San Antonio Measles: 1923-1948

alpha = 0.98

SAN <- read.csv("C:/Users/Lisa/Desktop/677/SAN.csv", header = TRUE, stringsAsFactors = FALSE)

SAN <- SAN[seq(1, length(SAN$CASES.i), by = 2), ]

## definition of school indicator
SCH <- c(-1, -1, 1, 1, 1, 1, 1, 1, 1, 1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 
    1, 1, 1, 1, 1, 1, -1)

SCH <- rep(SCH, length(SAN$CASES))[1:length(SAN$CASES)]

SAN$SCH <- SCH

## to analyze a subset of the data
SAN <- SAN[c(1:length(SAN$CASES)), ]

SAN$CASES <- as.numeric(SAN$CASES)
SAN$CASES.i <- as.numeric(SAN$CASES.i)
SAN$TMAX <- as.numeric(SAN$TMAX)
SAN$TMIN <- as.numeric(SAN$TMIN)
SAN$WEEK <- as.numeric(SAN$WEEK)
SAN$BWK <- as.numeric(SAN$BWK)
SAN$SCH <- as.numeric(SAN$SCH)
SAN$B <- as.numeric(SAN$B)
SAN$B.5 <- as.numeric(SAN$B.5)

## to change back and forth from B.5 vs. B SAN$B.5 <- SAN$B

## this is what the data looks like head(SAN)

plot(cumsum(SAN$B.5), cumsum(SAN$CASES.i), type = "l", xlab = "Cumulative sum of births (lagged 5 years)", 
    ylab = "Cumulative sum of reported cases")
x <- c(1:1e+06)
lines(x, x, col = "red")
legend("bottomright", c("incidence", "expected incidence"), col = c("black", 
    "red", "gray"), lty = 1)


## fit a smooth spline of cumulative measles on cumulative births with 2.5
## degrees of freedom

cum.reg <- smooth.spline(cumsum(SAN$B.5), cumsum(SAN$CASES.i), df = 2.5)

lm <- lm(cumsum(SAN$CASES.i) ~ cumsum(SAN$B.5))
# abline(lm, col='gray')

## predict points using the smooth spline and calculate residuals, D
D <- predict(cum.reg)$y - cumsum(SAN$CASES.i)

B <- SAN$B.5

# plot(D, type='l')

## under reporting is given by slope of smooth spline
u <- predict(cum.reg, deriv = 1)$y
rho <- mean(u)

legend("topleft", paste("rho", round(rho, 3), sep = " = "))

plot of chunk unnamed-chunk-1



## Ic are actual cases - reported cases divided by u
Ic = SAN$CASES.i/u

# plot(Ic, type='l')

lIt = log(Ic[2:(length(SAN$CASES) + 1)])
lItm1 = log(Ic[1:length(SAN$CASES)])
Dtm1 = D[1:length(SAN$CASES)]

## remove values of -Inf from I - glm function does not like these!
for (i in 1:(length(lIt) - 1)) {
    if (lIt[i] == -Inf) {
        lIt[i] <- 0
    }
}

for (i in 1:length(lItm1)) {
    if (lItm1[i] == -Inf) {
        lItm1[i] <- 0
    }
}

## mean populaiton estimate
pop = mean(SAN$POP.5)
seas = rep(1:26, length(SAN$CASES))[1:length(SAN$CASES)]

seas <- as.factor(seas)

## test Smeans from 1% to whole population
Smean = seq(0.001, 1, by = 0.001) * pop

## this is a place to store the likelihoods of the data for each setting
## of Smean
llik = rep(NA, length(Smean))

## now perform the log linear regressions at each Smean
for (i in 1:length(Smean)) {
    lStm1 = log(Smean[i] + Dtm1)
    glmfit = glm(lIt ~ -1 + as.factor(seas) + lItm1 + offset(lStm1))
    llik[i] = glmfit$deviance
}
## Warning: NaNs produced

sbar <- Smean[which(llik == min(llik))]
sbar
## [1] 1320

## plot likelihood curve
plot(Smean, llik, type = "l", xlim = c(0, (0.1 * pop)), xlab = "sbar", ylab = "deviance (- log likelihood)")
legend("topright", paste("sbar", round(sbar, 0), sep = " = "))

