0.06 | 0.05 – 0.08 | <0.001 | 0.09 | 0.08 – 0.10 | <0.001 |
| indiv_1 * diff.c | 0.03 | 0.02 – 0.03 | <0.001 | |||
| charity_1 * diff.c | 0.02 | 0.02 – 0.03 | <0.001 | -0.00 | -0.01 – 0.00 | 0.398 |
| pract_1 | -0.07 | -0.09 – -0.05 | <0.001 | |||
| pract_1 * diff.c | -0.03 | -0.03 – -0.02 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.05 participant | 0.09 participant | ||||
| τ11 | 0.03 participant.indiv_1 | 0.03 participant.pract_1 | ||||
| 0.03 participant.charity_1 | 0.01 participant.charity_1 | |||||
| 0.01 participant.diff.c | 0.01 participant.diff.c | |||||
| ρ01 | 0.11 | -0.65 | ||||
| 0.06 | -0.22 | |||||
| 0.50 | 0.42 | |||||
| ICC | 0.82 | 0.82 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.169 / 0.855 | 0.169 / 0.855 | ||||
#########################################
mplot <- lmer(propDonate ~ condition * diff.c + (condition + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d)
(p <- plot_model(mplot, type = "pred",
terms = c("diff.c", "condition")) +
ggtitle("") +
ylab("proportion donated") +
xlab("mean-centered difference rating") +
theme_minimal() +
theme(panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.line = element_line(colour = "black"),
legend.position = c(.5, .2),
legend.direction = "horizontal",
legend.box = "horizontal",
legend.background = element_rect(fill = "white", color = "white"),
legend.title = element_blank()) +
scale_color_manual(
labels = c("charity","individual", "practice"),
values = c("blue", "red", "purple")) +
scale_fill_manual(values = c("blue", "red", "purple")) +
scale_x_continuous(breaks = c(-2.5, -2, -1.5, -1, -.5, 0, .5, 1, 1.5, 2, 2.5),
limits = c(-2, 2)) +
scale_y_continuous(breaks = c(0, .10, .20, .30, .40, .50, .6),
limits = c(0, .6)))## Scale for 'colour' is already present. Adding another scale for 'colour',
## which will replace the existing scale.## Scale for 'y' is already present. Adding another scale for 'y', which will
## replace the existing scale.## Warning: Removed 9 row(s) containing missing values (geom_path).
7. is there an interaction with condition and money allocated while controlling need and difference made
a. raw donated
summary(m15 <- lmer(donate ~ (indiv_1 + charity_1) * money.c + need.c + diff.c +
(indiv_1 + charity_1 + diff.c + money.c + need.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (indiv_1 + charity_1) * money.c + need.c + diff.c +
## (indiv_1 + charity_1 + diff.c + money.c + need.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -15832.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.6753 -0.3386 -0.0286 0.2685 7.8021
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.0150814 0.12281
## indiv_1 0.0045513 0.06746 0.04
## charity_1 0.0053696 0.07328 -0.05 0.74
## diff.c 0.0007508 0.02740 0.15 -0.15 -0.14
## money.c 0.0755429 0.27485 0.83 0.42 0.33 -0.16
## need.c 0.0007198 0.02683 0.71 0.13 -0.10 -0.11 0.62
## Residual 0.0082539 0.09085
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.674e-01 6.837e-03 3.655e+02 24.488 <2e-16 ***
## indiv_1 1.038e-02 4.486e-03 3.373e+02 2.315 0.0212 *
## charity_1 -2.877e-03 4.769e-03 3.478e+02 -0.603 0.5467
## money.c 2.014e-01 1.598e-02 5.468e+02 12.599 <2e-16 ***
## need.c 2.872e-02 1.707e-03 3.533e+02 16.820 <2e-16 ***
## diff.c 1.938e-02 1.949e-03 2.471e+02 9.946 <2e-16 ***
## indiv_1:money.c 1.192e-01 9.297e-03 7.867e+03 12.821 <2e-16 ***
## charity_1:money.c 1.202e-01 9.292e-03 7.852e+03 12.935 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 mony.c need.c diff.c in_1:.
## indiv_1 -0.139
## charity_1 -0.199 0.727
## money.c 0.698 0.260 0.206
## need.c 0.579 -0.022 -0.175 0.451
## diff.c 0.165 -0.092 -0.091 -0.130 -0.262
## indv_1:mny. -0.032 0.042 0.049 -0.374 -0.009 0.049
## chrty_1:mn. -0.030 0.051 0.037 -0.375 -0.007 0.051 0.645summary(m16 <- lmer(donate ~ (pract_1 + charity_1) * money.c + need.c + diff.c +
(pract_1 + charity_1 + diff.c + money.c + need.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (pract_1 + charity_1) * money.c + need.c + diff.c +
## (pract_1 + charity_1 + diff.c + money.c + need.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -15832.9
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.6753 -0.3386 -0.0286 0.2685 7.8021
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.0202944 0.14246
## pract_1 0.0045513 0.06746 -0.51
## charity_1 0.0025626 0.05062 -0.23 0.26
## diff.c 0.0007508 0.02740 0.06 0.15 0.00
## money.c 0.0755429 0.27485 0.92 -0.42 -0.08 -0.16
## need.c 0.0007198 0.02683 0.67 -0.13 -0.32 -0.11 0.62
## Residual 0.0082539 0.09085
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.778e-01 7.639e-03 3.627e+02 23.276 < 2e-16 ***
## pract_1 -1.038e-02 4.486e-03 3.373e+02 -2.315 0.021240 *
## charity_1 -1.326e-02 3.432e-03 3.744e+02 -3.864 0.000131 ***
## money.c 3.206e-01 1.519e-02 4.466e+02 21.108 < 2e-16 ***
## need.c 2.872e-02 1.707e-03 3.533e+02 16.820 < 2e-16 ***
## diff.c 1.939e-02 1.949e-03 2.471e+02 9.946 < 2e-16 ***
## pract_1:money.c -1.192e-01 9.297e-03 7.867e+03 -12.821 < 2e-16 ***
## charity_1:money.c 9.902e-04 7.827e-03 7.855e+03 0.127 0.899335
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 mony.c need.c diff.c pr_1:.
