Source code for this document is found here.
###################### Set up data
# devtools::install_github("fredhasselman/casnet")
# edidata %>%
# dplyr::select(-date) %>%
# names() %>%
# purrr::map(~ggplot(edidata, aes_string(x = .)) + geom_histogram(binwidth = 500))
#
# edidata %>%
# dplyr::select(-date) %>%
# names() %>%
# purrr::map(~ggplot(edidata, aes_string(x = .)) +
# geom_density() +
# theme_bw())
#
# edidata %>%
# dplyr::select(-date) %>%
# purrr::map(~summary(.))
# edidata <- readr::read_tsv("../motivation-dynamics/data/data.tsv") %>%
# tidyr::spread(Field, Value) %>%
# dplyr::select(autonomy, competence, relatedness,
# pleasure, interest, importance,
# situation_requires = required,
# anxiety_guilt_avoidance = anxiety_guilt,
# another_wants = for_others,
# Date,
# User) %>%
# type.convert() %>%
# dplyr::mutate(Date = as.POSIXct(Date)) %>%
# dplyr::filter(stringr::str_detect(User, "Moti")) %>%
# na.omit()
#
# readr::write_csv(edidata, path = "./data/data_20p_9var_plus_time.csv")
mydata <- readr::read_csv("./data/data_20p_9var_plus_time.csv")
emadata_nested <- mydata %>% dplyr::group_by(User) %>%
tidyr::nest()
# Show sample size for each participant:
# emadata_nested %>%
# mutate(n = map_dbl(data, nrow))
emadata_nested_wrangled <- emadata_nested %>%
dplyr::mutate(data = purrr::map(data, ~dplyr::mutate(.x,
date = as.Date(Date),
timediff = c(NA, diff(Date))))) %>%
# Filter out answers less than 15 minutes from the last one, then remove the difference variable
dplyr::mutate(data = purrr::map(data, ~dplyr::filter(.x, timediff > 15))) %>%
dplyr::mutate(data = purrr::map(data, ~dplyr::select(.x,
-timediff,
-Date,
-date)))###################### Generate result tables
emadata_nested_wrangled_tests <- emadata_nested_wrangled %>%
dplyr::mutate(observations = purrr::map_dbl(.x = data,
.f = ~nrow(.)))
test_results <- list()
data_assumptions <- list()
alphaLevel <- 0.05 / 4
for(i in 1:nrow(emadata_nested_wrangled_tests)){
data_assumptions[[i]] <- emadata_nested_wrangled_tests$data[[i]]
H0_randomness_H1_nonrandomness <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::bartels.rank.test(., alternative = "two.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_nonrandomness$name <- "Bartel's rank test\nH0: randomness\nH1: nonrandomness"
H0_randomness_H1_nonrandomness$User <- emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_trend <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::bartels.rank.test(., alternative = "left.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_trend$name <- "Bartel's rank test\nH0: randomness\nH1: trend"
H0_randomness_H1_trend$User <- emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_systematic_oscillation <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::bartels.rank.test(., alternative = "right.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_systematic_oscillation$name <- "Bartel's rank test\nH0: randomness\nH1: systematic oscillation"
H0_randomness_H1_systematic_oscillation$User <- emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_upward_or_downward_trend <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::cox.stuart.test(na.exclude(.), alternative = "two.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_upward_or_downward_trend$name <- "Cox-Stuart test\nH0: randomness\nH1: upward or downward trend"
H0_randomness_H1_upward_or_downward_trend$User <- emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_upward_trend <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::cox.stuart.test(na.exclude(.), alternative = "right.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_upward_trend$name <- "Cox-Stuart test\nH0: randomness\nH1: upward trend"
H0_randomness_H1_upward_trend$User <- emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_downward_trend <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::cox.stuart.test(na.exclude(.), alternative = "left.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_downward_trend$name <- "Cox-Stuart test\nH0: randomness\nH1: downward trend"
H0_randomness_H1_downward_trend$User <- emadata_nested_wrangled[i, 1][[1]]
H0_level_stationarity_H1_unit_root_no_level_stationarity <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~tseries::kpss.test(na.exclude(.), lshort = TRUE, null = "Level")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_level_stationarity_H1_unit_root_no_level_stationarity$name <- "KPSS test\nH0: stationary level\nH1: non-stationary level"
H0_level_stationarity_H1_unit_root_no_level_stationarity$User <- emadata_nested_wrangled[i, 1][[1]]
