Conference submission analysis
Samuel Choi
10/3/2021
1 Retrieve dataset and install packages
library(readr)
pmdata1 <- read_csv("pmdata1.csv")## Rows: 54 Columns: 280## -- Column specification --------------------------------------------------------
## Delimiter: ","
## chr (18): StartDate, IPAddress, ResponseId, gender, race, edu, marital, inc...
## dbl (262): Progress, Duration..in.seconds., stdysal, benefits, goodsal, jobs...##
## i Use `spec()` to retrieve the full column specification for this data.
## i Specify the column types or set `show_col_types = FALSE` to quiet this message.2 specify categorical variables and relevel
pmdata1$gender <- as.factor(pmdata1$gender)
pmdata1$race <- as.factor(pmdata1$race)
pmdata1$edu <- as.factor(pmdata1$edu)
pmdata1$marital <- as.factor(pmdata1$marital)
pmdata1$income <- as.factor(pmdata1$income)
pmdata1$religion <- as.factor(pmdata1$religion)
pmdata1$rank <- as.factor(pmdata1$rank)
pmdata1$family <- as.factor(pmdata1$family)
pmdata1$nopoexp <- as.factor(pmdata1$nopoexp)
pmdata1$military <- as.factor(pmdata1$military)
library(stats)
pmdata1$gender <- relevel(pmdata1$gender, ref = "female")
pmdata1$race <- relevel(pmdata1$race, ref = "black")
pmdata1$edu <- relevel(pmdata1$edu, ref = "high school")
pmdata1$marital <- relevel(pmdata1$marital, ref = "married")
pmdata1$income <- relevel(pmdata1$income, ref = "25k to 49.9k")
pmdata1$religion <- relevel(pmdata1$religion, ref = "no affil")
pmdata1$rank <- relevel(pmdata1$rank, ref = "police officer")
pmdata1$family <- relevel(pmdata1$family, ref = "no")
pmdata1$nopoexp <- relevel(pmdata1$nopoexp, ref = "no")
pmdata1$military <- relevel(pmdata1$military, ref = "no")3 Data screening
IVs
sdo = social dominance orientation (e.g., we should not push for group equality)
rwa = right-wing authoritarianism (e.g., its better to accept bad literature than to censor it)
legit = police perceptions of how the community views them in terms of legitimacy (e.g., citizens in your community trust the police) ferg = the ferguson effect (negative impact of publicity on officers)
prom = commitment to prominence goals (e.g., glory, championship); TIP-END goals
neg = commitment to negativity prevention goals (e.g., abnormality, craziness); TIP-END goals
trad = commitment to tradition goals (e.g., faith, obedience); TIP-END goals
inclus = commitment to inclusiveness goals (e.g., diversity, comradery, equity); TIP-END goals
elite = commitment to elitism goals (e.g., authoritarianism, boastfulness); TIP-END goals
disrep = commitment to disrepute (e.g., addiction, corruption); TIP-END goals
rebel = commitment to rebellion (e.g., wildness; temptation); TIP-END goals
loyal = loyalty to fellow officers (e.g., If I violate a rule, I expect my fellow officer to protect me)
bpaq = Buss-Perry Aggression Questionnaire (e.g., Given enough provocation, I may hit another person)
guardian = police officers as guardians orientation (e.g., As a police officer, I see myself as a civil servant)
warrior = police officers as warriors orientation (e.g., My primary responsibility as a police officer is to fight crime)
DVs
reason = endorsement of reasonable use of force (e.g., A police officer uses guns and clubs to stop violent demonstrations)
excess = endorsement of excessive use of force (e.g., A police officer uses violence to control non-violent demonstrations)
projust = endorsement of procedural justice (e.g., When interacting with community residents, how important is it to show an interest in what they have to say?)
3.1 Histograms
Based on histograms below, loyal needs a transform. Excess and reason may need a transform too, but their skew is not as bad. I removed loyal from analysis.
hist(pmdata1$sdo)
hist(pmdata1$rwa)
hist(pmdata1$legit)
hist(pmdata1$ferg)
hist(pmdata1$prom)
hist(pmdata1$neg)
hist(pmdata1$trad)
hist(pmdata1$inclus)
hist(pmdata1$elite)
hist(pmdata1$disrep)
hist(pmdata1$rebel)
hist(pmdata1$reason)
hist(pmdata1$excess)
hist(pmdata1$projust)
hist(pmdata1$loyal)
hist(pmdata1$bpaq)
hist(pmdata1$desirab)
hist(pmdata1$guardian)
hist(pmdata1$warrior)
3.2 Outliers (beyond 1.5*IQR was removed)
3.3 Multicollinearity: for hierarchical regression
Based on the multicollinearity analysis below, I removed rank, marital, education, income, totalexp, race, religion, disrep, and rebel from further analysis.
