The MBA students surveyed likely were not the leaders of the teams that they were reflecting on. So, I will focus our analyses on two things:
Do descriptive perceptions of former team SEBs influence the MBA students as team members? For example, if they perceived their former team as high in SEBs, are they better future listeners (“List” items) and team mates (“Team” items) in their learning teams?
Do prescriptive perceptions of how status should have been distributed and attributed in their former teams influence MBA students as leaders? For example, if they believe that their team should have been higher in SEBs, are they better perspective takers (“PerTak” items) and leaders (“MotVis” items) in their learning teams?
I think it makes the most sense to split it up into descriptive and prescriptive for our analyses, given the items asked. But am open to feedback! I know the data is a little funky…
We also have coworker data, so in our meeting maybe we can talk about the best use of this data.
SEB Items:
Think about the team you recently worked with at your prior job. If you worked with multiple teams, focus on your primary or main team.
To what extent do you agree or disagree with each of the following statements about your team? Please read each statement carefully.
In my team,…
…A small number of members received the most respect and admiration. (Reverse-coded)
…Prestige and influence were concentrated in just a few members. (Reverse-coded)
…High status was concentrated around certain members and not distributed across all members. (Reverse-coded)
…Many members should have been able to gain respect and admiration.
…High status should not have been granted to just a few people.
…High status should have been shared among a wide range of members.
…Many different attributes and skills were seen as worthy of respect and admiration.
…People gained status for contributing in a wide variety of ways.
…People valued a broad range of strengths when offering respect.
…High status should have been based on a wide variety of attributes.
…Everyone should have had an opportunity to gain status for the unique skills they brought.
…People should have recognized a wide range of qualities when determining who deserved status.
Teams (If Relationship != Self):
How much is this characteristic of ${e://Field/SubjectFirstName}’s behavior?
When working in a team, ${e://Field/SubjectFirstName} makes sure everybody is kept informed and in the loop
${e://Field/SubjectFirstName} creates an atmosphere in which group members feel free to disagree with one another
${e://Field/SubjectFirstName} is unwilling to sacrifice his/her self interest for the good of the team
${e://Field/SubjectFirstName} takes initiative in contributing to the team’s efforts
When working on a group project, ${e://Field/SubjectFirstName} tends to want to do it all him/herself
PerTak (If Relationship != Self):
How much is this characteristic of ${e://Field/SubjectFirstName}’s behavior?
${e://Field/SubjectFirstName} misjudges people’s personality and character
${e://Field/SubjectFirstName} is good at sensing what other people are thinking and feeling
${e://Field/SubjectFirstName} fails to realize the impact of what s/he says and does on others
${e://Field/SubjectFirstName} is good at assessing other people’s strengths and weaknesses
${e://Field/SubjectFirstName} is able to understand someone else’s perspective
List (If Relationship != Self):
How much is this characteristic of ${e://Field/SubjectFirstName}’s behavior?
When someone else is speaking, ${e://Field/SubjectFirstName} interrupts and/or shows impatience
As a listener, ${e://Field/SubjectFirstName} gets others to open up, elaborate, and share information
${e://Field/SubjectFirstName} listens effectively to criticism and alternative points of view
When someone else is speaking, ${e://Field/SubjectFirstName} tends to drift off, appearing distracted or inattentive
${e://Field/SubjectFirstName} builds on what he/she has heard, incorporating it into the conversation
MotVis (If Relationship != Self):
How much is this characteristic of ${e://Field/SubjectFirstName}’s behavior?
${e://Field/SubjectFirstName} finds ways to recognize others for their contributions
${e://Field/SubjectFirstName} maintains focus on the goal at hand
${e://Field/SubjectFirstName} sets achievable, yet challenging goals for others and him/herself
${e://Field/SubjectFirstName} is not effective at giving helpful/constructive feedback to others
${e://Field/SubjectFirstName} inspires others to contribute
MotVis (Self):
How much is this characteristic of your behavior?