plot of chunk unnamed-chunk-1


## The Smean we want to use is the one that minimizes the log likelihood


plot(D + sbar, type = "l", xlab = "Biweek", ylab = "S")

plot of chunk unnamed-chunk-1


sbar.def <- sbar
D.def <- D
B.def <- SAN$B.5
alpha.def <- 0.98

## TSIR code

## pass B, sbar, and D results from above and guess at coefficients for
## Beta function

runTSIR <- function(alpha = alpha.def, B = B.def, sbar = sbar.def, D = D.def, 
    Beta = "TMP", guess = c(x1 = 3.8e-05, x2 = 0.4), initial.state = c(S = sbar.def - 
        1, I = 1, R = SAN$POP[1] - sbar.def - 1, CI = 1)) {

    ## create empty vectors to store S, I, R, B, Beta estimates
    S <- rep(NA, length(SAN$CASES))
    I <- rep(NA, length(SAN$CASES))
    R <- rep(NA, length(SAN$CASES))
    CI <- rep(NA, length(SAN$CASES))

    ## set time = 1 values to initial states
    S[1] <- sbar + D[1]
    I[1] <- initial.state["I"]
    R[1] <- initial.state["R"]
    CI[1] <- initial.state["CI"]

    ## betas are a function of the normalized climate data - I used tmax here.
    ## The x1-x2 are parameters to fit the seasonal forcing equation.
    tmax <- (SAN$TMAX - 260)/105
    Beta.TMP <- guess["x1"] * (1 + (guess["x2"] * (tmax)))
    Beta.SCH <- guess["x1"] * (1 + (guess["x2"] * (SAN$SCH)))
    Beta.CST <- rep(guess["x1"], length(SAN$CASES))

    if (Beta == "TMP") {
        for (t in 2:length(SAN$CASES)) {
            S[t] <- D[t] + sbar
            I[t] <- Beta.TMP[t] * S[t - 1] * (I[t - 1]^alpha)
            R[t] <- I[t - 1] + R[t - 1]
            CI[t] <- I[t] + CI[t - 1]
        }
    } else if (Beta == "SCH") {
        for (t in 2:length(SAN$CASES)) {
            S[t] <- D[t] + sbar
            I[t] <- Beta.SCH[t] * S[t - 1] * (I[t - 1]^alpha)
            R[t] <- I[t - 1] + R[t - 1]
            CI[t] <- I[t] + CI[t - 1]
        }
    } else if (Beta == "CST") {
        for (t in 2:length(SAN$CASES)) {
            S[t] <- D[t] + sbar
            I[t] <- Beta.CST[t] * S[t - 1] * (I[t - 1]^alpha)
            R[t] <- I[t - 1] + R[t - 1]
            CI[t] <- I[t] + CI[t - 1]
        }
    }

    tsir.output <- data.frame(S, I, R, CI, Beta.TMP, Beta.SCH, Beta.CST)
}


######################## LS1 is temperature ##
LS1 <- function(x) {
    sum((runTSIR(guess = x, Beta = "TMP")$I - SAN$CASES.i/u)^2)
}

g <- c(x1 = 2.5e-05, x2 = -0.4)
p <- optim(g, LS1)

## show optimal values
p$par
##         x1         x2 
##  0.0007651 -0.3632455

## show MSE
MSE1 <- LS1(p$par)
MSE1
## [1] 102888648

optimal1 <- as.vector(p$par)

out.opt1 <- runTSIR(guess = c(x1 = as.numeric(p$par[1]), x2 = as.numeric(p$par[2])), 
    Beta = "TMP")

head(out.opt1)
##      S      I      R     CI  Beta.TMP  Beta.SCH  Beta.CST
## 1 1693  1.000 186237  1.000 0.0008957 0.0010430 0.0007651
## 2 1698  1.502 186238  2.502 0.0008870 0.0010430 0.0007651
## 3 1701  2.546 186239  5.048 0.0010067 0.0004872 0.0007651
## 4 1707  4.441 186242  9.489 0.0010445 0.0004872 0.0007651
## 5 1713  7.563 186246 17.052 0.0010276 0.0004872 0.0007651
## 6 1716 12.001 186254 29.053 0.0009647 0.0004872 0.0007651

