Note: “focalman” and “focalwoman” indicate the which columns the focal man and focal woman are in.
Labeling notes:
pers_simplified references a variable coded for EVERY
candidate.
targ_gend_f references a variable coded for the candidate’s
gender.
deiexpert_f references a variable our between-subjects
manipulations.
Snapshot of the dataset is below:
Items
Ranking:
I reverse-coded the ranking variable. So I coded ‘1’ ranking as ‘4’, ‘2’ ranking as ‘3’, and ‘4’ as ‘1’ So higher #’s means person was more likely to be picked.
Voice Quality
- I think they can offer useful ideas for this initiative.
- I think their ideas will likely have a lot of value for improving this initiative.
Voice Solicitation
- I would ask for help/advice from them on this initiative.
- I would encourage them to speak out on this initiative.
Interest
How interested do you think each candidate would be in offering their perspectives or insights on this initiative?
We will now ask for you to imagine that each candidate had their voice solicited. We are curious to know how you think each candidate would experience their voice being solicited.
Each candidate was shown the following items:
| Scale | VS Citation | Justification |
|---|---|---|
| Positive Affect | Tangirala, S., & Ramanujam, R. (2012). | Controlled for in their studies (which found that voice solicitation was POSITIVELY associated with PA), and there was a positive association. |
| Negative Affect | Tangirala, S., & Ramanujam, R. (2012). | Controlled for in their studies (which found that voice solicitation was NEGATIVELY associated with NA), and there was a negative association. |
| Voice | Tangirala, S., & Ramanujam, R. (2012). | Hypothesis was that voice solicitation leads to greater subsequent upward voice. |
| Rewards for voicer | Park, H., Tangirala, S., Hussain, I., & Ekkirala, S. (2022). | Table 3: voice solicitation and manager-rated job rewards are positively correlated*. |
- This paper shows that managers reward employees less when they solicit voice (vs. expressing voice). But they show that there is a moderate correlation (r = .22, p < .01, n = 385) between managerial voice solicitation and manager-rated job rewards
Affect
If you asked Laura Moffett to provide her perspective or insight on this position, she would be….
- inspired (PA)
- determined (PA)
- attentive (PA)
- active (PA)
- upset (NA)
- hostile (NA)
- alert (NA)
- ashamed (NA)
- nervous (NA)
- afraid (NA)
Voice
After asking Laura Moffett to provide her perspective or insight on this position, how likely would she be to engage in the following behaviors more generally at work?
- make recommendations to you for improving work procedures in your
unit
- speak up to you with ideas for change in work procedures in your
unit
- express her opinions on work-related issues to you even when you disagree with her
Rewards
For offering her perspectives or insights on this initiative, how likely would Laura Moffett be to receive the following?
- a salary increase.
- a promotion.
- more high-profile projects.
- more public recognition.
Scale information
Alphas + Means
## Some items ( lm_na_3 ka_na_3 ) were negatively correlated with the total scale and
## probably should be reversed.
## To do this, run the function again with the 'check.keys=TRUE' optionAnalyses - Men Vs. Women
Ranking
Estimated marginal means
## Call:
## clm2(location = rank_rf ~ deiexpert_f * backlash_f * gendertarget +
## (1 | pid), data = nonebacklash_long1)
##
## Location coefficients:
## Estimate Std. Error z value Pr(>|z|)
## deiexpert_fTrad 0.742 0.173 4.284 0.00001834211366
## backlash_fNo Backlash Cond. -0.052 0.174 -0.297 0.76621
## gendertargetWoman trgt 1.329 0.181 7.328 0.00000000000023
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.090 0.240 -0.375 0.70752
## deiexpert_fTrad:gendertargetWoman trgt -1.439 0.244 -5.895 0.00000000375510
## backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.140 0.243 0.576 0.56448
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.149 0.339 0.440 0.66022
##
## No scale coefficients
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 -0.478 0.131 -3.647
## 2|3 0.690 0.132 5.222
## 3|4 1.851 0.138 13.415
##
## log-likelihood: -2445.47
## AIC: 4910.93
## Condition number of Hessian: 317.23
## (8 observations deleted due to missingness)Anova
## Anova Table (Type 3 tests)
##
## Response: rank_r
## Effect df MSE F ges p.value
## 1 backlash_f 1, 449 0.00 0.00 <.001 >.999
## 2 deiexpert_f 1, 449 0.00 0.00 <.001 >.999
## 3 backlash_f:deiexpert_f 1, 449 0.00 0.00 <.001 >.999
## 4 gendertarget_f 1, 449 0.88 49.32 *** .099 <.001
## 5 backlash_f:gendertarget_f 1, 449 0.88 1.11 .002 .294
## 6 deiexpert_f:gendertarget_f 1, 449 0.88 44.59 *** .090 <.001
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 449 0.88 0.11 <.001 .737
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Full posthoc tests
Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Voice Quality
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vq ~ deiexpert_f * backlash_f * gendertarget + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6398
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.526 -0.503 0.039 0.566 2.633
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.82 0.906
## Residual 1.46 1.206
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.399 0.124 747.372 35.53 < 0.0000000000000002 ***
## deiexpert_fTrad 0.148 0.167 747.372 0.89 0.37518
## backlash_fNo Backlash Cond. -0.242 0.168 747.372 -1.44 0.14969
## gendertargetWoman trgt 0.611 0.120 1361.000 5.09 0.0000004 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.286 0.234 747.372 1.22 0.22261
## deiexpert_fTrad:gendertargetWoman trgt -0.605 0.162 1361.000 -3.74 0.00019 ***
## backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.439 0.163 1361.000 2.69 0.00718 **
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.323 0.227 1361.000 -1.42 0.15467
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) dxpr_T b_NBC. gndrWt d_T:BC d_T:Wt b_NBCt
## dexprt_fTrd -0.741
## bcklsh_NBC. -0.737 0.546
## gndrtrgtWmt -0.485 0.359 0.357
## dxp_T:_NBC. 0.529 -0.714 -0.718 -0.256
## dxprt_fT:Wt 0.359 -0.485 -0.265 -0.741 0.346
## bck_NBC.:Wt 0.357 -0.265 -0.485 -0.737 0.348 0.546
## d_T:_NBC.:t -0.256 0.346 0.348 0.529 -0.485 -0.714 -0.718Anova
## Anova Table (Type 3 tests)
##
## Response: vq
## Effect df MSE F ges p.value
## 1 backlash_f 1, 451 2.37 0.15 <.001 .703
## 2 deiexpert_f 1, 451 2.37 0.82 .001 .367
## 3 backlash_f:deiexpert_f 1, 451 2.37 0.37 <.001 .545
## 4 gendertarget_f 1, 451 1.08 41.73 *** .028 <.001
## 5 backlash_f:gendertarget_f 1, 451 1.08 4.00 * .003 .046
## 6 deiexpert_f:gendertarget_f 1, 451 1.08 30.66 *** .021 <.001
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 451 1.08 1.36 <.001 .244
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Full posthoc tests
Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Voice Solicitation
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vs ~ deiexpert_f * backlash_f * gendertarget + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6676
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.343 -0.519 0.048 0.536 2.686
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.07 1.04
## Residual 1.66 1.29
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.262 0.137 718.573 31.07 < 0.0000000000000002 ***
## deiexpert_fTrad 0.372 0.185 718.573 2.01 0.045 *
## backlash_fNo Backlash Cond. -0.204 0.186 718.573 -1.10 0.273
## gendertargetWoman trgt 0.866 0.128 1361.000 6.77 0.00000000002 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.155 0.259 718.573 -0.60 0.549
## deiexpert_fTrad:gendertargetWoman trgt -0.891 0.173 1361.000 -5.16 0.00000029100 ***
## backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.298 0.174 1361.000 1.72 0.086 .
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.091 0.242 1361.000 0.38 0.707
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) dxpr_T b_NBC. gndrWt d_T:BC d_T:Wt b_NBCt
## dexprt_fTrd -0.741
## bcklsh_NBC. -0.737 0.546
## gndrtrgtWmt -0.467 0.346 0.344
## dxp_T:_NBC. 0.529 -0.714 -0.718 -0.247
## dxprt_fT:Wt 0.346 -0.467 -0.255 -0.741 0.333
## bck_NBC.:Wt 0.344 -0.255 -0.467 -0.737 0.335 0.546
## d_T:_NBC.:t -0.247 0.333 0.335 0.529 -0.467 -0.714 -0.718Anova
## Anova Table (Type 3 tests)
##
## Response: vs
## Effect df MSE F ges p.value
## 1 backlash_f 1, 451 2.97 0.92 .001 .339
## 2 deiexpert_f 1, 451 2.97 1.26 .002 .263
## 3 backlash_f:deiexpert_f 1, 451 2.97 0.23 <.001 .632
## 4 gendertarget_f 1, 451 1.19 66.64 *** .041 <.001
## 5 backlash_f:gendertarget_f 1, 451 1.19 5.60 * .004 .018
## 6 deiexpert_f:gendertarget_f 1, 451 1.19 33.86 *** .021 <.001
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 451 1.19 0.10 <.001 .754
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Interest
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: interest ~ deiexpert_f * backlash_f * gendertarget + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6416
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.558 -0.479 0.052 0.550 3.174
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.04 1.02
## Residual 1.40 1.18
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.3564 0.1312 692.5232 33.22 < 0.0000000000000002 ***
## deiexpert_fTrad 0.1842 0.1770 692.5232 1.04 0.30
## backlash_fNo Backlash Cond. 0.0727 0.1780 692.5232 0.41 0.68
## gendertargetWoman trgt 0.7574 0.1177 1361.0000 6.43 0.00000000017 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.2109 0.2479 692.5232 0.85 0.40
## deiexpert_fTrad:gendertargetWoman trgt -0.6761 0.1588 1361.0000 -4.26 0.00002219364 ***
## backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.1051 0.1597 1361.0000 0.66 0.51
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.0963 0.2225 1361.0000 -0.43 0.67
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) dxpr_T b_NBC. gndrWt d_T:BC d_T:Wt b_NBCt
## dexprt_fTrd -0.741
## bcklsh_NBC. -0.737 0.546
## gndrtrgtWmt -0.449 0.333 0.331
## dxp_T:_NBC. 0.529 -0.714 -0.718 -0.237
## dxprt_fT:Wt 0.333 -0.449 -0.245 -0.741 0.320
## bck_NBC.:Wt 0.331 -0.245 -0.449 -0.737 0.322 0.546
## d_T:_NBC.:t -0.237 0.320 0.322 0.529 -0.449 -0.714 -0.718Anova
## Anova Table (Type 3 tests)
##
## Response: interest
## Effect df MSE F ges p.value
## 1 backlash_f 1, 451 2.77 3.48 + .005 .063
## 2 deiexpert_f 1, 451 2.77 0.43 <.001 .513
## 3 backlash_f:deiexpert_f 1, 451 2.77 0.54 <.001 .463
## 4 gendertarget_f 1, 451 1.10 41.13 *** .025 <.001
## 5 backlash_f:gendertarget_f 1, 451 1.10 0.17 <.001 .684
## 6 deiexpert_f:gendertarget_f 1, 451 1.10 26.90 *** .017 <.001
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 451 1.10 0.12 <.001 .730
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Full posthoc tests
Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Positive Affect
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: pa ~ deiexpert_f * backlash_f * gendertarget + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5409
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.666 -0.462 0.010 0.507 3.452
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.912 0.955
## Residual 0.723 0.850
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.1077 0.1123 606.9522 36.58 < 0.0000000000000002 ***
