Civil Cases of New Hampshire Businesses
DL
March 29, 2018
Import and get a big picture
The data we are using here are obtained from the different sources: the federal judiciary center and the free law project.
- How many cases are there by judgement?
- Who is more likely win?
# Import data
data <- read.csv("data/data_merged.csv")
# Sturecture of data
str(data)
## 'data.frame': 4200 obs. of 51 variables:
## $ CIRCUIT : int 1 1 1 1 1 1 1 1 1 1 ...
## $ DISTRICT : int 2 2 2 2 2 2 2 2 2 2 ...
## $ OFFICE : int 1 1 1 1 1 1 1 1 1 1 ...
## $ DOCKET : int 265 409 100015 100016 100018 100019 100020 100028 100030 100031 ...
## $ ORIGIN : int 4 4 1 1 5 1 1 5 1 1 ...
## $ FILEDATE : Factor w/ 2566 levels "1/1/2012","1/10/2001",..: 1107 1237 2 2 18 18 18 85 85 85 ...
## $ FILEYEAR : int 2001 2001 2001 2001 2001 2001 2001 2001 2001 2001 ...
## $ FDATEUSE : Factor w/ 204 levels "1/1/2001","1/1/2002",..: 86 103 1 1 1 1 1 1 1 1 ...
## $ JURIS : int 3 4 1 1 4 3 4 4 4 4 ...
## $ NOS : int 840 190 190 190 190 440 110 365 365 365 ...
## $ TITLE : Factor w/ 33 levels "-8","0","10",..: 5 13 13 13 13 20 13 20 13 13 ...
## $ SECTION : Factor w/ 144 levels "-8","1","10",..: 10 20 27 27 20 73 22 138 20 20 ...
## $ SUBSECT : Factor w/ 73 levels "-8","1","12",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ RESIDENC : int -8 43 -8 -8 25 -8 52 55 15 15 ...
## $ CLASSACT : int -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 ...
## $ DEMANDED : int 0 0 0 0 0 0 0 0 0 0 ...
## $ FILEJUDG : logi NA NA NA NA NA NA ...
## $ FILEMAG : logi NA NA NA NA NA NA ...
## $ COUNTY : int 99999 33015 33013 33013 88888 88888 88888 88888 33007 33015 ...
## $ ARBIT : Factor w/ 4 levels "-8","E","M","V": 1 1 1 1 1 1 1 1 1 1 ...
## $ MDLDOCK : int -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 ...
## $ PLT : Factor w/ 3128 levels "-8","108 DEGREES. LLC",..: 2968 1362 2944 2944 1546 268 85 1813 2166 1767 ...
## $ DEF : Factor w/ 3369 levels "-8",", ET AL",..: 1024 1637 993 2405 3274 649 2845 76 118 119 ...
## $ TRANSDAT : logi NA NA NA NA NA NA ...
## $ TRANSOFF : int -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 ...
## $ TRANSDOC : int -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 ...
## $ TRANSORG : int -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 ...
## $ TERMDATE : Factor w/ 2560 levels "1/10/2002","1/10/2003",..: 1184 2184 1584 1191 1082 2161 2042 1013 1100 1043 ...
## $ TDATEUSE : Factor w/ 204 levels "1/1/2001","1/1/2002",..: 86 171 120 86 86 171 154 69 86 69 ...
## $ TRCLACT : int -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 ...
## $ TERMJUDG : logi NA NA NA NA NA NA ...
## $ TERMMAG : logi NA NA NA NA NA NA ...
## $ PROCPROG : int 5 4 2 2 2 2 5 2 1 2 ...
## $ DISP : int 5 13 18 18 14 3 6 14 10 12 ...
## $ NOJ : int 2 -8 0 0 -8 -8 2 -8 -8 -8 ...
## $ AMTREC : int 5 54 0 0 0 0 33 0 0 0 ...
## $ JUDGMENT : int 1 -8 -8 -8 -8 -8 2 -8 -8 -8 ...
## $ DJOINED : Factor w/ 1512 levels "","1/10/2005",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ PRETRIAL : Factor w/ 418 levels "","1/10/2012",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ TRIBEGAN : Factor w/ 40 levels "","1/20/2016",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ TRIALEND : Factor w/ 83 levels "","1/13/2004",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ TRMARB : int -8 -8 -8 -8 -8 -8 -8 -8 -8 -8 ...