library(car)## Loading required package: carDatamulticollin <- lm(excess ~ age + gender + family + nopoexp + military + rankexp + sdo + rwa + legit + prom + neg + trad + inclus + elite + rebel + bpaq + guardian + warrior + desirab, na.action = na.omit, data = pmdata1)
vif(multicollin)## age gender family nopoexp military rankexp sdo rwa
## 1.501417 2.879692 5.205071 3.486756 2.942532 2.961819 2.672494 4.284721
## legit prom neg trad inclus elite rebel bpaq
## 2.824698 2.719625 4.079553 4.006909 4.137504 4.274605 6.496975 4.335127
## guardian warrior desirab
## 3.537075 2.363152 3.6943883.4 Linearity, constancy, normality: hierarchial regression
model1.1 <- lm(excess ~ age + gender + family + nopoexp + military + rankexp, na.action = na.omit, data = pmdata1)
model1.2 <- lm(reason ~ age + gender + family + nopoexp + military + rankexp, na.action = na.omit, data = pmdata1)
model1.3 <- lm(projust ~ age + gender + family + nopoexp + military + rankexp, na.action = na.omit, data = pmdata1)
model2.1 <- lm(excess ~ age + gender + family + nopoexp + military + rankexp + sdo + rwa + legit + prom + neg + trad + inclus + elite + rebel + bpaq + guardian + warrior + desirab, na.action = na.omit, data = pmdata1)
model2.2 <- lm(reason ~ age + gender + family + nopoexp + military + rankexp + sdo + rwa + legit + prom + neg + trad + inclus + elite + rebel + bpaq + guardian + warrior + desirab, na.action = na.omit, data = pmdata1)
model2.3 <- lm(projust ~ age + gender + family + nopoexp + military + rankexp + sdo + rwa + legit + prom + neg + trad + inclus + elite + rebel + bpaq + guardian + warrior + desirab, na.action = na.omit, data = pmdata1)
par(mfrow=c(2,2))
plot(model1.1)
plot(model1.2)
plot(model1.3)
plot(model2.1)
plot(model2.2)
plot(model2.3)
3.5 Linearity, constancy, normality: bivariate regressions
3.5.1 Linearity, constancy, normality: excess
par(mfrow=c(2,2))
model3 <- lm(excess ~ sdo, na.action = na.omit, data = pmdata1)
model4 <- lm(excess ~ rwa, na.action = na.omit, data = pmdata1)
model5 <- lm(excess ~ legit, na.action = na.omit, data = pmdata1)
model6 <- lm(excess ~ prom, na.action = na.omit, data = pmdata1)
model7 <- lm(excess ~ neg, na.action = na.omit, data = pmdata1)
model8 <- lm(excess ~ trad, na.action = na.omit, data = pmdata1)
model9 <- lm(excess ~ inclus, na.action = na.omit, data = pmdata1)
model10 <- lm(excess ~ elite, na.action = na.omit, data = pmdata1)
model11 <- lm(excess ~ rebel, na.action = na.omit, data = pmdata1)
model12 <- lm(excess ~ bpaq, na.action = na.omit, data = pmdata1)
model13 <- lm(excess ~ guardian, na.action = na.omit, data = pmdata1)
model14 <- lm(excess ~ warrior, na.action = na.omit, data = pmdata1)
plot(model3)
plot(model4)
plot(model5)
plot(model6)
plot(model7)
plot(model8)
plot(model9)
plot(model10)
plot(model11)
plot(model12)
plot(model13)
plot(model14)
3.5.2 Linearity, constancy, normality: reason
par(mfrow=c(2,2))
model15 <- lm(reason ~ sdo, na.action = na.omit, data = pmdata1)
model16 <- lm(reason ~ rwa, na.action = na.omit, data = pmdata1)
model17 <- lm(reason ~ legit, na.action = na.omit, data = pmdata1)
model18 <- lm(reason ~ prom, na.action = na.omit, data = pmdata1)
model19 <- lm(reason ~ neg, na.action = na.omit, data = pmdata1)
model20 <- lm(reason ~ trad, na.action = na.omit, data = pmdata1)
model21 <- lm(reason ~ inclus, na.action = na.omit, data = pmdata1)
model22 <- lm(reason ~ elite, na.action = na.omit, data = pmdata1)
model23 <- lm(reason ~ rebel, na.action = na.omit, data = pmdata1)
model24 <- lm(reason ~ bpaq, na.action = na.omit, data = pmdata1)
model25 <- lm(reason ~ guardian, na.action = na.omit, data = pmdata1)
model26 <- lm(reason ~ warrior, na.action = na.omit, data = pmdata1)
plot(model15)
plot(model16)
plot(model17)
plot(model18)
plot(model19)
plot(model20)
plot(model21)
plot(model22)
plot(model23)
plot(model24)
plot(model25)
plot(model26)
3.5.3 Linearity, constancy, normality: projust
par(mfrow=c(2,2))
model27 <- lm(projust ~ sdo, na.action = na.omit, data = pmdata1)
model28 <- lm(projust ~ rwa, na.action = na.omit, data = pmdata1)
model29 <- lm(projust ~ legit, na.action = na.omit, data = pmdata1)
model30 <- lm(projust ~ prom, na.action = na.omit, data = pmdata1)
model31 <- lm(projust ~ neg, na.action = na.omit, data = pmdata1)
model32 <- lm(projust ~ trad, na.action = na.omit, data = pmdata1)
model33 <- lm(projust ~ inclus, na.action = na.omit, data = pmdata1)
model34 <- lm(projust ~ elite, na.action = na.omit, data = pmdata1)
model35 <- lm(projust ~ rebel, na.action = na.omit, data = pmdata1)
model36 <- lm(projust ~ bpaq, na.action = na.omit, data = pmdata1)
model37 <- lm(projust ~ guardian, na.action = na.omit, data = pmdata1)
model38 <- lm(projust ~ warrior, na.action = na.omit, data = pmdata1)
plot(model27)
plot(model28)
plot(model29)
plot(model30)
plot(model31)
plot(model32)
plot(model33)
plot(model34)
plot(model35)
plot(model36)
plot(model37)
plot(model38)
4 Analyses
4.1 Hierarchical regressions
Note, the direction of guardian, warrior, rwa, and sdo (IVs) in relation with excessive use force (DV); the direction of rwa and sdo for reasonable use of force; and the direction for guardian, warrior, and rwa in relation with procedural justice does not make sense. The relationships seem to be opposite to what we would expect. I suspect that this is due to multicollinearity. I found high VIF values for multiple variables in the above analysis. I did remove the problematic variables as aforementioned, but the VIF values still weren’t great. To account for this, I conducted bivariate regression analyses (excluding all other control variables) below. The direction of the relationships starts to make sense again.