H0_trend_stationarity_H1_no_trend_stationarity <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~tseries::kpss.test(na.exclude(.), lshort = TRUE, null = "Trend")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_trend_stationarity_H1_no_trend_stationarity$name <- "KPSS test\nH0: stationary trend\nH1: non-stationary trend"
H0_trend_stationarity_H1_no_trend_stationarity$User <- emadata_nested_wrangled[i, 1][[1]]
H0_some_AR_process_H1_no_AR_process <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::Keenan.test(na.exclude(.))$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_some_AR_process_H1_no_AR_process$name <- "Keenan's test for nonlinearity\nH0: linear AR process\nH1: not a linear AR process"
H0_some_AR_process_H1_no_AR_process$User <- emadata_nested_wrangled[i, 1][[1]]
H0_some_AR_process_H1_no_ARCH_process <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::McLeod.Li.test(y = ., plot = FALSE, omit.initial = TRUE)$p.values %>%
max(.) %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_some_AR_process_H1_no_ARCH_process$name <- "McLeod-Li test\nH0: linear AR process\nH1: not an ARCH process"
H0_some_AR_process_H1_no_ARCH_process$User <- emadata_nested_wrangled[i, 1][[1]]
H0_some_AR_process_H1_no_ARiMA_process <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::McLeod.Li.test(object = forecast::auto.arima(.),
plot = FALSE,
omit.initial = TRUE)$p.values %>%
max(.) %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_some_AR_process_H1_no_ARiMA_process$name <- "McLeod-Li test\nH0: linear AR process\nH1: not an ARiMA process"
H0_some_AR_process_H1_no_ARiMA_process$User <- emadata_nested_wrangled[i, 1][[1]]
H0_AR_process_H1_no_AR_process <- data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::Tsay.test(na.exclude(.))$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_AR_process_H1_no_AR_process$name <- "Tsay's test for nonlinearity\nH0: linear AR process\nH1: not a linear AR process"
H0_AR_process_H1_no_AR_process$User <- emadata_nested_wrangled[i, 1][[1]]
test_results[[i]] <- rbind(H0_randomness_H1_nonrandomness,
H0_randomness_H1_trend,
H0_randomness_H1_systematic_oscillation,
H0_randomness_H1_upward_or_downward_trend,
H0_randomness_H1_upward_trend,
H0_randomness_H1_downward_trend,
H0_level_stationarity_H1_unit_root_no_level_stationarity,
H0_trend_stationarity_H1_no_trend_stationarity,
H0_some_AR_process_H1_no_AR_process,
H0_some_AR_process_H1_no_ARCH_process,
H0_some_AR_process_H1_no_ARiMA_process,
H0_AR_process_H1_no_AR_process) %>%
dplyr::select(User, name, everything())
}
test_nested <- test_results %>% purrr::map_df(., rbind) %>%
dplyr::group_by(User) %>%
tidyr::nest()
test_nested <- test_nested %>%
dplyr::mutate(data = purrr::map(.x = data,
.f = ~dplyr::mutate_at(.x, vars(2:ncol(test_nested$data[[1]])),
funs(as.numeric))),
data_binarised = purrr::map(.x = data,
.f = ~dplyr::transmute_if(.x, is.numeric,
~dplyr::case_when(. < alphaLevel ~ 1,
TRUE ~ 0)) %>%
dplyr::mutate(test_number = row_number())),
data = purrr::map(.x = data,
.f = ~dplyr::mutate(.x, test_number = row_number())))
test_nested <- dplyr::full_join(test_nested,
emadata_nested_wrangled_tests %>% dplyr::select(User, observations),
by = "User")
# test_nested_segments_aggregates$aggregated_proportions
# test_nested_segments_aggregates$aggregated_series
# test_nested_segments_aggregates$series_numbers
# test_nested_segments_aggregates$data_binarised
# test_nested$data
# test_nested$data_binarised
############### Rejections by variable
tests_number_of_series <- test_nested$data_binarised %>%
purrr::map_df(., rbind) %>%
tidyr::pivot_longer(cols = -test_number) %>%
dplyr::group_by(test_number, name) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::ungroup() %>%
tidyr::pivot_wider(names_from = name, values_from = value)
tests_number_of_series$name <- test_nested$data[[1]]$name
tests_number_of_series <- tests_number_of_series %>% dplyr::select(name,
everything(),
-test_number)
############### Rejections by participant
test_nested_by_participant <- test_nested %>%
dplyr::mutate(rejected_vars_per_test = purrr::map(.x = data_binarised,
.f = ~dplyr::select(.x, -test_number) %>%
rowSums))
rejected_vars_per_test <- test_nested_by_participant$rejected_vars_per_test %>%
dplyr::bind_cols()
names(rejected_vars_per_test) <- paste0(test_nested_by_participant$User,
" (n=",
test_nested_by_participant$observations,
")")
rejected_vars_per_test$name <- test_nested$data[[1]]$name
rejected_vars_per_test <- rejected_vars_per_test %>%
dplyr::select(name, everything())alphaLo_emadata_nested_wrangled <- emadata_nested_wrangled
alphaLo_emadata_nested_wrangled_tests <- alphaLo_emadata_nested_wrangled %>%
dplyr::mutate(observations = purrr::map_dbl(.x = data,
.f = ~nrow(.)))