I find ways to recognize others for their contributions
I maintain focus on the goal at hand
I set achievable, yet challenging goals for others and myself
I am not effective at giving helpful/constructive feedback to others
I inspire others to contribute
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errorsSEB_data <- read.csv("~/Google drive/My Drive/YEAR 2/PROJECTS/DEREK/Status Distribution/Studies/LEAD/Grayson_Lead_2025_numeric.csv") %>%
slice(-1) %>%
rename(SubjectPID = uni) %>%
mutate(SubjectPID = as.numeric(SubjectPID))lead360_data <- read.csv("~/Google Drive/My Drive/YEAR 2/PROJECTS/DEREK/Status Distribution/Studies/LEAD/Grayson_360_Data_12.1.25.csv") %>%
slice(-c(1:2))# Identify all rating variables automatically
rating_vars <- grep("^(Self_MotVis_|PerTak_|MotVis_|Teams_|List_)",
names(lead360_data),
value = TRUE)
rating_vars## [1] "Self_MotVis_1" "Self_MotVis_2" "Self_MotVis_3" "Self_MotVis_4"
## [5] "Self_MotVis_5" "PerTak_1" "PerTak_2" "PerTak_3"
## [9] "PerTak_4" "PerTak_5" "MotVis_1" "MotVis_2"
## [13] "MotVis_3" "MotVis_4" "MotVis_5" "Teams_1"
## [17] "Teams_2" "Teams_3" "Teams_4" "Teams_5"
## [21] "List_1" "List_2" "List_3" "List_4"
## [25] "List_5"lead360_data_clean <- lead360_data %>%
mutate(across(
c(starts_with("Self_MotVis_"),
starts_with("PerTak_"),
starts_with("MotVis_"),
starts_with("Teams_"),
starts_with("List_")),
~ as.numeric(as.character(.x)) # handles factors, characters, etc.
))aggregated_df <- lead360_data_clean %>%
group_by(SubjectPID, Q_RelationshipName) %>%
summarise(
across(c(starts_with("Self_MotVis_"),
starts_with("PerTak_"),
starts_with("MotVis_"),
starts_with("Teams_"),
starts_with("List_")),
mean, na.rm = TRUE),
.groups = "drop"
)## Warning: There was 1 warning in `summarise()`.
## ℹ In argument: `across(...)`.
## ℹ In group 1: `SubjectPID = 1020009` `Q_RelationshipName = "CBS Classmate"`.
## Caused by warning:
## ! The `...` argument of `across()` is deprecated as of dplyr 1.1.0.
## Supply arguments directly to `.fns` through an anonymous function instead.
##
## # Previously
## across(a:b, mean, na.rm = TRUE)
##
## # Now
## across(a:b, \(x) mean(x, na.rm = TRUE))aggregated_df <- aggregated_df %>%
rowwise() %>%
mutate(Self_MotVis_4_R = 8-Self_MotVis_4) %>%
mutate(MotVis_4_R = 8-MotVis_4) %>%
mutate(Teams_3_R = 8-Teams_3) %>%
mutate(Teams_5_R = 8-Teams_5) %>%
mutate(PerTak_1_R = 8-PerTak_1) %>%
mutate(PerTak_3_R = 8-PerTak_3) %>%
mutate(List_1_R = 8-List_1) %>%
mutate(List_4_R = 8-List_4) %>%
ungroup()items <- aggregated_df %>%
select(Self_MotVis_1,
Self_MotVis_2,
Self_MotVis_3,
Self_MotVis_4_R,
Self_MotVis_5) %>%
na.omit()
psych::alpha(items)##
## Reliability analysis
## Call: psych::alpha(x = items)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.56 0.57 0.55 0.21 1.3 0.025 5.3 0.65 0.19
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.51 0.56 0.61
## Duhachek 0.51 0.56 0.61
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r