######################## LS2 is school #######

LS2 <- function(x) {
    sum((runTSIR(guess = x, Beta = "SCH")$I - SAN$CASES.i/u)^2)
}

g <- c(x1 = 2.5e-05, x2 = 0.4)
k <- optim(g, LS2)

par(mfrow = c(1, 3), mar = c(4, 4, 4, 2))
plot(SAN$BWK, out.opt1$S, type = "l", xlab = "Biweek", ylab = "Number of people", 
    main = "S")
plot(SAN$BWK, out.opt1$I, type = "l", xlab = "Biweek", ylab = "", main = "I")
plot(SAN$BWK, out.opt1$R, type = "l", xlab = "Biweek", ylab = "", main = "R")

plot of chunk unnamed-chunk-1

par(mfrow = c(1, 1))

## show optimal values
k$par
##        x1        x2 
## 0.0007395 0.1961207

## show MSE
MSE2 <- LS2(k$par)
MSE2
## [1] 132625787

optimal2 <- as.vector(k$par)

out.opt2 <- runTSIR(guess = c(x1 = as.numeric(k$par[1]), x2 = as.numeric(k$par[2])), 
    Beta = "SCH")

head(out.opt2)
##      S     I      R     CI  Beta.TMP  Beta.SCH  Beta.CST
## 1 1693 1.000 186237  1.000 0.0006713 0.0005945 0.0007395
## 2 1698 1.006 186238  2.006 0.0006759 0.0005945 0.0007395
## 3 1701 1.512 186239  3.518 0.0006134 0.0008845 0.0007395
## 4 1707 2.256 186241  5.774 0.0005937 0.0008845 0.0007395
## 5 1713 3.352 186243  9.126 0.0006025 0.0008845 0.0007395
## 6 1716 4.957 186246 14.083 0.0006353 0.0008845 0.0007395

########################## LS3 is constant #######

LS3 <- function(x) {
    sum((runTSIR(guess = x, Beta = "CST")$I - SAN$CASES.i/u)^2)
}

g <- c(x1 = 2.5e-05, x2 = 0.8)
q <- optim(g, LS3)

## show optimal values
q$par
##        x1        x2 
## 0.0007352 0.8023559

## show MSE
MSE3 <- LS3(q$par)
MSE3
## [1] 137230951

optimal3 <- as.vector(q$par)
out.opt3 <- runTSIR(guess = c(x1 = as.numeric(q$par[1]), x2 = as.numeric(q$par[2])), 
    Beta = "CST")

head(out.opt3)
##      S     I      R     CI  Beta.TMP  Beta.SCH  Beta.CST
## 1 1693 1.000 186237  1.000 0.0004579 0.0001453 0.0007352
## 2 1698 1.245 186238  2.245 0.0004763 0.0001453 0.0007352
## 3 1701 1.547 186239  3.791 0.0002223 0.0013250 0.0007352
## 4 1707 1.918 186241  5.709 0.0001421 0.0013250 0.0007352
## 5 1713 2.376 186243  8.086 0.0001778 0.0013250 0.0007352
## 6 1716 2.941 186245 11.027 0.0003114 0.0013250 0.0007352


## get average betas for each biweek
Beta.TMP <- rep(NA, 26)

for (i in 1:26) {
    Beta.TMP[i] <- mean(out.opt1$Beta.TMP[rep(i, length(out.opt1$Beta.TMP), 
        by = 26)])
}

Beta.SCH <- rep(NA, 26)

for (i in 1:26) {
    Beta.SCH[i] <- mean(out.opt2$Beta.SCH[rep(i, length(out.opt2$Beta.SCH), 
        by = 26)])
}

Beta.CST <- rep(NA, 26)

for (i in 1:26) {
    Beta.CST[i] <- mean(out.opt3$Beta.CST[rep(i, length(out.opt3$Beta.CST), 
        by = 26)])
}

