PSID summary

1 Overview

1.1 Summary

This report provides an introductory examination of the Food Stamps participation trends from 1968 to 1988 using the PSID data, which assesses economic, social, and health aspects throughout the life span of families across multiple generations. First, data cleaning was performed so that the analysis is focused on the subset of survey takers who participated in the Food Stamps program. The variables I looked at are only those relevant to Food Stamps program such as income, state, family size, annual amount paid for food stamps, annual amount saved from using food stamps, annual food standards, and annual food bill. The number of observations is not constant across the years as families kept expanding.

1.2 Variable descriptions

Variable Descriptions

Variable	Description
participation	Number of food stamps participants in each year from 1969 to 1988 except 1973
weight	Weight of the sruvey
size	Family size
state	State where the family currently lives recoded to be the actual states names
food_std	Annual food needs based on the USDA Low Cost plan estimates of the weekly food costs
food_bill	Annual food expenditures excluding alcohol and cigarettes in nominal value
saved_FS	Money saved by using food stamps, which is the difference between the money spent on food stamps and the value of the food stamps purchased
income	Total annual family Money Income
paid_monthly_FS	Money spent on food stamps last month
saved_monthly_FS	Money saved using food stamps last month
avg_size	Weighted average family size across the years from 1968 to 1988 except 1973
avg_income	Weighted average nominal income across the years from 1967 to 1988 except 1973
avg_food_bill	Weighted average annual food expenditures across the years from 1968 to 1988 except 1972, 1987, and 1988
avg_saved_FS	Weighted average money saved annually from using food stamps across the years from 1967 to 1988 except 1972
avg_paid_FS	Weighted average money spent annually on food stamps across the years from 1974 to 1978
avg_paid_monthly_FS	Weighted average money spent monthly on food stamps across the years from 1975 to 1979
avg_saved_monthly_FS	Weighted average money saved monthly from using food stamps across the years from 1975 to 1987
year	Year from 1968 to 1988

2 Data Cleaning

# Data Cleaning for all datasets and renaming variables 

#participation vector to store number of food stamps participants 
participation<- c()

#1968----
PSID_1968$weight = na.omit(weights$Weight1968)
PSID_1968$STATE <-recode(PSID_1968$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_68 <- as.factor(PSID_1968$STATE)
PSID_68 <- subset(PSID_1968, PSID_1968$`YRLY FOOD STAMPS` > 0)
weight_68 <- as.numeric(PSID_68$weight)
participation <- append(participation, nrow(PSID_68))
size_68<- as.numeric(PSID_68$"FAMILY SIZE")
food_std_68= as.numeric(PSID_68$"YRLY FOOD STD.")
food_bill_68= as.numeric(PSID_68$"YRLY FOOD BILL")
saved_FS_67= as.numeric(PSID_68$"YRLY FOOD STAMPS")
income_67=as.numeric(PSID_68$"TOTAL INCOME")
state_68= as.factor(na.omit(PSID_68$"STATE"))

#Computing 1968 averages ----
avg_size_68= weighted.mean(size_68, weight_68)
avg_food_std_68= weighted.mean(food_std_68, weight_68)
avg_food_bill_68= weighted.mean(food_bill_68, weight_68)
avg_saved_FS_67= weighted.mean(saved_FS_67, weight_68)
avg_income_67= weighted.mean(income_67, weight_68)

#1969----
PSID_1969$weight = na.omit(weights$Weight1969)
PSID_1969$STATE <-recode(PSID_1969$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_69 <- as.factor(PSID_1969$STATE)
particip_68 <- nrow(subset(PSID_1969, PSID_1969$`FOOD STAMPS?` == 1))
PSID_69 <- subset(PSID_1969, PSID_1969$`SAVD FOOD STMP` > 0)
weight_69 <- as.numeric(PSID_69$weight)
participation<- append(participation, nrow(PSID_69))
size_69<- as.numeric(PSID_69$"FAMILY SIZE")
food_std_69= as.numeric(PSID_69$"YRLY FOOD STD")
food_bill_69_est= as.numeric(PSID_69$"YRLY FOOD BILL")
saved_FS_68= as.numeric(PSID_69$"SAVD FOOD STMP")
income_68=as.numeric(PSID_69$"TOTAL INCOME")
used_FS_68= as.numeric(PSID_69$"FOOD STAMPS?")
FS_participants_68= sum(used_FS_68 == 1)  
state_69= as.factor(PSID_69$"STATE")


#Computing 1969 averages ----
avg_size_69= weighted.mean(size_69, weight_69)
avg_food_std_69= weighted.mean(food_std_69, weight_69)
avg_saved_FS_68= weighted.mean(saved_FS_68, weight_69)
avg_income_68= weighted.mean(income_68, weight_69)

#1970----
PSID_1970$weight = na.omit(weights$Weight1970)
PSID_1970$STATE <-recode(PSID_1970$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_70 <- as.factor(PSID_1970$STATE)
particip_70 <- nrow(subset(PSID_1970, PSID_1970$`AMT PAID FOOD STAMPS`>0 & PSID_1970$`AMT PAID FOOD STAMPS` < 4681))
PSID_70 <- subset(PSID_1970, PSID_1970$`$  FOOD BOUGHT W/ STAMPS`>0)
weight_70 <- as.numeric(PSID_70$weight)
participation<- append(participation, nrow(PSID_70))
size_70<- as.numeric(PSID_70$"FAMILY SIZE")
food_std_70= as.numeric(PSID_70$"YRLY FOOD STD")
food_bill_69= as.numeric(PSID_70$"YRLY FOOD BILL")
saved_FS_69= as.numeric(PSID_70$"SAVD.FOOD.STMP")
income_69=as.numeric(PSID_70$"TOTAL INCOME")
paid_FS_69=as.numeric(PSID_70$"AMT PAID FOOD STAMPS")
value_FS_69=as.numeric(PSID_70$"$  FOOD BOUGHT W/ STAMPS")
FS_participants_70= sum(paid_FS_69>0)
state_70= as.factor(PSID_70$STATE)


#Computing 1970 averages ----
avg_size_70= weighted.mean(size_70, weight_70)
avg_food_std_70= weighted.mean(food_std_70, weight_70)
avg_food_bill_69= weighted.mean(food_bill_69, weight_70)
avg_saved_FS_69= weighted.mean(saved_FS_69, weight_70)
avg_income_69= weighted.mean(income_69, weight_70)
avg_paid_FS_69= weighted.mean(paid_FS_69, weight_70)
avg_value_FS_69= weighted.mean(value_FS_69, weight_70)


#1971----
PSID_1971$weight = na.omit(weights$Weight1971)
PSID_1971$STATE <-recode(PSID_1971$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_71 <- as.factor(PSID_1971$STATE)
PSID_71 <- subset(PSID_1971, PSID_1971$SAVD.FOOD.STMP> 0)
weight_71 <- as.numeric(PSID_71$weight)
participation<- append(participation, nrow(PSID_71))
size_71<- as.numeric(PSID_71$"FAMILY SIZE")
food_std_71= as.numeric(PSID_71$"YRLY FOOD STD")
food_bill_70= as.numeric(PSID_71$"YRLY FOOD BILL")
saved_FS_70= as.numeric(PSID_71$"SAVD.FOOD.STMP")
income_70=as.numeric(PSID_71$"TOTAL INCOME")
state_71= as.factor(PSID_71$STATE)