4.1.1 Step 1: Demographic model
DVs: excessive use force (excess), reasonable use of force (reason), procedural justice(projust) - higher scores = higher endorsement
summary(model1.1)##
## Call:
## lm(formula = excess ~ age + gender + family + nopoexp + military +
## rankexp, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.0400 -0.5426 -0.1985 0.5771 1.8535
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.384804 0.603006 3.955 0.000313 ***
## age -0.022300 0.013459 -1.657 0.105556
## gendermale 0.374130 0.316692 1.181 0.244611
## familyyes 0.138431 0.286112 0.484 0.631209
## nopoexpyes -0.024804 0.290659 -0.085 0.932429
## militaryyes -0.055955 0.269819 -0.207 0.836792
## rankexp -0.001774 0.016525 -0.107 0.915039
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7952 on 39 degrees of freedom
## (8 observations deleted due to missingness)
## Multiple R-squared: 0.1186, Adjusted R-squared: -0.01698
## F-statistic: 0.8748 on 6 and 39 DF, p-value: 0.5222summary(model1.2)##
## Call:
## lm(formula = reason ~ age + gender + family + nopoexp + military +
## rankexp, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.72172 -0.28266 0.09474 0.41901 0.99749
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 7.069755 0.517320 13.666 3.02e-16 ***
## age -0.016466 0.011614 -1.418 0.164
## gendermale -0.147328 0.269064 -0.548 0.587
## familyyes -0.043646 0.243741 -0.179 0.859
## nopoexpyes -0.013938 0.246829 -0.056 0.955
## militaryyes -0.240683 0.231151 -1.041 0.304
## rankexp -0.003485 0.014028 -0.248 0.805
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6749 on 38 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.1468, Adjusted R-squared: 0.0121
## F-statistic: 1.09 on 6 and 38 DF, p-value: 0.386summary(model1.3)##
## Call:
## lm(formula = projust ~ age + gender + family + nopoexp + military +
## rankexp, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.64075 -0.20058 0.00802 0.25200 0.74675
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.255420 0.250210 17.007 <2e-16 ***
## age 0.005227 0.005624 0.929 0.3584
## gendermale -0.234543 0.130854 -1.792 0.0808 .
## familyyes -0.035277 0.118233 -0.298 0.7670
## nopoexpyes -0.016606 0.120144 -0.138 0.8908
## militaryyes -0.023590 0.111352 -0.212 0.8333
## rankexp 0.001798 0.006819 0.264 0.7934
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3284 on 39 degrees of freedom
## (8 observations deleted due to missingness)
## Multiple R-squared: 0.09823, Adjusted R-squared: -0.0405
## F-statistic: 0.7081 on 6 and 39 DF, p-value: 0.6454.1.2 Step 2: Whole model (demographic + IVs)
DVs: excessive use force (excess), reasonable use of force (reason), procedural justice(projust) - higher scores = higher endorsement
summary(model2.1)##
## Call:
## lm(formula = excess ~ age + gender + family + nopoexp + military +
## rankexp + sdo + rwa + legit + prom + neg + trad + inclus +
## elite + rebel + bpaq + guardian + warrior + desirab, data = pmdata1,
## na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.93856 -0.18935 0.09424 0.20608 0.89141
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) -0.688381 4.598444 -0.150 0.885
## age -0.014925 0.018819 -0.793 0.451
## gendermale 0.290250 0.706973 0.411 0.692
## familyyes -0.035188 0.681017 -0.052 0.960
## nopoexpyes -0.588155 0.582879 -1.009 0.342
## militaryyes 0.081814 0.553562 0.148 0.886
## rankexp 0.003130 0.033721 0.093 0.928
## sdo -0.006493 0.298901 -0.022 0.983
## rwa -0.023454 0.395649 -0.059 0.954
## legit -0.385705 0.372608 -1.035 0.331
## prom -0.127533 0.316745 -0.403 0.698
## neg -0.443949 0.329670 -1.347 0.215
## trad -0.177406 0.366266 -0.484 0.641
## inclus -0.458348 0.321286 -1.427 0.192
## elite -0.128666 0.318187 -0.404 0.697
## rebel 0.211387 0.343597 0.615 0.556
## bpaq 0.372643 0.493235 0.756 0.472
## guardian 0.980184 0.699914 1.400 0.199
## warrior -0.175110 0.197382 -0.887 0.401
## desirab -0.344199 1.488634 -0.231 0.823
##
## Residual standard error: 0.7714 on 8 degrees of freedom
## (26 observations deleted due to missingness)
## Multiple R-squared: 0.6809, Adjusted R-squared: -0.07688
## F-statistic: 0.8985 on 19 and 8 DF, p-value: 0.6022summary(model2.2)##
## Call:
## lm(formula = reason ~ age + gender + family + nopoexp + military +
## rankexp + sdo + rwa + legit + prom + neg + trad + inclus +
## elite + rebel + bpaq + guardian + warrior + desirab, data = pmdata1,
## na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.56694 -0.33561 -0.03251 0.33938 0.83543
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.530220 4.090393 0.619 0.553
## age -0.013911 0.016740 -0.831 0.430
## gendermale 0.426776 0.628864 0.679 0.517
## familyyes -0.016695 0.605776 -0.028 0.979
## nopoexpyes 0.544937 0.518480 1.051 0.324
## militaryyes -0.117546 0.492402 -0.239 0.817
## rankexp 0.019228 0.029995 0.641 0.539
## sdo 0.140677 0.265877 0.529 0.611
## rwa 0.063344 0.351937 0.180 0.862
## legit -0.091408 0.331441 -0.276 0.790
## prom 0.485177 0.281750 1.722 0.123
## neg 0.052705 0.293247 0.180 0.862
## trad -0.513884 0.325799 -1.577 0.153
## inclus 0.292222 0.285789 1.023 0.336
## elite -0.003478 0.283033 -0.012 0.990
## rebel -0.368780 0.305635 -1.207 0.262
## bpaq -0.047157 0.438741 -0.107 0.917
## guardian 0.643247 0.622585 1.033 0.332
## warrior 0.094203 0.175575 0.537 0.606
## desirab -0.836532 1.324165 -0.632 0.545
##
## Residual standard error: 0.6862 on 8 degrees of freedom
## (26 observations deleted due to missingness)
## Multiple R-squared: 0.691, Adjusted R-squared: -0.04302
## F-statistic: 0.9414 on 19 and 8 DF, p-value: 0.572summary(model2.3)##
## Call:
## lm(formula = projust ~ age + gender + family + nopoexp + military +
## rankexp + sdo + rwa + legit + prom + neg + trad + inclus +
## elite + rebel + bpaq + guardian + warrior + desirab, data = pmdata1,
## na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.234829 -0.083597 0.007551 0.068291 0.230098
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.743571 1.204230 2.278 0.0522 .