## $ PROSE : int 0 0 0 0 0 1 2 0 0 0 ...
## $ IFP : Factor w/ 2 levels "-8","FP": 1 1 1 1 1 1 1 1 1 1 ...
## $ STATUSCD : Factor w/ 1 level "L": 1 1 1 1 1 1 1 1 1 1 ...
## $ TAPEYEAR : int 2001 2001 2001 2001 2001 2001 2001 2001 2001 2001 ...
## $ nature_of_suit: Factor w/ 44 levels "ADMINISTRATIVE PROCEDURE ACT/REVIEW OR APPEAL OF AGENCY DECISION",..: 43 29 29 29 29 28 19 36 36 36 ...
## $ busType_def : Factor w/ 5 levels "CORP","LLC","PARTNERSHIP",..: NA NA NA NA NA NA NA NA NA NA ...
## $ busType_plt : Factor w/ 4 levels "CORP","LLC","PARTNERSHIP",..: NA NA NA NA NA NA NA NA NA NA ...
## $ busType : Factor w/ 3 levels "Both","Neither",..: 2 2 2 2 2 2 2 2 2 2 ...
## $ cause : Factor w/ 173 levels "","0.415277778",..: NA NA NA NA NA NA NA NA NA NA ...
# See the first six rows of the data
head(data)
## CIRCUIT DISTRICT OFFICE DOCKET ORIGIN FILEDATE FILEYEAR FDATEUSE JURIS
## 1 1 2 1 265 4 3/21/2001 2001 3/1/2001 3
## 2 1 2 1 409 4 4/1/2001 2001 4/1/2001 4
## 3 1 2 1 100015 1 1/10/2001 2001 1/1/2001 1
## 4 1 2 1 100016 1 1/10/2001 2001 1/1/2001 1
## 5 1 2 1 100018 5 1/12/2001 2001 1/1/2001 4
## 6 1 2 1 100019 1 1/12/2001 2001 1/1/2001 3
## NOS TITLE SECTION SUBSECT RESIDENC CLASSACT DEMANDED FILEJUDG FILEMAG
## 1 840 15 1114 -8 -8 -8 0 NA NA
## 2 190 28 1332 -8 43 -8 0 NA NA
## 3 190 28 1345 -8 -8 -8 0 NA NA
## 4 190 28 1345 -8 -8 -8 0 NA NA
## 5 190 28 1332 -8 25 -8 0 NA NA
## 6 440 42 1983 -8 -8 -8 0 NA NA
## COUNTY ARBIT MDLDOCK PLT
## 1 99999 -8 -8 VELCRO INDUSTRIES BV, ET AL
## 2 33015 -8 -8 HIGHDATA SOFTWARE
## 3 33013 -8 -8 USA
## 4 33013 -8 -8 USA
## 5 88888 -8 -8 KAPUR
## 6 88888 -8 -8 BICKFORD
## DEF TRANSDAT TRANSOFF TRANSDOC TRANSORG TERMDATE
## 1 FASTECH, ET AL NA -8 -8 -8 3/22/2001
## 2 KOTHANDAN NA -8 -8 -8 8/15/2001
## 3 EVANS NA -8 -8 -8 5/17/2001
## 4 PICUCCI NA -8 -8 -8 3/23/2001
## 5 WEBMANAGE TECHNOLOG, ET AL NA -8 -8 -8 3/1/2001
## 6 CONCORD DISTRICT CT NA -8 -8 -8 8/10/2001
## TDATEUSE TRCLACT TERMJUDG TERMMAG PROCPROG DISP NOJ AMTREC JUDGMENT
## 1 3/1/2001 -8 NA NA 5 5 2 5 1
## 2 8/1/2001 -8 NA NA 4 13 -8 54 -8
## 3 5/1/2001 -8 NA NA 2 18 0 0 -8
## 4 3/1/2001 -8 NA NA 2 18 0 0 -8
## 5 3/1/2001 -8 NA NA 2 14 -8 0 -8
## 6 8/1/2001 -8 NA NA 2 3 -8 0 -8
## DJOINED PRETRIAL TRIBEGAN TRIALEND TRMARB PROSE IFP STATUSCD TAPEYEAR
## 1 -8 0 -8 L 2001
## 2 -8 0 -8 L 2001
## 3 -8 0 -8 L 2001
## 4 -8 0 -8 L 2001
## 5 -8 0 -8 L 2001
## 6 -8 1 -8 L 2001
## nature_of_suit busType_def busType_plt busType cause
## 1 TRADEMARK <NA> <NA> Neither <NA>
## 2 OTHER CONTRACT ACTIONS <NA> <NA> Neither <NA>
## 3 OTHER CONTRACT ACTIONS <NA> <NA> Neither <NA>
## 4 OTHER CONTRACT ACTIONS <NA> <NA> Neither <NA>
## 5 OTHER CONTRACT ACTIONS <NA> <NA> Neither <NA>
## 6 OTHER CIVIL RIGHTS <NA> <NA> Neither <NA>
# Basic descriptive statistics of data
summary(data)
