Krummhörn descriptives

pander_escape(missingness_patterns(krmh[, list(
    bdate, ddate, bdate.Father, ddate.Father, bdate.Mother, ddate.Mother
    )]))

ggplot(data = demo_trends[Year > 1680 & Year< 1900,]) + 
    geom_line(aes(x= Year, y = first, linetype = "first", colour = Parent),  size = 1) + 
  geom_line(aes(x = Year, y = all, linetype = "all", colour = Parent), size = 1) +
    geom_line(aes(x= Year, y = last, linetype = "last", colour = Parent),size = 1) + 
    scale_colour_manual(values = c(Father = "#6c92b2", Mother = "#aec05d")) + 
    scale_linetype_manual("Birth", breaks = c("last", "all","first"), values = c( "solid","dashed", "dotted")) +
    scale_y_continuous("Parental age at birth") + 
        geom_text(aes(x = Year, y = all + 0.5, 
                                    label = ifelse(Year %% 15 == 0, round(all), NA))) + 
    facet_wrap(~ Parent) +
    desc_theme + theme(legend.position = c(1,1),
  legend.justification = c(1,1), 
  legend.box = "horizontal",
  panel.margin = unit(2, "lines"))

round(cor(krmh[, list(
    paternalage, maternalage, birthorder, nr.siblings, children, grandchildren, byear, byear.Father, age_at_1st_child, age_at_last_child
    )], use = "pairwise.complete.obs"),2)

ggplot(data=krmh, aes(x = byear, y = paternalage)) +
    geom_linerange(stat = "summary", fun.data = "median_hilow", colour = "#aec05d") +
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#6c92b2") +
    desc_theme

ggplot(data=krmh, aes(x = byear, y = age_at_1st_child)) +
    geom_linerange(stat = "summary", fun.data = "median_hilow", colour = "#aec05d") +
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#6c92b2") +
    desc_theme

ggplot(data=krmh, aes(x = byear, y = age_at_last_child)) +
    geom_linerange(stat = "summary", fun.data = "median_hilow", colour = "#aec05d") +
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#6c92b2") +
    desc_theme

ggplot(data=krmh, aes(x = byear, y = children)) + 
    geom_linerange(stat = "summary", fun.data = "median_hilow", colour = "#aec05d", na.rm=T) + 
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#6c92b2") + 

    desc_theme

ggplot(data=krmh, aes(x = byear, y = survive1y)) + 
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#aec05d") + 

    desc_theme

ggplot(data=krmh, aes(x = byear, y = surviveR)) + 
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#aec05d") + 

    desc_theme

ggplot(data=krmh, aes(x = children, y = grandchildren)) + 
    geom_jitter(colour = "#aec05d", alpha = I(0.1)) + 
    geom_pointrange(stat = "summary", fun.data = "median_hilow", colour = "#6c92b2") +
    geom_smooth(method = "glm", formula = y ~ poly(x,3), colour = "#6e85b0") + 
    desc_theme

ggplot(data=krmh, aes(x = children, y = children.surviving5y)) + 
    geom_jitter(colour = "#aec05d", alpha = I(0.1)) + 
    geom_pointrange(stat = "summary", fun.data = "median_hilow", colour = "#6c92b2") +
    geom_smooth(method = "glm", formula = y ~ poly(x,3), colour = "#6e85b0") + 
    desc_theme

ggplot(data=krmh, aes(x = round(age), y = children)) + 
    geom_jitter(colour = "#aec05d", alpha = I(0.1)) + 
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#6c92b2") +
    geom_smooth(colour = "#6e85b0") + 
    xlab("Age") +
    ylab("Number of children") +
    desc_theme

ggplot(data=krmh[children>0,], aes(x = round(age), y = children)) + 
    geom_jitter(colour = "#aec05d", alpha = I(0.1)) + 
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#6c92b2") +
    geom_smooth(colour = "#6e85b0") + 
    xlab("Age") +
    ylab("Number of children") +
    desc_theme

plot_zero_infl(krmh[ spouses > 0, ]$children)

ggplot(data=krmh, aes(x = paternalage.factor, y = survive1y)) + 
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#aec05d") + 
    desc_theme

ggplot(data=krmh[spouses > 0, ], aes(x = paternalage.factor, y = children)) + 
    geom_pointrange(stat = "summary", fun.data = "mean_cl_boot", colour = "#aec05d") + 
    desc_theme

krmh.1$birth.decade = round(krmh.1$byear/5)*5


episodes = krmh.1 %>%
    filter(!is.na(male) | !is.na(survive1y) | !is.na(ever_married)) %>% 
    group_by(birth.decade) %>%
    summarise(
        "Population size" = as.numeric(length(idIndividu)),
        "0. Number of children" = ifelse(between(birth.decade, 1655,1840), cva(children), NA_real_ ), 
        "1. Surviving first year" = ifelse(between(birth.decade, 1655, 1870),cva_bin(survive1y), NA_real_ ),
        "2. Surviving to 15" = ifelse(between(birth.decade, 1655,1840), cva_bin(surviveR[survive1y==T]), NA_real_ ),
        "3. Ever married" = ifelse(between(birth.decade, 1655,1830), cva_bin(ever_married[surviveR==1]), NA_real_ ), 
        "4. Number of children" = ifelse(between(birth.decade, 1655,1840), cva(children[ever_married==1]), NA_real_ ), 
        "5. Grandchildren" = ifelse(between(birth.decade, 1655,1800), cva(grandchildren[children>0]), NA_real_ )
        ) %>%
    data.table()
data.frame(episodes[order(birth.decade), ])

save(episodes, file = "coefs/krmh_episodes.rdata")
# krmh.1 = merge(krmh.1, episodes, by = "birth.decade", all.x = T)

(episodes.plot = ggplot(melt(episodes,id.vars=c('birth.decade'), na.rm = T)) + geom_line(aes(x=birth.decade, y=value)) + facet_wrap(~ variable,scales='free_y',ncol = 1)) + mymin

(sex.ratio = krmh.1 %>% 
    filter(!is.na(male), byear > 1720) %>% 
    mutate(male = as.numeric(as.character(male))) %>%
    group_by(birth.decade) %>% 
    summarise(sex.ratio = sum(male)/length(male)) %>%
    data.frame()
)

ggplot(na.omit(sex.ratio)) + geom_line(aes(x=birth.decade, y=sex.ratio)) + mymin