## deiexpert_fTrad 0.4553 0.1516 606.9522 3.00 0.0028 **
## backlash_fNo Backlash Cond. 0.2725 0.1524 606.9522 1.79 0.0742 .
## gendertargetWoman trgt 0.5656 0.0846 1361.0000 6.69 0.000000000033 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.0968 0.2123 606.9522 -0.46 0.6485
## deiexpert_fTrad:gendertargetWoman trgt -0.3451 0.1142 1361.0000 -3.02 0.0026 **
## backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.1792 0.1148 1361.0000 1.56 0.1188
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.2725 0.1599 1361.0000 -1.70 0.0886 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) dxpr_T b_NBC. gndrWt d_T:BC d_T:Wt b_NBCt
## dexprt_fTrd -0.741
## bcklsh_NBC. -0.737 0.546
## gndrtrgtWmt -0.377 0.279 0.278
## dxp_T:_NBC. 0.529 -0.714 -0.718 -0.199
## dxprt_fT:Wt 0.279 -0.377 -0.206 -0.741 0.269
## bck_NBC.:Wt 0.278 -0.206 -0.377 -0.737 0.270 0.546
## d_T:_NBC.:t -0.199 0.269 0.270 0.529 -0.377 -0.714 -0.718Anova
## Anova Table (Type 3 tests)
##
## Response: pa
## Effect df MSE F ges p.value
## 1 backlash_f 1, 451 2.19 6.24 * .011 .013
## 2 deiexpert_f 1, 451 2.19 2.86 + .005 .091
## 3 backlash_f:deiexpert_f 1, 451 2.19 1.40 .002 .237
## 4 gendertarget_f 1, 451 0.57 68.42 *** .030 <.001
## 5 backlash_f:gendertarget_f 1, 451 0.57 0.18 <.001 .668
## 6 deiexpert_f:gendertarget_f 1, 451 0.57 23.06 *** .010 <.001
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 451 0.57 1.85 <.001 .175
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Full posthoc tests
Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Negative Affect
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: na ~ deiexpert_f * backlash_f * gendertarget + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 3891
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.011 -0.424 -0.094 0.324 6.446
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.559 0.747
## Residual 0.284 0.533
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.3210 0.0833 556.2553 27.86 <0.0000000000000002 ***
## deiexpert_fTrad 0.1330 0.1124 556.2553 1.18 0.24
## backlash_fNo Backlash Cond. 0.1457 0.1130 556.2553 1.29 0.20
## gendertargetWoman trgt 0.0099 0.0531 1361.0000 0.19 0.85
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.1807 0.1575 556.2553 -1.15 0.25
## deiexpert_fTrad:gendertargetWoman trgt -0.0357 0.0716 1361.0000 -0.50 0.62
## backlash_fNo Backlash Cond.:gendertargetWoman trgt 0.0102 0.0720 1361.0000 0.14 0.89
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.0130 0.1003 1361.0000 -0.13 0.90
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) dxpr_T b_NBC. gndrWt d_T:BC d_T:Wt b_NBCt
## dexprt_fTrd -0.741
## bcklsh_NBC. -0.737 0.546
## gndrtrgtWmt -0.319 0.236 0.235
## dxp_T:_NBC. 0.529 -0.714 -0.718 -0.169
## dxprt_fT:Wt 0.236 -0.319 -0.174 -0.741 0.227
## bck_NBC.:Wt 0.235 -0.174 -0.319 -0.737 0.229 0.546
## d_T:_NBC.:t -0.169 0.227 0.229 0.529 -0.319 -0.714 -0.718Anova
## Anova Table (Type 3 tests)
##
## Response: na
## Effect df MSE F ges p.value
## 1 backlash_f 1, 451 1.26 0.59 .001 .444
## 2 deiexpert_f 1, 451 1.26 0.08 <.001 .773
## 3 backlash_f:deiexpert_f 1, 451 1.26 1.57 .003 .210
## 4 gendertarget_f 1, 451 0.20 0.04 <.001 .837
## 5 backlash_f:gendertarget_f 1, 451 0.20 0.00 <.001 .950
## 6 deiexpert_f:gendertarget_f 1, 451 0.20 0.51 <.001 .474
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 451 0.20 0.01 <.001 .912
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Full posthoc tests
Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Voice
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: voice ~ deiexpert_f * backlash_f * gendertarget + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5708
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.821 -0.455 -0.009 0.512 3.012
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.766 0.875
## Residual 0.928 0.963
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.6320 0.1104 672.8237 41.97 <0.0000000000000002 ***
## deiexpert_fTrad 0.0143 0.1489 672.8237 0.10 0.9234
## backlash_fNo Backlash Cond. 0.1569 0.1498 672.8237 1.05 0.2953
## gendertargetWoman trgt 0.2904 0.0958 1361.0000 3.03 0.0025 **
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.0812 0.2086 672.8237 0.39 0.6973
## deiexpert_fTrad:gendertargetWoman trgt -0.1576 0.1293 1361.0000 -1.22 0.2231
## backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.0460 0.1301 1361.0000 -0.35 0.7237
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.2595 0.1811 1361.0000 -1.43 0.1522
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) dxpr_T b_NBC. gndrWt d_T:BC d_T:Wt b_NBCt
## dexprt_fTrd -0.741
## bcklsh_NBC. -0.737 0.546
## gndrtrgtWmt -0.434 0.322 0.320
## dxp_T:_NBC. 0.529 -0.714 -0.718 -0.230
## dxprt_fT:Wt 0.322 -0.434 -0.237 -0.741 0.310
## bck_NBC.:Wt 0.320 -0.237 -0.434 -0.737 0.312 0.546
## d_T:_NBC.:t -0.230 0.310 0.312 0.529 -0.434 -0.714 -0.718Anova
## Anova Table (Type 3 tests)
##
## Response: voice
## Effect df MSE F ges p.value
## 1 backlash_f 1, 451 2.00 1.36 .002 .244
## 2 deiexpert_f 1, 451 2.00 0.89 .001 .345
## 3 backlash_f:deiexpert_f 1, 451 2.00 0.07 <.001 .796
## 4 gendertarget_f 1, 451 0.70 4.93 * .003 .027
## 5 backlash_f:gendertarget_f 1, 451 0.70 2.48 .001 .116
## 6 deiexpert_f:gendertarget_f 1, 451 0.70 6.64 * .004 .010
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 451 0.70 1.35 <.001 .245
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Full posthoc tests
Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Rewards
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: rewards ~ deiexpert_f * backlash_f * gendertarget + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5766
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.334 -0.408 -0.022 0.412 3.601
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.636 1.28
## Residual 0.791 0.89
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.7005 0.1418 551.4578 26.09 <0.0000000000000002 ***
## deiexpert_fTrad 0.1643 0.1914 551.4578 0.86 0.391
## backlash_fNo Backlash Cond. 0.4776 0.1925 551.4578 2.48 0.013 *
## gendertargetWoman trgt 0.1448 0.0885 1361.0000 1.64 0.102
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.3841 0.2681 551.4578 -1.43 0.152
## deiexpert_fTrad:gendertargetWoman trgt -0.1814 0.1195 1361.0000 -1.52 0.129
## backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.1448 0.1201 1361.0000 -1.21 0.228
## deiexpert_fTrad:backlash_fNo Backlash Cond.:gendertargetWoman trgt -0.0033 0.1673 1361.0000 -0.02 0.984
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) dxpr_T b_NBC. gndrWt d_T:BC d_T:Wt b_NBCt
## dexprt_fTrd -0.741
## bcklsh_NBC. -0.737 0.546
## gndrtrgtWmt -0.312 0.231 0.230
## dxp_T:_NBC. 0.529 -0.714 -0.718 -0.165
## dxprt_fT:Wt 0.231 -0.312 -0.170 -0.741 0.223
## bck_NBC.:Wt 0.230 -0.170 -0.312 -0.737 0.224 0.546
## d_T:_NBC.:t -0.165 0.223 0.224 0.529 -0.312 -0.714 -0.718Anova
## Anova Table (Type 3 tests)
##
## Response: rewards
## Effect df MSE F ges p.value
## 1 backlash_f 1, 451 3.67 2.78 + .005 .096
## 2 deiexpert_f 1, 451 3.67 0.88 .002 .350
## 3 backlash_f:deiexpert_f 1, 451 3.67 2.29 .004 .131
## 4 gendertarget_f 1, 451 0.60 0.14 <.001 .710
## 5 backlash_f:gendertarget_f 1, 451 0.60 2.03 <.001 .155
## 6 deiexpert_f:gendertarget_f 1, 451 0.60 3.16 + <.001 .076
## 7 backlash_f:deiexpert_f:gendertarget_f 1, 451 0.60 0.00 <.001 .987
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '+' 0.1 ' ' 1Full posthoc tests
Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Analyses - Each candidate individually
Ranking
Estimated marginal means
## Call:
## clm2(location = rank_rf ~ deiexpert_f * backlash_f * person_f +
## (1 | pid), data = nonebacklash_long1)
##
## Location coefficients:
## Estimate Std. Error z value Pr(>|z|)
## deiexpert_fTrad 1.034 0.242 4.276 0.000018992821
## backlash_fNo Backlash Cond. 0.181 0.246 0.736 0.462
## person_fotherman 0.602 0.259 2.326 0.020
## person_fwoman1 1.705 0.254 6.717 0.000000000019
## person_fwoman2 1.532 0.253 6.042 0.000000001517
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.246 0.339 -0.726 0.468
## deiexpert_fTrad:person_fotherman -0.609 0.346 -1.760 0.078
## deiexpert_fTrad:person_fwoman1 -1.742 0.342 -5.092 0.000000354088
## deiexpert_fTrad:person_fwoman2 -1.721 0.342 -5.030 0.000000490769
## backlash_fNo Backlash Cond.:person_fotherman -0.496 0.349 -1.424 0.154
## backlash_fNo Backlash Cond.:person_fwoman1 -0.239 0.343 -0.696 0.487
## backlash_fNo Backlash Cond.:person_fwoman2 0.057 0.345 0.164 0.870
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman 0.343 0.481 0.713 0.476
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 0.430 0.479 0.899 0.369
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 0.177 0.480 0.369 0.712
##
## No scale coefficients
##
## Threshold coefficients:
## Estimate Std. Error z value
## 1|2 -0.193 0.181 -1.066
## 2|3 0.978 0.182 5.362
## 3|4 2.143 0.187 11.435
##
## log-likelihood: -2441.73
## AIC: 4919.46
## Condition number of Hessian: 1115.92
## (8 observations deleted due to missingness)Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Voice Quality
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vq ~ deiexpert_f * backlash_f * person_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6408
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.520 -0.525 0.024 0.571 2.611
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.819 0.905
## Residual 1.459 1.208
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.332 0.150 1299.902 28.84 < 0.0000000000000002 ***
## deiexpert_fTrad 0.270 0.203 1299.902 1.33 0.18314
## backlash_fNo Backlash Cond. -0.173 0.204 1299.902 -0.85 0.39521
## person_fotherman 0.134 0.170 1353.000 0.79 0.43181
## person_fwoman1 0.693 0.170 1353.000 4.08 0.000048 ***
## person_fwoman2 0.663 0.170 1353.000 3.90 0.000100 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.157 0.284 1299.902 0.55 0.57959