#Computing 1971 averages ----
avg_size_71= weighted.mean(size_71, weight_71)
avg_food_std_71= weighted.mean(food_std_71, weight_71)
avg_food_bill_70= weighted.mean(food_bill_70, weight_71)
avg_saved_FS_70= weighted.mean(saved_FS_70, weight_71)
avg_income_70= weighted.mean(income_70, weight_71)


#1972----
PSID_1972$weight = na.omit(weights$Weight1972)
PSID_1972$STATE <-recode(PSID_1972$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_72 <- as.factor(PSID_1972$STATE)
PSID_72 <- subset(PSID_1972, PSID_1972$`$  SAVD FD STMP`> 0)
PSID_72 <- filter(PSID_72, STATE != 0)
weight_72 <- as.numeric(PSID_72$weight)
participation<- append(participation, nrow(PSID_72))
size_72<- as.numeric(PSID_72$"FAMILY SIZE")
food_std_72= as.numeric(PSID_72$"YRLY FOOD STD")
food_bill_71= as.numeric(PSID_72$"YRLY FOOD BILL")
saved_FS_71= as.numeric(PSID_72$"$  SAVD FD STMP")
income_71=as.numeric(PSID_72$"TOTAL INCOME")
state_72= as.factor(PSID_72$"STATE")


#Computing 1972 averages ----
avg_size_72=weighted.mean(size_72, weight_72)
avg_food_std_72=weighted.mean(food_std_72, weight_72)
avg_food_bill_71=weighted.mean(food_bill_71, weight_72)
avg_saved_FS_71=weighted.mean(saved_FS_71, weight_72)
avg_income_71=weighted.mean(income_71, weight_72)


#1973----
PSID_1973$weight = na.omit(weights$Weight1973)
participation<- append(participation, NA)
size_73<- as.numeric(PSID_1973$"FAMILY SIZE")
food_std_73= as.numeric(PSID_1973$"YRLY FOOD STD")
income_72=as.numeric(PSID_1973$"TOTAL INCOME")
state_73= as.factor((PSID_1973$"STATE"))
state_73 <-recode(state_73, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")


#Computing 1973 averages ----
avg_size_73=weighted.mean(size_73, PSID_1973$weight)
avg_food_std_73=weighted.mean(food_std_73, PSID_1973$weight)
avg_income_72=weighted.mean(income_72, PSID_1973$weight)



#1974----
PSID_1974$weight = na.omit(weights$Weight1974)
PSID_1974$STATE <-recode(PSID_1974$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_74 <- as.factor(PSID_1974$STATE)
PSID_74 <- subset(PSID_1974, PSID_1974$`AMT SAVD FD STMP`> 0)
PSID_74 <- filter(PSID_74, STATE != 0)
weight_74 <- as.numeric(PSID_74$weight)
participation<- append(participation, nrow(PSID_74))
particip_73 <- nrow(subset(PSID_1974, PSID_1974$`FREQ USE FD STAMPS` != 0 & PSID_1974$`FREQ USE FD STAMPS` != 9 & PSID_1974$`FREQ USE FD STAMPS` != 5))
#yielded a different number of observations
size_74<- as.numeric(PSID_74$"FAMILY SIZE")
food_std_74= as.numeric(PSID_74$"YRLY FOOD STD")
food_bill_73= as.numeric(PSID_74$"YRLY FOOD BILL")
income_73=as.numeric(PSID_74$"TOTAL INCOME")
saved_FS_73= as.numeric(PSID_74$"AMT SAVD FD STMP")
frequency_FS_73= as.numeric(PSID_74$"FREQ USE FD STAMPS")
FS_participants_73= sum((frequency_FS_73) != 0 & (frequency_FS_73) != 5)
state_74= as.factor((PSID_74$STATE))


#Computing 1974 averages ----
avg_size_74=weighted.mean(size_74, weight_74)
avg_food_std_74=weighted.mean(food_std_74, weight_74)
avg_food_bill_73=weighted.mean(food_bill_73, weight_74)
avg_income_73=weighted.mean(income_73, weight_74)
avg_saved_FS_73=weighted.mean(saved_FS_73, weight_74)

#1975----
PSID_1975$weight = na.omit(weights$Weight1975)
PSID_1975$STATE <-recode(PSID_1975$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_75 <- as.factor(PSID_1975$STATE)
PSID_75 <- subset(PSID_1975, PSID_1975$`$  SAVD FDST`> 0)
PSID_75 <- filter(PSID_75, STATE != 0)
weight_75 <- as.numeric(PSID_75$weight)
participation<- append(participation, nrow(PSID_75))
size_75<- as.numeric(PSID_75$"FAMILY SIZE")
food_std_75= as.numeric(PSID_75$"YRLY FOOD STD")
food_bill_74= as.numeric(PSID_75$"YRLY FOOD BILL")
income_74=as.numeric(PSID_75$"TOTAL INCOME")
monthly_paid_FS_75= as.numeric(PSID_75$`$FD STMP LASTMO`)
monthly_saved_FS_75= as.numeric(PSID_75$`$ SAVD LASMO FDST`)
paid_FS_74=as.numeric(PSID_75$"$  FD STMP")
saved_FS_74= as.numeric(PSID_75$"$  SAVD FDST")
state_75= as.factor((PSID_75$STATE))


#Computing 1975 averages ----
avg_size_75=weighted.mean(size_75, weight_75)
avg_food_std_75=weighted.mean(food_std_75, weight_75)
avg_food_bill_74=weighted.mean(food_bill_74, weight_75)
avg_income_74=weighted.mean(income_74, weight_75)
avg_paid_FS_74=weighted.mean(paid_FS_74, weight_75)
avg_saved_FS_74=weighted.mean(saved_FS_74, weight_75)
avg_monthly_paid_FS_75=weighted.mean(monthly_paid_FS_75, weight_75)
avg_monthly_saved_FS_75=weighted.mean(monthly_saved_FS_75, weight_75)


#1976----
PSID_1976$weight = na.omit(weights$Weight1976)
PSID_1976$STATE <-recode(PSID_1976$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_76 <- as.factor(PSID_1976$STATE)
#Why is this yielding a different number of participants
particip_75 <- nrow(subset(PSID_1976, PSID_1976$`# MO FDSTAMP IN 75`> 0))
PSID_76 <- subset(PSID_1976, PSID_1976$`SAVD FDSTA 75`> 0)
PSID_76 <- filter(PSID_76, STATE != 0)
weight_76 <- as.numeric(PSID_76$weight)
participation<- append(participation, nrow(PSID_76))
size_76<- as.numeric(PSID_76$"FAMILY SIZE")
food_std_76= as.numeric(PSID_76$"YRLY FOOD STD")
food_bill_75= as.numeric(PSID_76$"YRLY FOOD BILL")
income_75=as.numeric(PSID_76$"TOTAL INCOME")
paid_FS_75=as.numeric(PSID_76$"SPENT FDSTA 75")
saved_FS_75= as.numeric(PSID_76$"SAVD FDSTA 75")
monthly_paid_FS_76= as.numeric(PSID_76$"$PAID FOR STAMPS")
monthly_saved_FS_76= as.numeric(PSID_76$"$SAV FDSTAM LASTMO")
frequency_FS_75= as.numeric(PSID_76$"# MO FDSTAMP IN 75")
FD_recipients_family_75=  as.numeric(PSID_76$"NUMBER FD RECIPIENTS")
FS_participants_75= sum(((frequency_FS_75) != 0 & (frequency_FS_75) != 5))
state_76= as.factor((PSID_76$STATE))