## Self_MotVis_1 0.49 0.50 0.46 0.20 1.00 0.030 0.0152
## Self_MotVis_2 0.52 0.53 0.48 0.22 1.15 0.028 0.0065
## Self_MotVis_3 0.46 0.48 0.43 0.18 0.91 0.032 0.0121
## Self_MotVis_4_R 0.56 0.57 0.53 0.25 1.31 0.026 0.0170
## Self_MotVis_5 0.49 0.51 0.46 0.21 1.05 0.030 0.0125
## med.r
## Self_MotVis_1 0.20
## Self_MotVis_2 0.20
## Self_MotVis_3 0.17
## Self_MotVis_4_R 0.20
## Self_MotVis_5 0.19
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## Self_MotVis_1 758 0.60 0.63 0.49 0.36 5.7 0.95
## Self_MotVis_2 758 0.55 0.59 0.43 0.29 5.7 0.97
## Self_MotVis_3 758 0.65 0.66 0.55 0.40 5.5 1.03
## Self_MotVis_4_R 758 0.61 0.54 0.32 0.25 4.8 1.31
## Self_MotVis_5 758 0.63 0.62 0.47 0.34 5.0 1.12
##
## Non missing response frequency for each item
## 1 2 3 4 5 6 7 miss
## Self_MotVis_1 0.00 0.00 0.02 0.07 0.27 0.44 0.20 0
## Self_MotVis_2 0.00 0.01 0.02 0.08 0.26 0.45 0.18 0
## Self_MotVis_3 0.00 0.01 0.03 0.12 0.26 0.44 0.14 0
## Self_MotVis_4_R 0.01 0.06 0.11 0.21 0.26 0.30 0.05 0
## Self_MotVis_5 0.00 0.02 0.07 0.23 0.34 0.27 0.07 0items <- aggregated_df %>%
select(MotVis_1,
MotVis_2,
MotVis_3,
MotVis_4_R,
MotVis_5) %>%
na.omit()
psych::alpha(items)## Number of categories should be increased in order to count frequencies.##
## Reliability analysis
## Call: psych::alpha(x = items)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.86 0.86 0.85 0.55 6.1 0.0057 6 0.48 0.53
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.84 0.86 0.87
## Duhachek 0.84 0.86 0.87
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## MotVis_1 0.82 0.83 0.80 0.55 4.9 0.0074 0.0091 0.54
## MotVis_2 0.84 0.84 0.81 0.57 5.2 0.0066 0.0065 0.55
## MotVis_3 0.82 0.82 0.79 0.53 4.5 0.0073 0.0097 0.52
## MotVis_4_R 0.85 0.85 0.83 0.59 5.8 0.0063 0.0091 0.57
## MotVis_5 0.80 0.81 0.78 0.52 4.3 0.0083 0.0088 0.50
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## MotVis_1 1515 0.81 0.80 0.75 0.69 6.1 0.60
## MotVis_2 1515 0.75 0.78 0.71 0.63 6.3 0.52
## MotVis_3 1515 0.81 0.83 0.79 0.71 6.1 0.52
## MotVis_4_R 1515 0.76 0.74 0.63 0.60 5.9 0.64
## MotVis_5 1515 0.87 0.85 0.82 0.75 5.8 0.70items <- aggregated_df %>%
select(Teams_1,
Teams_2,
Teams_3_R,
Teams_4,
Teams_5_R) %>%
na.omit()
psych::alpha(items)## Number of categories should be increased in order to count frequencies.##
## Reliability analysis
## Call: psych::alpha(x = items)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.72 0.74 0.76 0.36 2.8 0.012 6 0.46 0.37
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.69 0.72 0.74
## Duhachek 0.69 0.72 0.74
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## Teams_1 0.60 0.62 0.61 0.29 1.6 0.0171 0.031 0.34
## Teams_2 0.62 0.64 0.67 0.31 1.8 0.0164 0.059 0.32
## Teams_3_R 0.67 0.70 0.73 0.37 2.3 0.0149 0.075 0.39
## Teams_4 0.67 0.69 0.66 0.36 2.2 0.0140 0.019 0.35
## Teams_5_R 0.78 0.79 0.76 0.48 3.7 0.0096 0.019 0.42
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## Teams_1 1515 0.80 0.82 0.81 0.66 6.1 0.62