## age -0.003622 0.004928 -0.735 0.4834
## gendermale -0.477106 0.185140 -2.577 0.0328 *
## familyyes -0.190353 0.178343 -1.067 0.3170
## nopoexpyes -0.078591 0.152643 -0.515 0.6206
## militaryyes 0.274005 0.144965 1.890 0.0954 .
## rankexp 0.006221 0.008831 0.704 0.5011
## sdo -0.074288 0.078275 -0.949 0.3704
## rwa 0.224076 0.103612 2.163 0.0625 .
## legit 0.174239 0.097578 1.786 0.1120
## prom 0.195015 0.082948 2.351 0.0466 *
## neg 0.134182 0.086333 1.554 0.1587
## trad 0.110896 0.095917 1.156 0.2810
## inclus 0.122892 0.084138 1.461 0.1823
## elite 0.139624 0.083326 1.676 0.1323
## rebel -0.088708 0.089980 -0.986 0.3531
## bpaq -0.180114 0.129167 -1.394 0.2007
## guardian -0.021495 0.183292 -0.117 0.9095
## warrior 0.158515 0.051690 3.067 0.0154 *
## desirab 0.073691 0.389840 0.189 0.8548
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.202 on 8 degrees of freedom
## (26 observations deleted due to missingness)
## Multiple R-squared: 0.8729, Adjusted R-squared: 0.5709
## F-statistic: 2.891 on 19 and 8 DF, p-value: 0.063874.2 Bivariate regressions
4.2.1 Single IVs predicting excessive use of force (higher scores = higher endorsement)
library(lm.beta)
summary(model3)##
## Call:
## lm(formula = excess ~ sdo, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.0970 -0.5522 -0.1564 0.4961 2.1877
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.6497 0.3770 1.723 0.09101 .
## sdo 0.3796 0.1285 2.955 0.00475 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.762 on 50 degrees of freedom
## (2 observations deleted due to missingness)
## Multiple R-squared: 0.1487, Adjusted R-squared: 0.1317
## F-statistic: 8.734 on 1 and 50 DF, p-value: 0.004754lm.beta(model3)##
## Call:
## lm(formula = excess ~ sdo, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) sdo
## 0.0000000 0.3856227summary(model4)##
## Call:
## lm(formula = excess ~ rwa, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.7363 -0.6961 -0.3330 0.5899 2.2965
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.61182 0.67722 2.380 0.0212 *
## rwa 0.02456 0.16718 0.147 0.8838
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.839 on 49 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.0004403, Adjusted R-squared: -0.01996
## F-statistic: 0.02158 on 1 and 49 DF, p-value: 0.8838lm.beta(model4)##
## Call:
## lm(formula = excess ~ rwa, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) rwa
## 0.00000000 0.02098293summary(model5)##
## Call:
## lm(formula = excess ~ legit, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.1930 -0.4760 -0.3378 0.5644 2.4622
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.5036 0.9959 3.518 0.000948 ***
## legit -0.2979 0.1650 -1.805 0.077216 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8077 on 49 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.06235, Adjusted R-squared: 0.04321
## F-statistic: 3.258 on 1 and 49 DF, p-value: 0.07722lm.beta(model5)##
## Call:
## lm(formula = excess ~ legit, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) legit
## 0.0000000 -0.2496936summary(model6)##
## Call:
## lm(formula = excess ~ prom, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.0211 -0.6080 -0.2711 0.5525 2.2473
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.7527 0.1193 14.688 <2e-16 ***
## prom 0.1736 0.1270 1.368 0.178
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8217 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.03908, Adjusted R-squared: 0.01819
## F-statistic: 1.871 on 1 and 46 DF, p-value: 0.178lm.beta(model6)##
## Call:
## lm(formula = excess ~ prom, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) prom
## 0.0000000 0.1976811summary(model7)##
## Call:
## lm(formula = excess ~ neg, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8872 -0.6108 -0.3567 0.5449 2.2466
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.0656 0.2793 7.396 1.82e-09 ***
## neg 0.1487 0.1160 1.282 0.206
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.821 on 48 degrees of freedom
## (4 observations deleted due to missingness)
## Multiple R-squared: 0.03311, Adjusted R-squared: 0.01296
## F-statistic: 1.643 on 1 and 48 DF, p-value: 0.206lm.beta(model7)##
## Call:
## lm(formula = excess ~ neg, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) neg
## 0.0000000 0.1819503summary(model8)##
## Call:
## lm(formula = excess ~ trad, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.1026 -0.5187 -0.2308 0.3994 2.3001
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.1428 0.2987 7.174 6.37e-09 ***
## trad -0.2215 0.1412 -1.568 0.124
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.8053 on 44 degrees of freedom
## (8 observations deleted due to missingness)
## Multiple R-squared: 0.05292, Adjusted R-squared: 0.0314
## F-statistic: 2.459 on 1 and 44 DF, p-value: 0.124lm.beta(model8)##
## Call:
## lm(formula = excess ~ trad, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) trad
## 0.0000000 -0.2300469summary(model9)##
## Call:
## lm(formula = excess ~ inclus, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.9921 -0.5398 -0.2581 0.4373 2.3061
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.0150 0.1839 10.96 1.55e-14 ***
## inclus -0.2523 0.1243 -2.03 0.0481 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7999 on 47 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.0806, Adjusted R-squared: 0.06104
## F-statistic: 4.12 on 1 and 47 DF, p-value: 0.04806lm.beta(model9)##
## Call:
## lm(formula = excess ~ inclus, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) inclus
## 0.0000000 -0.2838976summary(model10)##
## Call:
## lm(formula = excess ~ elite, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.0352 -0.5280 -0.2178 0.5339 2.0546
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3559 0.2471 9.533 1.47e-12 ***
