library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.6
## ✔ forcats   1.0.1     ✔ stringr   1.6.0
## ✔ ggplot2   4.0.1     ✔ tibble    3.3.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.2
## ✔ purrr     1.2.1     
## ── 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 errors
library(readxl)
library(stargazer)
## 
## Please cite as: 
## 
##  Hlavac, Marek (2022). stargazer: Well-Formatted Regression and Summary Statistics Tables.
##  R package version 5.2.3. https://CRAN.R-project.org/package=stargazer
library(dplyr)
library(stringr)
library(janitor)
## 
## Attaching package: 'janitor'
## 
## The following objects are masked from 'package:stats':
## 
##     chisq.test, fisher.test
library(psych)
## 
## Attaching package: 'psych'
## 
## The following objects are masked from 'package:ggplot2':
## 
##     %+%, alpha
library(lm.beta)
library(car)
## Loading required package: carData
## 
## Attaching package: 'car'
## 
## The following object is masked from 'package:psych':
## 
##     logit
## 
## The following object is masked from 'package:dplyr':
## 
##     recode
## 
## The following object is masked from 'package:purrr':
## 
##     some
raw_data <- read_excel("Copy 11.4 Ready Data - PGF Alumni Survey 1-33.xlsx")

complete_data <- raw_data[, c(1,13,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,47,48,49,50,51)]
#ID: 1
#Year: 13
#OCS: 15-20
#SCS: 21-38
#Demographic: 47-51

#Convert OCS char to numeric

# Yes == 1
# No == 0
# Decreased == -1
# No change == 0
# Increased == 1

OCS_data <- raw_data %>%
mutate(
`Salary Increase` = ifelse(`Salary Increase` == "Yes", 1, 0),
`Promotion` = ifelse(Promotion == "Yes", 1, 0),
`Multiple Promotions` = ifelse(`Multiple Promotions` == "Yes", 1, 0),

`Direct Reports` = case_when(
`Direct Reports` == "Decreased" ~ -1,
`Direct Reports` == "No change" ~ 0,
`Direct Reports` == "Increased" ~ 1
),

`Fiscal Responsibilities` = case_when(
`Fiscal Responsibilities` == "Decreased" ~ -1,
`Fiscal Responsibilities` == "No change" ~ 0,
`Fiscal Responsibilities` == "Increased" ~ 1
)
)

OCS_data <- OCS_data %>%
  mutate(
    `Multiple Promotions` = ifelse(
      is.na(`Multiple Promotions`),
      0,
      `Multiple Promotions`
    )
  )

OCS_data <- OCS_data %>%
  mutate(
    `Number of Promotions` = ifelse(
      is.na(`Number of Promotions`),
      0,
      `Number of Promotions`
    )
  )

OCS_data$`Number of Promotions` <-
  as.numeric(OCS_data$`Number of Promotions`)

#OCS_data <- OCS_data |> drop_na()

OCS_data <- OCS_data[, c(15,16,17,18,19,20)]

summary(OCS_data)
##  Salary Increase    Promotion      Multiple Promotions Number of Promotions
##  Min.   :0.0000   Min.   :0.0000   Min.   :0.000       Min.   :0.000       
##  1st Qu.:1.0000   1st Qu.:1.0000   1st Qu.:0.000       1st Qu.:0.000       
##  Median :1.0000   Median :1.0000   Median :0.000       Median :0.000       
##  Mean   :0.8788   Mean   :0.7879   Mean   :0.303       Mean   :0.697       
##  3rd Qu.:1.0000   3rd Qu.:1.0000   3rd Qu.:1.000       3rd Qu.:2.000       
##  Max.   :1.0000   Max.   :1.0000   Max.   :1.000       Max.   :3.000       
##  Direct Reports    Fiscal Responsibilities
##  Min.   :-1.0000   Min.   :-1.0000        
##  1st Qu.: 0.0000   1st Qu.: 1.0000        
##  Median : 1.0000   Median : 1.0000        
##  Mean   : 0.5152   Mean   : 0.7576        
##  3rd Qu.: 1.0000   3rd Qu.: 1.0000        
##  Max.   : 1.0000   Max.   : 1.0000

#Convert SCS char to numeric

likert_cols <- c(21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38)

SCS_data <- raw_data %>%
  mutate(across(
    all_of(likert_cols),
    ~ as.numeric(str_extract(., "^[1-5]"))
  ))

SCS_data <- SCS_data[, c(21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38)]