## pract_1 -0.463
## charity_1 -0.260 0.298
## money.c 0.816 -0.299 -0.049
## need.c 0.505 0.022 -0.214 0.469
## diff.c 0.093 0.092 -0.005 -0.107 -0.262
## prct_1:mny. 0.004 0.042 -0.012 -0.218 0.009 -0.049
## chrty_1:mn. 0.007 -0.010 -0.032 -0.258 0.002 0.003 0.422tab_model(m15, m16)| donate | donate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.17 | 0.15 – 0.18 | <0.001 | 0.18 | 0.16 – 0.19 | <0.001 |
| indiv_1 | 0.01 | 0.00 – 0.02 | 0.021 | |||
| charity_1 | -0.00 | -0.01 – 0.01 | 0.546 | -0.01 | -0.02 – -0.01 | <0.001 |
| money.c | 0.20 | 0.17 – 0.23 | <0.001 | 0.32 | 0.29 – 0.35 | <0.001 |
| need.c | 0.03 | 0.03 – 0.03 | <0.001 | 0.03 | 0.03 – 0.03 | <0.001 |
| diff.c | 0.02 | 0.02 – 0.02 | <0.001 | 0.02 | 0.02 – 0.02 | <0.001 |
| indiv_1 * money.c | 0.12 | 0.10 – 0.14 | <0.001 | |||
| charity_1 * money.c | 0.12 | 0.10 – 0.14 | <0.001 | 0.00 | -0.01 – 0.02 | 0.899 |
| pract_1 | -0.01 | -0.02 – -0.00 | 0.021 | |||
| pract_1 * money.c | -0.12 | -0.14 – -0.10 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.01 | 0.01 | ||||
| τ00 | 0.02 participant | 0.02 participant | ||||
| τ11 | 0.00 participant.indiv_1 | 0.00 participant.pract_1 | ||||
| 0.01 participant.charity_1 | 0.00 participant.charity_1 | |||||
| 0.00 participant.diff.c | 0.00 participant.diff.c | |||||
| 0.08 participant.money.c | 0.08 participant.money.c | |||||
| 0.00 participant.need.c | 0.00 participant.need.c | |||||
| ρ01 | 0.04 | -0.51 | ||||
| -0.05 | -0.23 | |||||
| 0.15 | 0.06 | |||||
| 0.83 | 0.92 | |||||
| 0.71 | 0.67 | |||||
| ICC | 0.78 | 0.78 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.256 / 0.836 | 0.256 / 0.836 | ||||
b. proportion donated
summary(m17 <- lmer(propDonate ~ (indiv_1 + charity_1) * money.c + need.c + diff.c +
(indiv_1 + charity_1 + money.c + need.c + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (indiv_1 + charity_1) * money.c + need.c + diff.c +
## (indiv_1 + charity_1 + money.c + need.c + diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -8072
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.4102 -0.3149 -0.0248 0.2524 6.1190
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.050832 0.22546
## indiv_1 0.016355 0.12789 -0.09
## charity_1 0.020152 0.14196 -0.18 0.80
## money.c 0.003838 0.06195 -0.25 0.09 0.10
## need.c 0.002669 0.05166 0.63 0.11 -0.06 -0.20
## diff.c 0.003297 0.05742 0.24 -0.12 -0.11 -0.48 0.02
## Residual 0.017623 0.13275
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.004e-01 1.237e-02 3.641e+02 24.287 < 2e-16 ***
## indiv_1 1.268e-02 7.903e-03 3.295e+02 1.604 0.10966
## charity_1 -1.192e-02 8.577e-03 3.472e+02 -1.389 0.16564
## money.c -4.511e-02 1.142e-02 3.674e+03 -3.950 7.95e-05 ***
## need.c 5.124e-02 3.155e-03 3.609e+02 16.241 < 2e-16 ***
## diff.c 4.456e-02 3.815e-03 2.645e+02 11.682 < 2e-16 ***
## indiv_1:money.c 3.853e-02 1.368e-02 8.001e+03 2.816 0.00488 **
## charity_1:money.c 5.380e-02 1.367e-02 7.973e+03 3.936 8.36e-05 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 mony.c need.c diff.c in_1:.