## elite 0.3140 0.1154 2.722 0.00908 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7776 on 47 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.1361, Adjusted R-squared: 0.1178
## F-statistic: 7.407 on 1 and 47 DF, p-value: 0.009081lm.beta(model10)##
## Call:
## lm(formula = excess ~ elite, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) elite
## 0.000000 0.368983summary(model11)##
## Call:
## lm(formula = excess ~ rebel, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.0160 -0.5271 -0.1826 0.3913 1.6950
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.3050 0.2262 10.192 1.73e-13 ***
## rebel 0.2890 0.1036 2.789 0.00762 **
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.775 on 47 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.142, Adjusted R-squared: 0.1237
## F-statistic: 7.776 on 1 and 47 DF, p-value: 0.00762lm.beta(model11)##
## Call:
## lm(formula = excess ~ rebel, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) rebel
## 0.000000 0.376773summary(model12)##
## Call:
## lm(formula = excess ~ bpaq, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.0445 -0.5695 -0.2904 0.6138 2.0180
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.9820 0.4282 2.294 0.0261 *
## bpaq 0.2500 0.1516 1.649 0.1054
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.751 on 49 degrees of freedom
## (3 observations deleted due to missingness)
## Multiple R-squared: 0.05261, Adjusted R-squared: 0.03327
## F-statistic: 2.721 on 1 and 49 DF, p-value: 0.1054lm.beta(model12)##
## Call:
## lm(formula = excess ~ bpaq, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) bpaq
## 0.0000000 0.2293609summary(model13)##
## Call:
## lm(formula = excess ~ guardian, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6792 -0.5924 -0.2310 0.5690 1.6076
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.99748 1.79760 1.111 0.273
## guardian -0.05786 0.27670 -0.209 0.835
##
## Residual standard error: 0.7139 on 43 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.001016, Adjusted R-squared: -0.02222
## F-statistic: 0.04373 on 1 and 43 DF, p-value: 0.8353lm.beta(model13)##
## Call:
## lm(formula = excess ~ guardian, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) guardian
## 0.00000000 -0.03187431summary(model14)##
## Call:
## lm(formula = excess ~ warrior, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.7503 -0.6295 -0.2844 0.5595 2.2387
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.49766 0.58866 2.544 0.0143 *
## warrior 0.03296 0.09917 0.332 0.7411
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.7754 on 47 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.002345, Adjusted R-squared: -0.01888
## F-statistic: 0.1105 on 1 and 47 DF, p-value: 0.7411lm.beta(model14)##
## Call:
## lm(formula = excess ~ warrior, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) warrior
## 0.00000000 0.048420224.2.2 Single IVs predicting reasonable use of force (higher scores = higher endorsement)
summary(model15)##
## Call:
## lm(formula = reason ~ sdo, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7066 -0.3129 0.2877 0.4788 0.9093
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.07732 0.34416 17.658 <2e-16 ***
## sdo 0.01017 0.11658 0.087 0.931
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.678 on 47 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.0001618, Adjusted R-squared: -0.02111
## F-statistic: 0.007606 on 1 and 47 DF, p-value: 0.9309lm.beta(model15)##
## Call:
## lm(formula = reason ~ sdo, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) sdo
## 0.00000000 0.01271999summary(model16)##
## Call:
## lm(formula = reason ~ rwa, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7074 -0.3487 0.1994 0.3566 0.9119
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.062583 0.562548 10.777 3.57e-14 ***
## rwa 0.009348 0.138375 0.068 0.946
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6814 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 9.919e-05, Adjusted R-squared: -0.02164
## F-statistic: 0.004563 on 1 and 46 DF, p-value: 0.9464lm.beta(model16)##
## Call:
## lm(formula = reason ~ rwa, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) rwa
## 0.000000000 0.009959658summary(model17)##
## Call:
## lm(formula = reason ~ legit, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7333 -0.3341 0.1673 0.4657 0.8683
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.121193 0.880115 6.955 1.06e-08 ***
## legit 0.002011 0.144953 0.014 0.989
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6465 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 4.183e-06, Adjusted R-squared: -0.02173
## F-statistic: 0.0001924 on 1 and 46 DF, p-value: 0.989lm.beta(model17)##
## Call:
## lm(formula = reason ~ legit, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) legit
## 0.00000000 0.00204533summary(model18)##
## Call:
## lm(formula = reason ~ prom, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4636 -0.3699 0.1355 0.4645 1.1819
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.08684 0.09741 62.49 <2e-16 ***
## prom 0.24554 0.10146 2.42 0.0197 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6566 on 44 degrees of freedom
## (8 observations deleted due to missingness)
## Multiple R-squared: 0.1175, Adjusted R-squared: 0.0974
## F-statistic: 5.856 on 1 and 44 DF, p-value: 0.01972lm.beta(model18)##
## Call:
## lm(formula = reason ~ prom, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) prom
## 0.000000 0.342726summary(model19)##
## Call:
## lm(formula = reason ~ neg, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7138 -0.3623 0.2642 0.4846 0.9019
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.14360 0.25094 24.483 <2e-16 ***