summary(SCS_data)
##  Do What I Like - Before Do What I Like - Now Dedicated to Work - Before
##  Min.   :1.000           Min.   :3.000        Min.   :3.000             
##  1st Qu.:3.000           1st Qu.:4.000        1st Qu.:4.000             
##  Median :4.000           Median :5.000        Median :4.000             
##  Mean   :3.758           Mean   :4.545        Mean   :4.242             
##  3rd Qu.:4.000           3rd Qu.:5.000        3rd Qu.:5.000             
##  Max.   :5.000           Max.   :5.000        Max.   :5.000             
##  Dedicated to Work - Now Successful - Before Successful - Now
##  Min.   :4.000           Min.   :3.000       Min.   :4.000   
##  1st Qu.:5.000           1st Qu.:4.000       1st Qu.:5.000   
##  Median :5.000           Median :4.000       Median :5.000   
##  Mean   :4.788           Mean   :4.394       Mean   :4.758   
##  3rd Qu.:5.000           3rd Qu.:5.000       3rd Qu.:5.000   
##  Max.   :5.000           Max.   :5.000       Max.   :5.000   
##  Peer Respect - Before Peer Respect - Now Network - Before Network - Now  
##  Min.   :1             Min.   :3.000      Min.   :2.000    Min.   :3.000  
##  1st Qu.:4             1st Qu.:4.000      1st Qu.:3.000    1st Qu.:4.000  
##  Median :4             Median :5.000      Median :4.000    Median :5.000  
##  Mean   :4             Mean   :4.697      Mean   :3.758    Mean   :4.636  
##  3rd Qu.:5             3rd Qu.:5.000      3rd Qu.:4.000    3rd Qu.:5.000  
##  Max.   :5             Max.   :5.000      Max.   :5.000    Max.   :5.000  
##  Recognized - Before Recognized - Now Give Support - Before Give Support - Now
##  Min.   :1.000       Min.   :2.000    Min.   :2.000         Min.   :4.000     
##  1st Qu.:3.000       1st Qu.:4.000    1st Qu.:4.000         1st Qu.:4.000     
##  Median :4.000       Median :5.000    Median :4.000         Median :5.000     
##  Mean   :3.545       Mean   :4.273    Mean   :3.788         Mean   :4.697     
##  3rd Qu.:4.000       3rd Qu.:5.000    3rd Qu.:4.000         3rd Qu.:5.000     
##  Max.   :5.000       Max.   :5.000    Max.   :5.000         Max.   :5.000     
##  Positive Impact - Before Positive Impact - Now Address Challenges - Before
##  Min.   :2.000            Min.   :4.000         Min.   :2.000              
##  1st Qu.:4.000            1st Qu.:5.000         1st Qu.:4.000              
##  Median :4.000            Median :5.000         Median :4.000              
##  Mean   :4.121            Mean   :4.788         Mean   :3.818              
##  3rd Qu.:5.000            3rd Qu.:5.000         3rd Qu.:4.000              
##  Max.   :5.000            Max.   :5.000         Max.   :5.000              
##  Address Challenges - Now
##  Min.   :3.000           
##  1st Qu.:4.000           
##  Median :5.000           
##  Mean   :4.576           
##  3rd Qu.:5.000           
##  Max.   :5.000

#Demographic Information Counts

#table(complete_data$Gender)
#summary(as.factor(complete_data$Gender))

tabyl(complete_data, Gender)
##  Gender  n   percent
##  Female 23 0.6969697
##    Male 10 0.3030303
tabyl(complete_data, Age)
##    Age  n    percent
##  25-34  7 0.21212121
##  35-44 15 0.45454545
##  45-54 10 0.30303030
##  55-64  1 0.03030303
tabyl(complete_data, `Race-Ethnicity`)
##                      Race-Ethnicity  n    percent
##        Alaska Native or Indigenous;  2 0.06060606
##                    American Indian;  2 0.06060606
##              American Indian;White;  1 0.03030303
##                        Asian;White;  1 0.03030303
##             Black/African American;  1 0.03030303
##       Black/African American;White;  1 0.03030303
##                              White; 24 0.72727273
##  White;Alaska Native or Indigenous;  1 0.03030303
tabyl(complete_data, Disability)
##  Disability  n    percent
##          No 32 0.96969697
##         Yes  1 0.03030303
#gendercount <- complete_data %>%
#  count(Gender) %>%
#  mutate(percentage = (n / sum(n)) * 100)

#Convert Year to num value

complete_data$`Year` <-
  as.numeric(complete_data$`Year`)

summary(complete_data$Year)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    2010    2021    2024    2022    2025    2025
describe(complete_data$Year)
##    vars  n    mean   sd median trimmed  mad  min  max range  skew kurtosis   se
## X1    1 33 2022.39 3.58   2024 2022.96 1.48 2010 2025    15 -1.59     2.15 0.62

#OCS Descriptive Statistics

tabyl(complete_data, `Salary Increase`)
##  Salary Increase  n   percent
##               No  4 0.1212121
##              Yes 29 0.8787879
tabyl(complete_data, `Promotion`)
##  Promotion  n   percent
##         No  7 0.2121212
##        Yes 26 0.7878788
tabyl(complete_data, `Multiple Promotions`)
##  Multiple Promotions  n   percent valid_percent
##                   No 16 0.4848485     0.6153846
##                  Yes 10 0.3030303     0.3846154
##                 <NA>  7 0.2121212            NA
tabyl(complete_data, `Number of Promotions`)
##  Number of Promotions  n    percent valid_percent
##                     2  7 0.21212121           0.7
##                     3  3 0.09090909           0.3
##                  <NA> 23 0.69696970            NA
tabyl(complete_data, `Direct Reports`)
##  Direct Reports  n    percent
##       Decreased  3 0.09090909
##       Increased 20 0.60606061
##       No change 10 0.30303030
tabyl(complete_data, `Fiscal Responsibilities`)
##  Fiscal Responsibilities  n    percent
##                Decreased  1 0.03030303
##                Increased 26 0.78787879
##                No change  6 0.18181818
tabyl(complete_data, `Year`)
##  Year  n    percent
##  2010  1 0.03030303
##  2017  3 0.09090909
##  2018  3 0.09090909
##  2020  1 0.03030303
##  2021  1 0.03030303
##  2022  1 0.03030303
##  2023  3 0.09090909
##  2024  8 0.24242424
##  2025 12 0.36363636