#computing 1976 averages----
avg_size_76=weighted.mean(size_76, weight_76)
avg_food_std_76=weighted.mean(food_std_76, weight_76)
avg_food_bill_75=weighted.mean(food_bill_75, weight_76)
avg_income_75=weighted.mean(income_75, weight_76)
avg_paid_FS_75=weighted.mean(paid_FS_75, weight_76)
avg_saved_FS_75=weighted.mean(saved_FS_75, weight_76)
avg_monthly_paid_FS_76=weighted.mean(monthly_paid_FS_76, weight_76)
avg_monthly_saved_FS_76=weighted.mean(monthly_saved_FS_76, weight_76) 
avg_frequency_FS_75= weighted.mean(frequency_FS_75, weight_76)


#1977----
PSID_1977$weight = na.omit(weights$Weight1977)
PSID_1977$STATE <-recode(PSID_1977$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii") 
STATE_77 <- as.factor(PSID_1977$STATE)
PSID_77 <- subset(PSID_1977, PSID_1977$`BONUS $  FD STAMPS 76` > 0)
particip_76 <- nrow(subset(PSID_1977, PSID_1977$"WTR FD STMPS IN 76" == 1))
particip_76_mos <- nrow(subset(PSID_1977, PSID_1977$`# MONTHS USED STAMPS  76`> 0 & PSID_1977$`# MONTHS USED STAMPS  76`< 13))
particip_76_paid <- nrow(subset(PSID_1977, PSID_1977$`$  PAID FD STAMPS 76` >0))
PSID_77 <- filter(PSID_77, STATE != 0)
weight_77 <- as.numeric(PSID_77$weight)
participation<- append(participation, nrow(PSID_77))
size_77<- as.numeric(PSID_77$"FAMILY SIZE")
food_std_77= as.numeric(PSID_77$"YRLY FOOD STD")
food_bill_76= as.numeric(PSID_77$"ANNUAL FOOD$  EXCL FDSTMP")
income_76=as.numeric(PSID_77$"TOTAL FAMILY INCOME")
paid_FS_76=as.numeric(PSID_77$"$  PAID FD STAMPS 76")
saved_FS_76= as.numeric(PSID_77$"BONUS $  FD STAMPS 76")
monthly_paid_FS_77= as.numeric(PSID_77$"$  PAID FD STAMP LAST MO")
monthly_saved_FS_77= as.numeric(PSID_77$"$  BONUS FD STAMP LAST MO")
frequency_FS_76= as.numeric(PSID_77$"# MONTHS USED STAMPS  76")
FS_participants_76= sum((frequency_FS_76) != 0)
state_77= as.factor((PSID_77$STATE))
eligibility_76= as.factor(PSID_1977$`WTR ELIG FD STMPS`)

#computing 1977 averages ---- 
avg_size_77=weighted.mean(size_77, weight_77)
avg_food_std_77=weighted.mean(food_std_77, weight_77)
avg_food_bill_76=weighted.mean(food_bill_76, weight_77)
avg_income_76=weighted.mean(income_76, weight_77)
avg_paid_FS_76=weighted.mean(paid_FS_76, weight_77)
avg_saved_FS_76=weighted.mean(saved_FS_76, weight_77)
avg_monthly_paid_FS_77=weighted.mean(monthly_paid_FS_77, weight_77)
avg_monthly_saved_FS_77=weighted.mean(monthly_saved_FS_77, weight_77)



#1978----
PSID_1978$weight = na.omit(weights$Weight1978)
PSID_1978$STATE <-recode(PSID_1978$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_78 <- as.factor(PSID_1978$STATE)
PSID_78 <- subset(PSID_1978, PSID_1978$`BONUS FDSTMP 77`> 0)
particip_77 <- nrow(subset(PSID_1978, PSID_1978$`# MONTHS USED FDSTMP 77` > 0))
particip_77_paid <- nrow(subset(PSID_1978, PSID_1978$`PAID FDSTMP 77` > 0))
PSID_78 <- filter(PSID_78, STATE != 0)
weight_78 <- as.numeric(PSID_78$weight)
participation<- append(participation, nrow(PSID_78))
size_78<- as.numeric(PSID_78$"FAMILY SIZE" )
food_std_78= as.numeric(PSID_78$"YRLY FOOD STD")
food_bill_77= as.numeric(PSID_78$"ANN FD $  EXCL FDSTMP")
income_77=as.numeric(PSID_78$"TOTAL FAMILY INCOME")
paid_FS_77=as.numeric(PSID_78$"PAID FDSTMP 77")
saved_FS_77= as.numeric(PSID_78$"BONUS FDSTMP 77")
monthly_paid_FS_78= as.numeric(PSID_78$"$  PAID FD ST LAST MO")
monthly_saved_FS_78= as.numeric(PSID_78$"$  BONUS PD ST LAST MO")
frequency_FS_77= as.numeric(PSID_78$"# MONTHS USED FDSTMP 77")
FD_recipients_family_78=  as.numeric(PSID_78$"# FD ST ISSUED FOR")
FS_participants_77= sum((frequency_FS_77) != 0)
state_78= as.factor((PSID_78$STATE))


#computing 1978 averages ----
avg_size_78=weighted.mean(size_78, weight_78)
avg_food_std_78=weighted.mean(food_std_78, weight_78)
avg_food_bill_77=weighted.mean(food_bill_77, weight_78)
avg_income_77=weighted.mean(income_77, weight_78)
avg_paid_FS_77=weighted.mean(paid_FS_77, weight_78)
avg_saved_FS_77=weighted.mean(saved_FS_77, weight_78)
avg_monthly_paid_FS_78=weighted.mean(monthly_paid_FS_78, weight_78)
avg_monthly_saved_FS_78=weighted.mean(monthly_saved_FS_78, weight_78)