## indiv_1 -0.190
## charity_1 -0.256 0.778
## money.c -0.033 -0.029 -0.022
## need.c 0.542 -0.002 -0.131 -0.034
## diff.c 0.227 -0.088 -0.082 -0.158 -0.155
## indv_1:mny. -0.026 0.034 0.038 -0.771 -0.010 0.047
## chrty_1:mn. -0.024 0.041 0.029 -0.772 -0.009 0.051 0.646summary(m18 <- lmer(propDonate ~ (pract_1 + charity_1) * money.c + need.c + diff.c +
(pract_1 + charity_1 + money.c + need.c + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (pract_1 + charity_1) * money.c + need.c + diff.c +
## (pract_1 + charity_1 + money.c + need.c + diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -8072
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.4102 -0.3149 -0.0248 0.2524 6.1190
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.062064 0.24913
## pract_1 0.016355 0.12789 -0.43
## charity_1 0.007304 0.08546 -0.23 0.16
## money.c 0.003838 0.06195 -0.18 -0.09 0.04
## need.c 0.002669 0.05166 0.63 -0.11 -0.28 -0.20
## diff.c 0.003297 0.05742 0.16 0.12 0.00 -0.48 0.02
## Residual 0.017623 0.13275
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.131e-01 1.335e-02 3.647e+02 23.452 < 2e-16 ***
## pract_1 -1.268e-02 7.903e-03 3.295e+02 -1.604 0.10966
## charity_1 -2.459e-02 5.525e-03 3.726e+02 -4.451 1.13e-05 ***
## money.c -6.580e-03 8.765e-03 1.593e+03 -0.751 0.45294
## need.c 5.124e-02 3.155e-03 3.609e+02 16.241 < 2e-16 ***
## diff.c 4.456e-02 3.815e-03 2.645e+02 11.682 < 2e-16 ***
## pract_1:money.c -3.853e-02 1.368e-02 8.001e+03 -2.816 0.00488 **
## charity_1:money.c 1.527e-02 1.151e-02 7.997e+03 1.326 0.18483
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 mony.c need.c diff.c pr_1:.
## pract_1 -0.415
## charity_1 -0.248 0.222
## money.c -0.069 -0.015 0.027
## need.c 0.501 0.002 -0.200 -0.060
## diff.c 0.159 0.088 -0.002 -0.133 -0.155
## prct_1:mny. 0.004 0.034 -0.011 -0.557 0.010 -0.047
## chrty_1:mn. 0.007 -0.008 -0.029 -0.659 0.001 0.004 0.422tab_model(m17, m18)| propDonate | propDonate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.30 | 0.28 – 0.32 | <0.001 | 0.31 | 0.29 – 0.34 | <0.001 |
| indiv_1 | 0.01 | -0.00 – 0.03 | 0.109 | |||
| charity_1 | -0.01 | -0.03 – 0.00 | 0.165 | -0.02 | -0.04 – -0.01 | <0.001 |
| money.c | -0.05 | -0.07 – -0.02 | <0.001 | -0.01 | -0.02 – 0.01 | 0.453 |
| need.c | 0.05 | 0.05 – 0.06 | <0.001 | 0.05 | 0.05 – 0.06 | <0.001 |
| diff.c | 0.04 | 0.04 – 0.05 | <0.001 | 0.04 | 0.04 – 0.05 | <0.001 |
| indiv_1 * money.c | 0.04 | 0.01 – 0.07 | 0.005 | |||
| charity_1 * money.c | 0.05 | 0.03 – 0.08 | <0.001 | 0.02 | -0.01 – 0.04 | 0.185 |
| pract_1 | -0.01 | -0.03 – 0.00 | 0.109 | |||
| pract_1 * money.c | -0.04 | -0.07 – -0.01 | 0.005 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.05 participant | 0.06 participant | ||||
| τ11 | 0.02 participant.indiv_1 | 0.02 participant.pract_1 | ||||
| 0.02 participant.charity_1 | 0.01 participant.charity_1 | |||||
| 0.00 participant.money.c | 0.00 participant.money.c | |||||
| 0.00 participant.need.c | 0.00 participant.need.c | |||||
| 0.00 participant.diff.c | 0.00 participant.diff.c | |||||
| ρ01 | -0.09 | -0.43 | ||||
| -0.18 | -0.23 | |||||
| -0.25 | -0.18 | |||||
| 0.63 | 0.63 | |||||
| 0.24 | 0.16 | |||||
| ICC | 0.82 | 0.82 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.196 / 0.853 | 0.196 / 0.853 | ||||
8. is there an interaction with condition and need while controlling money allocted and difference made
a. raw donated
summary(m15 <- lmer(donate ~ (indiv_1 + charity_1) * need.c + diff.c + money.c +
(indiv_1 + charity_1 + diff.c + money.c + need.c | participant) + (1 | stimulus),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (indiv_1 + charity_1) * need.c + diff.c + money.c +
## (indiv_1 + charity_1 + diff.c + money.c + need.c | participant) +
## (1 | stimulus)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -15690.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.5314 -0.3313 -0.0259 0.2600 7.8652
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 1.606e-02 0.126725
## indiv_1 4.128e-03 0.064249 -0.02
## charity_1 5.064e-03 0.071164 -0.11 0.73
## diff.c 7.480e-04 0.027350 0.09 -0.08 -0.06
## money.c 7.543e-02 0.274649 0.88 0.28 0.20 -0.17
## need.c 7.144e-04 0.026729 0.72 0.09 -0.14 -0.15 0.65
## stimulus (Intercept) 1.291e-05 0.003592
## Residual 8.419e-03 0.091753
## Number of obs: 9827, groups: participant, 378; stimulus, 21
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.543e-01 8.113e-03 5.290e+01 19.019 < 2e-16 ***
## indiv_1 2.243e-02 6.036e-03 1.447e+01 3.717 0.00219 **
## charity_1 8.832e-03 6.260e-03 1.669e+01 1.411 0.17667
## need.c 1.425e-02 2.419e-03 7.463e+02 5.890 5.84e-09 ***
## diff.c 1.779e-02 1.942e-03 2.466e+02 9.161 < 2e-16 ***
## money.c 2.961e-01 1.456e-02 3.771e+02 20.345 < 2e-16 ***
## indiv_1:need.c 1.766e-02 2.164e-03 1.059e+03 8.160 9.42e-16 ***
## charity_1:need.c 1.714e-02 2.215e-03 1.114e+03 7.737 2.27e-14 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 need.c diff.c mony.c in_1:.