#SCS Descriptive Statistics

describe(SCS_data$`Do What I Like - Before`)
##    vars  n mean sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 33 3.76  1      4    3.85 1.48   1   5     4 -0.61    -0.01 0.17
describe(SCS_data$`Do What I Like - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 4.55 0.62      5    4.63   0   3   5     2 -0.94    -0.23 0.11
describe(SCS_data$`Dedicated to Work - Before`)
##    vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 33 4.24 0.71      4     4.3 1.48   3   5     2 -0.35    -1.05 0.12
describe(SCS_data$`Dedicated to Work - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 4.79 0.42      5    4.85   0   4   5     1 -1.34    -0.19 0.07
describe(SCS_data$`Successful - Before`)
##    vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 33 4.39 0.61      4    4.44 1.48   3   5     2 -0.41    -0.81 0.11
describe(SCS_data$`Successful - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 4.76 0.44      5    4.81   0   4   5     1 -1.15     -0.7 0.08
describe(SCS_data$`Peer Respect - Before`)
##    vars  n mean   sd median trimmed mad min max range skew kurtosis   se
## X1    1 33    4 0.97      4    4.15   0   1   5     4 -1.2     1.34 0.17
describe(SCS_data$`Peer Respect - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33  4.7 0.53      5    4.78   0   3   5     2 -1.41        1 0.09
describe(SCS_data$`Network - Before`)
##    vars  n mean   sd median trimmed mad min max range skew kurtosis   se
## X1    1 33 3.76 0.83      4    3.81   0   2   5     3 -0.5    -0.26 0.14
describe(SCS_data$`Network - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis  se
## X1    1 33 4.64 0.55      5     4.7   0   3   5     2 -1.08     0.07 0.1
describe(SCS_data$`Recognized - Before`)
##    vars  n mean sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 3.55  1      4    3.59   0   1   5     4 -0.66    -0.31 0.17
describe(SCS_data$`Recognized - Now`)
##    vars  n mean   sd median trimmed mad min max range skew kurtosis   se
## X1    1 33 4.27 0.88      5    4.37   0   2   5     3 -0.8    -0.57 0.15
describe(SCS_data$`Give Support - Before`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 3.79 0.93      4    3.85   0   2   5     3 -0.73    -0.33 0.16
describe(SCS_data$`Give Support - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33  4.7 0.47      5    4.74   0   4   5     1 -0.82    -1.37 0.08
describe(SCS_data$`Positive Impact - Before`)
##    vars  n mean  sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 4.12 0.7      4    4.19   0   2   5     3 -0.69     0.91 0.12
describe(SCS_data$`Positive Impact - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 4.79 0.42      5    4.85   0   4   5     1 -1.34    -0.19 0.07
describe(SCS_data$`Address Challenges - Before`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 3.82 0.88      4    3.89   0   2   5     3 -0.72    -0.14 0.15
describe(SCS_data$`Address Challenges - Now`)
##    vars  n mean   sd median trimmed mad min max range  skew kurtosis   se
## X1    1 33 4.58 0.61      5    4.67   0   3   5     2 -1.06     0.01 0.11

#SCS Cronbach alpha tests

SCS_Before <- SCS_data %>%
  select(
    `Do What I Like - Before`,
    `Dedicated to Work - Before`,
    `Successful - Before`,
    `Peer Respect - Before`,
    `Network - Before`,
    `Recognized - Before`,
    `Give Support - Before`,
    `Positive Impact - Before`,
    `Address Challenges - Before`
  )

alpha(SCS_Before) #Before a = 0.88
## 
## Reliability analysis   
## Call: alpha(x = SCS_Before)
## 
##   raw_alpha std.alpha G6(smc) average_r S/N   ase mean   sd median_r
##       0.88      0.88    0.92      0.46 7.6 0.032  3.9 0.61     0.44
## 
##     95% confidence boundaries 
##          lower alpha upper
## Feldt     0.80  0.88  0.93
## Duhachek  0.81  0.88  0.94
## 
##  Reliability if an item is dropped:
##                             raw_alpha std.alpha G6(smc) average_r S/N alpha se
## Do What I Like - Before          0.86      0.87    0.90      0.45 6.6    0.035
## Dedicated to Work - Before       0.86      0.86    0.89      0.44 6.2    0.037
## Successful - Before              0.87      0.88    0.91      0.47 7.2    0.034
## Peer Respect - Before            0.86      0.86    0.90      0.44 6.3    0.038
## Network - Before                 0.86      0.87    0.91      0.46 6.8    0.036
## Recognized - Before              0.87      0.87    0.91      0.46 6.9    0.035
## Give Support - Before            0.87      0.87    0.91      0.46 6.9    0.036
## Positive Impact - Before         0.86      0.87    0.90      0.45 6.4    0.037
## Address Challenges - Before      0.87      0.88    0.91      0.47 7.1    0.034
##                             var.r med.r
## Do What I Like - Before     0.020  0.42
## Dedicated to Work - Before  0.020  0.42
## Successful - Before         0.021  0.45
## Peer Respect - Before       0.023  0.42
## Network - Before            0.025  0.45
## Recognized - Before         0.023  0.45
## Give Support - Before       0.024  0.44
## Positive Impact - Before    0.026  0.42
## Address Challenges - Before 0.022  0.45
## 
##  Item statistics 
##                              n raw.r std.r r.cor r.drop mean   sd
## Do What I Like - Before     33  0.73  0.73  0.72   0.63  3.8 1.00
## Dedicated to Work - Before  33  0.78  0.80  0.80   0.73  4.2 0.71
## Successful - Before         33  0.61  0.64  0.59   0.54  4.4 0.61
## Peer Respect - Before       33  0.78  0.78  0.76   0.70  4.0 0.97
## Network - Before            33  0.72  0.71  0.67   0.63  3.8 0.83
## Recognized - Before         33  0.71  0.69  0.65   0.59  3.5 1.00
## Give Support - Before       33  0.71  0.69  0.65   0.61  3.8 0.93
## Positive Impact - Before    33  0.76  0.77  0.75   0.70  4.1 0.70
## Address Challenges - Before 33  0.66  0.65  0.62   0.55  3.8 0.88
## 
## Non missing response frequency for each item
##                                1    2    3    4    5 miss
## Do What I Like - Before     0.03 0.06 0.27 0.39 0.24    0
## Dedicated to Work - Before  0.00 0.00 0.15 0.45 0.39    0
## Successful - Before         0.00 0.00 0.06 0.48 0.45    0
## Peer Respect - Before       0.03 0.06 0.09 0.52 0.30    0
## Network - Before            0.00 0.09 0.21 0.55 0.15    0
## Recognized - Before         0.03 0.15 0.18 0.52 0.12    0
## Give Support - Before       0.00 0.15 0.09 0.58 0.18    0
## Positive Impact - Before    0.00 0.03 0.09 0.61 0.27    0
## Address Challenges - Before 0.00 0.12 0.12 0.58 0.18    0
SCS_Now <- SCS_data %>%
  select(
    `Do What I Like - Now`,
    `Dedicated to Work - Now`,
    `Successful - Now`,
    `Peer Respect - Now`,
    `Network - Now`,
    `Recognized - Now`,
    `Give Support - Now`,
    `Positive Impact - Now`,
    `Address Challenges - Now`
  )