## deiexpert_fTrad:person_fotherman -0.243 0.229 1353.000 -1.06 0.28881
## deiexpert_fTrad:person_fwoman1 -0.608 0.229 1353.000 -2.65 0.00816 **
## deiexpert_fTrad:person_fwoman2 -0.846 0.229 1353.000 -3.69 0.00023 ***
## backlash_fNo Backlash Cond.:person_fotherman -0.138 0.231 1353.000 -0.60 0.55028
## backlash_fNo Backlash Cond.:person_fwoman1 0.353 0.231 1353.000 1.53 0.12644
## backlash_fNo Backlash Cond.:person_fwoman2 0.387 0.231 1353.000 1.68 0.09396 .
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman 0.257 0.321 1353.000 0.80 0.42465
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 -0.285 0.321 1353.000 -0.89 0.37526
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 -0.105 0.321 1353.000 -0.33 0.74479
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Voice Solicitation
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vs ~ deiexpert_f * backlash_f * person_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6684
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.306 -0.519 0.043 0.543 2.697
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.07 1.04
## Residual 1.66 1.29
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.1386 0.1645 1233.6684 25.17 < 0.0000000000000002 ***
## deiexpert_fTrad 0.5281 0.2219 1233.6684 2.38 0.017 *
## backlash_fNo Backlash Cond. -0.0636 0.2232 1233.6684 -0.29 0.776
## person_fotherman 0.2475 0.1813 1353.0000 1.37 0.172
## person_fwoman1 1.0545 0.1813 1353.0000 5.82 0.0000000075 ***
## person_fwoman2 0.9257 0.1813 1353.0000 5.11 0.0000003738 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.3868 0.3108 1233.6684 -1.24 0.214
## deiexpert_fTrad:person_fotherman -0.3126 0.2446 1353.0000 -1.28 0.202
## deiexpert_fTrad:person_fwoman1 -1.0016 0.2446 1353.0000 -4.09 0.0000447872 ***
## deiexpert_fTrad:person_fwoman2 -1.0924 0.2446 1353.0000 -4.47 0.0000086398 ***
## backlash_fNo Backlash Cond.:person_fotherman -0.2809 0.2460 1353.0000 -1.14 0.254
## backlash_fNo Backlash Cond.:person_fwoman1 0.0497 0.2460 1353.0000 0.20 0.840
## backlash_fNo Backlash Cond.:person_fwoman2 0.2659 0.2460 1353.0000 1.08 0.280
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman 0.4630 0.3426 1353.0000 1.35 0.177
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 0.3434 0.3426 1353.0000 1.00 0.316
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 0.3016 0.3426 1353.0000 0.88 0.379
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Interest
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: interest ~ deiexpert_f * backlash_f * person_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6428
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.537 -0.523 0.019 0.538 3.233
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.04 1.02
## Residual 1.40 1.19
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.2772 0.1555 1170.9100 27.51 < 0.0000000000000002 ***
## deiexpert_fTrad 0.2187 0.2098 1170.9100 1.04 0.2974
## backlash_fNo Backlash Cond. 0.1644 0.2110 1170.9100 0.78 0.4359
## person_fotherman 0.1584 0.1668 1353.0000 0.95 0.3424
## person_fwoman1 0.9010 0.1668 1353.0000 5.40 0.000000078 ***
## person_fwoman2 0.7723 0.1668 1353.0000 4.63 0.000003999 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.1594 0.2938 1170.9100 0.54 0.5875
## deiexpert_fTrad:person_fotherman -0.0690 0.2251 1353.0000 -0.31 0.7593
## deiexpert_fTrad:person_fwoman1 -0.7059 0.2251 1353.0000 -3.14 0.0017 **
## deiexpert_fTrad:person_fwoman2 -0.7154 0.2251 1353.0000 -3.18 0.0015 **
## backlash_fNo Backlash Cond.:person_fotherman -0.1834 0.2263 1353.0000 -0.81 0.4179
## backlash_fNo Backlash Cond.:person_fwoman1 -0.0343 0.2263 1353.0000 -0.15 0.8795
## backlash_fNo Backlash Cond.:person_fwoman2 0.0611 0.2263 1353.0000 0.27 0.7874
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman 0.1030 0.3152 1353.0000 0.33 0.7439
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 -0.0437 0.3152 1353.0000 -0.14 0.8898
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 -0.0459 0.3152 1353.0000 -0.15 0.8843
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Positive Affect
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: pa ~ deiexpert_f * backlash_f * person_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5426
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.593 -0.475 0.013 0.501 3.513
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.912 0.955
## Residual 0.725 0.852
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.09653 0.12732 934.50893 32.18 < 0.0000000000000002 ***
## deiexpert_fTrad 0.47460 0.17181 934.50893 2.76 0.0059 **
## backlash_fNo Backlash Cond. 0.22638 0.17278 934.50893 1.31 0.1904
## person_fotherman 0.02228 0.11985 1353.00001 0.19 0.8526
## person_fwoman1 0.57921 0.11985 1353.00001 4.83 0.0000015 ***
## person_fwoman2 0.57426 0.11985 1353.00001 4.79 0.0000018 ***
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.00653 0.24065 934.50893 0.03 0.9783
## deiexpert_fTrad:person_fotherman -0.03854 0.16174 1353.00001 -0.24 0.8117
## deiexpert_fTrad:person_fwoman1 -0.39222 0.16174 1353.00001 -2.42 0.0154 *
## deiexpert_fTrad:person_fwoman2 -0.33645 0.16174 1353.00001 -2.08 0.0377 *
## backlash_fNo Backlash Cond.:person_fotherman 0.09231 0.16265 1353.00001 0.57 0.5705
## backlash_fNo Backlash Cond.:person_fwoman1 0.22496 0.16265 1353.00001 1.38 0.1669
## backlash_fNo Backlash Cond.:person_fwoman2 0.22574 0.16265 1353.00001 1.39 0.1654
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman -0.20668 0.22654 1353.00001 -0.91 0.3618
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 -0.30835 0.22654 1353.00001 -1.36 0.1737
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 -0.44328 0.22654 1353.00001 -1.96 0.0506 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Negative Affect
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: na ~ deiexpert_f * backlash_f * person_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 3915
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.994 -0.417 -0.097 0.322 6.496
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.558 0.747
## Residual 0.285 0.534
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.31518 0.09140 779.46229 25.33 <0.0000000000000002 ***
## deiexpert_fTrad 0.16043 0.12334 779.46229 1.30 0.19
## backlash_fNo Backlash Cond. 0.13760 0.12403 779.46229 1.11 0.27
## person_fotherman 0.01155 0.07516 1353.00002 0.15 0.88
## person_fwoman1 -0.02805 0.07516 1353.00002 -0.37 0.71
## person_fwoman2 0.05941 0.07516 1353.00002 0.79 0.43
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.17176 0.17276 779.46228 -0.99 0.32
## deiexpert_fTrad:person_fotherman -0.05491 0.10142 1353.00002 -0.54 0.59
## deiexpert_fTrad:person_fwoman1 -0.00447 0.10142 1353.00002 -0.04 0.96
## deiexpert_fTrad:person_fwoman2 -0.12174 0.10142 1353.00002 -1.20 0.23
## backlash_fNo Backlash Cond.:person_fotherman 0.01623 0.10199 1353.00002 0.16 0.87
## backlash_fNo Backlash Cond.:person_fwoman1 0.09333 0.10199 1353.00002 0.92 0.36
## backlash_fNo Backlash Cond.:person_fwoman2 -0.05663 0.10199 1353.00002 -0.56 0.58
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman -0.01791 0.14206 1353.00002 -0.13 0.90
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 -0.07733 0.14206 1353.00002 -0.54 0.59
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 0.03337 0.14206 1353.00002 0.23 0.81
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Voice
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: voice ~ deiexpert_f * backlash_f * person_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5718
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.786 -0.444 0.013 0.514 3.021
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.767 0.876
## Residual 0.927 0.963
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.64026 0.12950 1117.40391 35.83 <0.0000000000000002 ***
## deiexpert_fTrad 0.14835 0.17476 1117.40391 0.85 0.396
## backlash_fNo Backlash Cond. 0.09307 0.17574 1117.40391 0.53 0.597
## person_fotherman -0.01650 0.13550 1353.00000 -0.12 0.903
## person_fwoman1 0.22772 0.13550 1353.00000 1.68 0.093 .
## person_fwoman2 0.33663 0.13550 1353.00000 2.48 0.013 *
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.07927 0.24477 1117.40392 0.32 0.746
## deiexpert_fTrad:person_fotherman -0.26805 0.18286 1353.00000 -1.47 0.143
## deiexpert_fTrad:person_fwoman1 -0.27108 0.18286 1353.00000 -1.48 0.138
## deiexpert_fTrad:person_fwoman2 -0.31224 0.18286 1353.00000 -1.71 0.088 .
## backlash_fNo Backlash Cond.:person_fotherman 0.12761 0.18389 1353.00000 0.69 0.488
## backlash_fNo Backlash Cond.:person_fwoman1 0.07506 0.18389 1353.00000 0.41 0.683
## backlash_fNo Backlash Cond.:person_fwoman2 -0.03941 0.18389 1353.00000 -0.21 0.830
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman 0.00379 0.25612 1353.00000 0.01 0.988
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 -0.27193 0.25612 1353.00000 -1.06 0.289
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 -0.24324 0.25612 1353.00000 -0.95 0.342
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Rewards
Estimated marginal means
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: rewards ~ deiexpert_f * backlash_f * person_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5782
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.283 -0.416 -0.013 0.408 3.551
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.635 1.279
## Residual 0.794 0.891
## Number of obs: 1820, groups: pid, 455
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.6559 0.1551 764.7498 23.57 <0.0000000000000002 ***