## Teams_2 1515 0.76 0.79 0.72 0.63 6.1 0.55
## Teams_3_R 1515 0.71 0.69 0.54 0.48 5.9 0.73
## Teams_4 1515 0.68 0.70 0.65 0.47 6.2 0.65
## Teams_5_R 1515 0.54 0.50 0.32 0.24 5.6 0.76items <- aggregated_df %>%
select(PerTak_1_R,
PerTak_2,
PerTak_3_R,
PerTak_4,
PerTak_5) %>%
na.omit()
psych::alpha(items)## Number of categories should be increased in order to count frequencies.##
## Reliability analysis
## Call: psych::alpha(x = items)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.85 0.86 0.84 0.54 6 0.0059 5.9 0.48 0.55
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.84 0.85 0.86
## Duhachek 0.84 0.85 0.86
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## PerTak_1_R 0.83 0.84 0.81 0.56 5.1 0.0072 0.0092 0.58
## PerTak_2 0.81 0.81 0.78 0.52 4.3 0.0081 0.0098 0.54
## PerTak_3_R 0.83 0.83 0.80 0.56 5.0 0.0067 0.0083 0.56
## PerTak_4 0.83 0.84 0.80 0.57 5.2 0.0069 0.0029 0.55
## PerTak_5 0.81 0.81 0.79 0.52 4.4 0.0079 0.0122 0.52
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## PerTak_1_R 1515 0.76 0.77 0.69 0.64 6.2 0.50
## PerTak_2 1515 0.84 0.84 0.79 0.73 5.7 0.65
## PerTak_3_R 1515 0.80 0.78 0.71 0.64 6.0 0.71
## PerTak_4 1515 0.76 0.77 0.69 0.63 5.8 0.57
## PerTak_5 1515 0.83 0.83 0.78 0.72 6.0 0.58items <- aggregated_df %>%
select(List_1_R,
List_2,
List_3,
List_4_R,
List_5) %>%
na.omit()
psych::alpha(items)## Number of categories should be increased in order to count frequencies.##
## Reliability analysis
## Call: psych::alpha(x = items)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.86 0.86 0.84 0.55 6.1 0.0059 6.1 0.47 0.54
##
## 95% confidence boundaries
## lower alpha upper
## Feldt 0.84 0.86 0.87
## Duhachek 0.84 0.86 0.87
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r med.r
## List_1_R 0.86 0.86 0.83 0.60 6.1 0.0061 0.0053 0.60
## List_2 0.81 0.81 0.79 0.52 4.4 0.0079 0.0099 0.54
## List_3 0.80 0.80 0.77 0.51 4.1 0.0083 0.0094 0.52
## List_4_R 0.83 0.83 0.81 0.56 5.1 0.0071 0.0180 0.59
## List_5 0.83 0.83 0.80 0.55 4.9 0.0072 0.0064 0.53
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## List_1_R 1515 0.73 0.72 0.61 0.56 6.3 0.61
## List_2 1515 0.84 0.84 0.79 0.73 5.9 0.60
## List_3 1515 0.86 0.86 0.83 0.77 6.1 0.57
## List_4_R 1515 0.79 0.78 0.70 0.65 6.2 0.62
## List_5 1515 0.78 0.80 0.74 0.67 6.1 0.52Ok, for now I think it is ok to make averages for the other-rated items
aggregated_df <- aggregated_df %>%
mutate(
PerTak_avg = rowMeans(select(.,
PerTak_1_R,
PerTak_2,
PerTak_3_R,
PerTak_4,
PerTak_5),
na.rm = TRUE)
)
aggregated_df <- aggregated_df %>%
mutate(
MotVis_avg = rowMeans(select(.,
MotVis_1,
MotVis_2,
MotVis_3,
MotVis_4_R,
MotVis_5),
na.rm = TRUE)
)
aggregated_df <- aggregated_df %>%
mutate(
Teams_avg = rowMeans(select(.,
Teams_1,
Teams_2,
Teams_3_R,
Teams_4,
Teams_5_R),
na.rm = TRUE)
)
aggregated_df <- aggregated_df %>%
mutate(
List_avg = rowMeans(select(.,
List_1_R,
List_2,
List_3,
List_4_R,
List_5),
na.rm = TRUE)
)SEB_numeric <- SEB_data %>%
mutate(across(
c(starts_with("dist_"),
starts_with("attr_")),
~ as.numeric(as.character(.x)) # handles factors, characters, etc.