## indiv_1 -0.446
## charity_1 -0.471 0.808
## need.c 0.524 -0.234 -0.297
## diff.c 0.107 -0.034 -0.030 -0.209
## money.c 0.686 0.143 0.109 0.353 -0.124
## indv_1:nd.c -0.218 0.273 0.275 -0.675 0.015 0.008
## chrty_1:nd. -0.221 0.281 0.232 -0.656 0.002 0.011 0.760summary(m16 <- lmer(donate ~ (pract_1 + charity_1) * need.c + diff.c + money.c +
(pract_1 + charity_1 + diff.c + money.c + need.c | participant) + (1 | stimulus),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (pract_1 + charity_1) * need.c + diff.c + money.c +
## (pract_1 + charity_1 + diff.c + money.c + need.c | participant) +
## (1 | stimulus)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -15690.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.5314 -0.3313 -0.0259 0.2600 7.8652
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 1.988e-02 0.140988
## pract_1 4.128e-03 0.064249 -0.44
## charity_1 2.520e-03 0.050204 -0.23 0.25
## diff.c 7.480e-04 0.027350 0.05 0.08 0.02
## money.c 7.543e-02 0.274649 0.91 -0.28 -0.07 -0.17
## need.c 7.144e-04 0.026729 0.69 -0.09 -0.31 -0.15 0.65
## stimulus (Intercept) 1.291e-05 0.003592
## Residual 8.419e-03 0.091753
## Number of obs: 9827, groups: participant, 378; stimulus, 21
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.767e-01 7.653e-03 3.489e+02 23.095 < 2e-16 ***
## pract_1 -2.243e-02 6.036e-03 1.447e+01 -3.717 0.002186 **
## charity_1 -1.360e-02 3.812e-03 6.273e+01 -3.568 0.000696 ***
## need.c 3.191e-02 1.861e-03 5.040e+02 17.143 < 2e-16 ***
## diff.c 1.779e-02 1.942e-03 2.466e+02 9.161 < 2e-16 ***
## money.c 2.961e-01 1.456e-02 3.771e+02 20.345 < 2e-16 ***
## pract_1:need.c -1.766e-02 2.164e-03 1.059e+03 -8.160 9.42e-16 ***
## charity_1:need.c -5.205e-04 1.519e-03 2.965e+03 -0.343 0.731866
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 need.c diff.c mony.c pr_1:.
## pract_1 -0.316
## charity_1 -0.274 0.256
## need.c 0.464 -0.013 -0.131
## diff.c 0.087 0.034 0.005 -0.255
## money.c 0.840 -0.143 -0.047 0.468 -0.124
## prct_1:nd.c 0.016 0.273 -0.020 -0.285 -0.015 -0.008
## chrty_1:nd. 0.005 -0.021 -0.121 -0.361 -0.018 0.004 0.317tab_model(m15, m16)| donate | donate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.15 | 0.14 – 0.17 | <0.001 | 0.18 | 0.16 – 0.19 | <0.001 |
| indiv_1 | 0.02 | 0.01 – 0.03 | <0.001 | |||
| charity_1 | 0.01 | -0.00 – 0.02 | 0.158 | -0.01 | -0.02 – -0.01 | <0.001 |
| need.c | 0.01 | 0.01 – 0.02 | <0.001 | 0.03 | 0.03 – 0.04 | <0.001 |
| diff.c | 0.02 | 0.01 – 0.02 | <0.001 | 0.02 | 0.01 – 0.02 | <0.001 |
| money.c | 0.30 | 0.27 – 0.32 | <0.001 | 0.30 | 0.27 – 0.32 | <0.001 |
| indiv_1 * need.c | 0.02 | 0.01 – 0.02 | <0.001 | |||
| charity_1 * need.c | 0.02 | 0.01 – 0.02 | <0.001 | -0.00 | -0.00 – 0.00 | 0.732 |
| pract_1 | -0.02 | -0.03 – -0.01 | <0.001 | |||
| pract_1 * need.c | -0.02 | -0.02 – -0.01 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.01 | 0.01 | ||||
| τ00 | 0.02 participant | 0.02 participant | ||||
| 0.00 stimulus | 0.00 stimulus | |||||
| τ11 | 0.00 participant.indiv_1 | 0.00 participant.pract_1 | ||||
| 0.01 participant.charity_1 | 0.00 participant.charity_1 | |||||
| 0.00 participant.diff.c | 0.00 participant.diff.c | |||||
| 0.08 participant.money.c | 0.08 participant.money.c | |||||
| 0.00 participant.need.c | 0.00 participant.need.c | |||||
| ρ01 | -0.02 participant.indiv_1 | -0.44 participant.pract_1 | ||||
| -0.11 participant.charity_1 | -0.23 participant.charity_1 | |||||