## neg 0.01567 0.10250 0.153 0.879
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.685 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.000508, Adjusted R-squared: -0.02122
## F-statistic: 0.02338 on 1 and 46 DF, p-value: 0.8791lm.beta(model19)##
## Call:
## lm(formula = reason ~ neg, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) neg
## 0.00000000 0.02253955summary(model20)##
## Call:
## lm(formula = reason ~ trad, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6140 -0.4356 0.2159 0.4167 0.9626
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.10975 0.27423 22.279 <2e-16 ***
## trad -0.02567 0.12871 -0.199 0.843
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6864 on 42 degrees of freedom
## (10 observations deleted due to missingness)
## Multiple R-squared: 0.0009465, Adjusted R-squared: -0.02284
## F-statistic: 0.03979 on 1 and 42 DF, p-value: 0.8429lm.beta(model20)##
## Call:
## lm(formula = reason ~ trad, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) trad
## 0.00000000 -0.03076516summary(model21)##
## Call:
## lm(formula = reason ~ inclus, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5913 -0.4445 0.1579 0.5049 1.1298
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.8702 0.1583 37.071 <2e-16 ***
## inclus 0.1903 0.1066 1.785 0.0812 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6687 on 44 degrees of freedom
## (8 observations deleted due to missingness)
## Multiple R-squared: 0.0675, Adjusted R-squared: 0.04631
## F-statistic: 3.185 on 1 and 44 DF, p-value: 0.08121lm.beta(model21)##
## Call:
## lm(formula = reason ~ inclus, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) inclus
## 0.0000000 0.2598118summary(model22)##
## Call:
## lm(formula = reason ~ elite, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6998 -0.3436 0.1931 0.4587 0.9197
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.3725 0.2285 27.889 <2e-16 ***
## elite 0.1266 0.1049 1.207 0.234
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6737 on 45 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.03138, Adjusted R-squared: 0.009852
## F-statistic: 1.458 on 1 and 45 DF, p-value: 0.2336lm.beta(model22)##
## Call:
## lm(formula = reason ~ elite, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) elite
## 0.0000000 0.1771362summary(model23)##
## Call:
## lm(formula = reason ~ rebel, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.5994 -0.3785 0.1868 0.4143 0.9043
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 6.25378 0.20758 30.127 <2e-16 ***
## rebel 0.08250 0.09396 0.878 0.385
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6791 on 45 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.01684, Adjusted R-squared: -0.005006
## F-statistic: 0.7709 on 1 and 45 DF, p-value: 0.3846lm.beta(model23)##
## Call:
## lm(formula = reason ~ rebel, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) rebel
## 0.0000000 0.1297758summary(model24)##
## Call:
## lm(formula = reason ~ bpaq, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.7368 -0.3310 0.1566 0.4559 0.9912
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.5627 0.4033 13.79 <2e-16 ***
## bpaq 0.1968 0.1458 1.35 0.184
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6595 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.03809, Adjusted R-squared: 0.01718
## F-statistic: 1.822 on 1 and 46 DF, p-value: 0.1837lm.beta(model24)##
## Call:
## lm(formula = reason ~ bpaq, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) bpaq
## 0.0000000 0.1951676summary(model25)##
## Call:
## lm(formula = reason ~ guardian, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.4702 -0.2702 0.1253 0.4191 1.1388
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.3535 1.6898 1.985 0.0537 .
## guardian 0.4180 0.2606 1.604 0.1162
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6585 on 42 degrees of freedom
## (10 observations deleted due to missingness)
## Multiple R-squared: 0.05772, Adjusted R-squared: 0.03528
## F-statistic: 2.573 on 1 and 42 DF, p-value: 0.1162lm.beta(model25)##
## Call:
## lm(formula = reason ~ guardian, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) guardian
## 0.0000000 0.2402472summary(model26)##
## Call:
## lm(formula = reason ~ warrior, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.6298 -0.3190 0.1485 0.4052 0.9052
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.72674 0.51846 11.046 2.11e-14 ***
## warrior 0.06494 0.08813 0.737 0.465
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.6612 on 45 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.01192, Adjusted R-squared: -0.01003
## F-statistic: 0.543 on 1 and 45 DF, p-value: 0.465lm.beta(model26)##
## Call:
## lm(formula = reason ~ warrior, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) warrior
## 0.0000000 0.10919454.2.3 Single IVs predicting procedural justice (higher scores = higher endorsement)
summary(model27)##
## Call:
## lm(formula = projust ~ sdo, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.66812 -0.21345 -0.01266 0.26333 0.55833
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.62431 0.15767 29.329 <2e-16 ***
## sdo -0.12737 0.05347 -2.382 0.0213 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3028 on 47 degrees of freedom
## (5 observations deleted due to missingness)
## Multiple R-squared: 0.1077, Adjusted R-squared: 0.08873
## F-statistic: 5.674 on 1 and 47 DF, p-value: 0.02132lm.beta(model27)##
## Call:
## lm(formula = projust ~ sdo, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) sdo
## 0.0000000 -0.3282011summary(model28)##
## Call:
## lm(formula = projust ~ rwa, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.72676 -0.24468 -0.09138 0.32460 0.63976
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.230887 0.271061 15.609 <2e-16 ***