alphaLo_test_results <- list()
alphaLo_data_assumptions <- list()
alphaLo <- 0.05 / 12
for(i in 1:nrow(alphaLo_emadata_nested_wrangled_tests)){
alphaLo_data_assumptions[[i]] <- alphaLo_emadata_nested_wrangled_tests$data[[i]]
H0_randomness_H1_nonrandomness <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::bartels.rank.test(., alternative = "two.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_nonrandomness$name <- "Bartel's rank test\nH0: randomness\nH1: nonrandomness"
H0_randomness_H1_nonrandomness$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_trend <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::bartels.rank.test(., alternative = "left.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_trend$name <- "Bartel's rank test\nH0: randomness\nH1: trend"
H0_randomness_H1_trend$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_systematic_oscillation <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::bartels.rank.test(., alternative = "right.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_systematic_oscillation$name <- "Bartel's rank test\nH0: randomness\nH1: systematic oscillation"
H0_randomness_H1_systematic_oscillation$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_upward_or_downward_trend <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::cox.stuart.test(na.exclude(.), alternative = "two.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_upward_or_downward_trend$name <- "Cox-Stuart test\nH0: randomness\nH1: upward or downward trend"
H0_randomness_H1_upward_or_downward_trend$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_upward_trend <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::cox.stuart.test(na.exclude(.), alternative = "right.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_upward_trend$name <- "Cox-Stuart test\nH0: randomness\nH1: upward trend"
H0_randomness_H1_upward_trend$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_randomness_H1_downward_trend <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~randtests::cox.stuart.test(na.exclude(.), alternative = "left.sided")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_randomness_H1_downward_trend$name <- "Cox-Stuart test\nH0: randomness\nH1: downward trend"
H0_randomness_H1_downward_trend$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_level_stationarity_H1_unit_root_no_level_stationarity <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~tseries::kpss.test(na.exclude(.), lshort = TRUE, null = "Level")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_level_stationarity_H1_unit_root_no_level_stationarity$name <- "KPSS test\nH0: stationary level\nH1: non-stationary level"
H0_level_stationarity_H1_unit_root_no_level_stationarity$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_trend_stationarity_H1_no_trend_stationarity <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~tseries::kpss.test(na.exclude(.), lshort = TRUE, null = "Trend")$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_trend_stationarity_H1_no_trend_stationarity$name <- "KPSS test\nH0: stationary trend\nH1: non-stationary trend"
H0_trend_stationarity_H1_no_trend_stationarity$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_some_AR_process_H1_no_AR_process <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::Keenan.test(na.exclude(.))$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_some_AR_process_H1_no_AR_process$name <- "Keenan's test for nonlinearity\nH0: linear AR process\nH1: not a linear AR process"
H0_some_AR_process_H1_no_AR_process$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_some_AR_process_H1_no_ARCH_process <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::McLeod.Li.test(y = ., plot = FALSE, omit.initial = TRUE)$p.values %>%
max(.) %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_some_AR_process_H1_no_ARCH_process$name <- "McLeod-Li test\nH0: linear AR process\nH1: not an ARCH process"
H0_some_AR_process_H1_no_ARCH_process$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_some_AR_process_H1_no_ARiMA_process <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::McLeod.Li.test(object = forecast::auto.arima(.),
plot = FALSE,
omit.initial = TRUE)$p.values %>%
max(.) %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_some_AR_process_H1_no_ARiMA_process$name <- "McLeod-Li test\nH0: linear AR process\nH1: not an ARiMA process"