## CIRCUIT DISTRICT OFFICE DOCKET ORIGIN
## Min. :1 Min. :2 Min. :1 Min. : 73 Min. : 1.000
## 1st Qu.:1 1st Qu.:2 1st Qu.:1 1st Qu.: 400138 1st Qu.: 1.000
## Median :1 Median :2 Median :1 Median : 800364 Median : 1.000
## Mean :1 Mean :2 Mean :1 Mean : 855885 Mean : 1.467
## 3rd Qu.:1 3rd Qu.:2 3rd Qu.:1 3rd Qu.:1200343 3rd Qu.: 2.000
## Max. :1 Max. :2 Max. :1 Max. :9900606 Max. :13.000
##
## FILEDATE FILEYEAR FDATEUSE JURIS
## 9/16/2002 : 10 Min. :2001 10/1/2002: 50 Min. :1.000
## 11/25/2003: 9 1st Qu.:2004 5/1/2002 : 40 1st Qu.:3.000
## 9/24/2002 : 8 Median :2008 9/1/2002 : 40 Median :3.000
## 11/23/2010: 7 Mean :2008 10/1/2003: 36 Mean :3.315
## 5/7/2004 : 7 3rd Qu.:2012 4/1/2013 : 36 3rd Qu.:4.000
## 11/23/2004: 6 Max. :2017 6/1/2005 : 34 Max. :4.000
## (Other) :4153 (Other) :3964
## NOS TITLE SECTION SUBSECT
## Min. :110.0 28 :2717 1332 :1147 -8 :1562
## 1st Qu.:350.0 42 : 656 1441 : 912 CV : 430
## Median :440.0 15 : 396 1983 : 355 PI : 269
## Mean :443.9 29 : 112 1331 : 322 BC : 249
## 3rd Qu.:446.0 17 : 63 1692 : 163 ED : 229
## Max. :899.0 47 : 55 2000 : 146 OC : 177
## (Other): 201 (Other):1155 (Other):1284
## RESIDENC CLASSACT DEMANDED FILEJUDG
## Min. :-8.000 Min. :-8.000 Min. : 0.00 Mode:logical
## 1st Qu.:-8.000 1st Qu.:-8.000 1st Qu.: 0.00 NA's:4200
## Median :-8.000 Median :-8.000 Median : 0.00
## Mean : 6.339 Mean :-7.916 Mean : 2.64
## 3rd Qu.:15.000 3rd Qu.:-8.000 3rd Qu.: 0.00
## Max. :64.000 Max. : 1.000 Max. :5000.00
##
## FILEMAG COUNTY ARBIT MDLDOCK
## Mode:logical Min. :33001 -8:4180 Min. : -8.000
## NA's:4200 1st Qu.:33011 E : 7 1st Qu.: -8.000
## Median :33013 M : 5 Median : -8.000
## Mean :46637 V : 8 Mean : 9.216
## 3rd Qu.:33019 3rd Qu.: -8.000
## Max. :99999 Max. :2320.000
##
## PLT DEF TRANSDAT
## USA : 82 -8 : 61 Mode:logical
## -8 : 20 TYCO INTERNATIONAL, ET AL : 34 NA's:4200
## DIRECTV, INC.: 20 USA : 34
## AMATUCCI : 17 GUTIERREZ, ET AL : 12
## WILSON : 15 NH DEPARTMENT OF HEALTH AND HU: 12
## JOHNSON : 13 SEALED : 11
## (Other) :4033 (Other) :4036
## TRANSOFF TRANSDOC TRANSORG TERMDATE TDATEUSE
## Min. :-8 Min. :-8 Min. :-8 2/4/2015 : 13 3/1/2006 : 43
## 1st Qu.:-8 1st Qu.:-8 