#1979----
PSID_1979$weight = na.omit(weights$Weight1979)
PSID_1979$STATE <-recode(PSID_1979$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_79 <- as.factor(PSID_1979$STATE)
PSID_79 <- subset(PSID_1979, PSID_1979$`BONUS FDSTMP 78`> 0)
particip_78 <- nrow(subset(PSID_1979, PSID_1979$`# MOS USED FDSTMP 78`> 0 &  PSID_1979$`# MOS USED FDSTMP 78` < 13))
particip_78_paid <-nrow(subset(PSID_1979, PSID_1979$`PAID FDSTMP 78`> 0 ))
PSID_79 <- filter(PSID_79, STATE != 0)
weight_79 <- as.numeric(PSID_79$weight)
participation<- append(participation, nrow(PSID_79))
size_79<- as.numeric(PSID_79$"FAMILY SIZE")
food_std_79= as.numeric(PSID_79$"YRLY FOOD STD")
food_bill_78= as.numeric(PSID_79$"ANN FD $  EXCL FDSTMP")
income_78=as.numeric(PSID_79$"TOTAL FAMILY INCOME")
paid_FS_78=as.numeric(PSID_79$"PAID FDSTMP 78")
saved_FS_78= as.numeric(PSID_79$"BONUS FDSTMP 78")
monthly_paid_FS_79= as.numeric(PSID_79$"$  PD FD ST LAST MO" )
monthly_saved_FS_79= as.numeric(PSID_79$"$  BONUS PD LAST MO")
frequency_FS_78= as.numeric(PSID_79$"# MOS USED FDSTMP 78")
FD_recipients_family_79=as.numeric(PSID_79$"# FD ST ISSUED FOR")
FS_participants_78= sum(frequency_FS_78 != 0)
state_79= as.factor(PSID_79$STATE)


#computing 1979 averages ----
avg_size_79=weighted.mean(size_79, weight_79)
avg_food_std_79=weighted.mean(food_std_79, weight_79)
avg_food_bill_78=weighted.mean(food_bill_78, weight_79)
avg_income_78=weighted.mean(income_78, weight_79)
avg_paid_FS_78=weighted.mean(paid_FS_78, weight_79)
avg_saved_FS_78=weighted.mean(saved_FS_78, weight_79)
avg_monthly_paid_FS_79=weighted.mean(monthly_paid_FS_79, weight_79)
avg_monthly_saved_FS_79=weighted.mean(monthly_saved_FS_79, weight_79)



#1980----
PSID_1980$weight = na.omit(weights$Weight1980)
PSID_1980$STATE <-recode(PSID_1980$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
PSID_1980 <- PSID_1980 %>% rename('WTR ELIG FD STMPS' = `ELGBL FOR FD STMPS`)
STATE_80 <- as.factor(PSID_1980$STATE)
PSID_80 <- subset(PSID_1980, PSID_1980$`VALUE FD ST 79`> 0)
particip_79 <- nrow(subset(PSID_1980, PSID_1980$`# MOS USED FD STMP 79`> 0 & PSID_1980$`# MOS USED FD STMP 79`< 13 ))
PSID_80 <- filter(PSID_80, STATE != 0)
weight_80 <- as.numeric(PSID_80$weight)
participation<- append(participation, nrow(PSID_80))
size_80<- as.numeric(PSID_80$"FAMILY SIZE")
food_std_80= as.numeric(PSID_80$"YRLY FOOD STD")
food_bill_79= as.numeric(PSID_80$"ANN FD $  EXCL FD STMP")
income_79=as.numeric(PSID_80$"TOTAL FAMILY INCOME")
saved_FS_79= as.numeric(PSID_80$"VALUE FD ST 79")
monthly_saved_FS_80= as.numeric(PSID_80$"$ VLUE FD ST LST MO")
frequency_FS_79= as.numeric(PSID_80$"# MOS USED FD STMP 79")
FD_recipients_family_80=as.numeric(PSID_80$"# FD ST ISSUED FOR")
FS_participants_79= sum(frequency_FS_79 != 0)
eligibility_79= as.factor(PSID_1980$`WTR ELIG FD STMPS`)
state_80= as.factor(PSID_80$STATE)

#computing 1980 averages ----
avg_size_80=weighted.mean(size_80, weight_80)
avg_food_std_80=weighted.mean(food_std_80, weight_80)
avg_food_bill_79=weighted.mean(food_bill_79, weight_80)
avg_income_79=weighted.mean(income_79, weight_80)
avg_saved_FS_79=weighted.mean(saved_FS_79, weight_80)
avg_monthly_saved_FS_80=weighted.mean(monthly_saved_FS_80, weight_80)


#1981----
PSID_1981$weight = na.omit(weights$Weight1981)
PSID_1981$STATE <-recode(PSID_1981$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
PSID_1981 <- PSID_1981 %>%rename('WTR ELIG FD STMPS'= `WTR ELGBL FOOD STAMP`)
STATE_81 <- as.factor(PSID_1981$STATE)
PSID_81 <- subset(PSID_1981, PSID_1981$`VALUE FOOD STMPS 80`> 0)
particip_80 <- nrow(subset(PSID_1981, PSID_1981$`# MOS USED FD ST`> 0 & PSID_1981$`# MOS USED FD ST`< 13))
PSID_81 <- filter(PSID_81, STATE != 0)
weight_81 <- as.numeric(PSID_81$weight)
participation<- append(participation, nrow(PSID_81))
size_81= as.numeric(PSID_81$"FAMILY SIZE")
food_std_81= as.numeric(PSID_81$"YRLY FOOD STD")
food_bill_80= as.numeric(PSID_81$"ANN FD $ $  EXC FD STMP")
income_80=as.numeric(PSID_81$"TOTAL FAMILY INCOME")
saved_FS_80= as.numeric(PSID_81$"VALUE FOOD STMPS 80")
monthly_saved_FS_81= as.numeric(PSID_81$"$ $  VALU FD ST LST MO")
frequency_FS_80= as.numeric(PSID_81$"# MOS USED FD ST")
FD_recipients_family_81=as.numeric(PSID_81$"# PERSONS GOT FOOD STAMP")
eligibility_80= as.factor(PSID_1981$`WTR ELIG FD STMPS`)
FS_participants_80= sum(frequency_FS_80 != 0)
state_81= as.factor(PSID_81$STATE)


#computing 1981 averages ----
avg_size_81=weighted.mean(size_81, weight_81)
avg_food_std_81=weighted.mean(food_std_81, weight_81)
avg_food_bill_80=weighted.mean(food_bill_80, weight_81)
avg_income_80=weighted.mean(income_80, weight_81)
avg_saved_FS_80=weighted.mean(saved_FS_80, weight_81)
avg_monthly_saved_FS_81=weighted.mean(monthly_saved_FS_81, weight_81)


#1982----
PSID_1982$weight = na.omit(weights$Weight1982)
PSID_1982$STATE <-recode(PSID_1982$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_82 <- as.factor(PSID_1982$STATE)
PSID_82 <- subset(PSID_1982, PSID_1982$`VALUE FD ST 81`> 0)
particip_81 <- nrow(subset(PSID_1982, PSID_1982$`# MOS USED FD ST 81`> 0 & PSID_1982$`# MOS USED FD ST 81`< 13 ))
PSID_82 <- filter(PSID_82, STATE != 0)
weight_82 <- as.numeric(PSID_82$weight)
participation<- append(participation, nrow(PSID_82))
size_82= as.numeric(PSID_82$"FAMILY SIZE")
food_std_82= as.numeric(PSID_82$"ANNUAL FOOD STD")
food_bill_81= as.numeric(PSID_82$"ANN FOOD COST EXC FD ST" )
income_81=as.numeric(PSID_82$"TOTAL FAMILY INCOME")
saved_FS_81= as.numeric(PSID_82$"VALUE FD ST 81")
monthly_saved_FS_82= as.numeric(PSID_82$"VALUE FD ST LAST MO")
frequency_FS_81= as.numeric(PSID_82$"# MOS USED FD ST 81")
FD_recipients_family_82=as.numeric(PSID_82$"# PERSONS GOT FOOD STAMP")
FS_participants_81= sum(frequency_FS_81 != 0)
state_82= as.factor(PSID_82$STATE)