H0_some_AR_process_H1_no_ARiMA_process$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
H0_AR_process_H1_no_AR_process <- alphaLo_data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::Tsay.test(na.exclude(.))$p.value %>%
round(., digits = 3) %>% format(., nsmall = 3))
H0_AR_process_H1_no_AR_process$name <- "Tsay's test for nonlinearity\nH0: linear AR process\nH1: not a linear AR process"
H0_AR_process_H1_no_AR_process$User <- alphaLo_emadata_nested_wrangled[i, 1][[1]]
alphaLo_test_results[[i]] <- rbind(H0_randomness_H1_nonrandomness,
H0_randomness_H1_trend,
H0_randomness_H1_systematic_oscillation,
H0_randomness_H1_upward_or_downward_trend,
H0_randomness_H1_upward_trend,
H0_randomness_H1_downward_trend,
H0_level_stationarity_H1_unit_root_no_level_stationarity,
H0_trend_stationarity_H1_no_trend_stationarity,
H0_some_AR_process_H1_no_AR_process,
H0_some_AR_process_H1_no_ARCH_process,
H0_some_AR_process_H1_no_ARiMA_process,
H0_AR_process_H1_no_AR_process) %>%
dplyr::select(User, name, everything())
}
alphaLo_test_nested <- alphaLo_test_results %>% purrr::map_df(., rbind) %>%
dplyr::group_by(User) %>%
tidyr::nest()
alphaLo_test_nested <- alphaLo_test_nested %>%
dplyr::mutate(data = purrr::map(.x = data,
.f = ~dplyr::mutate_at(.x, vars(2:ncol(alphaLo_test_nested$data[[1]])),
funs(as.numeric))),
data_binarised = purrr::map(.x = data,
.f = ~dplyr::transmute_if(.x, is.numeric,
~dplyr::case_when(. < alphaLo ~ 1,
TRUE ~ 0)) %>%
dplyr::mutate(test_number = row_number())),
data = purrr::map(.x = data,
.f = ~dplyr::mutate(.x, test_number = row_number())))
alphaLo_test_nested <- dplyr::full_join(alphaLo_test_nested,
alphaLo_emadata_nested_wrangled_tests %>% dplyr::select(User, observations),
by = "User")
# alphaLo_test_nested_segments_aggregates$aggregated_proportions
# alphaLo_test_nested_segments_aggregates$aggregated_series
# alphaLo_test_nested_segments_aggregates$series_numbers
# alphaLo_test_nested_segments_aggregates$data_binarised
# alphaLo_test_nested$data
# alphaLo_test_nested$data_binarised
############### Rejections by variable
alphaLo_tests_number_of_series <- alphaLo_test_nested$data_binarised %>%
purrr::map_df(., rbind) %>%
tidyr::pivot_longer(cols = -test_number) %>%
dplyr::group_by(test_number, name) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::ungroup() %>%
tidyr::pivot_wider(names_from = name, values_from = value)
alphaLo_tests_number_of_series$name <- alphaLo_test_nested$data[[1]]$name
alphaLo_tests_number_of_series <- alphaLo_tests_number_of_series %>% dplyr::select(name,
everything(),
-test_number)
############### Rejections by participant
alphaLo_test_nested_by_participant <- alphaLo_test_nested %>%
dplyr::mutate(alphaLo_rejected_vars_per_test = purrr::map(.x = data_binarised,
.f = ~dplyr::select(.x, -test_number) %>%
rowSums))
alphaLo_rejected_vars_per_test <- alphaLo_test_nested_by_participant$alphaLo_rejected_vars_per_test %>%
dplyr::bind_cols()
names(alphaLo_rejected_vars_per_test) <- paste0(alphaLo_test_nested_by_participant$User,
" (n=",
alphaLo_test_nested_by_participant$observations,
")")
alphaLo_rejected_vars_per_test$name <- alphaLo_test_nested$data[[1]]$name
alphaLo_rejected_vars_per_test <- alphaLo_rejected_vars_per_test %>%
dplyr::select(name, everything())
# DT::datatable(alphaLo_test_results,
# options = list(pageLength = 11),
# caption = "P-values (or maximum p-values in case of McLeod-Li test)
# for tests of assumptions of data-generating processes") %>%
# DT::formatRound(columns = colnames(alphaLo_test_results), digits=3)
# alphaLo_test_results %>% summarise_if(is.numeric, ~((sum(.<0.05) / nrow(alphaLo_test_results)) %>% scales::percent())) %>%
# knitr::kable(caption = paste0("Percentage of ",
# nrow(alphaLo_test_results),
# " assumption tests indicating deviance at the p < 0.05 level"))#Keenan's test error message
data_assumptions[[i]] %>% # dplyr::select(-date) %>%
purrr::map_df(~TSA::Keenan.test(na.exclude(.))$p.value)
TSA::Keenan.test(c(20, 25, 15, 45, 45, 46, 8, 46, 44, 40, 24, 6, 23, 33, 45, 28, 23, 37, 39, 35, 39, 38, 41, 38))
nonlinearTseries::nonlinearityTest(c(20, 25, 15, 45, 45, 46, 8, 46, 44, 40, 24, 6, 23, 33, 45, 28, 23, 37, 39, 35, 39, 38, 41, 38))
cat(data_assumptions[[3]]$competence, sep = ", ")This dataset consists of 20 individuals and their responses to 9 questions. See “Dataset” in the top navigation bar for details.