## deiexpert_fTrad 0.2587 0.2093 764.7498 1.24 0.217
## backlash_fNo Backlash Cond. 0.5274 0.2105 764.7498 2.51 0.012 *
## person_fotherman 0.0891 0.1254 1353.0000 0.71 0.478
## person_fwoman1 0.1535 0.1254 1353.0000 1.22 0.221
## person_fwoman2 0.2252 0.1254 1353.0000 1.80 0.073 .
## deiexpert_fTrad:backlash_fNo Backlash Cond. -0.4645 0.2931 764.7498 -1.58 0.113
## deiexpert_fTrad:person_fotherman -0.1887 0.1692 1353.0000 -1.11 0.265
## deiexpert_fTrad:person_fwoman1 -0.2714 0.1692 1353.0000 -1.60 0.109
## deiexpert_fTrad:person_fwoman2 -0.2801 0.1692 1353.0000 -1.66 0.098 .
## backlash_fNo Backlash Cond.:person_fotherman -0.0995 0.1702 1353.0000 -0.58 0.559
## backlash_fNo Backlash Cond.:person_fwoman1 -0.1201 0.1702 1353.0000 -0.71 0.480
## backlash_fNo Backlash Cond.:person_fwoman2 -0.2690 0.1702 1353.0000 -1.58 0.114
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fotherman 0.1608 0.2371 1353.0000 0.68 0.498
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman1 -0.0142 0.2371 1353.0000 -0.06 0.952
## deiexpert_fTrad:backlash_fNo Backlash Cond.:person_fwoman2 0.1685 0.2371 1353.0000 0.71 0.477
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Pairwise comparisons (comparing conditions across candidates)
Pairwise comparisons (comparing candidates across conditions)
Pairwise comparisons (comparing candidates across backlash conditions)
Graphs
Exploratory analyses
Part. gender as a control
Ranking
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: rank ~ deiexpert_f * person * backlash + part_gend_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5286
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.9559 -0.9336 -0.0081 0.8205 1.8428
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.00 0.00
## Residual 1.17 1.08
## Number of obs: 1756, groups: pid, 439
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.97368421052631415 0.10340156321675377 1739.00000002338219929 28.76 < 0.0000000000000002 ***
## deiexpert_fTrad -0.47368421052631493 0.14442643364110391 1739.00000002352317097 -3.28 0.00106 **
## personotherman -0.07017543859649203 0.14312212004147110 1739.00000000053955773 -0.49 0.62397
## personwoman1 -0.85964912280701844 0.14312212004147098 1739.00000002034926183 -6.01 0.000000002305 ***
## personwoman2 -0.96491228070175572 0.14312212004147110 1739.00000000053955773 -6.74 0.000000000021 ***
## backlashyes 0.13971785132935624 0.14926254618172105 1739.00000000853538040 0.94 0.34938
## part_gend_fMale Participants 0.00000000000000119 0.05256674953489465 1739.00000000879163053 0.00 1.00000
## deiexpert_fTrad:personotherman 0.17926634768740157 0.20423700223285635 1739.00000001180751497 0.88 0.38021
## deiexpert_fTrad:personwoman1 0.75964912280701935 0.20423700223285635 1739.00000001446414899 3.72 0.00021 ***
## deiexpert_fTrad:personwoman2 0.95582137161084757 0.20423700223285637 1739.00000001446505848 4.68 0.000003091338 ***
## deiexpert_fTrad:backlashyes -0.21598903777003378 0.20692669644445255 1739.00000000859813554 -1.04 0.29673
## personotherman:backlashyes -0.35250497377464274 0.21108730794279118 1739.00000001275907380 -1.67 0.09511 .
## personwoman1:backlashyes -0.19189726894555956 0.21108730794279101 1739.00000001267358130 -0.91 0.36343
## personwoman2:backlashyes -0.01446916259721390 0.21108730794279107 1739.00000001275520845 -0.07 0.94536
## deiexpert_fTrad:personotherman:backlashyes 0.27731236976847884 0.29253415828913359 1739.00000001418788997 0.95 0.34328
## deiexpert_fTrad:personwoman1:backlashyes 0.40206676047098222 0.29253415828913354 1739.00000001418652573 1.37 0.16949
## deiexpert_fTrad:personwoman2:backlashyes 0.18457702084066430 0.29253415828913354 1739.00000001418652573 0.63 0.52815
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')Voice Solicitation
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vs ~ deiexpert_f * person * backlash + part_gend_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6478
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.317 -0.520 0.041 0.548 2.659
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.04 1.02
## Residual 1.67 1.29
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.0899 0.1605 1109.7536 25.49 < 0.0000000000000002 ***
## deiexpert_fTrad 0.0662 0.2195 1209.3349 0.30 0.7630
## personotherman -0.0348 0.1703 1311.0000 -0.20 0.8382
## personwoman1 1.0565 0.1703 1311.0000 6.20 0.000000000739 ***
## personwoman2 1.1130 0.1703 1311.0000 6.54 0.000000000091 ***
## backlashyes -0.1035 0.2262 1209.5400 -0.46 0.6475
## part_gend_fMale Participants 0.1664 0.1173 436.0000 1.42 0.1565
## deiexpert_fTrad:personotherman 0.1348 0.2436 1311.0000 0.55 0.5801
## deiexpert_fTrad:personwoman1 -0.5974 0.2436 1311.0000 -2.45 0.0143 *
## deiexpert_fTrad:personwoman2 -0.7221 0.2436 1311.0000 -2.96 0.0031 **
## deiexpert_fTrad:backlashyes 0.5053 0.3145 1207.7398 1.61 0.1083
## personotherman:backlashyes 0.3001 0.2511 1311.0000 1.20 0.2322
## personwoman1:backlashyes 0.0302 0.2511 1311.0000 0.12 0.9042
## personwoman2:backlashyes -0.1590 0.2511 1311.0000 -0.63 0.5268
## deiexpert_fTrad:personotherman:backlashyes -0.4679 0.3488 1311.0000 -1.34 0.1800
## deiexpert_fTrad:personwoman1:backlashyes -0.4596 0.3488 1311.0000 -1.32 0.1878
## deiexpert_fTrad:personwoman2:backlashyes -0.3845 0.3488 1311.0000 -1.10 0.2705
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Voice Quality
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vq ~ deiexpert_f * person * backlash + part_gend_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6228
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.487 -0.521 0.027 0.571 2.581
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.811 0.90
## Residual 1.478 1.22
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.1680 0.1473 1165.0365 28.30 < 0.0000000000000002 ***
## deiexpert_fTrad 0.3962 0.2018 1267.5641 1.96 0.04984 *
## personotherman 0.0217 0.1603 1311.0000 0.14 0.89217
## personwoman1 1.0174 0.1603 1311.0000 6.35 0.000000000305 ***
## personwoman2 1.0609 0.1603 1311.0000 6.62 0.000000000053 ***
## backlashyes 0.1044 0.2080 1267.7729 0.50 0.61565
## part_gend_fMale Participants 0.0473 0.1055 436.0000 0.45 0.65421
## deiexpert_fTrad:personotherman -0.0308 0.2293 1311.0000 -0.13 0.89307
## deiexpert_fTrad:personwoman1 -0.8628 0.2293 1311.0000 -3.76 0.00018 ***
## deiexpert_fTrad:personwoman2 -0.9609 0.2293 1311.0000 -4.19 0.000029720030 ***
## deiexpert_fTrad:backlashyes -0.0763 0.2891 1265.9396 -0.26 0.79197
## personotherman:backlashyes 0.1262 0.2364 1311.0000 0.53 0.59344
## personwoman1:backlashyes -0.3031 0.2364 1311.0000 -1.28 0.19996
## personwoman2:backlashyes -0.3772 0.2364 1311.0000 -1.60 0.11078
## deiexpert_fTrad:personotherman:backlashyes -0.2315 0.3283 1311.0000 -0.71 0.48082
## deiexpert_fTrad:personwoman1:backlashyes 0.1867 0.3283 1311.0000 0.57 0.56971
## deiexpert_fTrad:personwoman2:backlashyes 0.0780 0.3283 1311.0000 0.24 0.81215
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Interest
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: interest ~ deiexpert_f * person * backlash + part_gend_f + rank + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6010
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.830 -0.538 0.029 0.558 3.870
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.09 1.04
## Residual 1.21 1.10
## Number of obs: 1756, groups: pid, 439
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 5.5708 0.1658 1249.9904 33.59 < 0.0000000000000002 ***
## deiexpert_fTrad 0.1909 0.2027 1042.4550 0.94 0.34661
## personotherman -0.0531 0.1455 1304.0000 -0.36 0.71523
## personwoman1 0.5578 0.1470 1304.0000 3.79 0.00016 ***
## personwoman2 0.4825 0.1474 1304.0000 3.27 0.00109 **
## backlashyes -0.1566 0.2092 1038.4482 -0.75 0.45432
## part_gend_fMale Participants 0.0293 0.1146 434.0000 0.26 0.79831
## rank -0.3818 0.0244 1304.0000 -15.66 < 0.0000000000000002 ***
## deiexpert_fTrad:personotherman 0.1038 0.2077 1304.0000 0.50 0.61718
## deiexpert_fTrad:personwoman1 -0.4778 0.2085 1304.0000 -2.29 0.02208 *
## deiexpert_fTrad:personwoman2 -0.3951 0.2090 1304.0000 -1.89 0.05889 .
## deiexpert_fTrad:backlashyes -0.1935 0.2901 1036.9769 -0.67 0.50506
## personotherman:backlashyes 0.0670 0.2148 1304.0000 0.31 0.75513
## personwoman1:backlashyes -0.0211 0.2147 1304.0000 -0.10 0.92179
## personwoman2:backlashyes -0.0523 0.2146 1304.0000 -0.24 0.80759
## deiexpert_fTrad:personotherman:backlashyes -0.0455 0.2975 1304.0000 -0.15 0.87853
## deiexpert_fTrad:personwoman1:backlashyes 0.1441 0.2976 1304.0000 0.48 0.62819
## deiexpert_fTrad:personwoman2:backlashyes 0.0348 0.2975 1304.0000 0.12 0.90693
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Positive Affect
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: pa ~ deiexpert_f * person * backlash + part_gend_f + rank + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5086
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.888 -0.487 0.045 0.509 3.672
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.899 0.948
## Residual 0.649 0.806
## Number of obs: 1756, groups: pid, 439
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 5.0003 0.1343 1034.6986 37.22 < 0.0000000000000002 ***
## deiexpert_fTrad 0.2848 0.1666 866.4866 1.71 0.08760 .
## personotherman 0.0738 0.1067 1304.0000 0.69 0.48965
## personwoman1 0.6005 0.1078 1304.0000 5.57 0.000000031 ***
## personwoman2 0.5500 0.1081 1304.0000 5.09 0.000000418 ***
## backlashyes -0.2816 0.1719 863.4189 -1.64 0.10174
## part_gend_fMale Participants 0.2107 0.1002 434.0000 2.10 0.03610 *
## rank -0.2300 0.0179 1304.0000 -12.86 < 0.0000000000000002 ***
## deiexpert_fTrad:personotherman -0.1782 0.1524 1304.0000 -1.17 0.24230
## deiexpert_fTrad:personwoman1 -0.5144 0.1529 1304.0000 -3.36 0.00079 ***
## deiexpert_fTrad:personwoman2 -0.5180 0.1533 1304.0000 -3.38 0.00075 ***
## deiexpert_fTrad:backlashyes 0.0532 0.2385 862.2939 0.22 0.82338
## personotherman:backlashyes -0.1349 0.1576 1304.0000 -0.86 0.39199
## personwoman1:backlashyes -0.2393 0.1575 1304.0000 -1.52 0.12884
## personwoman2:backlashyes -0.1722 0.1574 1304.0000 -1.09 0.27433
## deiexpert_fTrad:personotherman:backlashyes 0.2217 0.2182 1304.0000 1.02 0.30978
## deiexpert_fTrad:personwoman1:backlashyes 0.3480 0.2183 1304.0000 1.59 0.11110
## deiexpert_fTrad:personwoman2:backlashyes 0.4018 0.2182 1304.0000 1.84 0.06580 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Negative Affect
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: na ~ deiexpert_f * person * backlash + part_gend_f + rank + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 3794
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.017 -0.426 -0.085 0.332 6.444
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.555 0.745
## Residual 0.287 0.536
## Number of obs: 1756, groups: pid, 439
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.27622 0.09803 888.05305 23.22 < 0.0000000000000002 ***
## deiexpert_fTrad 0.02507 0.12284 756.26718 0.20 0.83837
## personotherman 0.03936 0.07099 1304.00002 0.55 0.57941
## personwoman1 0.11625 0.07172 1304.00002 1.62 0.10527
## personwoman2 0.06198 0.07191 1304.00002 0.86 0.38885
## backlashyes -0.13103 0.12681 753.92263 -1.03 0.30183
## part_gend_fMale Participants 0.11853 0.07705 433.99995 1.54 0.12472
## rank 0.04000 0.01189 1304.00003 3.36 0.00079 ***
## deiexpert_fTrad:personotherman -0.08917 0.10132 1304.00002 -0.88 0.37895
## deiexpert_fTrad:personwoman1 -0.12892 0.10170 1304.00002 -1.27 0.20515
## deiexpert_fTrad:personwoman2 -0.14344 0.10193 1304.00002 -1.41 0.15961
## deiexpert_fTrad:backlashyes 0.18320 0.17593 753.06324 1.04 0.29805
## personotherman:backlashyes -0.00183 0.10478 1304.00002 -0.02 0.98605
## personwoman1:backlashyes -0.09481 0.10472 1304.00002 -0.91 0.36541
## personwoman2:backlashyes 0.05794 0.10469 1304.00002 0.55 0.58005
## deiexpert_fTrad:personotherman:backlashyes 0.00086 0.14513 1304.00002 0.01 0.99527
## deiexpert_fTrad:personwoman1:backlashyes 0.06777 0.14517 1304.00002 0.47 0.64072
## deiexpert_fTrad:personwoman2:backlashyes -0.05214 0.14511 1304.00002 -0.36 0.71943
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Voice
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: voice ~ deiexpert_f * person * backlash + part_gend_f + rank + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5367
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.831 -0.506 0.032 0.539 2.859
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.721 0.849
## Residual 0.842 0.917
## Number of obs: 1756, groups: pid, 439
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 5.5221 0.1372 1274.3342 40.26 <0.0000000000000002 ***
