Background

In a 2 (taboo vs. standard) cell design, participants read about a transaction involving storing potentially hazardous chemicals OR a transaction involving storing furniture. They were then asked, in a random order, about the actors’ benefit from the transaction and the power balance in the transaction.

Attention check

What are the roles of Person A and Person B in the transaction that took place?
The correct answer is: Person A paid money and Person B received money

cond failcheck passcheck
nontaboo 5 95
taboo 2 99

Alright, that leaves us with 194, pretty evenly distributed between conditions.

Demographics

Race

race N Perc
asian 14 7.22
black 14 7.22
hispanic 10 5.15
multiracial 11 5.67
white 141 72.68
NA 4 2.06

Gender

gender N Perc
man 101 52.06
woman 86 44.33
NA 7 3.61

Age

age_mean age_sd
38.29897 11.5181

Education

edu N Perc
noHS 2 1.03
GED 51 26.29
2yearColl 21 10.82
4yearColl 85 43.81
MA 28 14.43
PHD 7 3.61

Income

Analysis

Condition -> Benefit

Descriptives

cond benefit_A_m benefit_A_sd benefit_B_m benefit_B_sd
nontaboo 0.9473684 1.214876 1.4210526 0.7660197
taboo 1.7676768 1.219135 -0.3939394 1.8451159

Two-way Repeated Measures ANOVA

Effect DFn DFd F p p<.05 ges
cond 1 192 13.322 0.000338
0.034
person 1 192 40.482 0.000000
0.093
cond:person 1 192 98.676 0.000000
0.200

Bonferroni-corrected post-hoc comparisons: Party

person Effect DFn DFd F p p<.05 ges p.adj
benefit_A cond 1 192 22.024 5.1e-06
0.103 1.02e-05
benefit_B cond 1 192 78.866 0.0e+00
0.291 0.00e+00

Bonferroni-corrected post-hoc comparisons: Condition

cond Effect DFn DFd F p p<.05 ges p.adj
nontaboo person 1 94 14.767 0.000221
0.052 0.000442
taboo person 1 98 87.278 0.000000
0.325 0.000000

One-sample t-tests

Buyers in Taboo Condition: t(98) = 14.43, p < .001, d = 1.45

Buyers in Standard Condition: t(94) = 18.08, p < .001, d = 1.86

Sellers in Taboo Condition: t(98) = -2.12, p = .018, d = -0.21

Sellers in Standard Condition: t(94) = 18.08, p < .001, d = 1.86

Condition -> Power

Let’s take a look at the effect on power. Power was rated from -3 (Buyer has much more power) to 3 (Seller has much more power).

Descriptives

cond power_M power_SD
nontaboo 0.99 1.01
taboo -0.39 1.73

Power is pretty much balanced in the taboo condition. In the non-taboo condition, the seller has more power.

t-test

t(158.89) = 6.86, p < .001, d = 0.97

One-sample t-tests

Taboo Condition:

t(98) = -2.27, p = .025, d = -0.23
Non-Taboo Condition:

t(94) = 9.59, p < .001, d = 0.98

Plot: Condition -> Power


Mediation model: condition -> power -> seller benefit

0 = Standard; 1 = Taboo

a = -1.38 (p = 0); b = 0.43 (p = 0); direct = -1.81 (p = 0); indirect = -1.22 (p = 0).

Ok.. a partial mediation. Not bad.

Order effects: Benefit first

Condition -> Benefit

Descriptives

cond benefit_A_m benefit_A_sd benefit_B_m benefit_B_sd
nontaboo 1.075472 1.253442 1.3773585 0.8599288
taboo 1.930233 1.162824 -0.5813953 2.0613514

Two-way Repeated Measures ANOVA

Effect DFn DFd F p p<.05 ges
cond 1 94 6.958 1e-02
0.039
person 1 94 34.060 1e-07
0.140
cond:person 1 94 55.216 0e+00
0.209

Bonferroni-corrected post-hoc comparisons: Party

person Effect DFn DFd F p p<.05 ges p.adj
benefit_A cond 1 94 11.773 0.000895
0.111 0.00179
benefit_B cond 1 94 39.470 0.000000
0.296 0.00000

Bonferroni-corrected post-hoc comparisons: Condition

cond Effect DFn DFd F p p<.05 ges p.adj
nontaboo person 1 52 3.255 0.077 0.020 0.154
taboo person 1 42 46.933 0.000
0.366 0.000

One-sample t-tests

Buyers in Taboo Condition: t(42) = 10.89, p < .001, d = 1.66

Buyers in Standard Condition: t(52) = 11.66, p < .001, d = 1.60

Sellers in Taboo Condition: t(42) = -1.85, p = .036, d = -0.28

Sellers in Standard Condition: t(52) = 11.66, p < .001, d = 1.60

Condition -> Power

Let’s take a look at the effect on power. Power was rated from -3 (Buyer has much more power) to 3 (Seller has much more power).

Descriptives

cond power_M power_SD
nontaboo 0.87 0.96
taboo -0.44 1.72

t-test

t(62.69) = 4.45, p < .001, d = 0.97

One-sample t-tests

Taboo Condition:

t(42) = -1.68, p = .100, d = -0.26
Non-Taboo Condition:

t(52) = 6.57, p < .001, d = 0.90

Plot: Condition -> Power


Ok, same patterns for “benefit first” participants.

Order effects: Power first

Condition -> Benefit

Descriptives

cond benefit_A_m benefit_A_sd benefit_B_m benefit_B_sd
nontaboo 0.7857143 1.158967 1.47619 0.6339229
taboo 1.6428571 1.256671 -0.25000 1.6651508

Two-way Repeated Measures ANOVA

Effect DFn DFd F p p<.05 ges
cond 1 96 5.810 0.018
0.028
person 1 96 10.334 0.002
0.053
cond:person 1 96 47.702 0.000
0.205

Bonferroni-corrected post-hoc comparisons: Party

person Effect DFn DFd F p p<.05 ges p.adj
benefit_A cond 1 96 11.927 0.000825
0.111 0.00165
benefit_B cond 1 96 40.629 0.000000
0.297 0.00000

Bonferroni-corrected post-hoc comparisons: Condition

cond Effect DFn DFd F p p<.05 ges p.adj
nontaboo person 1 41 14.933 0.000389
0.123 7.78e-04
taboo person 1 55 41.276 0.000000
0.295 1.00e-07

One-sample t-tests

Buyers in Taboo Condition: t(55) = 9.78, p < .001, d = 1.31

Buyers in Standard Condition: t(41) = 15.09, p < .001, d = 2.33

Sellers in Taboo Condition: t(55) = -1.12, p = .133, d = -0.15

Sellers in Standard Condition: t(41) = 15.09, p < .001, d = 2.33

Condition -> Power

Let’s take a look at the effect on power. Power was rated from -3 (Buyer has much more power) to 3 (Seller has much more power).

Descriptives

cond power_M power_SD
nontaboo 1.14 1.05
taboo -0.36 1.74

t-test

t(92.16) = 5.29, p < .001, d = 1.01

One-sample t-tests

Taboo Condition:

t(55) = -1.53, p = .131, d = -0.21
Non-Taboo Condition:

t(41) = 7.06, p < .001, d = 1.09

Plot: Condition -> Power



Yeah, there’s basically no order effects.