In those tables below, where exact p-values are not reported, we choose the threshold of p < 0.0125 to reject the test. The rationale for this is that we consider what’s presented as the “Overview table” of four tests to consist of a family of tests, hence 0.05 / 4 = 0.0125. We also present the tables using an alpha level of 0.05 / 12 = 0.0041667. Ultimately, many different choices could be justified, and we encourage the reader to do their own analysis with the shared data. Obviously, not correcting for multiple testing and using 0.05 as the cutoff, would reject much more time series. Note: the KPSS test is built in such a way that it does not produce p-values < 0.01, hence interpretation is not sensible for alpha levels below that.
The four tests presented in the Overview table, show what we consider the most important factors in this context:
In the first tables, the participants are segmented into those with less than 100 response occasions, those with more than 100, and those (one person) with more than 100 response occasions.
Interpretation instructions: One time series is one variable in one person’s data. The top-left percentage indicates the proportion of time series, which is rejected at p < alpha. In other words, it is the number of rejected time series in the segment signified in the column header, divided by total number of time series (i.e. number of individuals in that segment, multiplied by the number of variables per individual, i.e. 9).
test_nested <- test_nested %>%
dplyr::mutate(obs_segment = dplyr::case_when(observations < 100 ~ 1,
observations < 1000 ~ 2,
TRUE ~ 3))
test_nested_segments <- test_nested %>% dplyr::select(data_binarised, obs_segment) %>%
dplyr::group_by(obs_segment) %>%
tidyr::nest()
test_nested_segments <- test_nested_segments %>%
dplyr::mutate(people = purrr::map_dbl(.x = data,
.f = ~nrow(.)))
test_nested_segments_aggregates <- test_nested_segments %>%
dplyr::mutate(data_binarised = purrr::map(.x = data,
.f = ~.x[["data_binarised"]] %>%
purrr::map_df(., rbind)))
test_nested_segments_aggregates <- test_nested_segments_aggregates %>%
dplyr::mutate(series_numbers = purrr::map(.x = data_binarised,
.f = ~tidyr::pivot_longer(.x, cols = -test_number) %>%
dplyr::group_by(test_number, name) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::ungroup() %>%
tidyr::pivot_wider(names_from = name, values_from = value)
))
test_nested_segments_aggregates <- test_nested_segments_aggregates %>%
dplyr::mutate(aggregated_series = purrr::map(.x = series_numbers,
.f = ~tidyr::pivot_longer(.x, cols = -test_number) %>%
dplyr::group_by(test_number) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::ungroup() %>%
tidyr::pivot_wider(names_from = test_number, values_from = value)
))
test_nested_segments_aggregates <- test_nested_segments_aggregates %>%
dplyr::mutate(aggregated_proportions = purrr::pmap(list(..1 = aggregated_series,
..2 = people),
.f = ~..1 %>% dplyr::mutate(., people_n = ..2)),
aggregated_proportions = purrr::map(.x = aggregated_proportions,
.f = ~dplyr::mutate_at(.x,
vars(-contains("people_n")),
funs(./(people_n*9)))))
segment1_max <- test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations < 100) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == 1) %>%
dplyr::pull(observations)
segment1_min <- test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations < 100) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == n()) %>%
dplyr::pull(observations)
segment2_max <- test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations >= 100 & observations <= 1000) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == 1) %>%
dplyr::pull(observations)
segment2_min <- test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations >= 100 & observations <= 1000) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == n()) %>%
dplyr::pull(observations)
segment3_minmax <- test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations > 1000) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == n()) %>%
dplyr::pull(observations)
segment_proportions <- test_nested_segments_aggregates$aggregated_proportions %>%
dplyr::bind_rows() %>%
dplyr::mutate(group = c(paste0(segment1_min, "-", segment1_max, " observations (n = ", people_n[1], ")"),
paste0(segment2_min, "-", segment2_max, " observations (n = ", people_n[2], ")"),
paste0(segment3_minmax, " observations (n = ", people_n[3], ")"))) %>%
tidyr::pivot_longer(cols = c(-"people_n", -"group")) %>%
dplyr::select(-people_n) %>%
tidyr::pivot_wider(names_from = group, values_from = value)
segment_proportions$name <- test_nested$data[[1]]$name
DT::datatable(segment_proportions %>%
dplyr::mutate_at(vars(-name), funs(scales::percent(., accuracy = 0.1))) %>%
dplyr::slice(c(7, 8, 9, 12)),
options = list(pageLength = 12),
caption = paste0("Tests for stationarity and non-linearity. Columns indicate
segments in the full sample of n = 20, and rows indicate tests.
Each cell indicates the percentage of time series (out of n
times 9, as each participant collected data on 9 variables),
where H0 is rejected at p<", alphaLevel, ". AR = autoregressive."))