alpha(SCS_Now) #After a = 0.86
## 
## Reliability analysis   
## Call: alpha(x = SCS_Now)
## 
##   raw_alpha std.alpha G6(smc) average_r S/N   ase mean   sd median_r
##       0.86      0.88    0.91      0.44 7.1 0.034  4.6 0.39     0.45
## 
##     95% confidence boundaries 
##          lower alpha upper
## Feldt     0.78  0.86  0.92
## Duhachek  0.80  0.86  0.93
## 
##  Reliability if an item is dropped:
##                          raw_alpha std.alpha G6(smc) average_r S/N alpha se
## Do What I Like - Now          0.86      0.87    0.89      0.45 6.6    0.035
## Dedicated to Work - Now       0.86      0.87    0.91      0.46 6.8    0.036
## Successful - Now              0.84      0.85    0.88      0.41 5.5    0.041
## Peer Respect - Now            0.83      0.85    0.88      0.42 5.7    0.042
## Network - Now                 0.86      0.88    0.91      0.49 7.6    0.035
## Recognized - Now              0.85      0.86    0.89      0.44 6.2    0.039
## Give Support - Now            0.85      0.86    0.89      0.44 6.3    0.038
## Positive Impact - Now         0.85      0.86    0.89      0.44 6.2    0.038
## Address Challenges - Now      0.84      0.86    0.90      0.44 6.2    0.041
##                          var.r med.r
## Do What I Like - Now     0.024  0.45
## Dedicated to Work - Now  0.026  0.48
## Successful - Now         0.022  0.41
## Peer Respect - Now       0.023  0.42
## Network - Now            0.018  0.50
## Recognized - Now         0.026  0.43
## Give Support - Now       0.025  0.44
## Positive Impact - Now    0.030  0.47
## Address Challenges - Now 0.026  0.46
## 
##  Item statistics 
##                           n raw.r std.r r.cor r.drop mean   sd
## Do What I Like - Now     33  0.64  0.66  0.63   0.52  4.5 0.62
## Dedicated to Work - Now  33  0.59  0.63  0.57   0.50  4.8 0.42
## Successful - Now         33  0.82  0.85  0.85   0.77  4.8 0.44
## Peer Respect - Now       33  0.82  0.82  0.82   0.76  4.7 0.53
## Network - Now            33  0.54  0.51  0.43   0.41  4.6 0.55
## Recognized - Now         33  0.79  0.73  0.71   0.66  4.3 0.88
## Give Support - Now       33  0.70  0.72  0.69   0.62  4.7 0.47
## Positive Impact - Now    33  0.69  0.72  0.69   0.63  4.8 0.42
## Address Challenges - Now 33  0.77  0.73  0.70   0.68  4.6 0.61
## 
## Non missing response frequency for each item
##                             2    3    4    5 miss
## Do What I Like - Now     0.00 0.06 0.33 0.61    0
## Dedicated to Work - Now  0.00 0.00 0.21 0.79    0
## Successful - Now         0.00 0.00 0.24 0.76    0
## Peer Respect - Now       0.00 0.03 0.24 0.73    0
## Network - Now            0.00 0.03 0.30 0.67    0
## Recognized - Now         0.03 0.18 0.27 0.52    0
## Give Support - Now       0.00 0.00 0.30 0.70    0
## Positive Impact - Now    0.00 0.00 0.21 0.79    0
## Address Challenges - Now 0.00 0.06 0.30 0.64    0

#Composite OCS Score

#Creates a new column that provides the count of promotions one received - essentially combines three promotion variables into one. Use in the Comp Score variable
OCS_data <- OCS_data %>%
  mutate(
    Promotion_Count = if_else(
      Promotion == 1 & `Number of Promotions` == 0,
      1,
      `Number of Promotions`
    )
  )

Comp_OCS_Score <- OCS_data %>%
  mutate(
    OCSCareerSuccess =
      rowMeans(
        select(.,
               `Salary Increase`,
               Promotion_Count,
               `Direct Reports`,
               `Fiscal Responsibilities`),
        na.rm = TRUE
      )
  )

# t.test(
#   Comp_OCS_Score$OCSCareerSuccess,
#   paired = TRUE
# )

summary(Comp_OCS_Score$OCSCareerSuccess)
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.0000  0.5000  1.0000  0.8333  1.2500  1.5000
describe(Comp_OCS_Score$OCSCareerSuccess)
##    vars  n mean   sd median trimmed  mad min max range  skew kurtosis   se
## X1    1 33 0.83 0.45      1    0.86 0.37   0 1.5   1.5 -0.58    -0.89 0.08

#Composite SCS Score

Comp_SCS_Score <- SCS_data %>%
  mutate(
    BeforeCareerSuccess =
      rowMeans(
        select(.,
               `Do What I Like - Before`,
               `Dedicated to Work - Before`,
               `Successful - Before`,
               `Peer Respect - Before`,
               `Network - Before`,
               `Recognized - Before`,
               `Give Support - Before`,
               `Positive Impact - Before`,
               `Address Challenges - Before`),
        na.rm = TRUE
      ),