#computing 1982 averages ----
avg_size_82=weighted.mean(size_82, weight_82)
avg_food_std_82=weighted.mean(food_std_82, weight_82)
avg_food_bill_81=weighted.mean(food_bill_81, weight_82)
avg_income_81=weighted.mean(income_81, weight_82)
avg_saved_FS_81=weighted.mean(saved_FS_81, weight_82)
avg_monthly_saved_FS_82=weighted.mean(monthly_saved_FS_82, weight_82)



#1983----
PSID_1983$weight = na.omit(weights$Weight1983)
PSID_1983$STATE <-recode(PSID_1983$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
PSID_1983 <- PSID_1983 %>% rename('WTR ELIG FD STMPS'= `IG FD STMP 82`)
STATE_83 <- as.factor(PSID_1983$STATE)
PSID_83 <- subset(PSID_1983, PSID_1983$`VALUE FD ST 82`> 0)
particip_82 <- nrow(subset(PSID_1983, PSID_1983$`# MOS USED FD ST 82`> 0 & PSID_1983$`# MOS USED FD ST 82`< 13))
PSID_83 <- filter(PSID_83, STATE != 0)
weight_83 <- as.numeric(PSID_83$weight)
participation<- append(participation, nrow(PSID_83))
size_83= as.numeric(PSID_83$"FAMILY SIZE")
food_std_83= as.numeric(PSID_83$"ANNUAL FOOD STD")
food_bill_82= as.numeric(PSID_83$"ANN FOOD COST EXC FD ST")
income_82=as.numeric(PSID_83$"TOTAL FAMILY INCOME")
saved_FS_82= as.numeric(PSID_83$"VALUE FD ST 82")
monthly_saved_FS_83= as.numeric(PSID_83$"VALUE FD ST LAST MO" )
frequency_FS_82= as.numeric(PSID_83$"# MOS USED FD ST 82")
FD_recipients_family_83=as.numeric(PSID_83$"# PERSONS GOT FOOD STAMP")
FS_participants_82= sum(frequency_FS_82 != 0)
eligibility_82= as.factor(PSID_1983$`WTR ELIG FD STMPS`)
state_83= as.factor(PSID_83$STATE)

#computing 1983 averages ----
avg_size_83=weighted.mean(size_83, weight_83)
avg_food_std_83=weighted.mean(food_std_83, weight_83)
avg_food_bill_82=weighted.mean(food_bill_82, weight_83)
avg_income_82=weighted.mean(income_82, weight_83)
avg_saved_FS_82=weighted.mean(saved_FS_82, weight_83)
avg_monthly_saved_FS_83=weighted.mean(monthly_saved_FS_83, weight_83)



#1984----
PSID_1984$weight = na.omit(weights$Weight1984)
PSID_1984$STATE <-recode(PSID_1984$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_84 <- as.factor(PSID_1984$STATE)
PSID_84 <- subset(PSID_1984, PSID_1984$`VALUE FD ST 83`> 0)
particip_83 <- nrow(subset(PSID_1984, PSID_1984$`# MOS USED FD ST 83`> 0 &  PSID_1984$`# MOS USED FD ST 83`< 13))
PSID_84 <- filter(PSID_84, STATE != 0)
weight_84 <- as.numeric(PSID_84$weight)
participation<- append(participation, nrow(PSID_84))
size_84= as.numeric(PSID_84$"FAMILY SIZE")
food_std_84= as.numeric(PSID_84$"ANNUAL FOOD STD")
food_bill_83= as.numeric(PSID_84$"ANN FOOD COST EXC FD ST")
income_83=as.numeric(PSID_84$"TOTAL FAMILY INCOME")
saved_FS_83= as.numeric(PSID_84$"VALUE FD ST 83")
monthly_saved_FS_84= as.numeric(PSID_84$"VALUE FD ST LAST MO")
frequency_FS_83= as.numeric(PSID_84$"# MOS USED FD ST 83")
FD_recipients_family_84=as.numeric(PSID_84$"# PERS GOT FD ST LAST MO")
FS_participants_83= sum(frequency_FS_83 != 0)
state_84= as.factor(PSID_84$STATE)


#computing 1984 averages ----
avg_size_84=weighted.mean(size_84, weight_84)
avg_food_std_84=weighted.mean(food_std_84, weight_84)
avg_food_bill_83=weighted.mean(food_bill_83, weight_84)
avg_income_83=weighted.mean(income_83, weight_84)
avg_saved_FS_83=weighted.mean(saved_FS_83, weight_84)
avg_monthly_saved_FS_84=weighted.mean(monthly_saved_FS_84, weight_84)



#1985----
PSID_1985$weight = na.omit(weights$Weight1985)
PSID_1985$STATE <-recode(PSID_1985$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_85 <- as.factor(PSID_1985$STATE)
PSID_85 <- subset(PSID_1985, PSID_1985$`VALUE FD ST 84`> 0)
particip_84 <- nrow(subset(PSID_1985, PSID_1985$`# MOS USED FD ST 84`> 0 & PSID_1985$`# MOS USED FD ST 84`< 13))
weight_85 <- as.numeric(PSID_85$weight)
participation<- append(participation, nrow(PSID_85))
size_85= as.numeric(PSID_85$"FAMILY SIZE")
food_std_85= as.numeric(PSID_85$"YRLY FOOD STD")
food_bill_84= as.numeric(PSID_85$"ANN FOOD COST EXC FD ST")
income_84=as.numeric(PSID_85$"TOTAL FAMILY INCOME")
saved_FS_84= as.numeric(PSID_85$"VALUE FD ST 84")
monthly_saved_FS_85= as.numeric(PSID_85$"VALUE FD ST LAST MO")
frequency_FS_84= as.numeric(PSID_85$"# MOS USED FD ST 84")
FD_recipients_family_85=as.numeric(PSID_85$"# PERSONS GOT FOOD STAMP")
FS_participants_84= sum(frequency_FS_84 != 0)
state_85= as.factor(PSID_85$STATE)

#computing 1985 averages ----
avg_size_85=weighted.mean(size_85, weight_85)
avg_food_std_85=weighted.mean(food_std_85, weight_85)
avg_food_bill_84=weighted.mean(food_bill_84, weight_85)
avg_income_84=weighted.mean(income_84, weight_85)
avg_saved_FS_84=weighted.mean(saved_FS_84, weight_85)
avg_monthly_saved_FS_85=weighted.mean(monthly_saved_FS_85, weight_85)


