Synopsis

This analysis aims to address to questions:

Across the United States, which types of (storm) events are most harmful with respect to population health?
Across the United States, which types of (storm) events have the greatest economic consequences?

The storm database from the U.S. National Oceanic and Atmospheric Administrations (NOAA) from 1950 to November 2011 was used. The analysis was done in RStudio.

Data Processing

# downloading data and reading it into work space
download.file(url = "http://d396qusza40orc.cloudfront.net/repdata%2Fdata%2FStormData.csv.bz2",destfile = "data.csv.bz2")
data<-read.csv("data.csv.bz2")

str(data)

## 'data.frame':    902297 obs. of  37 variables:
##  $ STATE__   : num  1 1 1 1 1 1 1 1 1 1 ...
##  $ BGN_DATE  : Factor w/ 16335 levels "1/1/1966 0:00:00",..: 6523 6523 4242 11116 2224 2224 2260 383 3980 3980 ...
##  $ BGN_TIME  : Factor w/ 3608 levels "00:00:00 AM",..: 272 287 2705 1683 2584 3186 242 1683 3186 3186 ...
##  $ TIME_ZONE : Factor w/ 22 levels "ADT","AKS","AST",..: 7 7 7 7 7 7 7 7 7 7 ...
##  $ COUNTY    : num  97 3 57 89 43 77 9 123 125 57 ...
##  $ COUNTYNAME: Factor w/ 29601 levels "","5NM E OF MACKINAC BRIDGE TO PRESQUE ISLE LT MI",..: 13513 1873 4598 10592 4372 10094 1973 23873 24418 4598 ...
##  $ STATE     : Factor w/ 72 levels "AK","AL","AM",..: 2 2 2 2 2 2 2 2 2 2 ...
##  $ EVTYPE    : Factor w/ 985 levels "   HIGH SURF ADVISORY",..: 834 834 834 834 834 834 834 834 834 834 ...
##  $ BGN_RANGE : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ BGN_AZI   : Factor w/ 35 levels "","  N"," NW",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ BGN_LOCATI: Factor w/ 54429 levels "","- 1 N Albion",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ END_DATE  : Factor w/ 6663 levels "","1/1/1993 0:00:00",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ END_TIME  : Factor w/ 3647 levels ""," 0900CST",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ COUNTY_END: num  0 0 0 0 0 0 0 0 0 0 ...
##  $ COUNTYENDN: logi  NA NA NA NA NA NA ...
##  $ END_RANGE : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ END_AZI   : Factor w/ 24 levels "","E","ENE","ESE",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ END_LOCATI: Factor w/ 34506 levels "","- .5 NNW",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ LENGTH    : num  14 2 0.1 0 0 1.5 1.5 0 3.3 2.3 ...
##  $ WIDTH     : num  100 150 123 100 150 177 33 33 100 100 ...
##  $ F         : int  3 2 2 2 2 2 2 1 3 3 ...
##  $ MAG       : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ FATALITIES: num  0 0 0 0 0 0 0 0 1 0 ...
##  $ INJURIES  : num  15 0 2 2 2 6 1 0 14 0 ...
##  $ PROPDMG   : num  25 2.5 25 2.5 2.5 2.5 2.5 2.5 25 25 ...
##  $ PROPDMGEXP: Factor w/ 19 levels "","-","?","+",..: 17 17 17 17 17 17 17 17 17 17 ...
##  $ CROPDMG   : num  0 0 0 0 0 0 0 0 0 0 ...
##  $ CROPDMGEXP: Factor w/ 9 levels "","?","0","2",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ WFO       : Factor w/ 542 levels ""," CI","$AC",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ STATEOFFIC: Factor w/ 250 levels "","ALABAMA, Central",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ ZONENAMES : Factor w/ 25112 levels "","                                                                                                                               "| __truncated__,..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ LATITUDE  : num  3040 3042 3340 3458 3412 ...
##  $ LONGITUDE : num  8812 8755 8742 8626 8642 ...
##  $ LATITUDE_E: num  3051 0 0 0 0 ...
##  $ LONGITUDE_: num  8806 0 0 0 0 ...
##  $ REMARKS   : Factor w/ 436781 levels "","-2 at Deer Park\n",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ REFNUM    : num  1 2 3 4 5 6 7 8 9 10 ...