)) %>%
rowwise() %>%
mutate(dist_status_1_R = 8-dist_status_1) %>%
mutate(dist_status_2_R = 8-dist_status_2) %>%
mutate(dist_status_3_R = 8-dist_status_3) %>%
ungroup()
SEB_numeric <- SEB_numeric %>%
mutate(
status_expansion_belief = rowMeans(select(.,
dist_status_1_R,
dist_status_2_R,
dist_status_3_R,
dist_status_4,
dist_status_5,
dist_status_6,
attr_status_1,
attr_status_2,
attr_status_3,
attr_status_4,
attr_status_5,
attr_status_6),
na.rm = TRUE)
)
SEB_numeric <- SEB_numeric %>%
mutate(
dist_avg = rowMeans(select(.,
dist_status_1_R,
dist_status_2_R,
dist_status_3_R,
dist_status_4,
dist_status_5,
dist_status_6),
na.rm = TRUE)
)
SEB_numeric <- SEB_numeric %>%
mutate(
attr_avg = rowMeans(select(.,
attr_status_1,
attr_status_2,
attr_status_3,
attr_status_4,
attr_status_5,
attr_status_6),
na.rm = TRUE)
)
SEB_numeric <- SEB_numeric %>%
mutate(
desc_avg = rowMeans(select(.,
dist_status_1_R,
dist_status_2_R,
dist_status_3_R,
attr_status_1,
attr_status_2,
attr_status_3),
na.rm = TRUE)
)
SEB_numeric <- SEB_numeric %>%
mutate(
presc_avg = rowMeans(select(.,
dist_status_4,
dist_status_5,
dist_status_6,
attr_status_4,
attr_status_5,
attr_status_6),
na.rm = TRUE)
)
SEB_merge <- SEB_numeric %>%
select(SubjectPID, status_expansion_belief, dist_avg, attr_avg, desc_avg, presc_avg)lead_data <- SEB_merge %>%
left_join(aggregated_df, by = "SubjectPID")## Warning in left_join(., aggregated_df, by = "SubjectPID"): Detected an unexpected many-to-many relationship between `x` and `y`.
## ℹ Row 1 of `x` matches multiple rows in `y`.
## ℹ Row 881 of `y` matches multiple rows in `x`.
## ℹ If a many-to-many relationship is expected, set `relationship =
## "many-to-many"` to silence this warning.class <- lead_data %>%
filter(Q_RelationshipName == "CBS Classmate") %>%
select(-c(Self_MotVis_1:Self_MotVis_5))self <- lead_data %>%
filter(Q_RelationshipName == "Self")%>%
select(-c(PerTak_1:List_5))coworker <- lead_data %>%
filter(Q_RelationshipName == "Coworker")%>%
select(-c(Self_MotVis_1:Self_MotVis_5))model_teams <- lm(Teams_avg ~ desc_avg, data = class)
summary(model_teams)##
## Call:
## lm(formula = Teams_avg ~ desc_avg, data = class)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.14602 -0.26794 0.05139 0.34115 1.07641
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.86584 0.06202 94.576 <2e-16 ***
## desc_avg 0.01507 0.01437 1.049 0.295
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.49 on 756 degrees of freedom
## Multiple R-squared: 0.001452, Adjusted R-squared: 0.0001314
## F-statistic: 1.1 on 1 and 756 DF, p-value: 0.2947Students who were formerly on teams that were higher in SEBs are not more cooperative team members on their learning teams.
model_list <- lm(List_avg ~ desc_avg, data = class)
summary(model_list)##
## Call:
## lm(formula = List_avg ~ desc_avg, data = class)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.68034 -0.28314 0.06402 0.33602 1.06943
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.90194 0.06000 98.37 <2e-16 ***
## desc_avg 0.02863 0.01390 2.06 0.0397 *
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4741 on 756 degrees of freedom
## Multiple R-squared: 0.005582, Adjusted R-squared: 0.004267
## F-statistic: 4.244 on 1 and 756 DF, p-value: 0.03973Students who were formerly on teams that were higher in SEBs are better listeners on their learning teams.
model_pertak <- lm(PerTak_avg ~ presc_avg, data = class)
summary(model_pertak)##
## Call:
## lm(formula = PerTak_avg ~ presc_avg, data = class)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.14133 -0.27839 0.05236 0.38587 1.13867
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.80376 0.10385 55.887 <2e-16 ***
## presc_avg 0.01279 0.01931 0.663 0.508
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.5071 on 756 degrees of freedom
## Multiple R-squared: 0.0005803, Adjusted R-squared: -0.0007417
## F-statistic: 0.439 on 1 and 756 DF, p-value: 0.5078Students who believe their former team could distribute / attribute status more widely are not perceived as better perspective takers.
model_motvis <- lm(MotVis_avg ~ presc_avg, data = class)
summary(model_motvis)##
## Call:
## lm(formula = MotVis_avg ~ presc_avg, data = class)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.39459 -0.28352 0.07901 0.36204 1.07799
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.940200 0.100691 58.994 <2e-16 ***
## presc_avg -0.004043 0.018723 -0.216 0.829
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.4916 on 756 degrees of freedom
## Multiple R-squared: 6.168e-05, Adjusted R-squared: -0.001261
## F-statistic: 0.04663 on 1 and 756 DF, p-value: 0.8291Students who believe their former team could distribute / attribute status more widely are not perceived as more effective leaders.