1st Qu.:-8 3/3/2006 : 13 12/1/2011: 42
## Median :-8 Median :-8 Median :-8 10/14/2004: 9 4/1/2003 : 35
## Mean :-8 Mean :-8 Mean :-8 3/6/2006 : 9 10/1/2003: 34
## 3rd Qu.:-8 3rd Qu.:-8 3rd Qu.:-8 12/19/2011: 8 10/1/2006: 33
## Max. :-8 Max. :-8 Max. :-8 2/1/2016 : 7 3/1/2005 : 33
## (Other) :4141 (Other) :3980
## TRCLACT TERMJUDG TERMMAG PROCPROG
## Min. :-8.000 Mode:logical Mode:logical Min. : 1.000
## 1st Qu.:-8.000 NA's:4200 NA's:4200 1st Qu.: 2.000
## Median :-8.000 Median : 5.000
## Mean :-7.854 Mean : 4.229
## 3rd Qu.:-8.000 3rd Qu.: 5.000
## Max. : 3.000 Max. :13.000
##
## DISP NOJ AMTREC JUDGMENT
## Min. : 0.0 Min. :-8.000 Min. : 0.00 Min. :-8.00
## 1st Qu.: 6.0 1st Qu.:-8.000 1st Qu.: 0.00 1st Qu.:-8.00
## Median :13.0 Median : 0.000 Median : 0.00 Median : 0.00
## Mean :10.5 Mean :-3.177 Mean : 35.09 Mean :-3.25
## 3rd Qu.:13.0 3rd Qu.: 0.000 3rd Qu.: 0.00 3rd Qu.: 0.00
## Max. :20.0 Max. : 6.000 Max. :9999.00 Max. : 4.00
##
## DJOINED PRETRIAL TRIBEGAN TRIALEND
## :2163 :3717 :4160 :4118
## 7/1/2013 : 8 10/12/2011: 7 2/17/2016: 2 1/13/2004: 1
## 11/14/2011: 6 10/24/2011: 4 1/20/2016: 1 1/20/2016: 1
## 10/12/2006: 5 3/5/2012 : 4 1/4/2011 : 1 1/23/2007: 1
## 10/22/2004: 5 11/24/2009: 3 1/6/2015 : 1 1/27/2009: 1
## 5/14/2007 : 5 12/16/2011: 3 1/6/2016 : 1 1/27/2016: 1
## (Other) :2008 (Other) : 462 (Other) : 34 (Other) : 77
## TRMARB PROSE IFP STATUSCD TAPEYEAR
## Min. :-8 Min. :0.000 -8:3943 L:4200 Min. :2001
## 1st Qu.:-8 1st Qu.:0.000 FP: 257 1st Qu.:2005
## Median :-8 Median :0.000 Median :2009
## Mean :-8 Mean :0.221 Mean :2009
## 3rd Qu.:-8 3rd Qu.:0.000 3rd Qu.:2013
## Max. :-8 Max. :3.000 Max. :2018
##
## nature_of_suit busType_def busType_plt
## OTHER CONTRACT ACTIONS : 610 CORP : 877 CORP : 409
## OTHER CIVIL RIGHTS : 574 LLC : 390 LLC : 264
## CIVIL RIGHTS JOBS : 437 PARTNERSHIP: 30 PARTNERSHIP: 4
## OTHER PERSONAL INJURY : 356 PC : 6 PC : 9
## OTHER STATUTORY ACTIONS: 344 PLLC : 2 NA's :3514
## INSURANCE : 245 NA's :2895
## (Other) :1634
## busType cause
## Both : 275 42:1983 Civil Rights Act : 183
## Neither :2484 28:1332 Diversity-Personal Injury : 79
## Only one:1441 28:1332 Diversity-Breach of Contract : 78
## 28:1441 Petition for Removal - Employment Discrim: 70
## 28:1331 Federal Question: Other Civil Rights : 68
## (Other) :1250
## NA's :2472Length of suit
The length of suit (days) was calculated by taking the difference between FILEDATE and TERMDATE. Datacamp offers a video lecture on times and dates.