str(data$EVTYPE)

##  Factor w/ 985 levels "   HIGH SURF ADVISORY",..: 834 834 834 834 834 834 834 834 834 834 ...

According to the National Weather Service Storm Data Documentation, p.6, the event type can be classified into 3 designator groups: Z, C, and M. Hence, we processed the data$EVTYPE back to the corresponding designator groups by picking specific keywords as follows:

M group – keywords: “marine”, “tstm”, and “spout”
C group – keywords: “debris”, “dust devil”, “flood”, “cloud”, “hail”, “rain”, “lightning”, “thunderstorm”, and “tornado”
Z group – keywords: “astronomical”, “avalanche”, “blizzard”, “coastal”, “chill”, “dense”, “drought”, “dust storm”, “excessive”, “extreme”, “frost”, “freeze”, “fog”, “heat”, “snow”, “high”, “hurricane”, “typhoon”, “ice”, “lake”, “current”, “seiche”, “sleet”, “surge”, “wind”, “tropical”, “tsunami”, “volcanic”, “wild”, “winter”, and “wintry”

type<-data$EVTYPE
type<-as.character(type)
type<-tolower(type)

# M group
type[grep("marine",type)]<-"m"
type[grep("tstm",type)]<-"m"
type[grep("spout",type)]<-"m"

# C group
type[grep("debris",type)]<-"c"
type[grep("dust devil",type)]<-"c"
type[grep("flood",type)]<-"c"
type[grep("cloud",type)]<-"c"
type[grep("hail",type)]<-"c"
type[grep("rain",type)]<-"c"
type[grep("lightning",type)]<-"c"
type[grep("thunderstorm",type)]<-"c"
type[grep("tornado",type)]<-"c"

# Z group
type[grep("astronomical",type)]<-"z"
type[grep("avalanche",type)]<-"z"
type[grep("blizzard",type)]<-"z"
type[grep("coastal",type)]<-"z"
type[grep("chill",type)]<-"z"
type[grep("dense",type)]<-"z"
type[grep("drought",type)]<-"z"
type[grep("dust storm",type)]<-"z"
type[grep("excessive",type)]<-"z"
type[grep("extreme",type)]<-"z"
type[grep("frost",type)]<-"z"
type[grep("freeze",type)]<-"z"
type[grep("fog",type)]<-"z"
type[grep("heat",type)]<-"z"
type[grep("snow",type)]<-"z"
type[grep("high",type)]<-"z"
type[grep("hurricane",type)]<-"z"
type[grep("typhoon",type)]<-"z"
type[grep("ice",type)]<-"z"
type[grep("lake",type)]<-"z"
type[grep("current",type)]<-"z"
type[grep("seiche",type)]<-"z"
type[grep("sleet",type)]<-"z"
type[grep("surge",type)]<-"z"
type[grep("wind",type)]<-"z"
type[grep("tropical",type)]<-"z"
type[grep("tsunami",type)]<-"z"
type[grep("volcanic",type)]<-"z"
type[grep("wild",type)]<-"z"
type[grep("winter",type)]<-"z"
type[grep("wintry",type)]<-"z"

datam <- subset(x = data,subset = type=="m")
datac <- subset(x = data,subset = type=="c")
dataz <- subset(x = data,subset = type=="z")

We extracted 896672 observations out of 902297 total observations, which is 99.3765911 percents.

Results

Q1: Across the United States, which types of (storm) events are most harmful with respect to population health?

According to the data, we have two recorded variables which relate to population health: FATALITIES and INJURIES. In this analysis, we concern only INJURIES.

tempdatam<-subset(x = datam,select = INJURIES)
tempdatac<-subset(x = datac,select = INJURIES)
tempdataz<-subset(x = dataz,select = INJURIES)

tempm=tempdatam$INJURIES
tempc=tempdatac$INJURIES
tempz=tempdataz$INJURIES
boxplot(tempm,tempc,tempz,
        horizontal=TRUE,
        names=c("M","C","Z"),
        xlab = "Numbers of Injury",ylab = "Group",main = "Numbers of Injury by Storm Types in US (1950 - NOV 2011)")

To answer the question, we applied linear regression to see the impact of event type on numbers of injury.