#1986----
PSID_1986$weight = na.omit(weights$Weight1986)
PSID_1986$STATE <-recode(PSID_1986$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_86 <- as.factor(PSID_1986$STATE)
PSID_86 <- subset(PSID_1986, PSID_1986$`VALUE FD ST 85`> 0)
particip_85 <- nrow(subset(PSID_1986, PSID_1986$`# MOS USED FD ST 85`> 0 & PSID_1986$`# MOS USED FD ST 85`< 13))
weight_86 <- as.numeric(PSID_86$weight)
participation<- append(participation, nrow(PSID_86))
size_86= as.numeric(PSID_86$"FAMILY SIZE")
food_std_86= as.numeric(PSID_86$"YRLY FOOD STD")
food_bill_85= as.numeric(PSID_86$"ANN FOOD COST EXC FD ST")
income_85=as.numeric(PSID_86$"TOTAL FAMILY INCOME")
saved_FS_85= as.numeric(PSID_86$"VALUE FD ST 85")
monthly_saved_FS_86= as.numeric(PSID_86$"VALUE FD ST LAST MO" )
frequency_FS_85= as.numeric(PSID_86$"# MOS USED FD ST 85")
FD_recipients_family_86=as.numeric(PSID_86$"# PERSONS GOT FOOD STAMP" )
FS_participants_85= sum(frequency_FS_85 != 0)
state_86= as.factor(PSID_86$STATE)

#computing 1986 averages ----
avg_size_86=weighted.mean(size_86, weight_86)
avg_food_std_86=weighted.mean(food_std_86, weight_86)
avg_food_bill_85=weighted.mean(food_bill_85, weight_86)
avg_income_85=weighted.mean(income_85, weight_86)
avg_saved_FS_85=weighted.mean(saved_FS_85, weight_86)
avg_monthly_saved_FS_86=weighted.mean(monthly_saved_FS_86, weight_86)


#1987----
PSID_1987$weight = na.omit(weights$Weight1987)
PSID_1987$STATE <-recode(PSID_1987$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
PSID_1987 <- PSID_1987 %>% rename('WTR ELIG FD STMPS'= `ELIG FOR FD STMPS 86`)
STATE_87 <- as.factor(PSID_1987$STATE)
PSID_87 <- subset(PSID_1987, PSID_1987$`VALUE FD ST 86`> 0)
particip_86 <- nrow(subset(PSID_1987, PSID_1987$`# MOS USED FD ST 86`> 0 & PSID_1987$`# MOS USED FD ST 86`< 13 ))
weight_87 <- as.numeric(PSID_87$weight)
participation<- append(participation, nrow(PSID_87))
size_87= as.numeric(PSID_87$"FAMILY SIZE")
food_std_87= as.numeric(PSID_87$"YRLY FOOD STD")
food_bill_86= as.numeric(PSID_87$"ANN FOOD COST EXC FD ST")
income_86=as.numeric(PSID_87$"TOTAL FAMILY INCOME")
saved_FS_86= as.numeric(PSID_87$"VALUE FD ST 86")
monthly_saved_FS_87= as.numeric(PSID_87$"VALUE FD ST LAST MO" )
frequency_FS_86= as.numeric(PSID_87$"# MOS USED FD ST 86")
FD_recipients_family_87=as.numeric(PSID_87$"# PERSONS GOT FOOD STAMP")
FS_participants_86= sum(frequency_FS_86 != 0)
state_87= as.factor(PSID_87$STATE)
eligibility_86= as.factor(PSID_1987$`WTR ELIG FD STMPS`)


#computing 1987 averages ----
avg_size_87=weighted.mean(size_87, weight_87)
avg_food_std_87=weighted.mean(food_std_87, weight_87)
avg_food_bill_86=weighted.mean(food_bill_86, weight_87)
avg_income_86=weighted.mean(income_86, weight_87)
avg_saved_FS_86=weighted.mean(saved_FS_86, weight_87)
avg_monthly_saved_FS_87=weighted.mean(monthly_saved_FS_87, weight_87)


#1988----
PSID_1988$weight = na.omit(weights$Weight1988)
PSID_1988$STATE <-recode(PSID_1988$STATE, "1"= "Alabama", "2"= "Arizona", "3"= "Arkansas", "4"= "California", "5"= "Colorado", "6"= "Connecticut", "7"= "Delaware", "8"= "District of Columbia", "9"= "Florida", "10"= "Georgia", "11"= "Idaho", "12"= "Illinois", "13"= "Indiana", "14"= "Iowa", "15"= "Kansas", "16"= "Kentucky", "17"= "Louisiana", "18"= "Maine", "19"= "Maryland", "20"= "Massachusetts", "21"= "Michigan", "22"= "Minnesota", "23"= "Mississippi", "24"= "Missouri", "25"= "Montana", "26"= "Nebraska", "27"= "Nevada", "28"= "New Hampshire", "29"= "New Jersey", "30"= "New Mexico", "31"= "New York", "32"= "North Carolina", "33"= "North Dakota", "34"= "Ohio", "35"= "Oklahoma", "36"= "Oregon", "37"= "Pennsylvania", "38"= "Rhode Island", "39"= "South Carolina", "40"= "South Dakota", "41"= "Tennessee", "42"= "Texas", "43"= "Utah", "44"= "Vermont", "45"= "Virginia", "46"= "Washington", "47"= "West Virginia", "48"= "Wisconsin", "49"= "Wyoming", "50"= "Alaska", "51"= "Hawaii")
STATE_88 <- as.factor(PSID_1988$STATE)
PSID_88 <- subset(PSID_1988, PSID_1988$`VALUE FD ST 87`> 0)
particip_87 <- nrow(subset(PSID_1988, PSID_1988$`# MOS USED FD ST 87`> 0 & PSID_1988$`# MOS USED FD ST 87`< 13 ))
weight_88 <- as.numeric(PSID_88$weight)
participation<- append(participation, nrow(PSID_88))
size_88= as.numeric(PSID_88$"FAMILY SIZE")
food_std_88= as.numeric(PSID_88$"YRLY FOOD STD")
income_87=as.numeric(PSID_88$"TOTAL FAMILY INCOME")
saved_FS_87= as.numeric(PSID_88$"VALUE FD ST 87")
frequency_FS_87= as.numeric(PSID_88$"# MOS USED FD ST 87")
FS_participants_87= sum(frequency_FS_87 != 0)
state_88= as.factor(PSID_88$STATE)


#computing 1988 averages ----
avg_size_88=weighted.mean(size_88, weight_88)
avg_food_std_88=weighted.mean(food_std_88, weight_88)
avg_income_87=weighted.mean(income_87, weight_88)
avg_saved_FS_87=weighted.mean(saved_FS_87, weight_88)


#1989----
PSID_1989$weight = na.omit(weights$Weight1989)
PSID_89 <- subset(PSID_1989, PSID_1989$`VALUE FD ST 88`> 0)
particip_88 <- nrow(subset(PSID_1989, PSID_1989$`# MOS USED FD ST 88`> 0 & PSID_1989$`# MOS USED FD ST 88`< 13))
weight_89 <- as.numeric(PSID_89$weight)
participation<- append(participation, nrow(PSID_89))
income_88=as.numeric(PSID_89$"TOTAL FAMILY INCOME")
saved_FS_88= as.numeric(PSID_89$"VALUE FD ST 88" )
frequency_FS_88= as.numeric(PSID_89$"# MOS USED FD ST 88")
FS_participants_89= sum(frequency_FS_88 != 0)