| 0.09 participant.diff.c | 0.05 participant.diff.c | |||||
| 0.88 participant.money.c | 0.91 participant.money.c | |||||
| 0.72 participant.need.c | 0.69 participant.need.c | |||||
| ICC | 0.77 | 0.77 | ||||
| N | 378 participant | 378 participant | ||||
| 21 stimulus | 21 stimulus | |||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.251 / 0.831 | 0.251 / 0.831 | ||||
b. proportion donated
summary(m17 <- lmer(propDonate ~ (indiv_1 + charity_1) * need.c + diff.c + money.c +
(indiv_1 + charity_1 + money.c + need.c + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (indiv_1 + charity_1) * need.c + diff.c + money.c +
## (indiv_1 + charity_1 + money.c + need.c + diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -8087.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.4031 -0.3154 -0.0271 0.2498 6.1310
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.052305 0.22870
## indiv_1 0.015067 0.12275 -0.11
## charity_1 0.019075 0.13811 -0.20 0.79
## money.c 0.003852 0.06206 -0.23 0.08 0.09
## need.c 0.002655 0.05153 0.65 0.10 -0.08 -0.20
## diff.c 0.003284 0.05731 0.21 -0.08 -0.06 -0.48 0.01
## Residual 0.017608 0.13270
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.805e-01 1.297e-02 4.026e+02 21.625 < 2e-16 ***
## indiv_1 3.138e-02 8.332e-03 3.872e+02 3.766 0.000191 ***
## charity_1 6.490e-03 8.979e-03 4.003e+02 0.723 0.470244
## need.c 3.199e-02 4.440e-03 9.741e+02 7.205 1.16e-12 ***
## diff.c 4.401e-02 3.804e-03 2.636e+02 11.570 < 2e-16 ***
## money.c -7.499e-03 6.021e-03 3.766e+02 -1.245 0.213787
## indiv_1:need.c 2.191e-02 3.685e-03 1.248e+03 5.945 3.58e-09 ***
## charity_1:need.c 2.223e-02 3.790e-03 1.414e+03 5.867 5.53e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 need.c diff.c mony.c in_1:.
## indiv_1 -0.284
## charity_1 -0.337 0.795
## need.c 0.562 -0.285 -0.343
## diff.c 0.194 -0.054 -0.046 -0.119
## money.c -0.109 0.020 0.025 -0.085 -0.213
## indv_1:nd.c -0.248 0.367 0.352 -0.679 0.012 0.035
## chrty_1:nd. -0.250 0.376 0.314 -0.664 0.001 0.042 0.813summary(m18 <- lmer(propDonate ~ (pract_1 + charity_1) * need.c + diff.c + money.c +
(pract_1 + charity_1 + money.c + need.c + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (pract_1 + charity_1) * need.c + diff.c + money.c +
## (pract_1 + charity_1 + money.c + need.c + diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -8087.5
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.4031 -0.3154 -0.0271 0.2498 6.1310
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.061299 0.24759
## pract_1 0.015067 0.12275 -0.40
## charity_1 0.007340 0.08567 -0.23 0.16
## money.c 0.003852 0.06206 -0.18 -0.08 0.04
## need.c 0.002655 0.05153 0.65 -0.10 -0.27 -0.20
## diff.c 0.003284 0.05731 0.15 0.08 0.01 -0.48 0.01
## Residual 0.017608 0.13270
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.118e-01 1.327e-02 3.645e+02 23.495 < 2e-16 ***
## pract_1 -3.138e-02 8.332e-03 3.872e+02 -3.766 0.000191 ***
## charity_1 -2.489e-02 5.571e-03 3.786e+02 -4.467 1.05e-05 ***
## need.c 5.390e-02 3.330e-03 4.511e+02 16.187 < 2e-16 ***
## diff.c 4.401e-02 3.804e-03 2.636e+02 11.570 < 2e-16 ***
## money.c -7.499e-03 6.021e-03 3.766e+02 -1.245 0.213787
## pract_1:need.c -2.191e-02 3.685e-03 1.248e+03 -5.945 3.58e-09 ***
## charity_1:need.c 3.227e-04 2.287e-03 3.472e+03 0.141 0.887806
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 need.c diff.c mony.c pr_1:.