DT::datatable(segment_proportions %>%
dplyr::mutate_at(vars(-name), funs(scales::percent(., accuracy = 0.1))),
options = list(pageLength = 12),
caption = paste0("Tests for stationarity and non-linearity. Columns indicate
segments in the full sample of n = 20, and rows indicate tests.
Each cell indicates the percentage of time series (out of n
times 9, as each participant collected data on 9 variables),
where H0 is rejected at p<", alphaLevel, ". AR = autoregressive."))
alphaLo_test_nested <- alphaLo_test_nested %>%
dplyr::mutate(obs_segment = dplyr::case_when(observations < 100 ~ 1,
observations < 1000 ~ 2,
TRUE ~ 3))
alphaLo_test_nested_segments <- alphaLo_test_nested %>%
dplyr::select(data_binarised, obs_segment) %>%
dplyr::group_by(obs_segment) %>%
tidyr::nest()
alphaLo_test_nested_segments <- alphaLo_test_nested_segments %>%
dplyr::mutate(people = purrr::map_dbl(.x = data,
.f = ~nrow(.)))
alphaLo_test_nested_segments_aggregates <- alphaLo_test_nested_segments %>%
dplyr::mutate(data_binarised = purrr::map(.x = data,
.f = ~.x[["data_binarised"]] %>%
purrr::map_df(., rbind)))
alphaLo_test_nested_segments_aggregates <- alphaLo_test_nested_segments_aggregates %>%
dplyr::mutate(series_numbers = purrr::map(.x = data_binarised,
.f = ~tidyr::pivot_longer(.x, cols = -test_number) %>%
dplyr::group_by(test_number, name) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::ungroup() %>%
tidyr::pivot_wider(names_from = name,
values_from = value)
))
alphaLo_test_nested_segments_aggregates <- alphaLo_test_nested_segments_aggregates %>%
dplyr::mutate(aggregated_series = purrr::map(.x = series_numbers,
.f = ~tidyr::pivot_longer(.x, cols = -test_number) %>%
dplyr::group_by(test_number) %>%
dplyr::summarise(value = sum(value)) %>%
dplyr::ungroup() %>%
tidyr::pivot_wider(names_from = test_number,
values_from = value)
))
alphaLo_test_nested_segments_aggregates <- alphaLo_test_nested_segments_aggregates %>%
dplyr::mutate(aggregated_proportions =
purrr::pmap(list(..1 = aggregated_series,
..2 = people),
.f = ~..1 %>%
dplyr::mutate(., people_n = ..2)),
aggregated_proportions =
purrr::map(.x = aggregated_proportions,
.f = ~dplyr::mutate_at(.x,
vars(-contains("people_n")),
funs(./(people_n*9)))))
segment1_max <- alphaLo_test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations < 100) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == 1) %>%
dplyr::pull(observations)
segment1_min <- alphaLo_test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations < 100) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == n()) %>%
dplyr::pull(observations)
segment2_max <- alphaLo_test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations >= 100 & observations <= 1000) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == 1) %>%
dplyr::pull(observations)
segment2_min <- alphaLo_test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations >= 100 & observations <= 1000) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == n()) %>%
dplyr::pull(observations)
segment3_minmax <- alphaLo_test_nested %>%
dplyr::ungroup() %>%
dplyr::filter(observations > 1000) %>%
dplyr::arrange(desc(observations)) %>%
dplyr::filter(row_number() == n()) %>%
dplyr::pull(observations)
alphaLo_segment_proportions <- alphaLo_test_nested_segments_aggregates$aggregated_proportions %>%
dplyr::bind_rows() %>%
dplyr::mutate(group = c(paste0(segment1_min, "-", segment1_max, " observations (n = ", people_n[1], ")"),
paste0(segment2_min, "-", segment2_max, " observations (n = ", people_n[2], ")"),
paste0(segment3_minmax, " observations (n = ", people_n[3], ")"))) %>%
tidyr::pivot_longer(cols = c(-"people_n", -"group")) %>%
dplyr::select(-people_n) %>%
tidyr::pivot_wider(names_from = group, values_from = value)
alphaLo_segment_proportions$name <- alphaLo_test_nested$data[[1]]$name
DT::datatable(alphaLo_segment_proportions %>%
dplyr::mutate_at(vars(-name), funs(scales::percent(., accuracy = 0.1))) %>%
dplyr::slice(c(7, 8, 9, 12)),
options = list(pageLength = 12),
caption = paste0("Tests for stationarity and non-linearity. Columns indicate
segments in the full sample of n = 20, and rows indicate tests.
Each cell indicates the percentage of time series (out of n
times 9, as each participant collected data on 9 variables),
where H0 is rejected at p<", alphaLo %>% round(., 4),
". AR = autoregressive."))