## Betas.26 is dataframe of average betas for 1 year
Betas.26 <- data.frame(Beta.TMP, Beta.SCH, Beta.CST)


plot(Betas.26$Beta.TMP, col = "magenta", type = "l", ylab = "Beta", xlab = "Biweek", 
    xlim = c(1, 26), lwd = 2, pch = 16, ylim = c(min(Beta.SCH, Beta.TMP), max(Beta.TMP, 
        Beta.SCH)))
lines(Betas.26$Beta.SCH, col = "darkgreen", lwd = 2)
lines(Betas.26$Beta.CST, col = "blue", lwd = 2)
legend("topright", c("Constant     ", "School", "Temperature   "), col = c("blue", 
    "darkgreen", "magenta"), lwd = 2)

plot of chunk unnamed-chunk-1


## Betas is all betas
Betas <- data.frame(Beta.TMP = out.opt1$Beta.TMP, Beta.SCH = out.opt2$Beta.SCH, 
    Beta.CST = out.opt3$Beta.CST)


# plot(SAN$BWK,out.opt1$I, type='l', col='purple',
# ylim=c(0,4000),xlim=c(0,26*10)) lines(SAN$BWK, out.opt2$I, type='l',
# col='orange')


## Fourier analysis - plot spectrum and ID dominant frequencies
freq <- spectrum(SAN$CASES.i)$freq

plot of chunk unnamed-chunk-1

spec <- spectrum(SAN$CASES.i)$spec

data <- data.frame(freq, spec, period = 1/freq, period.yrs = (1/freq)/26)
data <- data[order(-spec), ]
head(data)
##       freq  spec period period.yrs
## 26 0.03852 16551  25.96     0.9985
## 13 0.01926  7818  51.92     1.9970
## 8  0.01185  5695  84.38     3.2452
## 9  0.01333  4403  75.00     2.8846
## 24 0.03556  4310  28.12     1.0817
## 15 0.02222  4080  45.00     1.7308

par(mar = c(4, 4, 2, 2))
spectrum(SAN$CASES.i, main = "", xlab = "Frequency (1/Period)", ylab = "Spectral Density", 
    ylim = c(10, 1e+08), xlim = c(-0.01, 0.5))
text(data[1, 1], data[1, 2], paste(round(data[1, 3], 1), "bwks", sep = "\n"), 
    pos = 4, cex = 0.7)
text(data[2, 1], data[2, 2], paste(round(data[2, 3], 1), "bwks", sep = "\n"), 
    pos = 3, cex = 0.7)

plot of chunk unnamed-chunk-1


## parameters
param <- data.frame(TEMP = p$par, SCHOOL = k$par, CONSTANT = c(q$par[1], NA))
row.names(param) <- c("beta_0", "beta_1")

## plot fits against data
plot(SAN$BWK, out.opt1$I, type = "l", col = "red", lwd = 2)
lines(SAN$BWK, SAN$CASES.i)
legend("topright", c(paste("MSE:", round(MSE1, 0), sep = "")))

plot of chunk unnamed-chunk-1


# plot(SAN$BWK, SAN$CASES.i, type='l') lines(SAN$BWK, out.opt2$I,
# type='l', col='red', lwd=2)
plot(SAN$BWK, out.opt2$I, type = "l", col = "red", lwd = 2)
lines(SAN$BWK, SAN$CASES.i)
legend("topright", c(paste("MSE:", round(MSE2, 0), sep = "")))

plot of chunk unnamed-chunk-1


# plot(SAN$BWK, SAN$CASES.i, type='l') lines(SAN$BWK, out.opt3$I,
# type='l', col='red', lwd=2)
plot(SAN$BWK, out.opt3$I, type = "l", col = "red", lwd = 2)
lines(SAN$BWK, SAN$CASES.i)
legend("topright", c(paste("MSE:", round(MSE3, 0), sep = "")))

plot of chunk unnamed-chunk-1


param
##              TEMP    SCHOOL  CONSTANT
## beta_0  0.0007651 0.0007395 0.0007352
## beta_1 -0.3632455 0.1961207        NA