## deiexpert_fTrad 0.0218 0.1674 1063.8671 0.13 0.897
## personotherman 0.0731 0.1215 1304.0000 0.60 0.548
## personwoman1 0.0567 0.1228 1304.0000 0.46 0.644
## personwoman2 0.0333 0.1231 1304.0000 0.27 0.787
## backlashyes -0.1567 0.1727 1059.7695 -0.91 0.365
## part_gend_fMale Participants 0.0655 0.0939 434.0000 0.70 0.486
## rank -0.2503 0.0204 1304.0000 -12.30 <0.0000000000000002 ***
## deiexpert_fTrad:personotherman -0.2003 0.1734 1304.0000 -1.15 0.248
## deiexpert_fTrad:personwoman1 -0.3242 0.1741 1304.0000 -1.86 0.063 .
## deiexpert_fTrad:personwoman2 -0.2962 0.1745 1304.0000 -1.70 0.090 .
## deiexpert_fTrad:backlashyes -0.0483 0.2396 1058.2646 -0.20 0.840
## personotherman:backlashyes -0.1892 0.1794 1304.0000 -1.05 0.292
## personwoman1:backlashyes -0.0554 0.1793 1304.0000 -0.31 0.757
## personwoman2:backlashyes 0.0927 0.1792 1304.0000 0.52 0.605
## deiexpert_fTrad:personotherman:backlashyes 0.0368 0.2484 1304.0000 0.15 0.882
## deiexpert_fTrad:personwoman1:backlashyes 0.2883 0.2485 1304.0000 1.16 0.246
## deiexpert_fTrad:personwoman2:backlashyes 0.2444 0.2484 1304.0000 0.98 0.325
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Rewards
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: rewards ~ deiexpert_f * person * backlash + part_gend_f + rank + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5516
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.387 -0.460 -0.014 0.440 3.910
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.612 1.269
## Residual 0.758 0.871
## Number of obs: 1756, groups: pid, 439
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.7087 0.1639 851.2496 28.73 <0.0000000000000002 ***
## deiexpert_fTrad -0.3679 0.2060 729.4177 -1.79 0.0745 .
## personotherman -0.0370 0.1153 1304.0000 -0.32 0.7484
## personwoman1 -0.1687 0.1165 1304.0000 -1.45 0.1478
## personwoman2 -0.2692 0.1168 1304.0000 -2.30 0.0214 *
## backlashyes -0.5963 0.2127 727.2603 -2.80 0.0052 **
## part_gend_fMale Participants 0.2373 0.1306 433.9999 1.82 0.0699 .
## rank -0.1835 0.0193 1304.0000 -9.50 <0.0000000000000002 ***
## deiexpert_fTrad:personotherman 0.0184 0.1646 1304.0000 0.11 0.9111
## deiexpert_fTrad:personwoman1 -0.1042 0.1652 1304.0000 -0.63 0.5284
## deiexpert_fTrad:personwoman2 0.1084 0.1656 1304.0000 0.65 0.5128
## deiexpert_fTrad:backlashyes 0.5431 0.2950 726.4696 1.84 0.0660 .
## personotherman:backlashyes 0.0651 0.1702 1304.0000 0.38 0.7021
## personwoman1:backlashyes 0.1484 0.1701 1304.0000 0.87 0.3831
## personwoman2:backlashyes 0.3266 0.1701 1304.0000 1.92 0.0550 .
## deiexpert_fTrad:personotherman:backlashyes -0.1483 0.2357 1304.0000 -0.63 0.5294
## deiexpert_fTrad:personwoman1:backlashyes 0.0133 0.2358 1304.0000 0.06 0.9550
## deiexpert_fTrad:personwoman2:backlashyes -0.1892 0.2357 1304.0000 -0.80 0.4223
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Part. gender as a moderator
VQ
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vq ~ gendertarget_f * part_gend_f * deiexpert_f * backlash_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6203
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.382 -0.515 0.047 0.574 2.688
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.809 0.899
## Residual 1.460 1.208
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.4417 0.1602 721.2096 27.73 < 0.0000000000000002 ***
## gendertarget_fWoman trgt 0.5833 0.1560 1315.0000 3.74 0.00019 ***
## part_gend_fMale Participants -0.1982 0.2572 721.2096 -0.77 0.44110
## deiexpert_fTrad 0.0702 0.2238 721.2096 0.31 0.75372
## backlash_fNo Backlash Cond. -0.5866 0.2190 721.2096 -2.68 0.00756 **
## gendertarget_fWoman trgt:part_gend_fMale Participants 0.1075 0.2505 1315.0000 0.43 0.66807
## gendertarget_fWoman trgt:deiexpert_fTrad -0.5040 0.2180 1315.0000 -2.31 0.02094 *
## part_gend_fMale Participants:deiexpert_fTrad 0.2954 0.3443 721.2096 0.86 0.39120
## gendertarget_fWoman trgt:backlash_fNo Backlash Cond. 0.7754 0.2133 1315.0000 3.63 0.00029 ***
## part_gend_fMale Participants:backlash_fNo Backlash Cond. 1.0551 0.3492 721.2096 3.02 0.00260 **
## deiexpert_fTrad:backlash_fNo Backlash Cond. 0.7595 0.3077 721.2096 2.47 0.01382 *
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad -0.3277 0.3354 1315.0000 -0.98 0.32871
## gendertarget_fWoman trgt:part_gend_fMale Participants:backlash_fNo Backlash Cond. -0.9335 0.3401 1315.0000 -2.74 0.00614 **
## gendertarget_fWoman trgt:deiexpert_fTrad:backlash_fNo Backlash Cond. -0.8366 0.2998 1315.0000 -2.79 0.00533 **
## part_gend_fMale Participants:deiexpert_fTrad:backlash_fNo Backlash Cond. -1.4408 0.4839 721.2096 -2.98 0.00301 **
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad:backlash_fNo Backlash Cond. 1.4589 0.4714 1315.0000 3.09 0.00201 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
VS
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: vs ~ gendertarget_f * part_gend_f * deiexpert_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6464
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.185 -0.515 0.042 0.576 2.719
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.04 1.02
## Residual 1.66 1.29
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.946 0.120 703.161 32.78 < 0.0000000000000002 ***
## gendertarget_fWoman trgt 1.223 0.113 1319.000 10.78 < 0.0000000000000002 ***
## part_gend_fMale Participants 0.542 0.192 703.161 2.83 0.0048 **
## deiexpert_fTrad 0.448 0.169 703.161 2.65 0.0083 **
## gendertarget_fWoman trgt:part_gend_fMale Participants -0.556 0.181 1319.000 -3.08 0.0021 **
## gendertarget_fWoman trgt:deiexpert_fTrad -1.037 0.160 1319.000 -6.50 0.00000000011 ***
## part_gend_fMale Participants:deiexpert_fTrad -0.431 0.265 703.161 -1.63 0.1046
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad 0.511 0.250 1319.000 2.04 0.0411 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) gnd_Wt pr__MP dxpr_T gn_Wt:__MP g_Wt:_ p__MP:
## gndrtrgt_Wt -0.471
## prt_gnd_fMP -0.628 0.296
## dexprt_fTrd -0.711 0.335 0.447
## gnd_Wt:__MP 0.296 -0.628 -0.471 -0.210
## gndrt_Wt:_T 0.335 -0.711 -0.210 -0.471 0.447
## prt_g_MP:_T 0.454 -0.214 -0.723 -0.638 0.341 0.301
## g_Wt:__MP:_ -0.214 0.454 0.341 0.301 -0.723 -0.638 -0.471## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
Ranking
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: rank_r ~ gendertarget_f * part_gend_f * deiexpert_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5268
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -1.8691 -0.9126 -0.0146 0.9126 1.8691
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.00 0.00
## Residual 1.16 1.08
## Number of obs: 1756, groups: pid, 439
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 1.9843 0.0677 1748.0000 29.32 < 0.0000000000000002 ***
## gendertarget_fWoman trgt 1.0315 0.0957 1748.0000 10.78 < 0.0000000000000002 ***
## part_gend_fMale Participants 0.2360 0.1072 1748.0000 2.20 0.0279 *
## deiexpert_fTrad 0.5006 0.0948 1748.0000 5.28 0.00000014437418 ***
## gendertarget_fWoman trgt:part_gend_fMale Participants -0.4720 0.1517 1748.0000 -3.11 0.0019 **
## gendertarget_fWoman trgt:deiexpert_fTrad -1.0012 0.1341 1748.0000 -7.47 0.00000000000013 ***
## part_gend_fMale Participants:deiexpert_fTrad -0.1896 0.1482 1748.0000 -1.28 0.2010
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad 0.3792 0.2096 1748.0000 1.81 0.0706 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) gnd_Wt pr__MP dxpr_T gn_Wt:__MP g_Wt:_ p__MP:
## gndrtrgt_Wt -0.707
## prt_gnd_fMP -0.631 0.446
## dexprt_fTrd -0.714 0.505 0.450
## gnd_Wt:__MP 0.446 -0.631 -0.707 -0.319
## gndrt_Wt:_T 0.505 -0.714 -0.319 -0.707 0.450
## prt_g_MP:_T 0.457 -0.323 -0.724 -0.640 0.512 0.452
## g_Wt:__MP:_ -0.323 0.457 0.512 0.452 -0.724 -0.640 -0.707
## optimizer (nloptwrap) convergence code: 0 (OK)
## boundary (singular) fit: see help('isSingular')## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
Interest
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: interest ~ gendertarget_f * part_gend_f * deiexpert_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 6239
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.454 -0.486 0.013 0.521 3.216
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.04 1.02
## Residual 1.42 1.19
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.306 0.117 672.432 36.95 < 0.0000000000000002 ***
## gendertarget_fWoman trgt 0.930 0.105 1319.000 8.87 < 0.0000000000000002 ***
## part_gend_fMale Participants 0.212 0.186 672.432 1.14 0.2545
## deiexpert_fTrad 0.432 0.164 672.432 2.64 0.0085 **
## gendertarget_fWoman trgt:part_gend_fMale Participants -0.258 0.167 1319.000 -1.54 0.1230
## gendertarget_fWoman trgt:deiexpert_fTrad -0.945 0.147 1319.000 -6.41 0.0000000002 ***
## part_gend_fMale Participants:deiexpert_fTrad -0.372 0.257 672.432 -1.45 0.1478
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad 0.476 0.231 1319.000 2.06 0.0396 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) gnd_Wt pr__MP dxpr_T gn_Wt:__MP g_Wt:_ p__MP:
## gndrtrgt_Wt -0.450
## prt_gnd_fMP -0.628 0.282
## dexprt_fTrd -0.711 0.320 0.447
## gnd_Wt:__MP 0.282 -0.628 -0.450 -0.201
## gndrt_Wt:_T 0.320 -0.711 -0.201 -0.450 0.447
## prt_g_MP:_T 0.454 -0.204 -0.723 -0.638 0.325 0.287
## g_Wt:__MP:_ -0.204 0.454 0.325 0.287 -0.723 -0.638 -0.450## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
Positive Affect