    AfterCareerSuccess =
      rowMeans(
        select(.,
               `Do What I Like - Now`,
               `Dedicated to Work - Now`,
               `Successful - Now`,
               `Peer Respect - Now`,
               `Network - Now`,
               `Recognized - Now`,
               `Give Support - Now`,
               `Positive Impact - Now`,
               `Address Challenges - Now`),
        na.rm = TRUE
      )
  )

t.test(
  Comp_SCS_Score$BeforeCareerSuccess,
  Comp_SCS_Score$AfterCareerSuccess,
  paired = TRUE
)
## 
##  Paired t-test
## 
## data:  Comp_SCS_Score$BeforeCareerSuccess and Comp_SCS_Score$AfterCareerSuccess
## t = -7.8847, df = 32, p-value = 5.367e-09
## alternative hypothesis: true mean difference is not equal to 0
## 95 percent confidence interval:
##  -0.8854988 -0.5219086
## sample estimates:
## mean difference 
##      -0.7037037
describe(Comp_SCS_Score)
##                             vars  n mean   sd median trimmed  mad  min max
## Do What I Like - Before        1 33 3.76 1.00   4.00    3.85 1.48 1.00   5
## Do What I Like - Now           2 33 4.55 0.62   5.00    4.63 0.00 3.00   5
## Dedicated to Work - Before     3 33 4.24 0.71   4.00    4.30 1.48 3.00   5
## Dedicated to Work - Now        4 33 4.79 0.42   5.00    4.85 0.00 4.00   5
## Successful - Before            5 33 4.39 0.61   4.00    4.44 1.48 3.00   5
## Successful - Now               6 33 4.76 0.44   5.00    4.81 0.00 4.00   5
## Peer Respect - Before          7 33 4.00 0.97   4.00    4.15 0.00 1.00   5
## Peer Respect - Now             8 33 4.70 0.53   5.00    4.78 0.00 3.00   5
## Network - Before               9 33 3.76 0.83   4.00    3.81 0.00 2.00   5
## Network - Now                 10 33 4.64 0.55   5.00    4.70 0.00 3.00   5
## Recognized - Before           11 33 3.55 1.00   4.00    3.59 0.00 1.00   5
## Recognized - Now              12 33 4.27 0.88   5.00    4.37 0.00 2.00   5
## Give Support - Before         13 33 3.79 0.93   4.00    3.85 0.00 2.00   5
## Give Support - Now            14 33 4.70 0.47   5.00    4.74 0.00 4.00   5
## Positive Impact - Before      15 33 4.12 0.70   4.00    4.19 0.00 2.00   5
## Positive Impact - Now         16 33 4.79 0.42   5.00    4.85 0.00 4.00   5
## Address Challenges - Before   17 33 3.82 0.88   4.00    3.89 0.00 2.00   5
## Address Challenges - Now      18 33 4.58 0.61   5.00    4.67 0.00 3.00   5
## BeforeCareerSuccess           19 33 3.94 0.61   4.00    3.97 0.49 2.44   5
## AfterCareerSuccess            20 33 4.64 0.39   4.78    4.68 0.33 3.89   5
##                             range  skew kurtosis   se
## Do What I Like - Before      4.00 -0.61    -0.01 0.17
## Do What I Like - Now         2.00 -0.94    -0.23 0.11
## Dedicated to Work - Before   2.00 -0.35    -1.05 0.12
## Dedicated to Work - Now      1.00 -1.34    -0.19 0.07
## Successful - Before          2.00 -0.41    -0.81 0.11
## Successful - Now             1.00 -1.15    -0.70 0.08
## Peer Respect - Before        4.00 -1.20     1.34 0.17
## Peer Respect - Now           2.00 -1.41     1.00 0.09
## Network - Before             3.00 -0.50    -0.26 0.14
## Network - Now                2.00 -1.08     0.07 0.10
## Recognized - Before          4.00 -0.66    -0.31 0.17
## Recognized - Now             3.00 -0.80    -0.57 0.15
## Give Support - Before        3.00 -0.73    -0.33 0.16
## Give Support - Now           1.00 -0.82    -1.37 0.08
## Positive Impact - Before     3.00 -0.69     0.91 0.12
## Positive Impact - Now        1.00 -1.34    -0.19 0.07
## Address Challenges - Before  3.00 -0.72    -0.14 0.15
## Address Challenges - Now     2.00 -1.06     0.01 0.11
## BeforeCareerSuccess          2.56 -0.49     0.23 0.11
## AfterCareerSuccess           1.11 -0.71    -0.97 0.07

#SCS Before and After Averages Table (DataFrame)

Q1_DWIL_BeforeAvg <- mean(SCS_data$`Do What I Like - Before`)
Q1_DWIL_NowAvg <- mean(SCS_data$`Do What I Like - Now`)

Q2_DtW_BeforeAvg <- mean(SCS_data$`Dedicated to Work - Before`)
Q2_DtW_NowAvg <- mean(SCS_data$`Dedicated to Work - Now`)

Q3_S_BeforeAvg <- mean(SCS_data$`Successful - Before`)
Q3_S_NowAvg <- mean(SCS_data$`Successful - Now`)

Q4_PR_BeforeAvg <- mean(SCS_data$`Peer Respect - Before`)
Q4_PR_NowAvg <- mean(SCS_data$`Peer Respect - Now`)

Q5_N_BeforeAvg <- mean(SCS_data$`Network - Before`)
Q5_N_NowAvg <- mean(SCS_data$`Network - Now`)

Q6_R_BeforeAvg <- mean(SCS_data$`Recognized - Before`)
Q6_R_NowAvg <- mean(SCS_data$`Recognized - Now`)

Q7_GS_BeforeAvg <- mean(SCS_data$`Give Support - Before`)
Q7_GS_NowAvg <- mean(SCS_data$`Give Support - Now`)

Q8_PI_BeforeAvg <- mean(SCS_data$`Positive Impact - Before`)
Q8_PI_NowAvg <- mean(SCS_data$`Positive Impact - Now`)

Q9_AC_BeforeAvg <- mean(SCS_data$`Address Challenges - Before`)
Q9_AC_NowAvg <- mean(SCS_data$`Address Challenges - Now`)