Create data table
# Convert to date object
data$FILEDATE = as.Date(data$FILEDATE, "%m/%d/%Y")
data$TERMDATE = as.Date(data$TERMDATE, "%m/%d/%Y")
# Create a new variable, length of suit
data$lengthOfsuit = as.numeric(difftime(time1 = data$TERMDATE,
time2 = data$FILEDATE,
units = "days"))
# Create a table
library(dplyr)
library(DT)
table <- data %>%
group_by(nature_of_suit) %>%
summarise(numberOfcases = n(),
avg_lengthOfsuit = round(mean(lengthOfsuit, na.rm = TRUE), 0)) %>%
arrange(desc(avg_lengthOfsuit))
datatable(table, options = list(pageLength = 10))
# Step by step
library(ggplot2)
data %>%
group_by(nature_of_suit) %>%
summarise(numberOfcases = n(),
avg_lengthOfsuit = round(mean(lengthOfsuit, na.rm = TRUE), 0)) %>%
arrange(desc(avg_lengthOfsuit)) %>%
filter(numberOfcases > 50) %>%
top_n(10, avg_lengthOfsuit) %>%
ggplot(aes(reorder(x = nature_of_suit, avg_lengthOfsuit), y = avg_lengthOfsuit, fill = nature_of_suit)) +
geom_col(show.legend = FALSE) +
coord_flip() +
labs(title = "Top 10 Nature of Suit by Length of Suit\n(Nature of Suit > 50 cases)",
x = "Nature of Suit",
y = "Length of Suit (days)")
Plot
library(ggplot2)
data %>%
group_by(nature_of_suit) %>%
summarise(numberOfcases = n(),
avg_lengthOfsuit = round(mean(lengthOfsuit, na.rm = TRUE), 0)) %>%
filter(numberOfcases > 50) %>%
top_n(10, avg_lengthOfsuit) %>%
ggplot(aes(x = reorder(nature_of_suit, avg_lengthOfsuit), y = avg_lengthOfsuit, fill = "Orange")) +
geom_col(show.legend = FALSE) +
labs(title = "Top 10 Nature of Suit by Length of Suit\n(Nature of Suit > 50 cases)",
x = "Nature of Suit",
y = "Length of Suit (days)") +
coord_flip()
# Step by step
# Can you do the same for Causes of Action in place of Nature of Suit?Length of Suit by NOS and by Disposition
The manner in which the case was disposed of.
Cases transferred or remanded:
- 0 - transfer to another district
- 1 - remanded to state court
- 10 - multi district litigation transfer
- 11 - remanded to U.S. Agency
Dismissals:
- 2 - want of prosecution
- 3 - lack of jurisdiction
- 12 - voluntarily
- 13 - settled
- 14 - other
Judgment on:
- 4 - default
- 5 - consent
- 6 - motion before trial
- 7 - jury verdict
- 8 - directed verdict
- 9 - court trial
- 15 - award of arbitrator
- 16 - stayed pending bankruptcy
- 17 - other
- 18 - statistical closing
- 19 - appeal affirmed (magistrate judge)
- 20 - appeal denied (magistrate judge)
- -8 - missing
See CIVIL CODE sheets, under disposition, for explanation of the three manners.