DT::datatable(alphaLo_segment_proportions %>%
dplyr::mutate_at(vars(-name), funs(scales::percent(., accuracy = 0.1))),
options = list(pageLength = 12),
caption = paste0("Tests for stationarity and non-linearity. Columns indicate
segments in the full sample of n = 20, and rows indicate tests.
Each cell indicates the percentage of time series (out of n
times 9, as each participant collected data on 9 variables),
where H0 is rejected at p<", alphaLo %>% round(., 4),
". AR = autoregressive."))Interpretation instructions: One time series is one variable in one person’s data. The top-left number indicates the number of rejected time series, using the test indicated by row name, in the variable indicated by column name. The total possible number of tested time series would be the number of collected time series of that variable, that is, the number of individuals in the dataset (20).
Rejections out of a total of 20 participants. Rejection threshold at p<0.0125.
DT::datatable(tests_number_of_series %>%
dplyr::slice(c(7, 8, 9, 12)),
options = list(pageLength = 12),
caption = paste0("Number of time series (out of number of participants = 20)
where H0 is rejected at p<",
alphaLevel))
DT::datatable(tests_number_of_series,
options = list(pageLength = 12),
caption = paste0("Number of time series (out of number of participants = 20)
where H0 is rejected at p<",
alphaLevel)) #%>%Rejections out of a total of 20 participants. Rejection threshold at p<0.0042.
DT::datatable(alphaLo_tests_number_of_series %>%
dplyr::slice(c(7, 8, 9, 12)),
options = list(pageLength = 12),
caption = paste0("Number of time series (out of number of participants = 20)
where H0 is rejected at p<",
alphaLo %>% round(., 4))) #%>%
DT::datatable(alphaLo_tests_number_of_series,
options = list(pageLength = 12),
caption = paste0("Number of time series (out of number of participants = 20)
where H0 is rejected at p<",
alphaLo %>% round(., 4))) #%>%Interpretation instructions: One time series is one variable in one person’s data. The top left number indicates how many time series—for the person indicated by the column heading—were rejected by the test indicated by the row heading. The maximum possible number of rejections is the number of variables collected by the person, that is, nine.
DT::datatable(rejected_vars_per_test %>%
dplyr::slice(c(7, 8, 9, 12)),
options = list(pageLength = 12),
caption = paste0("Number of time series (out of 9, i.e. per person per test),
where H0 is rejected at p<",
alphaLevel))DT::datatable(rejected_vars_per_test,
options = list(pageLength = 12),
caption = paste0("Number of time series (out of 9, i.e. per person per test),
where H0 is rejected at p<",
alphaLevel))DT::datatable(alphaLo_rejected_vars_per_test %>%
dplyr::slice(c(7, 8, 9, 12)),
options = list(pageLength = 12),
caption = paste0("Number of time series (out of 9, i.e. per person per test),
where H0 is rejected at p<",
alphaLo %>% round(., 4)))DT::datatable(alphaLo_rejected_vars_per_test,
options = list(pageLength = 12),
caption = paste0("Number of time series (out of 9, i.e. per person per test),
where H0 is rejected at p<",
alphaLo %>% round(., 4)))Interpretation instructions: Each table indicates results for one person. Numbers in cells show the p-values (or maximum p-values in case of McLeod-Li test) for tests of assumptions of data-generating processes.
for(i in test_nested$User) {
test_nested_oneperson <- test_nested %>%
dplyr::filter(User == i)
test_results <- DT::datatable(test_nested_oneperson$data[[1]] %>%
dplyr::select(-`test_number`) %>%
mutate_if(is.numeric, ~sprintf(., fmt="%#.3f")), # preserve 3 decimals
options = list(pageLength = 12),
caption = "P-values (or maximum p-values in case of McLeod-Li test)
for tests of assumptions of data-generating processes") %>%
DT::formatRound(columns = 2:10,
digits=3)
cat('\n\n##', i, '\n\n ')
cat(knitr::knit_print(test_results))
}\(~\)
Description of the R environment can be found below.