SCS_df <- data.frame(
  Average_Before = c(Q1_DWIL_BeforeAvg, Q2_DtW_BeforeAvg, Q3_S_BeforeAvg, Q4_PR_BeforeAvg, Q5_N_BeforeAvg, Q6_R_BeforeAvg, Q7_GS_BeforeAvg, Q8_PI_BeforeAvg, Q9_AC_BeforeAvg),
  
  Average_Now = c(Q1_DWIL_NowAvg, Q2_DtW_NowAvg, Q3_S_NowAvg, Q4_PR_NowAvg, Q5_N_NowAvg, Q6_R_NowAvg, Q7_GS_NowAvg, Q8_PI_NowAvg, Q9_AC_NowAvg)
  )

SCS_df <- SCS_df |> 
  mutate(Percent_Difference = ((Average_Now - Average_Before) / Average_Before) * 100)

print(SCS_df)
##   Average_Before Average_Now Percent_Difference
## 1       3.757576    4.545455          20.967742
## 2       4.242424    4.787879          12.857143
## 3       4.393939    4.757576           8.275862
## 4       4.000000    4.696970          17.424242
## 5       3.757576    4.636364          23.387097
## 6       3.545455    4.272727          20.512821
## 7       3.787879    4.696970          24.000000
## 8       4.121212    4.787879          16.176471
## 9       3.818182    4.575758          19.841270

#SCS Change Scores

SCS_data <- SCS_data %>% mutate(LikeJob_Change = `Do What I Like - Now` - `Do What I Like - Before`)

SCS_data <- SCS_data %>% mutate(Dedicated_Change = `Dedicated to Work - Now` - `Dedicated to Work - Before`)

SCS_data <- SCS_data %>% mutate(Success_Change = `Successful - Now` - `Successful - Before`)

SCS_data <- SCS_data %>% mutate(PR_Change = `Peer Respect - Now` - `Peer Respect - Before`)

SCS_data <- SCS_data %>% mutate(Network_Change = `Network - Now` - `Network - Before`)

SCS_data <- SCS_data %>% mutate(Recognized_Change = `Recognized - Now` - `Recognized - Before`)

SCS_data <- SCS_data %>% mutate(GS_Change = `Give Support - Now` - `Give Support - Before`)

SCS_data <- SCS_data %>% mutate(PI_Change = `Positive Impact - Now` - `Positive Impact - Before`)

SCS_data <- SCS_data %>% mutate(AC_Change = `Address Challenges - Now` - `Address Challenges - Before`)

#Add change scores as composition to Comp_SCS_Score df
Comp_SCS_Score <- Comp_SCS_Score %>%
  mutate(
    SCS_Change = AfterCareerSuccess - BeforeCareerSuccess
  )

describe(Comp_SCS_Score$SCS_Change)
##    vars  n mean   sd median trimmed  mad min  max range skew kurtosis   se
## X1    1 33  0.7 0.51   0.67    0.68 0.49   0 1.67  1.67 0.35    -0.98 0.09

#Adding Necessary Columns for Correlation Table

Correlation_Table <- SCS_data
Correlation_Table$OCS_Comp_Score <- Comp_OCS_Score$OCSCareerSuccess
Correlation_Table$SCS_Before_Comp_Score <- Comp_SCS_Score$BeforeCareerSuccess
Correlation_Table$SCS_Now_Comp_Score <- Comp_SCS_Score$AfterCareerSuccess
Correlation_Table$SCS_Change_Score <- Comp_SCS_Score$SCS_Change
Correlation_Table$OCS_Salary <- Comp_OCS_Score$`Salary Increase` #32
Correlation_Table$OCS_Promotion <- Comp_OCS_Score$Promotion_Count
Correlation_Table$DirectReports <- Comp_OCS_Score$`Direct Reports`
Correlation_Table$FiscalResp <- Comp_OCS_Score$`Fiscal Responsibilities`

Correlation_Table <- Correlation_Table[, c(1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,28,29,30,31,32,33,34,35)]

descripstats <- describe(Correlation_Table)
write.csv(descripstats, file = "descripstats.csv")

#Correlation Coefficient Table

cor_matrix <- cor(Correlation_Table)
#write.csv(cor_matrix, file = "correlation_matrix.csv")

#Adding Year to Comp_SCS_Score df

Comp_SCS_Score$Year <- complete_data$Year

Remember to put dependent variable first. You might have to reformulate your research question, if Reddick requires. #Multiple Regression Analysis Table 1

SCS_Analysis <- lm(SCS_Now_Comp_Score ~ SCS_Before_Comp_Score + OCS_Salary + OCS_Promotion + DirectReports + FiscalResp, data = Correlation_Table) 
summary(SCS_Analysis)
## 
## Call:
## lm(formula = SCS_Now_Comp_Score ~ SCS_Before_Comp_Score + OCS_Salary + 
##     OCS_Promotion + DirectReports + FiscalResp, data = Correlation_Table)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -0.70698 -0.17304  0.04772  0.22151  0.51644 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)            3.50720    0.42089   8.333 6.08e-09 ***
## SCS_Before_Comp_Score  0.18365    0.12709   1.445   0.1600    
## OCS_Salary             0.46697    0.25454   1.835   0.0776 .  
## OCS_Promotion         -0.05110    0.07726  -0.661   0.5140    
## DirectReports         -0.15219    0.11129  -1.368   0.1827    
## FiscalResp             0.18231    0.14577   1.251   0.2218    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.3241 on 27 degrees of freedom
## Multiple R-squared:  0.4141, Adjusted R-squared:  0.3056 
## F-statistic: 3.817 on 5 and 27 DF,  p-value: 0.009596
#beta value
model <- lm(
  SCS_Now_Comp_Score ~ SCS_Before_Comp_Score +
    OCS_Salary + OCS_Promotion +
    DirectReports + FiscalResp,
  data = Correlation_Table
)

lm.beta(model)
## 
## Call:
## lm(formula = SCS_Now_Comp_Score ~ SCS_Before_Comp_Score + OCS_Salary + 
##     OCS_Promotion + DirectReports + FiscalResp, data = Correlation_Table)
## 
## Standardized Coefficients::
##           (Intercept) SCS_Before_Comp_Score            OCS_Salary 
##                    NA             0.2879770             0.3979493 
##         OCS_Promotion         DirectReports            FiscalResp 
##            -0.1159223            -0.2610547             0.2352715
#VIF value
vif(model)
## SCS_Before_Comp_Score            OCS_Salary         OCS_Promotion 
##              1.830502              2.168518              1.415675 
##         DirectReports            FiscalResp 
##              1.679473              1.630887