## rwa 0.004755 0.066418 0.072 0.943
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3253 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.0001114, Adjusted R-squared: -0.02163
## F-statistic: 0.005125 on 1 and 46 DF, p-value: 0.9432lm.beta(model28)##
## Call:
## lm(formula = projust ~ rwa, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) rwa
## 0.00000000 0.01055516summary(model29)##
## Call:
## lm(formula = projust ~ legit, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.6796 -0.2444 -0.0943 0.2737 0.6067
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.55795 0.42721 8.328 9.75e-11 ***
## legit 0.11571 0.07078 1.635 0.109
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3209 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.0549, Adjusted R-squared: 0.03436
## F-statistic: 2.672 on 1 and 46 DF, p-value: 0.1089lm.beta(model29)##
## Call:
## lm(formula = projust ~ legit, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) legit
## 0.0000000 0.2343137summary(model30)##
## Call:
## lm(formula = projust ~ prom, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.70659 -0.21561 -0.07005 0.32138 0.60560
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.25275 0.04724 90.018 <2e-16 ***
## prom -0.03638 0.05030 -0.723 0.473
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3161 on 44 degrees of freedom
## (8 observations deleted due to missingness)
## Multiple R-squared: 0.01175, Adjusted R-squared: -0.01071
## F-statistic: 0.5232 on 1 and 44 DF, p-value: 0.4733lm.beta(model30)##
## Call:
## lm(formula = projust ~ prom, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) prom
## 0.0000000 -0.1084052summary(model31)##
## Call:
## lm(formula = projust ~ neg, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.72993 -0.21737 -0.06396 0.29688 0.67059
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.15536 0.11069 37.541 <2e-16 ***
## neg -0.04586 0.04619 -0.993 0.326
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.316 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.02098, Adjusted R-squared: -0.0003058
## F-statistic: 0.9856 on 1 and 46 DF, p-value: 0.326lm.beta(model31)##
## Call:
## lm(formula = projust ~ neg, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) neg
## 0.0000000 -0.1448354summary(model32)##
## Call:
## lm(formula = projust ~ trad, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.76120 -0.23181 -0.03492 0.26607 0.61279
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.13711 0.12206 33.893 <2e-16 ***
## trad 0.06128 0.05745 1.067 0.292
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3145 on 43 degrees of freedom
## (9 observations deleted due to missingness)
## Multiple R-squared: 0.02577, Adjusted R-squared: 0.003118
## F-statistic: 1.138 on 1 and 43 DF, p-value: 0.2921lm.beta(model32)##
## Call:
## lm(formula = projust ~ trad, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) trad
## 0.0000000 0.1605439summary(model33)##
## Call:
## lm(formula = projust ~ inclus, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.5680 -0.1691 -0.0376 0.2094 0.5416
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.04580 0.06450 62.725 < 2e-16 ***
## inclus 0.17793 0.04359 4.082 0.000181 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.275 on 45 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.2702, Adjusted R-squared: 0.254
## F-statistic: 16.66 on 1 and 45 DF, p-value: 0.0001806lm.beta(model33)##
## Call:
## lm(formula = projust ~ inclus, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) inclus
## 0.0000000 0.5198198summary(model34)##
## Call:
## lm(formula = projust ~ elite, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.74879 -0.23801 -0.03517 0.25391 0.57115
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.11349 0.10028 41.020 <2e-16 ***
## elite -0.07003 0.04677 -1.497 0.141
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3103 on 45 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.04745, Adjusted R-squared: 0.02629
## F-statistic: 2.242 on 1 and 45 DF, p-value: 0.1413lm.beta(model34)##
## Call:
## lm(formula = projust ~ elite, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) elite
## 0.0000000 -0.2178393summary(model35)##
## Call:
## lm(formula = projust ~ rebel, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.72303 -0.21380 -0.04223 0.24006 0.62079
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.11400 0.09131 45.057 <2e-16 ***
## rebel -0.07382 0.04237 -1.742 0.0883 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3116 on 45 degrees of freedom
## (7 observations deleted due to missingness)
## Multiple R-squared: 0.06319, Adjusted R-squared: 0.04237
## F-statistic: 3.035 on 1 and 45 DF, p-value: 0.08831lm.beta(model35)##
## Call:
## lm(formula = projust ~ rebel, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) rebel
## 0.000000 -0.251368summary(model36)##
## Call:
## lm(formula = projust ~ bpaq, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.62623 -0.24093 -0.07311 0.29741 0.56202
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 4.44314 0.19061 23.310 <2e-16 ***
## bpaq -0.06974 0.06755 -1.032 0.307
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3198 on 46 degrees of freedom
## (6 observations deleted due to missingness)
## Multiple R-squared: 0.02265, Adjusted R-squared: 0.001403
## F-statistic: 1.066 on 1 and 46 DF, p-value: 0.3072lm.beta(model36)##
## Call:
## lm(formula = projust ~ bpaq, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) bpaq
## 0.0000000 -0.1504974summary(model37)##
## Call:
## lm(formula = projust ~ guardian, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.57192 -0.22664 -0.08281 0.25612 0.60140
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 2.8423 0.7630 3.725 0.000589 ***
