Carlson_Laura_Class7_Store24_B

library(dplyr) # for manipulating data (group_by, filter, select, summarise, etc.) library(ggplot2) # for visualizing data using the ggplot command # note that dplyr and ggplot2 are part of a larger ecosystem of packages called `tidyverse` # in the future we can simply run `library(tidyverse)` to load all dplyr and ggplot2 library(jtools) # summ() commands to display regression output library(stargazer) # stargazer() command for displaying tables and regression output library(sjPlot) # plot_model() command for visualizing output # convert scientific notation to numerals throughout the notebook options(scipen=999) # change plot size to 6in x 5in to fit the Deepnote window options(repr.plot.width=6, repr.plot.height=5)


Attaching package: ‘dplyr’


The following objects are masked from ‘package:stats’:

    filter, lag


The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union



Please cite as: 


 Hlavac, Marek (2018). stargazer: Well-Formatted Regression and Summary Statistics Tables.

 R package version 5.2.2. https://CRAN.R-project.org/package=stargazer 


Registered S3 methods overwritten by 'broom':
  method            from  
  tidy.glht         jtools
  tidy.summary.glht jtools

Learn more about sjPlot with 'browseVignettes("sjPlot")'.

df_store <- read.csv("Data_Class7_Store24_B.csv")

names(df_store)

str(df_store)

'data.frame':	75 obs. of  14 variables:
 $ store     : int  1 2 3 4 5 6 7 8 9 10 ...
 $ sales     : int  1060294 1619874 1099921 1053860 1227841 1703140 1809256 1378482 2113089 1080979 ...
 $ profit    : int  265014 424007 222735 210122 300480 469050 476355 361115 474725 278625 ...
 $ mtenure   : num  0 86.22 23.89 0 3.88 ...
 $ ctenure   : num  24.8 6.64 5.03 5.37 6.87 ...
 $ pop       : int  7535 8630 9695 2797 20335 16926 17754 20824 26519 16381 ...
 $ comp      : num  2.8 4.24 4.49 4.25 1.65 ...
 $ visibility: int  3 4 3 4 2 3 2 4 2 4 ...
 $ pedcount  : int  3 3 3 2 5 4 5 3 4 3 ...
 $ res       : int  1 1 1 1 0 1 1 1 1 1 ...
 $ hours24   : int  1 1 1 1 1 0 1 1 1 0 ...
 $ crewskill : num  3.56 3.2 3.8 2.06 3.65 ...
 $ mgrskill  : num  3.15 3.56 4.12 4.1 3.59 ...
 $ servqual  : num  86.8 94.7 78.9 100 68.4 ...

head(df_store)

stargazer(df_store, type = "text", digits = 2)


===========================================================================
Statistic  N      Mean      St. Dev.    Min   Pctl(25)  Pctl(75)     Max   
---------------------------------------------------------------------------
store      75    38.00       21.79       1      19.5      56.5       75    
sales      75 1,205,413.00 304,531.30 699,306  984,579  1,362,388 2,113,089
profit     75  276,313.60  89,404.08  122,180 211,003.5 331,313.5  518,998 
mtenure    75    45.30       57.67       0       6.7      50.9       278   
ctenure    75    13.93       17.70     0.89     4.39      17.22    114.15  
pop        75   9,825.59    5,911.67   1,046   5,616.5   14,104    26,519  
comp       75     3.79        1.31     1.65     3.15      4.23      11.13  
visibility 75     3.08        0.75       2        3         4         5    
pedcount   75     2.96        0.99       1        2         4         5    
res        75     0.96        0.20       0        1         1         1    
hours24    75     0.84        0.37       0        1         1         1    
crewskill  75     3.46        0.41     2.06     3.22      3.66      4.64   
mgrskill   75     3.64        0.41     2.96     3.34      3.92      4.62   
servqual   75    87.15       12.61     57.90    78.95     99.90    100.00  
---------------------------------------------------------------------------

# Insert your own analyses here. You can add more code blocks as needed.

names(df_store)

model_1 <- lm(profit ~ mtenure + ctenure, data = df_store) summ(model_1)

#What is the relationship between service quality and profit? model_2 <- lm(profit ~ servqual, data = df_store) summ(model_2)

#What is the relationship between tenure and service quality? model_3 <- lm(servqual ~ mtenure + ctenure, data = df_store) summ(model_3)

#What is the relationship between service quality and other skill metrics? model_4 <- lm(servqual ~ crewskill + mgrskill, data = df_store) summ(model_4)

#What is the relationship between service quality and other intrinsic store metrics? model_5 <- lm(servqual ~ pop + comp + visibility + pedcount + res + hours24, data = df_store) summ(model_5)

#Last, just for fun, I'm going to run the "kitchen sink" regression. #What is the relationship between service quality, other variables used previously, and profit? #I'm hoping that adding servqual to the data we had in part A of the case will improve the predictive power of the regression model_6 <- lm(profit ~ mtenure + ctenure + pop + comp + visibility + pedcount + res + hours24 + crewskill + mgrskill + servqual, data = df_store) summ(model_6)