#Multiple Regression Analysis Table 2

SCS_Analysis2 <- lm(SCS_Now_Comp_Score ~ `Successful - Now` + `Peer Respect - Now` + `Recognized - Now` + `Address Challenges - Now` + `Give Support - Now`, data = Correlation_Table) 
summary(SCS_Analysis2)
## 
## Call:
## lm(formula = SCS_Now_Comp_Score ~ `Successful - Now` + `Peer Respect - Now` + 
##     `Recognized - Now` + `Address Challenges - Now` + `Give Support - Now`, 
##     data = Correlation_Table)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -0.24362 -0.05612  0.05499  0.05499  0.28047 
## 
## Coefficients:
##                            Estimate Std. Error t value Pr(>|t|)    
## (Intercept)                 0.88248    0.25523   3.458 0.001822 ** 
## `Successful - Now`          0.23352    0.09175   2.545 0.016954 *  
## `Peer Respect - Now`        0.16085    0.07009   2.295 0.029730 *  
## `Recognized - Now`          0.13830    0.03526   3.922 0.000544 ***
## `Address Challenges - Now`  0.12003    0.05284   2.271 0.031308 *  
## `Give Support - Now`        0.15981    0.06563   2.435 0.021785 *  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.121 on 27 degrees of freedom
## Multiple R-squared:  0.9183, Adjusted R-squared:  0.9031 
## F-statistic: 60.67 on 5 and 27 DF,  p-value: 7.853e-14
#beta value
model2 <- lm(SCS_Now_Comp_Score ~ `Successful - Now` + `Peer Respect - Now` + `Recognized - Now` + `Address Challenges - Now` + `Give Support - Now`, data = Correlation_Table)

lm.beta(model2)
## 
## Call:
## lm(formula = SCS_Now_Comp_Score ~ `Successful - Now` + `Peer Respect - Now` + 
##     `Recognized - Now` + `Address Challenges - Now` + `Give Support - Now`, 
##     data = Correlation_Table)
## 
## Standardized Coefficients::
##                (Intercept)         `Successful - Now` 
##                         NA                  0.2613009 
##       `Peer Respect - Now`         `Recognized - Now` 
##                  0.2189711                  0.3114356 
## `Address Challenges - Now`       `Give Support - Now` 
##                  0.1894667                  0.1917690
#VIF value
vif(model2)
##         `Successful - Now`       `Peer Respect - Now` 
##                   3.482381                   3.007286 
##         `Recognized - Now` `Address Challenges - Now` 
##                   2.083024                   2.298550 
##       `Give Support - Now` 
##                   2.049242

#SCS t-tests

comptt <- t.test(Correlation_Table$SCS_Before_Comp_Score, Correlation_Table$SCS_Now_Comp_Score, paired = TRUE)
#Did average subjective career success increase after participation in the fellowship?

tt_Q1 <- t.test(SCS_data$`Do What I Like - Before`, SCS_data$`Do What I Like - Now`, paired = TRUE)
tt_Q2 <- t.test(SCS_data$`Dedicated to Work - Before`, SCS_data$`Dedicated to Work - Now`, paired = TRUE)
tt_Q3 <- t.test(SCS_data$`Successful - Before`, SCS_data$`Successful - Now`, paired = TRUE)
tt_Q4 <- t.test(SCS_data$`Peer Respect - Before`, SCS_data$`Peer Respect - Now`, paired = TRUE)
tt_Q5 <- t.test(SCS_data$`Network - Before`, SCS_data$`Network - Now`, paired = TRUE)
tt_Q6 <- t.test(SCS_data$`Recognized - Before`, SCS_data$`Recognized - Now`, paired = TRUE)
tt_Q7 <- t.test(SCS_data$`Give Support - Before`, SCS_data$`Give Support - Now`, paired = TRUE)
tt_Q8 <- t.test(SCS_data$`Positive Impact - Before`, SCS_data$`Positive Impact - Now`, paired = TRUE)
tt_Q9 <- t.test(SCS_data$`Address Challenges - Before`, SCS_data$`Address Challenges - Now`, paired = TRUE)

#Compare Career Success Metrics by Demographic

#table(OCS_data$`Salary Increase`, raw_data$Age)
#table(OCS_data$`Salary Increase`, raw_data$Gender)
#table(OCS_data$`Salary Increase`, raw_data$`Race-Ethnicity`)
#table(OCS_data$`Salary Increase`, raw_data$`Year`)