data$DISP[data$DISP == "0"] <- "transfer to another district"
data$DISP[data$DISP == "1"] <- "remanded to state court"
data$DISP[data$DISP == "10"] <- "multi district litigation transfer"
data$DISP[data$DISP == "11"] <- "remanded to U.S. Agency"
data$DISP[data$DISP == "2"] <- "want of prosecution"
data$DISP[data$DISP == "3"] <- "lack of jurisdiction"
data$DISP[data$DISP == "12"] <- "voluntarily"
data$DISP[data$DISP == "13"] <- "settled"
data$DISP[data$DISP == "14"] <- "other, dismissals"
data$DISP[data$DISP == "4"] <- "default"
data$DISP[data$DISP == "5"] <- "consent"
data$DISP[data$DISP == "6"] <- "motion before trial"
data$DISP[data$DISP == "7"] <- "jury verdict"
data$DISP[data$DISP == "8"] <- "directed verdict"
data$DISP[data$DISP == "9"] <- "court trial"
data$DISP[data$DISP == "15"] <- "award of arbitrator"
data$DISP[data$DISP == "16"] <- "stayed pending bankruptcy"
data$DISP[data$DISP == "17"] <- "other, judgement on"
data$DISP[data$DISP == "18"] <- "statistical closing"
data$DISP[data$DISP == "19"] <- "appeal affirmed"
data$DISP[data$DISP == "20"] <- "appeal denied"
data$DISP[data$DISP == "-8"] <- "missing"
# Easy fix, but not ordered
data %>%
group_by(DISP, nature_of_suit) %>%
summarise(numberOfcases = n(),
avg_lengthOfsuit = round(mean(lengthOfsuit, na.rm = TRUE), 0)) %>%
filter(numberOfcases > 50) %>%
ggplot(aes(x = reorder(nature_of_suit, avg_lengthOfsuit), y = avg_lengthOfsuit, fill = DISP)) +
geom_col(show.legend = FALSE) +
labs(title = "Top 10 Nature of Suit by Length of Suit\n(Nature of Suit > 50 cases)",
x = NULL,
y = "Length of Suit (days)") +
coord_flip() +
facet_wrap(~ DISP, scales = "free", ncol = 2)
# Ordered but long fix
data_DISP <-
data %>%
group_by(DISP, nature_of_suit) %>%
summarise(numberOfcases = n(),
avg_lengthOfsuit = round(mean(lengthOfsuit, na.rm = TRUE), 0)) %>%
ungroup() %>%
arrange(avg_lengthOfsuit) %>%
mutate(order = row_number())
data_DISP
## # A tibble: 374 x 5
## DISP nature_of_suit numberO~ avg_leng~ order
## <chr> <fctr> <int> <dbl> <int>
## 1 appeal denied PERSONAL INJURY ~ 1 0 1
## 2 consent INSURANCE 1 0 2
## 3 other, dismissals LABOR/MANAGEMENT~ 1 0 3
## 4 settled ANTITRUST 1 5.00 4
## 5 consent CIVIL RIGHTS ADA~ 1 6.00 5
## 6 remanded to state court OTHER FRAUD 3 7.00 6
## 7 statistical closing ARBITRATION 1 10.0 7
## 8 settled LABOR/MANAGEMENT~ 1 13.0 8
## 9 transfer to another district TORT PRODUCT LIA~ 1 13.0 9
## 10 statistical closing CIVIL RIGHTS ACC~ 1 14.0 10
## # ... with 364 more rows
data_DISP %>%
filter(numberOfcases > 50) %>%
ggplot(aes(x = as.factor(order), y = avg_lengthOfsuit, fill = DISP)) +
geom_col(show.legend = FALSE) +
labs(title = "Top 10 Nature of Suit by Length of Suit\n(Nature of Suit > 50 cases)",
x = NULL,
y = "Length of Suit (days)") +
coord_flip() +
facet_wrap(~ DISP, scales = "free", ncol = 2) +
# Add categories to axis
scale_x_discrete(
breaks = data_DISP$order,
labels = data_DISP$nature_of_suit,
expand = c(0,0)
)