Change maps

07-basic_statistics.qmd

@@ -49,6 +49,17 @@ In epidemiology, the true meaning of point is very questionable. If it usually g
 # Aggregate cases over districts
 district$cases <- lengths(st_intersects(district, cases))
 
+# Plot number of cases using proportional symbol 
+mf_map(x = district) 
+mf_map(
+  x = district, 
+  var = "cases",
+  val_max = 50,
+  type = "prop",
+  col = "#990000", 
+  leg_title = "Cases")
+mf_layout(title = "Number of cases of W Fever")
+
 ```
 
 The incidence ($\frac{cases}{population}$) expressed per 100,000 population is commonly use to represent cases distribution related to population density but other indicators exists. As example, the standardized incidence ratios (SIRs) represent the deviation of observed and expected number of cases and is expressed as $SIR = \frac{Y_i}{E_i}$ with $Y_i$, the observed number of cases and $E_i$, the expected number of cases. In this study, we computed the expected number of cases in each district by assuming infections are homogeneously distributed across Cambodia, i.e., the incidence is the same in each district. The SIR therefore represents the deviation of incidence compared to the average incidence across Cambodia.
@@ -68,40 +79,33 @@ district$expected <- district$T_POP * rate
 district$SIR <- district$cases / district$expected
 ```
 
-```{r inc_visualization, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=8, fig.height=4, class.output="code-out", warning=FALSE, message=FALSE}
-par(mfrow = c(1, 3))
-# Plot number of cases using proportional symbol 
-mf_map(x = district) 
-mf_map(
-  x = district, 
-  var = "cases",
-  val_max = 50,
-  type = "prop",
-  col = "#990000", 
-  leg_title = "Cases")
-mf_layout(title = "Number of cases of W Fever")
+```{r inc_visualization, eval = TRUE, echo = TRUE, nm = TRUE, fig.width=11, fig.height=7, class.output="code-out", warning=FALSE, message=FALSE}
+par(mfrow = c(1, 2))
 
 # Plot incidence 
+mf_map(x = district)
 mf_map(x = district,
-       var = "incidence",
-       type = "choro",
-       pal = "Reds 3",
+       var = c("T_POP", "incidence"),
+       type = "prop_choro",
+       pal = "Reds",
+       inches = .1,
        breaks = exp(mf_get_breaks(log(district$incidence+1), breaks = "pretty"))-1,
-       leg_title = "Incidence \n(per 100 000)")
+       leg_title = c("Population", "Incidence \n(per 100 000)"))
 mf_layout(title = "Incidence of W Fever")
 
 # Plot SIRs
 # create breaks and associated color palette
 break_SIR <- c(0,exp(mf_get_breaks(log(district$SIR), nbreaks = 8, breaks = "pretty")))
 col_pal <- c("#273871", "#3267AD", "#6496C8", "#9BBFDD", "#CDE3F0", "#FFCEBC", "#FF967E", "#F64D41", "#B90E36")
-
+mf_map(x = district)
 mf_map(x = district,
-       var = "SIR",
-       type = "choro",
-       breaks = break_SIR, 
+       var = c("T_POP", "SIR"),
+       type = "prop_choro",
+       breaks = break_SIR,
        pal = col_pal,
-       cex = 2,
-       leg_title = "SIR")
+       inches = .1,
+       #cex = 2,
+       leg_title = c("Population", "SIR"))
 mf_layout(title = "Standardized Incidence Ratio of W Fever")
 ```
 
@@ -155,8 +159,11 @@ m_cases <- mean(district$incidence)
 sd_cases <- sd(district$incidence)
 
 hist(district$incidence, probability = TRUE, ylim = c(0, 0.4), xlim = c(-5, 16), xlab = "Number of cases", ylab = "Probability", main = "Histogram of observed incidence compared\nto Normal and Poisson distributions")
+
 curve(dnorm(x, m_cases, sd_cases),col = "blue",  lwd = 1, add = TRUE)
-points(0:max(district$incidence), dpois(0:max(district$incidence), m_cases),type = 'b', pch = 20, col = "red", ylim = c(0, 0.6), lty = 2)
+
+points(0:max(district$incidence), dpois(0:max(district$incidence),m_cases),
+       type = 'b', pch = 20, col = "red", ylim = c(0, 0.6), lty = 2)
 
 legend("topright", legend = c("Normal distribution", "Poisson distribution", "Observed distribution"), col = c("blue", "red", "black"),pch = c(NA, 20, NA), lty = c(1, 2, 1))
 ```