#computing 1989 averages ----
avg_income_88=weighted.mean(income_88, weight_89)
avg_saved_FS_88=weighted.mean(saved_FS_88, weight_89)

#average family size
avg_size<- c(NA, avg_size_68, avg_size_69, avg_size_70, avg_size_71, avg_size_72, avg_size_73, avg_size_74, avg_size_75, avg_size_76, avg_size_77,  avg_size_78,  avg_size_79,  avg_size_80,  avg_size_81, avg_size_82, avg_size_83, avg_size_84, avg_size_85, avg_size_86, avg_size_87, avg_size_88)

#average total family income
avg_income <- c(avg_income_67, avg_income_68, avg_income_69,avg_income_70, avg_income_71, avg_income_72, avg_income_73, avg_income_74, avg_income_75, avg_income_76, avg_income_77, avg_income_78, avg_income_79, avg_income_80, avg_income_81, avg_income_82, avg_income_83, avg_income_84, avg_income_85, avg_income_86, avg_income_87, avg_income_88)

#average annual food bill
avg_food_bill<- c(NA, avg_food_bill_68, avg_food_bill_69, avg_food_bill_70, avg_food_bill_71, NA , avg_food_bill_73, avg_food_bill_74, avg_food_bill_75, avg_food_bill_76, avg_food_bill_77, avg_food_bill_78, avg_food_bill_79, avg_food_bill_80, avg_food_bill_81, avg_food_bill_82, avg_food_bill_83, avg_food_bill_84, avg_food_bill_85, avg_food_bill_86, NA , NA)

#average amount saved by using food stamps 
avg_saved_FS<- c(avg_saved_FS_67, avg_saved_FS_68, avg_saved_FS_69, avg_saved_FS_70, avg_saved_FS_71, NA, avg_saved_FS_73, avg_saved_FS_74, avg_saved_FS_75, avg_saved_FS_76, avg_saved_FS_77, avg_saved_FS_78, avg_saved_FS_79, avg_saved_FS_80, avg_saved_FS_81, avg_saved_FS_82, avg_saved_FS_83, avg_saved_FS_84, avg_saved_FS_85, avg_saved_FS_86, avg_saved_FS_87, avg_saved_FS_88)

#average amount paid for food stamps 
avg_paid_FS<- c(NA, NA, NA, NA, NA, NA, NA, avg_paid_FS_74, avg_paid_FS_75, avg_paid_FS_76, avg_paid_FS_77, avg_paid_FS_78, NA, 0, 0, 0, 0, 0, 0, 0, 0, 0)

#average amount paid monthly for food stamps 
avg_paid_monthly_FS <-c(NA, NA, NA, NA, NA, NA, NA, NA, avg_monthly_paid_FS_75, avg_monthly_paid_FS_76, avg_monthly_paid_FS_77, avg_monthly_paid_FS_78, avg_monthly_paid_FS_79, 0, 0, 0, 0, 0, 0, 0, 0, 0)

#average amount saved monthly by using food stamps
avg_saved_monthly_FS<-c(NA, NA, NA, NA, NA, NA, NA, NA, avg_monthly_saved_FS_75, avg_monthly_saved_FS_76, avg_monthly_saved_FS_77, avg_monthly_saved_FS_78, avg_monthly_saved_FS_79, avg_monthly_saved_FS_80, avg_monthly_saved_FS_81, avg_monthly_saved_FS_82, avg_monthly_saved_FS_83, avg_monthly_saved_FS_84, avg_monthly_saved_FS_85, avg_monthly_saved_FS_86, avg_monthly_saved_FS_87, NA)

#year variable
year<- c(1967:1988)

#creating a data frame for necessary variables
df <- data.frame(year, participation, avg_size, avg_income, avg_food_bill, avg_saved_FS, avg_paid_FS, avg_paid_monthly_FS, avg_saved_monthly_FS)

3 Graphs and Figures

# Figures

# participation by year
participation_plot <- ggplot(data=df) +
  geom_point(aes(x=year, y=participation)) +
  # ggtitle("Number of Food Stamp Participants in the PSID data") +
  theme_classic()


#average amount of money paid annually for food stamps
FS_paid_plot_1 <- ggplot(df, aes(year, avg_paid_FS)) +
  geom_point(aes(colour = cut(avg_paid_FS, c(-Inf, 0, Inf)))) +
  scale_color_manual(values = c("(-Inf,0]" = "red","(0, Inf]" = "black"),
                     labels = c("estimated", "actual")) +
  theme_classic()


#average amount of money paid monthly for food stamps
FS_paid_plot_2 <- ggplot(df, aes(year, avg_paid_monthly_FS)) +
  geom_point(aes(colour = cut(avg_paid_monthly_FS, c(-Inf, 0, Inf)))) +
  scale_color_manual(values = c("(-Inf,0]" = "red","(0, Inf]" = "black"),
                     labels = c("estimated", "actual")) +
  theme_classic()


#average amount of money saved annualy from stamps by year
FS_saved_plot_1 <- ggplot(data=df) +
  geom_point(aes(x=year, y=avg_saved_FS)) +
  theme_classic()


#average amount of money saved monthly from stamps by year
FS_saved_plot_2 <- ggplot(data=df) +
  geom_point(aes(x=year, y=avg_saved_monthly_FS)) +
  theme_classic()

3.1 Participation rates by State

#calculate participation rates

# Create an empty list to store participation rates for each year
participation_rates_list <- list()

#define cut off levels 
cutoffs <- c(0, 15, 40, 70, Inf)
labels <- c("low", "medium", "high", "very high")

# Iterate over each year from 1968 to 1989
for (year in 68:88) {
  if (year != 73) {
  freq <- table(get(paste0("state_", year)))
  total <- table(get(paste0('STATE_', year)))  
  
  data_1 <- data.frame(
    state = tolower(names(freq)),
    participants = freq
  )
  
  data_2 <- data.frame(
    state = tolower(names(total)),
    population = total
  )
  
  merged_data <- merge(data_1, data_2, by = "state", all.x = TRUE)
  
  # Calculate the participation rate for the current year
  participation_rate <- (merged_data$participants.Freq / merged_data$population.Freq) * 100

  
  # Store the participation rate in the list
  participation_rates_list[[as.character(year)]] <- participation_rate
  
  state_data <- data.frame(
  state = tolower(names(freq)),
  category = cut(as.numeric(participation_rate), breaks = cutoffs, labels = labels,         include.lowest = TRUE)
   )

 temp <- plot_usmap(regions = "state", data= state_data, values = "category",color="grey")+ 
  theme(panel.background = element_rect(colour = "black")) +
  scale_fill_manual(values = c("lightblue2", "steelblue1", "steelblue4", "blue3"))+
  theme(legend.position = "right")
 assign(paste0("map_19", year), temp)
 
  }
}

The following maps show Food Stamps participation rates by State as per the PSID data every year from 1967 to 1988 except 1972 in a chronological order

Food Stamps Participation rates across the US in 1968

Food Stamps Participation rates across the US in 1969

Food Stamps Participation rates across the US in 1970

Food Stamps Participation rates across the US in 1971

Food Stamps Participation rates across the US in 1972

Food Stamps Participation rates across the US in 1974

Food Stamps Participation rates across the US in 1975

Food Stamps Participation rates across the US in 1976

Food Stamps Participation rates across the US in 1977

Food Stamps Participation rates across the US in 1978

Food Stamps Participation rates across the US in 1979

Food Stamps Participation rates across the US in 1980

Food Stamps Participation rates across the US in 1981

Food Stamps Participation rates across the US in 1982

Food Stamps Participation rates across the US in 1983

Food Stamps Participation rates across the US in 1984

Food Stamps Participation rates across the US in 1985

Food Stamps Participation rates across the US in 1986

Food Stamps Participation rates across the US in 1987

Food Stamps Participation rates across the US in 1988

3.2 Food Stamp Participation trends

This plot shows the number of Food Stamps participants across the year. Notice that 1972 is missing its data point since there was no information collected about food stamps for that year.