## pract_1 -0.350
## charity_1 -0.248 0.214
## need.c 0.481 -0.026 -0.150
## diff.c 0.156 0.054 0.006 -0.146
## money.c -0.094 -0.020 0.010 -0.075 -0.213
## prct_1:nd.c 0.011 0.367 -0.018 -0.202 -0.012 -0.035
## chrty_1:nd. 0.005 -0.031 -0.122 -0.301 -0.017 0.014 0.264tab_model(m17, m18)| propDonate | propDonate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.28 | 0.26 – 0.31 | <0.001 | 0.31 | 0.29 – 0.34 | <0.001 |
| indiv_1 | 0.03 | 0.02 – 0.05 | <0.001 | |||
| charity_1 | 0.01 | -0.01 – 0.02 | 0.470 | -0.02 | -0.04 – -0.01 | <0.001 |
| need.c | 0.03 | 0.02 – 0.04 | <0.001 | 0.05 | 0.05 – 0.06 | <0.001 |
| diff.c | 0.04 | 0.04 – 0.05 | <0.001 | 0.04 | 0.04 – 0.05 | <0.001 |
| money.c | -0.01 | -0.02 – 0.00 | 0.213 | -0.01 | -0.02 – 0.00 | 0.213 |
| indiv_1 * need.c | 0.02 | 0.01 – 0.03 | <0.001 | |||
| charity_1 * need.c | 0.02 | 0.01 – 0.03 | <0.001 | 0.00 | -0.00 – 0.00 | 0.888 |
| pract_1 | -0.03 | -0.05 – -0.02 | <0.001 | |||
| pract_1 * need.c | -0.02 | -0.03 – -0.01 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.05 participant | 0.06 participant | ||||
| τ11 | 0.02 participant.indiv_1 | 0.02 participant.pract_1 | ||||
| 0.02 participant.charity_1 | 0.01 participant.charity_1 | |||||
| 0.00 participant.money.c | 0.00 participant.money.c | |||||
| 0.00 participant.need.c | 0.00 participant.need.c | |||||
| 0.00 participant.diff.c | 0.00 participant.diff.c | |||||
| ρ01 | -0.11 | -0.40 | ||||
| -0.20 | -0.23 | |||||
| -0.23 | -0.18 | |||||
| 0.65 | 0.65 | |||||
| 0.21 | 0.15 | |||||
| ICC | 0.82 | 0.82 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.193 / 0.852 | 0.193 / 0.852 | ||||
9. is there an interaction with condition and difference made while controlling money allocted and need
a. raw donated
summary(m15 <- lmer(donate ~ (indiv_1 + charity_1) * diff.c + money.c + need.c +
(indiv_1 + charity_1 + diff.c + money.c + need.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (indiv_1 + charity_1) * diff.c + money.c + need.c +
## (indiv_1 + charity_1 + diff.c + money.c + need.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -15668
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.5092 -0.3304 -0.0278 0.2521 7.8654
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.0159874 0.12644
## indiv_1 0.0046685 0.06833 -0.03
## charity_1 0.0052822 0.07268 -0.11 0.75
## diff.c 0.0007301 0.02702 0.11 -0.08 -0.07
## money.c 0.0757557 0.27524 0.86 0.30 0.21 -0.16
## need.c 0.0007187 0.02681 0.72 0.08 -0.14 -0.13 0.63
## Residual 0.0084124 0.09172
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.634e-01 7.085e-03 3.683e+02 23.059 < 2e-16 ***
## indiv_1 1.393e-02 4.629e-03 3.435e+02 3.009 0.00282 **
## charity_1 3.023e-04 4.842e-03 3.531e+02 0.062 0.95026
## diff.c 5.955e-03 2.563e-03 5.871e+02 2.323 0.02050 *
## money.c 2.972e-01 1.459e-02 3.774e+02 20.372 < 2e-16 ***
## need.c 2.890e-02 1.711e-03 3.530e+02 16.894 < 2e-16 ***
## indiv_1:diff.c 1.429e-02 2.260e-03 1.010e+03 6.323 3.84e-10 ***
## charity_1:diff.c 1.525e-02 2.257e-03 1.038e+03 6.757 2.35e-11 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 diff.c mony.c need.c in_1:.
## indiv_1 -0.209
## charity_1 -0.260 0.737
## diff.c 0.195 -0.173 -0.159
## money.c 0.773 0.212 0.154 -0.101
## need.c 0.576 -0.051 -0.197 -0.213 0.497
## indv_1:dff. -0.133 0.189 0.188 -0.608 0.019 -0.008
## chrty_1:df. -0.138 0.197 0.162 -0.622 0.020 0.011 0.758summary(m16 <- lmer(donate ~ (pract_1 + charity_1) * diff.c + money.c + need.c +
(pract_1 + charity_1 + diff.c + money.c + need.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: donate ~ (pract_1 + charity_1) * diff.c + money.c + need.c +
## (pract_1 + charity_1 + diff.c + money.c + need.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -15668
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -7.5092 -0.3304 -0.0278 0.2521 7.8654
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.0201179 0.14184
## pract_1 0.0046685 0.06833 -0.45
## charity_1 0.0025360 0.05036 -0.24 0.28
## diff.c 0.0007301 0.02702 0.06 0.08 0.01
## money.c 0.0757561 0.27524 0.91 -0.30 -0.09 -0.16
## need.c 0.0007187 0.02681 0.68 -0.08 -0.31 -0.13 0.63
## Residual 0.0084124 0.09172
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.773e-01 7.610e-03 3.620e+02 23.300 < 2e-16 ***
## pract_1 -1.393e-02 4.629e-03 3.435e+02 -3.009 0.00282 **
## charity_1 -1.363e-02 3.441e-03 3.756e+02 -3.960 8.96e-05 ***
## diff.c 2.025e-02 2.151e-03 3.628e+02 9.411 < 2e-16 ***
## money.c 2.972e-01 1.459e-02 3.774e+02 20.372 < 2e-16 ***
## need.c 2.890e-02 1.711e-03 3.530e+02 16.894 < 2e-16 ***
## pract_1:diff.c -1.429e-02 2.260e-03 1.010e+03 -6.323 3.84e-10 ***
## charity_1:diff.c 9.592e-04 1.571e-03 1.152e+03 0.611 0.54161
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 diff.c mony.c need.c pr_1:.