table(Correlation_Table$SCS_Change_Score, raw_data$`Gender`)
##                    
##                     Female Male
##   0                      3    2
##   0.111111111111111      1    0
##   0.222222222222222      1    0
##   0.333333333333333      2    0
##   0.444444444444445      2    1
##   0.555555555555555      2    1
##   0.555555555555556      1    0
##   0.666666666666667      1    2
##   0.777777777777778      1    2
##   0.888888888888889      1    0
##   1                      2    1
##   1.22222222222222       1    0
##   1.44444444444444       1    1
##   1.55555555555556       3    0
##   1.66666666666667       1    0
table(Correlation_Table$SCS_Change_Score, raw_data$`Race-Ethnicity`)
##                    
##                     Alaska Native or Indigenous; American Indian;
##   0                                            0                0
##   0.111111111111111                            0                0
##   0.222222222222222                            0                0
##   0.333333333333333                            0                0
##   0.444444444444445                            0                0
##   0.555555555555555                            0                0
##   0.555555555555556                            0                0
##   0.666666666666667                            0                1
##   0.777777777777778                            1                0
##   0.888888888888889                            1                0
##   1                                            0                1
##   1.22222222222222                             0                0
##   1.44444444444444                             0                0
##   1.55555555555556                             0                0
##   1.66666666666667                             0                0
##                    
##                     American Indian;White; Asian;White; Black/African American;
##   0                                      0            0                       1
##   0.111111111111111                      0            0                       0
##   0.222222222222222                      0            0                       0
##   0.333333333333333                      1            0                       0
##   0.444444444444445                      0            0                       0
##   0.555555555555555                      0            0                       0
##   0.555555555555556                      0            0                       0
##   0.666666666666667                      0            1                       0
##   0.777777777777778                      0            0                       0
##   0.888888888888889                      0            0                       0
##   1                                      0            0                       0
##   1.22222222222222                       0            0                       0
##   1.44444444444444                       0            0                       0
##   1.55555555555556                       0            0                       0
##   1.66666666666667                       0            0                       0
##                    
##                     Black/African American;White; White;
##   0                                             0      4
##   0.111111111111111                             0      0
##   0.222222222222222                             0      1
##   0.333333333333333                             0      1
##   0.444444444444445                             1      2
##   0.555555555555555                             0      3
##   0.555555555555556                             0      1
##   0.666666666666667                             0      1
##   0.777777777777778                             0      2
##   0.888888888888889                             0      0
##   1                                             0      2
##   1.22222222222222                              0      1
##   1.44444444444444                              0      2
##   1.55555555555556                              0      3
##   1.66666666666667                              0      1
##                    
##                     White;Alaska Native or Indigenous;
##   0                                                  0
##   0.111111111111111                                  1
##   0.222222222222222                                  0
##   0.333333333333333                                  0
##   0.444444444444445                                  0
##   0.555555555555555                                  0
##   0.555555555555556                                  0
##   0.666666666666667                                  0
##   0.777777777777778                                  0
##   0.888888888888889                                  0
##   1                                                  0
##   1.22222222222222                                   0
##   1.44444444444444                                   0
##   1.55555555555556                                   0
##   1.66666666666667                                   0
table(Correlation_Table$SCS_Change_Score, raw_data$`Age`)
##                    
##                     25-34 35-44 45-54 55-64
##   0                     2     2     1     0
##   0.111111111111111     0     1     0     0
##   0.222222222222222     0     1     0     0
##   0.333333333333333     0     2     0     0
##   0.444444444444445     0     2     1     0
##   0.555555555555555     1     2     0     0
##   0.555555555555556     0     1     0     0
##   0.666666666666667     1     1     1     0
##   0.777777777777778     0     1     2     0
##   0.888888888888889     0     0     1     0
##   1                     0     1     2     0
##   1.22222222222222      1     0     0     0
##   1.44444444444444      1     1     0     0
##   1.55555555555556      1     0     2     0
##   1.66666666666667      0     0     0     1
table(Correlation_Table$SCS_Change_Score, raw_data$`Year`)
##                    
##                     2010 2017 2018 2020 2021 2022 2023 2024 2025
##   0                    0    1    1    0    0    0    0    2    1
##   0.111111111111111    0    1    0    0    0    0    0    0    0
##   0.222222222222222    0    0    0    0    0    0    0    0    1
##   0.333333333333333    0    0    0    0    0    0    0    0    2
##   0.444444444444445    0    0    0    0    0    0    0    3    0
##   0.555555555555555    0    0    1    0    0    1    1    0    0
##   0.555555555555556    0    0    0    0    0    0    0    0    1
##   0.666666666666667    0    0    0    0    0    0    1    1    1
##   0.777777777777778    0    0    1    0    0    0    0    0    2
##   0.888888888888889    0    0    0    0    0    0    0    0    1
##   1                    0    0    0    1    0    0    0    0    2
##   1.22222222222222     0    0    0    0    0    0    0    1    0
##   1.44444444444444     0    1    0    0    1    0    0    0    0
##   1.55555555555556     1    0    0    0    0    0    0    1    1
##   1.66666666666667     0    0    0    0    0    0    1    0    0
table(Correlation_Table$SCS_Now_Comp_Score, raw_data$`Gender`)
##                   
##                    Female Male
##   3.88888888888889      2    1
##   4                     1    0
##   4.11111111111111      2    0
##   4.22222222222222      1    0
##   4.33333333333333      2    0
##   4.44444444444444      1    0
##   4.55555555555556      2    1
##   4.66666666666667      1    2
##   4.77777777777778      1    0
##   4.88888888888889      4    1
##   5                     6    5
table(raw_data$Year, raw_data$`Number of Promotions`)
##       
##        2 3
##   2010 0 1
##   2017 1 0
##   2018 0 1
##   2020 1 0
##   2021 0 0
##   2022 0 1
##   2023 0 0
##   2024 2 0
##   2025 3 0
table(raw_data$Year, raw_data$`Promotion`)
##       
##        No Yes
##   2010  0   1
##   2017  1   2
##   2018  0   3
##   2020  0   1
##   2021  0   1
##   2022  0   1
##   2023  0   3
##   2024  2   6
##   2025  4   8

#Promotion rate

Years_Employed <- 2026 - complete_data$Year
promotion_rate <- OCS_data$Promotion_Count / Years_Employed
OCS_data$Years_Employed <- Years_Employed

complete_data$Years_employed <- Years_Employed
complete_data$Promotion_Count <- OCS_data$Promotion_Count
complete_data$promotion_rate <- promotion_rate

#write.csv(complete_data, file = "promotion rate.csv")