In litteR: Litter Analysis

logger$info("Entering regional trend analysis section")

Regional trend analysis

For each region_code and the type names and group codes specified in the settings file, the following statistics have been estimated for the period r str_c(DATE_FROM, " to ", DATE_TO):

• the number of surveys (N);
• Theil-Sen slope: the median of all Theil-Sen slopes within a region;
• p-value: the p-value associated with the one-tailed Regional Kendall test (Van Belle & Hughes, 1984; Gilbert, 1987) to test the null hypothesis of
  • no monotonically increasing trend in case the regional Theil-Sen slope is greater than zero;
  • no monotonically decreasing trend in case the regional Theil-Sen slope is smaller than zero;

A p-value less than an a priori specified significance level (e.g., often α = 0.05), indicates a significant trend. If the p-value is greater than this significance level, we can't say that there is no trend. We can only conclude that our data do not show evidence for a significant trend (due to lack of data, noise, etc.).

The Regional Kendall test is a non-parametric test and as such does not make distributional assumptions on the data.

Note that the trend statistics can only be computed if all location_codes of a region_code have at least three records (surveys). If that is not the case, the table below contains NA.

# check region_codes
missing_region_codes <- REGION_CODE %>%
  setdiff(unique(d_stats_reg$region_code))
if (length(missing_region_codes) > 0) {
    logger$warn("The following specified region code(s) are not found and will be skipped: ",
        missing_region_codes %>% sQuote %>% enumerate)
}
REGION_CODE <- d_stats_reg %>%
    chuck("region_code") %>% 
    unique %>%
    intersect(REGION_CODE)

# check type names
missing_type_names <- TYPE_NAME %>%
  setdiff(unique(d_stats_reg$type_name))
if (length(missing_type_names) > 0) {
    logger$warn("The following specified type name(s) are not found and will be skipped: ",
        missing_type_names %>% sQuote %>% enumerate)
}
TYPE_NAME <- d_stats_reg %>%
    chuck("type_name") %>% 
    unique %>%
    intersect(TYPE_NAME)

# check group codes
missing_group_codes <- GROUP_CODE %>%
  setdiff(unique(d_stats_reg$type_name))
if (length(missing_group_codes) > 0) {
    logger$warn("The following specified group code(s) are not found and will be skipped: ",
        missing_group_codes %>% sQuote %>% enumerate)
}
GROUP_CODE <- d_stats_reg %>%
    chuck("type_name") %>% 
    unique %>%
    intersect(GROUP_CODE)

logger$info("Creating table with trend statistics")
d_stats_reg %>%
    filter(type_name %in% unique(c("TC", TYPE_NAME, GROUP_CODE))) %>%
    select(region_code, type_name, N = n, slope, `p-value` = p_value) %>%
    arrange(region_code, desc(abs(slope))) %>%
    rename(`type name / group code` = type_name) %>%
    mutate(
        slope = slope %>%
            formatC(format = "fg", digits = 4),
        `p-value` = `p-value` %>%
            formatC(format = "f",  digits = 4)) %>%
    kable(align = "llrrr")
logger$info("Table with trend statistics created")

  logger$info("No valid region_code(s) found. Therefore, time-series plot are skipped")

litteR documentation built on Aug. 27, 2022, 1:05 a.m.