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: pa ~ gendertarget_f * part_gend_f * deiexpert_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5232
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.862 -0.466 0.036 0.503 3.321
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.894 0.945
## Residual 0.721 0.849
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.0795 0.0986 590.4826 41.37 < 0.0000000000000002 ***
## gendertarget_fWoman trgt 0.8072 0.0748 1319.0000 10.80 < 0.0000000000000002 ***
## part_gend_fMale Participants 0.5232 0.1570 590.4826 3.33 0.00092 ***
## deiexpert_fTrad 0.5597 0.1387 590.4826 4.04 0.00006131748 ***
## gendertarget_fWoman trgt:part_gend_fMale Participants -0.3607 0.1191 1319.0000 -3.03 0.00249 **
## gendertarget_fWoman trgt:deiexpert_fTrad -0.6822 0.1051 1319.0000 -6.49 0.00000000012 ***
## part_gend_fMale Participants:deiexpert_fTrad -0.4932 0.2173 590.4826 -2.27 0.02361 *
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad 0.4779 0.1648 1319.0000 2.90 0.00379 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) gnd_Wt pr__MP dxpr_T gn_Wt:__MP g_Wt:_ p__MP:
## gndrtrgt_Wt -0.379
## prt_gnd_fMP -0.628 0.238
## dexprt_fTrd -0.711 0.270 0.447
## gnd_Wt:__MP 0.238 -0.628 -0.379 -0.169
## gndrt_Wt:_T 0.270 -0.711 -0.169 -0.379 0.447
## prt_g_MP:_T 0.454 -0.172 -0.723 -0.638 0.274 0.242
## g_Wt:__MP:_ -0.172 0.454 0.274 0.242 -0.723 -0.638 -0.379## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
Negative Affect
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: na ~ gendertarget_f * part_gend_f * deiexpert_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 3788
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.989 -0.422 -0.096 0.330 6.397
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.557 0.747
## Residual 0.288 0.537
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 2.38566 0.07374 540.34364 32.35 <0.0000000000000002 ***
## gendertarget_fWoman trgt 0.01809 0.04725 1319.00002 0.38 0.70
## part_gend_fMale Participants 0.05879 0.11742 540.34364 0.50 0.62
## deiexpert_fTrad 0.00386 0.10369 540.34364 0.04 0.97
## gendertarget_fWoman trgt:part_gend_fMale Participants 0.01763 0.07524 1319.00002 0.23 0.81
## gendertarget_fWoman trgt:deiexpert_fTrad -0.05155 0.06644 1319.00002 -0.78 0.44
## part_gend_fMale Participants:deiexpert_fTrad 0.09162 0.16251 540.34364 0.56 0.57
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad -0.00240 0.10413 1319.00002 -0.02 0.98
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) gnd_Wt pr__MP dxpr_T gn_Wt:__MP g_Wt:_ p__MP:
## gndrtrgt_Wt -0.320
## prt_gnd_fMP -0.628 0.201
## dexprt_fTrd -0.711 0.228 0.447
## gnd_Wt:__MP 0.201 -0.628 -0.320 -0.143
## gndrt_Wt:_T 0.228 -0.711 -0.143 -0.320 0.447
## prt_g_MP:_T 0.454 -0.145 -0.723 -0.638 0.231 0.204
## g_Wt:__MP:_ -0.145 0.454 0.231 0.204 -0.723 -0.638 -0.320## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
Voice
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: voice ~ gendertarget_f * part_gend_f * deiexpert_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5517
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.839 -0.456 -0.001 0.550 2.961
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 0.695 0.833
## Residual 0.939 0.969
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 4.6757 0.0950 671.3590 49.22 <0.0000000000000002 ***
## gendertarget_fWoman trgt 0.2713 0.0853 1319.0000 3.18 0.0015 **
## part_gend_fMale Participants 0.1616 0.1513 671.3590 1.07 0.2858
## deiexpert_fTrad 0.0983 0.1336 671.3590 0.74 0.4621
## gendertarget_fWoman trgt:part_gend_fMale Participants -0.0114 0.1358 1319.0000 -0.08 0.9331
## gendertarget_fWoman trgt:deiexpert_fTrad -0.3408 0.1199 1319.0000 -2.84 0.0046 **
## part_gend_fMale Participants:deiexpert_fTrad -0.2481 0.2093 671.3590 -1.19 0.2364
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad 0.1364 0.1880 1319.0000 0.73 0.4682
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) gnd_Wt pr__MP dxpr_T gn_Wt:__MP g_Wt:_ p__MP:
## gndrtrgt_Wt -0.449
## prt_gnd_fMP -0.628 0.282
## dexprt_fTrd -0.711 0.319 0.447
## gnd_Wt:__MP 0.282 -0.628 -0.449 -0.201
## gndrt_Wt:_T 0.319 -0.711 -0.201 -0.449 0.447
## prt_g_MP:_T 0.454 -0.204 -0.723 -0.638 0.324 0.286
## g_Wt:__MP:_ -0.204 0.454 0.324 0.286 -0.723 -0.638 -0.449## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
Rewards
## Linear mixed model fit by REML. t-tests use Satterthwaite's method ['lmerModLmerTest']
## Formula: rewards ~ gendertarget_f * part_gend_f * deiexpert_f + (1 | pid)
## Data: nonebacklash_long1
##
## REML criterion at convergence: 5600
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -4.441 -0.403 -0.020 0.426 3.595
##
## Random effects:
## Groups Name Variance Std.Dev.
## pid (Intercept) 1.610 1.269
## Residual 0.802 0.895
## Number of obs: 1764, groups: pid, 441
##
## Fixed effects:
## Estimate Std. Error df t value Pr(>|t|)
## (Intercept) 3.8934 0.1249 536.9044 31.18 <0.0000000000000002 ***
## gendertarget_fWoman trgt -0.0678 0.0788 1319.0000 -0.86 0.390
## part_gend_fMale Participants 0.2614 0.1988 536.9044 1.31 0.189
## deiexpert_fTrad 0.0299 0.1756 536.9044 0.17 0.865
## gendertarget_fWoman trgt:part_gend_fMale Participants 0.2940 0.1255 1319.0000 2.34 0.019 *
## gendertarget_fWoman trgt:deiexpert_fTrad -0.1026 0.1108 1319.0000 -0.93 0.355
## part_gend_fMale Participants:deiexpert_fTrad -0.2589 0.2752 536.9044 -0.94 0.347
## gendertarget_fWoman trgt:part_gend_fMale Participants:deiexpert_fTrad -0.1509 0.1737 1319.0000 -0.87 0.385
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Correlation of Fixed Effects:
## (Intr) gnd_Wt pr__MP dxpr_T gn_Wt:__MP g_Wt:_ p__MP:
## gndrtrgt_Wt -0.316
## prt_gnd_fMP -0.628 0.198
## dexprt_fTrd -0.711 0.224 0.447
## gnd_Wt:__MP 0.198 -0.628 -0.316 -0.141
## gndrt_Wt:_T 0.224 -0.711 -0.141 -0.316 0.447
## prt_g_MP:_T 0.454 -0.143 -0.723 -0.638 0.228 0.201
## g_Wt:__MP:_ -0.143 0.454 0.228 0.201 -0.723 -0.638 -0.316## [[1]]
##
## [[2]]
##
## [[3]]
##
## [[4]]
##
## [[5]]
##
## [[6]]
##
## [[7]]
##
## [[8]]
##
## [[9]]
##
## [[10]]
##
## [[11]]
## [[11]][[1]]
##
## [[11]][[2]]
Rank woman as #1
Here, I compare whether participants ranked a woman as Number 1
##
## Call:
## lm(formula = rank_wom ~ deiexpert, data = nonebacklash_clean1)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.708 -0.534 0.292 0.466 0.466
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.7078 0.0324 21.86 < 0.0000000000000002 ***
## deiexperttrad -0.1736 0.0450 -3.85 0.00013 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.479 on 451 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.0319, Adjusted R-squared: 0.0297
## F-statistic: 14.8 on 1 and 451 DF, p-value: 0.000133
Mediation
## Warning: package 'lavaan' was built under R version 4.3.1## This is lavaan 0.6-17
## lavaan is FREE software! Please report any bugs.##
## Attaching package: 'lavaan'## The following object is masked from 'package:JWileymisc':
##
## cor2covdeitraddata <- nonebacklash_long1 %>%
filter(deiexpert == "Trad")
deidata <- nonebacklash_long1 %>%
filter(deiexpert == "DEI")Voice Quality
DEI
library(lavaan)
deivq_mediationdat <- data.frame(
X = deidata$gendertarget,
M = scale(deidata$vq, scale = F),
Y = scale(deidata$rank_r, scale = F),
pid = deidata$pid
)
med_mod_deivq <-
'
# Direct Effect
Y ~ c*X
# Mediator
M~a*X
Y~b*M
# Indirect effect
ab:= a*b
# Total effect
total:= c+ (a*b)
'
sem_med_deivq <- lavaan::sem(med_mod_deivq, cluster = "pid", data = deivq_mediationdat)## Warning in lav_model_vcov(lavmodel = lavmodel, lavsamplestats = lavsamplestats, : lavaan WARNING:
## The variance-covariance matrix of the estimated parameters (vcov)
## does not appear to be positive definite! The smallest eigenvalue
## (= -3.468178e-18) is smaller than zero. This may be a symptom that
## the model is not identified.## lavaan 0.6.17 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 876 884
## Number of clusters [pid] 219
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Y ~
## X (c) 0.653 0.084 7.752 0.000
## M ~
## X (a) 0.857 0.114 7.531 0.000
## Y ~
## M (b) 0.240 0.022 10.979 0.000
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .Y -0.979 0.128 -7.676 0.000
## .M -1.286 0.195 -6.605 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .Y 0.935 0.036 26.287 0.000
## .M 2.280 0.161 14.190 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.205 0.032 6.370 0.000
## total 0.858 0.089 9.640 0.000as.data.frame(lavaan::parameterEstimates(sem_med_deivq, ci = TRUE, level = 0.95)) %>%
filter(lhs == "ab") %>%
dplyr::select(est, ci.lower, ci.upper)Trad
library(lavaan)
tradvq_mediationdat <- data.frame(
X = deitraddata$gendertarget,
M = scale(deitraddata$vq, scale = F),
Y = scale(deitraddata$rank_r, scale = F),
pid = deitraddata$pid
)
med_mod_tradvq <-
'
# Direct Effect
Y ~ c*X
# Mediator
M~a*X
Y~b*M
# Indirect effect
ab:= a*b
# Total effect
total:= c+ (a*b)
'
sem_med_tradvq <- lavaan::sem(med_mod_tradvq, cluster = "pid", data = tradvq_mediationdat)## Warning in lav_model_vcov(lavmodel = lavmodel, lavsamplestats = lavsamplestats, : lavaan WARNING:
## The variance-covariance matrix of the estimated parameters (vcov)
## does not appear to be positive definite! The smallest eigenvalue
## (= 2.148811e-19) is close to zero. This may be a symptom that the
## model is not identified.## lavaan 0.6.17 ended normally after 8 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 936
## Number of clusters [pid] 234
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Y ~
## X (c) -0.002 0.074 -0.028 0.978
## M ~
## X (a) 0.061 0.082 0.740 0.459
## Y ~
## M (b) 0.315 0.022 14.076 0.000
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .Y 0.003 0.113 0.027 0.978
## .M -0.091 0.140 -0.650 0.516
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .Y 1.026 0.029 35.727 0.000
## .M 2.264 0.130 17.388 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.019 0.026 0.739 0.460
## total 0.017 0.087 0.197 0.844as.data.frame(lavaan::parameterEstimates(sem_med_tradvq, ci = TRUE, level = 0.95)) %>%
filter(lhs == "ab") %>%
dplyr::select(est, ci.lower, ci.upper)Interest
DEI
library(lavaan)
deiinterest_mediationdat <- data.frame(
X = deidata$gendertarget,
M = scale(deidata$interest, scale = F),
Y = scale(deidata$rank_r, scale = F),
pid = deidata$pid
)
med_mod_deiinterest <-
'
# Direct Effect
Y ~ c*X
# Mediator
M~a*X
Y~b*M
# Indirect effect
ab:= a*b
# Total effect
total:= c+ (a*b)
'
sem_med_deiinterest <- lavaan::sem(med_mod_deiinterest, cluster = "pid", data = deiinterest_mediationdat)## Warning in lav_model_vcov(lavmodel = lavmodel, lavsamplestats = lavsamplestats, : lavaan WARNING:
## The variance-covariance matrix of the estimated parameters (vcov)
## does not appear to be positive definite! The smallest eigenvalue
## (= -2.692763e-18) is smaller than zero. This may be a symptom that
## the model is not identified.## lavaan 0.6.17 ended normally after 1 iteration
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Used Total
## Number of observations 876 884
## Number of clusters [pid] 219
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Y ~
## X (c) 0.735 0.089 8.231 0.000
## M ~
## X (a) 0.822 0.116 7.074 0.000
## Y ~
## M (b) 0.150 0.021 7.284 0.000
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .Y -1.102 0.134 -8.220 0.000
## .M -1.235 0.200 -6.175 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .Y 1.012 0.037 27.301 0.000
## .M 2.367 0.141 16.830 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.123 0.025 4.868 0.000
## total 0.858 0.089 9.640 0.000as.data.frame(lavaan::parameterEstimates(sem_med_deiinterest, ci = TRUE, level = 0.95)) %>%
filter(lhs == "ab") %>%
dplyr::select(est, ci.lower, ci.upper)Trad
library(lavaan)
tradinterest_mediationdat <- data.frame(
X = deitraddata$gendertarget,
M = scale(deitraddata$interest, scale = F),
Y = scale(deitraddata$rank_r, scale = F),
pid = deitraddata$pid
)
med_mod_tradinterest <-
'
# Direct Effect
Y ~ c*X
# Mediator
M~a*X
Y~b*M
# Indirect effect
ab:= a*b
# Total effect
total:= c+ (a*b)
'
sem_med_tradinterest <- lavaan::sem(med_mod_tradinterest, cluster = "pid", data = tradinterest_mediationdat)## Warning in lav_model_vcov(lavmodel = lavmodel, lavsamplestats = lavsamplestats, : lavaan WARNING:
## The variance-covariance matrix of the estimated parameters (vcov)
## does not appear to be positive definite! The smallest eigenvalue
## (= -6.496565e-19) is smaller than zero. This may be a symptom that
## the model is not identified.## lavaan 0.6.17 ended normally after 8 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 7
##
## Number of observations 936
## Number of clusters [pid] 234
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 0.000 0.000
## Degrees of freedom 0 0
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Y ~
## X (c) -0.000 0.080 -0.006 0.996
## M ~
## X (a) 0.085 0.080 1.068 0.286
## Y ~
## M (b) 0.205 0.021 9.614 0.000
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|)
## .Y 0.001 0.122 0.005 0.996
## .M -0.128 0.140 -0.914 0.361
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .Y 1.144 0.020 56.031 0.000
## .M 2.508 0.148 16.973 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## ab 0.018 0.016 1.065 0.287
## total 0.017 0.087 0.197 0.844as.data.frame(lavaan::parameterEstimates(sem_med_tradinterest, ci = TRUE, level = 0.95)) %>%
filter(lhs == "ab") %>%
dplyr::select(est, ci.lower, ci.upper)Parallel Mediation just within the DEI condition
Dependent Variable: Ranking
dei_mediationdat2 <- data.frame(
X = deidata$gendertarget,
M1 = scale(deidata$vq, scale = F),
M2 = scale(deidata$interest, scale = F),
Y = scale(deidata$rank_r, scale = F),
pid = deidata$pid
)
multipleMediation <- '
Y ~ b1 * M1 + b2 * M2 + c * X
M1 ~ a1 * X
M2 ~ a2 * X
indirect1 := a1 * b1
indirect2 := a2 * b2
total := c + (a1 * b1) + (a2 * b2)
M1 ~~ M2
'
fit <- sem(model = multipleMediation, data = dei_mediationdat2)
summary(fit)## lavaan 0.6.17 ended normally after 12 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Used Total
## Number of observations 876 884
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Y ~
## M1 (b1) 0.220 0.025 8.660 0.000
## M2 (b2) 0.037 0.025 1.482 0.138
## X (c) 0.640 0.068 9.346 0.000
## M1 ~
## X (a1) 0.857 0.102 8.402 0.000
## M2 ~
## X (a2) 0.822 0.104 7.906 0.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## .M1 ~~
## .M2 1.220 0.089 13.759 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .Y 0.933 0.045 20.928 0.000
## .M1 2.280 0.109 20.928 0.000
## .M2 2.367 0.113 20.928 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## indirect1 0.188 0.031 6.030 0.000
## indirect2 0.030 0.021 1.457 0.145
## total 0.858 0.070 12.306 0.000as.data.frame(parameterestimates(fit)) %>%
dplyr::filter(lhs == "indirect1" | lhs == "indirect2" | lhs == "total") %>%
dplyr::select(label, est, se, ci.lower, ci.upper)Dependent Variable: Voice Solicitation
dei_mediationdat2 <- data.frame(
X = deidata$gendertarget,
M1 = scale(deidata$vq, scale = F),
M2 = scale(deidata$interest, scale = F),
Y = scale(deidata$vs, scale = F),
pid = deidata$pid
)
multipleMediation <- '
Y ~ b1 * M1 + b2 * M2 + c * X
M1 ~ a1 * X
M2 ~ a2 * X
indirect1 := a1 * b1
indirect2 := a2 * b2
total := c + (a1 * b1) + (a2 * b2)
M1 ~~ M2
'
fit <- sem(model = multipleMediation, data = dei_mediationdat2)
summary(fit)## lavaan 0.6.17 ended normally after 12 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 9
##
## Number of observations 884
##
## Model Test User Model:
##
## Test statistic 0.000
## Degrees of freedom 0
##
## Parameter Estimates:
##
## Standard errors Standard
## Information Expected
## Information saturated (h1) model Structured
##
## Regressions:
## Estimate Std.Err z-value P(>|z|)
## Y ~
## M1 (b1) 0.786 0.025 31.741 0.000
## M2 (b2) 0.151 0.024 6.218 0.000
## X (c) 0.237 0.067 3.565 0.000
## M1 ~
## X (a1) 0.850 0.101 8.373 0.000
## M2 ~
## X (a2) 0.814 0.103 7.888 0.000
##
## Covariances:
## Estimate Std.Err z-value P(>|z|)
## .M1 ~~
## .M2 1.222 0.088 13.874 0.000
##
## Variances:
## Estimate Std.Err z-value P(>|z|)
## .Y 0.890 0.042 21.024 0.000
## .M1 2.275 0.108 21.024 0.000
## .M2 2.356 0.112 21.024 0.000
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|)
## indirect1 0.668 0.082 8.096 0.000
## indirect2 0.123 0.025 4.883 0.000
## total 1.028 0.109 9.406 0.000as.data.frame(parameterestimates(fit)) %>%
dplyr::filter(lhs == "indirect1" | lhs == "indirect2" | lhs == "total") %>%
dplyr::select(label, est, se, ci.lower, ci.upper)Moderated mediation
modmed <- '
M ~ a1*X + a2*W + a3*X:W
Y ~ cdash1*X + cdash2*W + cdash3*X:W + b1*M
#Mean of centered W (for use in simple slopes)
#This is making a coefficient labeled "W" which equals the intercept because of the "1"
#(Y~1) gives you the intercept, which is the mean for our W variable
W ~ W.mean*1
#Variance of centered W (for use in simple slopes)
#This is making a coefficient labeled "W.var" which equals the variance because of the "~~"
#Two tildes separating the same variable gives you the variance
W ~~ W.var*W
#Indirect effects conditional on moderator (a1 + a3*ModValue)*b1
indirect.SDbelow := (a1 + a3*(W.mean-sqrt(W.var)))*b1
indirect.SDabove := (a1 + a3*(W.mean+sqrt(W.var)))*b1
#Direct effects conditional on moderator (cdash1 + cdash3*ModValue)
#We have to do it this way because you cannot call the mean and sd functions in lavaan package
direct.SDbelow := cdash1 + cdash3*(W.mean-sqrt(W.var))
direct.SDabove := cdash1 + cdash3*(W.mean+sqrt(W.var))
#Total effects conditional on moderator
total.SDbelow := direct.SDbelow + indirect.SDbelow
total.SDabove := direct.SDabove + indirect.SDabove
#Proportion mediated conditional on moderator
#To match the output of "mediate" package
prop.mediated.SDbelow := indirect.SDbelow / total.SDbelow
prop.mediated.SDabove := indirect.SDabove / total.SDabove
#Index of moderated mediation
#An alternative way of testing if conditional indirect effects are significantly different from each other
index.mod.med := a3*b1
'Rank as DV
VQ as mediator
nonebacklash_long1 <- nonebacklash_long1 %>%
mutate(
deiexpert_num = case_when(
deiexpert == "DEI" ~ 1,
deiexpert == "Trad" ~ 0),
gendertarget_num = case_when(
gendertarget == "Man trgt" ~ 0,
gendertarget == "Woman trgt" ~ 1
))
modmed_vq_rank <- data.frame(
X = nonebacklash_long1$gendertarget_num,
M = scale(nonebacklash_long1$vq, scale = F),
W = nonebacklash_long1$deiexpert_num,
Y = scale(nonebacklash_long1$rank_r, scale = F),
pid = nonebacklash_long1$pid
)
Mod.Med.SEM_vqrank <- sem(model = modmed,
data = modmed_vq_rank,