## pract_1 -0.414
## charity_1 -0.266 0.308
## diff.c 0.082 0.008 0.022
## money.c 0.849 -0.212 -0.069 -0.101
## need.c 0.505 0.051 -0.208 -0.262 0.497
## prct_1:dff. 0.009 0.189 -0.011 -0.326 -0.019 0.008
## chrty_1:df. 0.000 -0.012 -0.070 -0.390 0.002 0.027 0.350tab_model(m15, m16)| donate | donate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.16 | 0.15 – 0.18 | <0.001 | 0.18 | 0.16 – 0.19 | <0.001 |
| indiv_1 | 0.01 | 0.00 – 0.02 | 0.003 | |||
| charity_1 | 0.00 | -0.01 – 0.01 | 0.950 | -0.01 | -0.02 – -0.01 | <0.001 |
| diff.c | 0.01 | 0.00 – 0.01 | 0.020 | 0.02 | 0.02 – 0.02 | <0.001 |
| money.c | 0.30 | 0.27 – 0.33 | <0.001 | 0.30 | 0.27 – 0.33 | <0.001 |
| need.c | 0.03 | 0.03 – 0.03 | <0.001 | 0.03 | 0.03 – 0.03 | <0.001 |
| indiv_1 * diff.c | 0.01 | 0.01 – 0.02 | <0.001 | |||
| charity_1 * diff.c | 0.02 | 0.01 – 0.02 | <0.001 | 0.00 | -0.00 – 0.00 | 0.541 |
| pract_1 | -0.01 | -0.02 – -0.00 | 0.003 | |||
| pract_1 * diff.c | -0.01 | -0.02 – -0.01 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.01 | 0.01 | ||||
| τ00 | 0.02 participant | 0.02 participant | ||||
| τ11 | 0.00 participant.indiv_1 | 0.00 participant.pract_1 | ||||
| 0.01 participant.charity_1 | 0.00 participant.charity_1 | |||||
| 0.00 participant.diff.c | 0.00 participant.diff.c | |||||
| 0.08 participant.money.c | 0.08 participant.money.c | |||||
| 0.00 participant.need.c | 0.00 participant.need.c | |||||
| ρ01 | -0.03 | -0.45 | ||||
| -0.11 | -0.24 | |||||
| 0.11 | 0.06 | |||||
| 0.86 | 0.91 | |||||
| 0.72 | 0.68 | |||||
| ICC | 0.77 | 0.77 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.252 / 0.832 | 0.252 / 0.832 | ||||
b. proportion donated
summary(m17 <- lmer(propDonate ~ (indiv_1 + charity_1) * diff.c + money.c + need.c +
(indiv_1 + charity_1 + money.c + need.c + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (indiv_1 + charity_1) * diff.c + money.c + need.c +
## (indiv_1 + charity_1 + money.c + need.c + diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -8084.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.4088 -0.3146 -0.0271 0.2500 6.1087
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.051960 0.22795
## indiv_1 0.016299 0.12767 -0.11
## charity_1 0.019555 0.13984 -0.19 0.80
## money.c 0.003897 0.06243 -0.22 0.04 0.06
## need.c 0.002654 0.05152 0.64 0.09 -0.08 -0.19
## diff.c 0.003241 0.05693 0.22 -0.08 -0.07 -0.48 0.02
## Residual 0.017580 0.13259
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.914e-01 1.260e-02 3.729e+02 23.123 < 2e-16 ***
## indiv_1 2.099e-02 8.053e-03 3.462e+02 2.606 0.00956 **
## charity_1 -3.695e-03 8.624e-03 3.597e+02 -0.429 0.66853
## diff.c 2.706e-02 4.737e-03 5.746e+02 5.713 1.78e-08 ***
## money.c -6.104e-03 6.043e-03 3.800e+02 -1.010 0.31309
## need.c 5.117e-02 3.149e-03 3.618e+02 16.251 < 2e-16 ***
## indiv_1:diff.c 2.058e-02 3.715e-03 1.276e+03 5.538 3.71e-08 ***
## charity_1:diff.c 2.112e-02 3.781e-03 1.422e+03 5.586 2.79e-08 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) indv_1 chrt_1 diff.c mony.c need.c in_1:.