Number of Food Stamp Participants in the PSID samples each year

This plot shows the weighted average annual amount of money spent on food stamps in nominal values across the years. Data was collected for the period from 1974 to 1978, as people stopped paying for food stamps after the 1977 act was officially implemented.

Annual Food Stamps Purchases

This plot shows the weighted average monthly amount of money spent on food stamps in nominal values across the years. Data was collected for the period from 1974 to 1979. It is contradictory to see that people still paid for food stamps in 1979 although the PSID survey stopped tracking annual food stamps purchases since the 1977 ACT eliminated the purchasing requirements.

Monthly Food Stamps Purchases

This plot shows the weighted average annual amount of money saved by using food stamps in nominal values across the years. Data was collected for the period from 1967 to 1988 except 1972, since there was no data collected on food stamps usage for that year. This variable is provided by the PSID data and is defined to be the difference between the monetary value of food purchased using food stamps and the money spent on food stamps

Average amount of money saved annually by using food stamps

This plot shows the weighted average monthly amount of money saved from using food stamps in nominal value across the years. This variable is provided by the PSID data and is defined to be the difference between the monetary value of food purchased using food stamps and the money spent on food stamps.

Average amount of money saved monthly by using food stamps

4 Potential limitations to consider

The number of food stamps participants was calculated based on the variables available for each year. For consistency, I consider those who saved an amount of money greater than 0 from using food stamps in a particular year to be food stamps participants for that year. “The SAVD_FS” variable was available in PSID for all years from 1967 to 1990 except 1973.

It is worth mentioning that there were other variables that tracked food stamps participation such as the number of months a family used food stamps or the amount of money spent on food stamps. I expected that calculating the number of participants who saved a positive amount of money from using food stamps in a specific year would yield the the same result as calculating the number of participants who used food stamps in at least one month throughout the same year. However, that was not always the case. I tried comparing the number of participants using other variables in addition to the number of months but there have been some discrepancies, which are illustrated in the table below.

4.1 Food Stamps participants according to different variables

Calculation of Food Stamps participants

saved_FS	used_FS?	# Months used FS	paid_FS
291	291
834			522
730		674
931		360
892	895	884	854
811		814	778
847		840	758
1013		1003
1067		1059
1064		1058
1144		1124
1090		1067
966		949
915		903
939		935
898		884
821		818

4.2 Eligibility by income levels based on PSID data

I was interested to know how many people in the sample knew that there were eligible each year and compare that number to the total number of food stamps participants in the same sample. Eligibility for Food Stamps Program was recorded in the PSID data only for 1976, 1979, 1980, 1982, and 1986.

Food Stamps eligibility vs actual participation

year	participated	eligible	maybe eligible	Don’t know if eligible
1976	892	667	214	316
1979	1013	650	219	430
1980	1067	653	179	454
1979	1064	587	188	335
1986	939	597	177	258

5 Income threshold levels obtained from PSID data

After running initial simple comparison to calculate the minimum income of those who reported that they were ineligible for food stamps in 1976, 1979, 1980, 1982, and 1986. The minimum value was $1 or less in all 5 years. Upon exclusion of the value $1, new income threshold levels were obtained. They are displayed in the table below.

# Computing income threshold levels based on the eligibility status 

threshold_income_76 <- min(PSID_1977$'TOTAL FAMILY INCOME'[PSID_1977$`WTR ELIG FD STMPS`== 5 & PSID_1977$'TOTAL FAMILY INCOME' != 1])
threshold_income_79 <- min(PSID_1980$'TOTAL FAMILY INCOME'[PSID_1980$`WTR ELIG FD STMPS`== 5 & PSID_1980$'TOTAL FAMILY INCOME' != 1])
threshold_income_80 <- min(PSID_1981$'TOTAL FAMILY INCOME' [PSID_1981$`WTR ELIG FD STMPS`== 5 & PSID_1981$'TOTAL FAMILY INCOME' != 1])
threshold_income_82 <- min(PSID_1983$`TOTAL FAMILY INCOME`[PSID_1983$`WTR ELIG FD STMPS`== 5 & PSID_1983$`TOTAL FAMILY INCOME` != 1])
threshold_income_86 <- min(PSID_1987$`TOTAL FAMILY INCOME`[PSID_1987$`WTR ELIG FD STMPS`== 5 & PSID_1987$`TOTAL FAMILY INCOME` != 1])



cols <- c("year", "thresold income")
inc_76<-c("1976", threshold_income_76)
inc_79<-c("1979", threshold_income_79)
inc_80<-c("1980", threshold_income_80)
inc_82<-c("1982", threshold_income_82)
inc_86<-c("1986", threshold_income_86)


table4 <- rbind(inc_76, inc_79, inc_80, inc_82, inc_86)

Income Threshold levels for Food Stamps Program Eligibility

1976	150
1979	61
1980	90
1982	200
1986	71

6 Income Threshold levels by state

# yrs<- c(1977, 1980, 1981, 1983, 1987)
# # Create a list of the data frames
# data_frames <- list(PSID_1977, PSID_1980, PSID_1981, PSID_1983, PSID_1987)
# 
# # Function to calculate threshold income for a specific year and state
# get_threshold_income <- function(data, year, state) {
#   min_income <- min(data$'TOTAL FAMILY INCOME'[data$'WTR ELIG FD STMPS' == 5 & data$'TOTAL FAMILY INCOME' != 1 & get(paste0('state_', year)) == state])
#   return(list(year = year, state = state, threshold_income = min_income))
# }
# 
# # Create an empty list to store the threshold incomes
# threshold_incomes <- list()
# 
# # Loop through each year and calculate the threshold income for each state
# for (year in yrs) {
# data <- data_frames[[year]]
# yr= year-1900
# states_available <- unique(get(paste0('STATE_',yr)))
#   
#   # Loop through each state in the current year
#   for (state in states_available) {
#     threshold_income <- get_threshold_income(data, year, state)
#     threshold_incomes <- c(threshold_incomes, threshold_income)
#   }
# }
# 
# # Convert the list to a data frame
# threshold_incomes_df <- do.call(rbind.data.frame, threshold_incomes)