## guardian 0.2232 0.1177 1.896 0.065028 .
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.2966 on 41 degrees of freedom
## (11 observations deleted due to missingness)
## Multiple R-squared: 0.08061, Adjusted R-squared: 0.05818
## F-statistic: 3.595 on 1 and 41 DF, p-value: 0.06503lm.beta(model37)##
## Call:
## lm(formula = projust ~ guardian, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) guardian
## 0.0000000 0.2839147summary(model38)##
## Call:
## lm(formula = projust ~ warrior, data = pmdata1, na.action = na.omit)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.75787 -0.25319 -0.02557 0.28000 0.61055
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.98977 0.25901 15.404 <2e-16 ***
## warrior 0.04649 0.04402 1.056 0.297
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.3249 on 44 degrees of freedom
## (8 observations deleted due to missingness)
## Multiple R-squared: 0.02472, Adjusted R-squared: 0.002555
## F-statistic: 1.115 on 1 and 44 DF, p-value: 0.2967lm.beta(model38)##
## Call:
## lm(formula = projust ~ warrior, data = pmdata1, na.action = na.omit)
##
## Standardized Coefficients::
## (Intercept) warrior
## 0.0000000 0.15722815 Descriptive statistics
5.1 Police motivation means and standard deviations
stdysal = steady salary
benefits = good benefits
goodsal = good salary
jobsec = job security
retire = early retirement
jobstat = job status
jobfit = person-job fit
power = power/authority
faminlu = influence from family
excite = the excitement from job
service = service to others
dream = childhood dream
danger = dangerousness of job
library(psych)##
## Attaching package: 'psych'## The following object is masked from 'package:car':
##
## logitmotivedf <- with(pmdata1, data.frame(stdysal, benefits, goodsal, jobsec, retire, jobstat, jobfit, power, faminflu, excite, service, dream, danger))
describeBy(motivedf)## Warning in describeBy(motivedf): no grouping variable requested5.2 Demographics
po = political orientation
rankexp = years of experience in current rank
totalexp = total years of police-related experience
edu = education
marital = marital status
family = having family or relative as police officers nopoexp = non-police related experience
military = military experience
library(psych)
pmdata1$age[pmdata1$age == 0] <- NA
contdemodf <- with(pmdata1, data.frame(age, po, rankexp, totalexp))
describeBy(contdemodf)## Warning in describeBy(contdemodf): no grouping variable requestedlibrary(summarytools)
summarytools::freq(pmdata1$gender, order = "freq")## Frequencies
## pmdata1$gender
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ------------ ------ --------- -------------- --------- --------------
## male 46 85.19 85.19 85.19 85.19
## female 8 14.81 100.00 14.81 100.00
## <NA> 0 0.00 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$race, order = "freq")## Frequencies
## pmdata1$race
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## -------------- ------ --------- -------------- --------- --------------
## white 49 92.45 92.45 90.74 90.74
## hispanic 3 5.66 98.11 5.56 96.30
## black 1 1.89 100.00 1.85 98.15
## <NA> 1 1.85 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$edu, order = "freq")## Frequencies
## pmdata1$edu
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ------------------ ------ --------- -------------- --------- --------------
## bachelors 30 55.56 55.56 55.56 55.56
## masters 9 16.67 72.22 16.67 72.22
## high school 7 12.96 85.19 12.96 85.19
## associates 6 11.11 96.30 11.11 96.30
## trade school 2 3.70 100.00 3.70 100.00
## <NA> 0 0.00 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$marital, order = "freq")## Frequencies
## pmdata1$marital
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## --------------- ------ --------- -------------- --------- --------------
## married 41 77.36 77.36 75.93 75.93
## single 5 9.43 86.79 9.26 85.19
## partnered 3 5.66 92.45 5.56 90.74
## separated 3 5.66 98.11 5.56 96.30
## widowed 1 1.89 100.00 1.85 98.15
## <NA> 1 1.85 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$income, order = "freq")## Frequencies
## pmdata1$income
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## -------------------- ------ --------- -------------- --------- --------------
## 50k to 99.9k 27 50.00 50.00 50.00 50.00
## 100k to 199.9k 23 42.59 92.59 42.59 92.59
## 25k to 49.9k 4 7.41 100.00 7.41 100.00
## <NA> 0 0.00 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$religion, order = "freq")## Frequencies
## pmdata1$religion
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ------------------ ------ --------- -------------- --------- --------------
## christianity 39 72.22 72.22 72.22 72.22
## no affil 11 20.37 92.59 20.37 92.59
## other 3 5.56 98.15 5.56 98.15
## judaism 1 1.85 100.00 1.85 100.00
## <NA> 0 0.00 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$rank, order = "freq")## Frequencies
## pmdata1$rank
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## -------------------- ------ --------- -------------- --------- --------------
## sergeant 16 30.77 30.77 29.63 29.63
## police officer 15 28.85 59.62 27.78 57.41
## detective 8 15.38 75.00 14.81 72.22
## chief 4 7.69 82.69 7.41 79.63
## other rank 4 7.69 90.38 7.41 87.04
## captain 3 5.77 96.15 5.56 92.59
## deputy chief 1 1.92 98.08 1.85 94.44
## lieutent 1 1.92 100.00 1.85 96.30
## <NA> 2 3.70 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$family, order = "freq")## Frequencies
## pmdata1$family
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ----------- ------ --------- -------------- --------- --------------
## no 37 69.81 69.81 68.52 68.52
## yes 16 30.19 100.00 29.63 98.15
## <NA> 1 1.85 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$nopoexp, order = "freq")## Frequencies
## pmdata1$nopoexp
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ----------- ------ --------- -------------- --------- --------------
## yes 38 70.37 70.37 70.37 70.37
## no 16 29.63 100.00 29.63 100.00
## <NA> 0 0.00 100.00
## Total 54 100.00 100.00 100.00 100.00summarytools::freq(pmdata1$military, order = "freq")## Frequencies
## pmdata1$military
## Type: Factor
##
## Freq % Valid % Valid Cum. % Total % Total Cum.
## ----------- ------ --------- -------------- --------- --------------
## no 41 75.93 75.93 75.93 75.93
## yes 13 24.07 100.00 24.07 100.00
## <NA> 0 0.00 100.00
## Total 54 100.00 100.00 100.00 100.00