## indiv_1 -0.227
## charity_1 -0.285 0.781
## diff.c 0.251 -0.171 -0.156
## money.c -0.105 0.008 0.014 -0.221
## need.c 0.542 -0.019 -0.142 -0.119 -0.079
## indv_1:dff. -0.128 0.188 0.183 -0.561 0.075 -0.019
## chrty_1:df. -0.132 0.198 0.165 -0.575 0.078 -0.005 0.792summary(m18 <- lmer(propDonate ~ (pract_1 + charity_1) * diff.c + money.c + need.c +
(pract_1 + charity_1 + money.c + need.c + diff.c | participant),
control = lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000)), data = d))## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula: propDonate ~ (pract_1 + charity_1) * diff.c + money.c + need.c +
## (pract_1 + charity_1 + money.c + need.c + diff.c | participant)
## Data: d
## Control: lmerControl(optimizer = "bobyqa", optCtrl = list(maxfun = 10000))
##
## REML criterion at convergence: -8084.3
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -6.4088 -0.3146 -0.0271 0.2500 6.1087
##
## Random effects:
## Groups Name Variance Std.Dev. Corr
## participant (Intercept) 0.061864 0.24872
## pract_1 0.016299 0.12767 -0.41
## charity_1 0.007372 0.08586 -0.23 0.19
## money.c 0.003897 0.06243 -0.18 -0.04 0.03
## need.c 0.002654 0.05152 0.63 -0.09 -0.27 -0.19
## diff.c 0.003241 0.05693 0.16 0.08 0.00 -0.48 0.02
## Residual 0.017580 0.13259
## Number of obs: 9827, groups: participant, 378
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.124e-01 1.333e-02 3.649e+02 23.438 < 2e-16 ***
## pract_1 -2.099e-02 8.053e-03 3.462e+02 -2.606 0.00956 **
## charity_1 -2.468e-02 5.548e-03 3.734e+02 -4.448 1.14e-05 ***
## diff.c 4.764e-02 4.063e-03 3.443e+02 11.725 < 2e-16 ***
## money.c -6.104e-03 6.043e-03 3.800e+02 -1.010 0.31309
## need.c 5.117e-02 3.149e-03 3.618e+02 16.251 < 2e-16 ***
## pract_1:diff.c -2.058e-02 3.715e-03 1.276e+03 -5.538 3.71e-08 ***
## charity_1:diff.c 5.434e-04 2.419e-03 1.338e+03 0.225 0.82232
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) prct_1 chrt_1 diff.c mony.c need.c pr_1:.
## pract_1 -0.390
## charity_1 -0.251 0.238
## diff.c 0.150 0.027 0.018
## money.c -0.095 -0.008 0.009 -0.189
## need.c 0.501 0.019 -0.192 -0.156 -0.079
## prct_1:dff. 0.007 0.188 -0.012 -0.261 -0.075 0.019
## chrty_1:df. 0.003 -0.021 -0.067 -0.317 0.008 0.021 0.298tab_model(m17, m18)| propDonate | propDonate | |||||
|---|---|---|---|---|---|---|
| Predictors | Estimates | CI | p | Estimates | CI | p |
| (Intercept) | 0.29 | 0.27 – 0.32 | <0.001 | 0.31 | 0.29 – 0.34 | <0.001 |
| indiv_1 | 0.02 | 0.01 – 0.04 | 0.009 | |||
| charity_1 | -0.00 | -0.02 – 0.01 | 0.668 | -0.02 | -0.04 – -0.01 | <0.001 |
| diff.c | 0.03 | 0.02 – 0.04 | <0.001 | 0.05 | 0.04 – 0.06 | <0.001 |
| money.c | -0.01 | -0.02 – 0.01 | 0.312 | -0.01 | -0.02 – 0.01 | 0.312 |
| need.c | 0.05 | 0.05 – 0.06 | <0.001 | 0.05 | 0.05 – 0.06 | <0.001 |
| indiv_1 * diff.c | 0.02 | 0.01 – 0.03 | <0.001 | |||
| charity_1 * diff.c | 0.02 | 0.01 – 0.03 | <0.001 | 0.00 | -0.00 – 0.01 | 0.822 |
| pract_1 | -0.02 | -0.04 – -0.01 | 0.009 | |||
| pract_1 * diff.c | -0.02 | -0.03 – -0.01 | <0.001 | |||
| Random Effects | ||||||
| σ2 | 0.02 | 0.02 | ||||
| τ00 | 0.05 participant | 0.06 participant | ||||
| τ11 | 0.02 participant.indiv_1 | 0.02 participant.pract_1 | ||||
| 0.02 participant.charity_1 | 0.01 participant.charity_1 | |||||
| 0.00 participant.money.c | 0.00 participant.money.c | |||||
| 0.00 participant.need.c | 0.00 participant.need.c | |||||
| 0.00 participant.diff.c | 0.00 participant.diff.c | |||||
| ρ01 | -0.11 | -0.41 | ||||
| -0.19 | -0.23 | |||||
| -0.22 | -0.18 | |||||
| 0.64 | 0.63 | |||||
| 0.22 | 0.16 | |||||
| ICC | 0.82 | 0.82 | ||||
| N | 378 participant | 378 participant | ||||
| Observations | 9827 | 9827 | ||||
| Marginal R2 / Conditional R2 | 0.197 / 0.853 | 0.197 / 0.853 | ||||