bootstrap = 100, cluster = "pid")
summary(Mod.Med.SEM_vqrank,
fit.measures = FALSE,
standardize = TRUE,
rsquare = TRUE)## lavaan 0.6.17 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 13
##
## Used Total
## Number of observations 1812 1820
## Number of clusters [pid] 453
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1255.983 NA
## Degrees of freedom 2 2
## P-value (Chi-square) 0.000 NA
## Scaling correction factor NA
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M ~
## X (a1) 0.061 0.082 0.741 0.459 0.061 0.020
## W (a2) -0.305 0.128 -2.388 0.017 -0.305 -0.098
## X:W (a3) 0.796 0.140 5.676 0.000 0.796 0.219
## Y ~
## X (cds1) 0.000 0.075 0.002 0.998 0.000 0.000
## W (cds2) -0.336 0.061 -5.548 0.000 -0.336 -0.145
## X:W (cds3) 0.620 0.108 5.726 0.000 0.620 0.229
## M (b1) 0.278 0.016 17.542 0.000 0.278 0.374
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.mn) 0.483 0.024 20.568 0.000 0.483 0.967
## .M -0.076 0.080 -0.952 0.341 -0.076 -0.049
## .Y 0.013 0.042 0.300 0.764 0.013 0.011
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.vr) 0.250 0.001 320.854 0.000 0.250 1.000
## .M 2.272 0.103 22.134 0.000 2.272 0.937
## .Y 0.985 0.022 44.422 0.000 0.985 0.736
##
## R-Square:
## Estimate
## M 0.063
## Y 0.264
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect.SDblw 0.013 0.024 0.561 0.575 0.013 0.005
## indirect.SDabv 0.235 0.034 6.970 0.000 0.235 0.169
## direct.SDbelow -0.010 0.077 -0.128 0.898 -0.010 -0.007
## direct.SDabove 0.610 0.079 7.686 0.000 0.610 0.451
## total.SDbelow 0.003 0.090 0.038 0.970 0.003 -0.003
## total.SDabove 0.844 0.090 9.400 0.000 0.844 0.620
## prp.mdtd.SDblw 3.927 99.980 0.039 0.969 3.927 -1.687
## prop.mdtd.SDbv 0.278 0.036 7.623 0.000 0.278 0.272
## index.mod.med 0.222 0.041 5.438 0.000 0.222 0.082parameterEstimates(Mod.Med.SEM_vqrank,
boot.ci.type = "bca.simple",
level = .95, ci = TRUE,
standardized = FALSE)[c(19:27),c(4:10)] #We index the matrix to only display columns we are interested inInterest as mediator
modmed_interest_rank <- data.frame(
X = nonebacklash_long1$gendertarget_num,
M = scale(nonebacklash_long1$interest, scale = F),
W = nonebacklash_long1$deiexpert_num,
Y = scale(nonebacklash_long1$rank_r, scale = F),
pid = nonebacklash_long1$pid
)
Mod.Med.SEM_interestrank <- sem(model = modmed,
data = modmed_interest_rank,
bootstrap = 100, cluster = "pid")
summary(Mod.Med.SEM_interestrank,
fit.measures = FALSE,
standardize = TRUE,
rsquare = TRUE)## lavaan 0.6.17 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 13
##
## Used Total
## Number of observations 1812 1820
## Number of clusters [pid] 453
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1255.983 2114646736595.255
## Degrees of freedom 2 2
## P-value (Chi-square) 0.000 0.000
## Scaling correction factor 0.000
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M ~
## X (a1) 0.085 0.080 1.069 0.285 0.085 0.027
## W (a2) -0.285 0.134 -2.118 0.034 -0.285 -0.089
## X:W (a3) 0.736 0.141 5.226 0.000 0.736 0.196
## Y ~
## X (cds1) 0.002 0.080 0.022 0.983 0.002 0.001
## W (cds2) -0.370 0.062 -5.957 0.000 -0.370 -0.160
## X:W (cds3) 0.709 0.118 6.032 0.000 0.709 0.262
## M (b1) 0.179 0.015 12.048 0.000 0.179 0.249
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.mn) 0.483 0.024 20.568 0.000 0.483 0.967
## .M -0.084 0.087 -0.972 0.331 -0.084 -0.052
## .Y 0.007 0.044 0.150 0.881 0.007 0.006
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.vr) 0.250 0.001 320.854 0.000 0.250 1.000
## .M 2.440 0.102 23.882 0.000 2.440 0.947
## .Y 1.082 0.021 52.624 0.000 1.082 0.809
##
## R-Square:
## Estimate
## M 0.053
## Y 0.191
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect.SDblw 0.013 0.015 0.886 0.376 0.013 0.005
## indirect.SDabv 0.145 0.024 5.946 0.000 0.145 0.103
## direct.SDbelow -0.010 0.083 -0.118 0.906 -0.010 -0.008
## direct.SDabove 0.699 0.086 8.141 0.000 0.699 0.517
## total.SDbelow 0.003 0.090 0.038 0.970 0.003 -0.003
## total.SDabove 0.844 0.090 9.400 0.000 0.844 0.620
## prp.mdtd.SDblw 3.883 100.806 0.039 0.969 3.883 -1.826
## prop.mdtd.SDbv 0.172 0.029 5.864 0.000 0.172 0.166
## index.mod.med 0.132 0.028 4.689 0.000 0.132 0.049parameterEstimates(Mod.Med.SEM_interestrank,
boot.ci.type = "bca.simple",
level = .95, ci = TRUE,
standardized = FALSE)[c(19:27),c(4:10)] #We index the matrix to only display columns we are interested inVS as DV
VQ as mediator
modmed_vq_vs <- data.frame(
X = nonebacklash_long1$gendertarget_num,
M = scale(nonebacklash_long1$vq, scale = F),
W = nonebacklash_long1$deiexpert_num,
Y = scale(nonebacklash_long1$vs, scale = F),
pid = nonebacklash_long1$pid
)
Mod.Med.SEM_vsrank <- sem(model = modmed,
data = modmed_vq_vs,
bootstrap = 100, cluster = "pid")
summary(Mod.Med.SEM_vsrank,
fit.measures = FALSE,
standardize = TRUE,
rsquare = TRUE)## lavaan 0.6.17 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 13
##
## Number of observations 1820
## Number of clusters [pid] 455
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1261.528 NA
## Degrees of freedom 2 2
## P-value (Chi-square) 0.000 NA
## Scaling correction factor NA
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M ~
## X (a1) 0.061 0.082 0.741 0.459 0.061 0.020
## W (a2) -0.300 0.127 -2.361 0.018 -0.300 -0.097
## X:W (a3) 0.789 0.140 5.650 0.000 0.789 0.217
## Y ~
## X (cds1) 0.109 0.063 1.735 0.083 0.109 0.032
## W (cds2) -0.057 0.091 -0.632 0.528 -0.057 -0.017
## X:W (cds3) 0.199 0.089 2.230 0.026 0.199 0.050
## M (b1) 0.848 0.021 39.481 0.000 0.848 0.771
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.mn) 0.486 0.023 20.707 0.000 0.486 0.972
## .M -0.076 0.080 -0.952 0.341 -0.076 -0.049
## .Y -0.075 0.065 -1.148 0.251 -0.075 -0.044
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.vr) 0.250 0.001 372.725 0.000 0.250 1.000
## .M 2.269 0.102 22.208 0.000 2.269 0.938
## .Y 1.092 0.077 14.132 0.000 1.092 0.373
##
## R-Square:
## Estimate
## M 0.062
## Y 0.627
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect.SDblw 0.042 0.072 0.583 0.560 0.042 0.010
## indirect.SDabv 0.711 0.099 7.189 0.000 0.711 0.346
## direct.SDbelow 0.106 0.064 1.663 0.096 0.106 0.030
## direct.SDabove 0.305 0.063 4.854 0.000 0.305 0.130
## total.SDbelow 0.148 0.088 1.675 0.094 0.148 0.041
## total.SDabove 1.016 0.120 8.494 0.000 1.016 0.476
## prp.mdtd.SDblw 0.285 0.388 0.734 0.463 0.285 0.255
## prop.mdtd.SDbv 0.700 0.051 13.693 0.000 0.700 0.726
## index.mod.med 0.669 0.120 5.550 0.000 0.669 0.168parameterEstimates(Mod.Med.SEM_vsrank,
boot.ci.type = "bca.simple",
level = .95, ci = TRUE,
standardized = FALSE)[c(19:27),c(4:10)] #We index the matrix to only display columns we are interested inInterest as mediator
modmed_interest_vs <- data.frame(
X = nonebacklash_long1$gendertarget_num,
M = scale(nonebacklash_long1$interest, scale = F),
W = nonebacklash_long1$deiexpert_num,
Y = scale(nonebacklash_long1$vs, scale = F),
pid = nonebacklash_long1$pid
)
Mod.Med.SEM_interestvs <- sem(model = modmed,
data = modmed_interest_vs,
bootstrap = 100, cluster = "pid")
summary(Mod.Med.SEM_interestvs,
fit.measures = FALSE,
standardize = TRUE,
rsquare = TRUE)## lavaan 0.6.17 ended normally after 11 iterations
##
## Estimator ML
## Optimization method NLMINB
## Number of model parameters 13
##
## Number of observations 1820
## Number of clusters [pid] 455
##
## Model Test User Model:
## Standard Scaled
## Test Statistic 1261.528 NA
## Degrees of freedom 2 2
## P-value (Chi-square) 0.000 NA
## Scaling correction factor NA
## Yuan-Bentler correction (Mplus variant)
##
## Parameter Estimates:
##
## Standard errors Robust.cluster
## Information Observed
## Observed information based on Hessian
##
## Regressions:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## M ~
## X (a1) 0.085 0.080 1.069 0.285 0.085 0.027
## W (a2) -0.279 0.134 -2.085 0.037 -0.279 -0.087
## X:W (a3) 0.729 0.140 5.201 0.000 0.729 0.195
## Y ~
## X (cds1) 0.113 0.073 1.534 0.125 0.113 0.033
## W (cds2) -0.156 0.123 -1.272 0.203 -0.156 -0.046
## X:W (cds3) 0.461 0.131 3.530 0.000 0.461 0.116
## M (b1) 0.558 0.035 15.914 0.000 0.558 0.523
##
## Intercepts:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.mn) 0.486 0.023 20.707 0.000 0.486 0.972
## .M -0.084 0.087 -0.972 0.331 -0.084 -0.052
## .Y -0.092 0.077 -1.199 0.231 -0.092 -0.054
##
## Variances:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## W (W.vr) 0.250 0.001 372.725 0.000 0.250 1.000
## .M 2.435 0.102 23.915 0.000 2.435 0.948
## .Y 1.965 0.113 17.374 0.000 1.965 0.671
##
## R-Square:
## Estimate
## M 0.052
## Y 0.329
##
## Defined Parameters:
## Estimate Std.Err z-value P(>|z|) Std.lv Std.all
## indirect.SDblw 0.042 0.046 0.904 0.366 0.042 0.011
## indirect.SDabv 0.449 0.072 6.258 0.000 0.449 0.215
## direct.SDbelow 0.106 0.075 1.412 0.158 0.106 0.030
## direct.SDabove 0.567 0.108 5.272 0.000 0.567 0.261
## total.SDbelow 0.148 0.088 1.675 0.094 0.148 0.041
## total.SDabove 1.016 0.120 8.494 0.000 1.016 0.476
## prp.mdtd.SDblw 0.284 0.267 1.064 0.287 0.284 0.272
## prop.mdtd.SDbv 0.442 0.066 6.724 0.000 0.442 0.452
## index.mod.med 0.407 0.083 4.914 0.000 0.407 0.102parameterEstimates(Mod.Med.SEM_interestvs,
boot.ci.type = "bca.simple",
level = .95, ci = TRUE,
standardized = FALSE)[c(19:27),c(4:10)] #We index the matrix to only display columns we are interested in