Scale information
FSR
Burden
Status
Spotlighting vs. no
Main effects
Graphs
my_graph_function(
d = email2_clean,
i_v = "cond",
y = c("fsr", "burden", "stat", "workwit", "timewit", "leaddei", "engagement"),
variable_labels = c("FSR", "Burden", "Status", "Work", "Time", "Lead DEI", "Engage"),
variable_levels = c("Direct Input", "No Input"),
legend_title = "Legend"
)## `summarise()` has grouped output by 'variable'. You can override using the `.groups` argument.
Transgression vs. no
Main effects
Graphs
Interactions
Fear of social retaliation
ANOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 16 15.58 6.08 0.014 *
## cond 1 12 11.98 4.68 0.031 *
## transgression:cond 1 0 0.11 0.04 0.836
## Residuals 347 889 2.56
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1ANCOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 16 15.58 6.10 0.014 *
## cond 1 12 11.98 4.69 0.031 *
## Residuals 348 889 2.56
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Grouped by seeking condition
Grouped by transgression
Graphs
Burden
ANOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 14 13.97 3.31 0.070 .
## cond 1 6 5.93 1.40 0.237
## transgression:cond 1 14 13.57 3.22 0.074 .
## Residuals 347 1465 4.22
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1ANCOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 14 13.97 3.29 0.071 .
## cond 1 6 5.93 1.40 0.238
## Residuals 348 1478 4.25
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Grouped by seeking condition
Grouped by transgression
Graphs
Status
ANOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 56 56.4 22.72 0.0000028 ***
## cond 1 0 0.0 0.00 0.990
## transgression:cond 1 15 14.9 5.99 0.015 *
## Residuals 347 862 2.5
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1ANCOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 56 56.4 22.4 0.0000032 ***
## cond 1 0 0.0 0.0 0.99
## Residuals 348 876 2.5
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Grouped by seeking condition
Grouped by transgression
Graphs
Work with
ANOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 101 100.6 52.45 0.0000000000029 ***
## cond 1 3 2.6 1.36 0.24
## transgression:cond 1 1 0.9 0.45 0.50
## Residuals 347 665 1.9
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1ANCOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 101 100.6 52.53 0.0000000000028 ***
## cond 1 3 2.6 1.36 0.24
## Residuals 348 666 1.9
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Grouped by seeking condition
Grouped by transgression
Graphs
Time with
ANOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 1 0.59 0.13 0.72
## cond 1 3 3.41 0.76 0.38
## transgression:cond 1 4 4.34 0.97 0.33
## Residuals 347 1554 4.48ANCOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 1 0.59 0.13 0.72
## cond 1 3 3.41 0.76 0.38
## Residuals 348 1559 4.48Grouped by seeking condition
Grouped by transgression
Graphs
Lead DEI
ANOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 125 124.6 42.54 0.00000000024 ***
## cond 1 4 3.9 1.32 0.25
## transgression:cond 1 2 1.6 0.53 0.47
## Residuals 347 1016 2.9
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1ANCOVA
## Df Sum Sq Mean Sq F value Pr(>F)
## transgression 1 125 124.6 42.60 0.00000000024 ***
## cond 1 4 3.9 1.33 0.25
## Residuals 348 1018 2.9
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1Grouped by seeking condition
Grouped by transgression
Graphs
Engage
Regression
##
## Call:
## glm(formula = engagement ~ transgression * cond, family = "binomial",
## data = email2_clean)
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 0.437 0.230 1.90 0.0578 .
## transgressionsexist 0.632 0.334 1.89 0.0584 .
## condNoInputSeeking -0.928 0.327 -2.84 0.0045 **
## transgressionsexist:condNoInputSeeking 0.354 0.454 0.78 0.4360
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for binomial family taken to be 1)
##
## Null deviance: 473.72 on 350 degrees of freedom
## Residual deviance: 449.70 on 347 degrees of freedom
## AIC: 457.7
##
## Number of Fisher Scoring iterations: 4Graph (Logit)
Graphs (Percentages)
Are the proportions significantly different from 50%?
##
## 1-sample proportions test with continuity correction
##
## data: 64 out of 103, null probability 0.5
## X-squared = 5.6, df = 1, p-value = 0.02
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.5200 0.7135
## sample estimates:
## p
## 0.6214##
## 1-sample proportions test with continuity correction
##
## data: 67 out of 90, null probability 0.5
## X-squared = 21, df = 1, p-value = 0.000006
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.6397 0.8280
## sample estimates:
## p
## 0.7444##
## 1-sample proportions test with continuity correction
##
## data: 30 out of 79, null probability 0.5
## X-squared = 4.1, df = 1, p-value = 0.04
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.2750 0.4963
## sample estimates:
## p
## 0.3797##
## 1-sample proportions test with continuity correction
##
## data: 48 out of 79, null probability 0.5
## X-squared = 3.2, df = 1, p-value = 0.07
## alternative hypothesis: true p is not equal to 0.5
## 95 percent confidence interval:
## 0.4910 0.7136
## sample estimates:
## p
## 0.6076Yes, all proportions are significantly different from 50%…except for the “direct, sexism” condition.