tempdatam<-data.frame("Injuries" = tempm,"Group" = "M")
tempdatac<-data.frame("Injuries" = tempc,"Group" = "C")
tempdataz<-data.frame("Injuries" = tempz,"Group" = "Z")

tempdata<-rbind(tempdatam,tempdatac,tempdataz)

M_GROUP<-c(rep(0,dim(tempdata)[1]))
M_GROUP[tempdata$Group=="M"]<-1
C_GROUP<-c(rep(0,dim(tempdata)[1]))
C_GROUP[tempdata$Group=="C"]<-1
Z_GROUP<-c(rep(0,dim(tempdata)[1]))
Z_GROUP[tempdata$Group=="Z"]<-1

tempdata<-data.frame(tempdata$Injuries,M_GROUP,C_GROUP,Z_GROUP)

lm(tempdata$tempdata.Injuries ~ tempdata$M_GROUP);lm(tempdata$tempdata.Injuries ~ tempdata$C_GROUP);lm(tempdata$tempdata.Injuries ~ tempdata$Z_GROUP)

## 
## Call:
## lm(formula = tempdata$tempdata.Injuries ~ tempdata$M_GROUP)
## 
## Coefficients:
##      (Intercept)  tempdata$M_GROUP  
##           0.2014           -0.1711

## 
## Call:
## lm(formula = tempdata$tempdata.Injuries ~ tempdata$C_GROUP)
## 
## Coefficients:
##      (Intercept)  tempdata$C_GROUP  
##          0.09393           0.09760

## 
## Call:
## lm(formula = tempdata$tempdata.Injuries ~ tempdata$Z_GROUP)
## 
## Coefficients:
##      (Intercept)  tempdata$Z_GROUP  
##           0.1442            0.1214

From the results, the coefficient of Z_GROUP is 0.1214493 which is the highest compared to other groups. Hence, the storm type Z is the most harmful with respect to population health in term of numbers of injury.

Q2: Across the United States, which types of (storm) events have the greatest economic consequences?

According to the data, we have four recorded variables which relate to economic consequences: PROPDMG, PROPDMGEXP, CROPDMG, and CROPDMGEXP. Only PROPDMG and CROPDMG are considered. We applied non-weighted method to accumulate both variables into one.

# non-weighted accumulation of PROPDMG and CROPDMG
econm<-datam$PROPDMG+datam$CROPDMG
econc<-datac$PROPDMG+datac$CROPDMG
econz<-dataz$PROPDMG+dataz$CROPDMG

tempdatam<-data.frame("Damage" = econm,"Group" = "M")
tempdatac<-data.frame("Damage" = econc,"Group" = "C")
tempdataz<-data.frame("Damage" = econz,"Group" = "Z")

tempdata<-rbind(tempdatam,tempdatac,tempdataz)

tempdata<-data.frame(tempdata$Damage,M_GROUP,C_GROUP,Z_GROUP)

lm(tempdata$tempdata.Damage ~ tempdata$M_GROUP);lm(tempdata$tempdata.Damage ~ tempdata$C_GROUP);lm(tempdata$tempdata.Damage ~ tempdata$Z_GROUP)

## 
## Call:
## lm(formula = tempdata$tempdata.Damage ~ tempdata$M_GROUP)
## 
## Coefficients:
##      (Intercept)  tempdata$M_GROUP  
##            16.28            -10.08

## 
## Call:
## lm(formula = tempdata$tempdata.Damage ~ tempdata$C_GROUP)
## 
## Coefficients:
##      (Intercept)  tempdata$C_GROUP  
##            8.364             8.236

## 
## Call:
## lm(formula = tempdata$tempdata.Damage ~ tempdata$Z_GROUP)
## 
## Coefficients:
##      (Intercept)  tempdata$Z_GROUP  
##          13.5453            0.6522

From the results, the coefficient of C_GROUP is 8.2359209 which is the highest compared to other groups. Hence, the storm type C has the greatest economic consequences.

Impact of Storm Types on Health and Economy in United States

Kornpob Bhirombhakdi

August 20, 2015

Synopsis

Data Processing

Results

Q1: Across the United States, which types of (storm) events are most harmful with respect to population health?

Q2: Across the United States, which types of (storm) events have the greatest economic consequences?