devtools::session_info()
## - Session info -------------
## setting
## version
## os
## system
## ui
## language
## collate
## ctype
## tz
## date
## value
## R version 4.0.5 (2021-03-31)
## Windows 10 x64
## x86_64, mingw32
## RStudio
## (EN)
## Finnish_Finland.1252
## Finnish_Finland.1252
## Europe/Helsinki
## 2021-05-19
##
## - Packages -----------------
## package *
## abind
## assertthat
## backports
## base64enc
## BiocManager
## bookdown *
## brainGraph
## broom
## bslib
## cachem
## callr
## casnet
## cellranger
## checkmate
## cli
## cluster
## codetools
## colorspace
## corpcor
## cowplot
## crayon
## crosstalk
## curl
## data.table
## DBI
## dbplyr
## desc
## devtools
## digest
## DirectedClustering
## doParallel
## dplyr *
## DT
## ellipsis
## evaluate
## fansi
## farver
## fastmap
## fdrtool
## forcats *
## foreach
## forecast
## foreign
## Formula
## fracdiff
## fs
## generics
## ggimage
## ggplot2 *
## ggplotify
## glasso
## glue
## gridExtra
## gridGraphics
## gtable
## gtools
## haven
## highr
## Hmisc
## hms
## htmlTable
## htmltools
## htmlwidgets
## httpuv
## httr
## igraph
## invctr
## iterators
## jpeg
## jquerylib
## jsonlite
## knitr *
## labeling
## later
## lattice
## latticeExtra
## lavaan
## leaps
## lifecycle
## lmtest
## locfit
## lubridate
## magick
## magrittr
## MASS
## Matrix
## memoise
## mgcv
## mime
## mnormt
## modelr
## munsell
## nlme
## nnet
## pander
## patchwork *
## pbapply
## pbivnorm
## permute
## pillar
## pkgbuild
## pkgconfig
## pkgload
## plyr
## png
## prettyunits
## processx
## promises
## proxy
## ps
## psych
## purrr *
## qgraph
## quadprog
## quantmod
## R6
## randtests
## RColorBrewer
## Rcpp
## readr *
## readxl
## remotes
## reprex
## reshape2
## rlang
## rmarkdown
## rpart
## rprojroot
## rstudioapi
## rvcheck
## rvest
## sass
## scales
## sessioninfo
## shiny *
## stabledist
## stringi
## stringr *
## survival
## testthat
## tibble *
## tidyr *
## tidyselect
## tidyverse *
## timeDate
## tmvnsim
## TSA
## tseries
## TTR
## urca
## usethis
## utf8
## vctrs
## viridisLite
## withr
## xfun
## xml2
## xtable
## xts
## yaml
## zoo
## version date lib
## 1.4-5 2016-07-21 [1]
## 0.2.1 2019-03-21 [1]
## 1.2.1 2020-12-09 [1]
## 0.1-3 2015-07-28 [1]
## 1.30.12 2021-03-28 [1]
## 0.21 2020-10-13 [1]
## 3.0.0 2020-09-29 [1]
## 0.7.6.9001 2021-04-19 [1]
## 0.2.4 2021-01-25 [1]
## 1.0.4 2021-02-13 [1]
## 3.6.0 2021-03-28 [1]
## 0.1.6 2021-05-17 [1]
## 1.1.0 2016-07-27 [1]
## 2.0.0 2020-02-06 [1]
## 2.4.0 2021-04-05 [1]
## 2.1.1 2021-02-14 [2]
## 0.2-18 2020-11-04 [2]
## 2.0-0 2020-11-11 [1]
## 1.6.9 2017-04-01 [1]
## 1.1.1 2020-12-30 [1]
## 1.4.1 2021-02-08 [1]
## 1.1.1 2021-01-12 [1]
## 4.3 2019-12-02 [1]
## 1.14.0 2021-02-21 [1]
## 1.1.1 2021-01-15 [1]
## 2.1.1 2021-04-06 [1]
## 1.3.0 2021-03-05 [1]
## 2.4.0 2021-04-07 [1]
## 0.6.27 2020-10-24 [1]
## 0.1.1 2018-01-11 [1]
## 1.0.16 2020-10-16 [1]
## 1.0.5 2021-03-05 [1]
## 0.18 2021-04-14 [1]
## 0.3.1 2020-05-15 [1]
## 0.14 2019-05-28 [1]
## 0.4.2 2021-01-15 [1]
## 2.1.0 2021-02-28 [1]
## 1.1.0 2021-01-25 [1]
## 1.2.16 2021-01-06 [1]
## 0.5.1 2021-01-27 [1]
## 1.5.1 2020-10-15 [1]
## 8.14 2021-03-11 [1]
## 0.8-81 2020-12-22 [2]
## 1.2-4 2020-10-16 [1]
## 1.5-1 2020-01-24 [1]
## 1.5.0 2020-07-31 [1]
## 0.1.0 2020-10-31 [1]
## 0.2.8 2020-04-02 [1]
## 3.3.3 2020-12-30 [1]
## 0.0.5 2020-03-12 [1]
## 1.11 2019-10-01 [1]
## 1.4.2 2020-08-27 [1]
## 2.3 2017-09-09 [1]
## 0.5-1 2020-12-13 [1]
## 0.3.0 2019-03-25 [1]
## 3.8.2 2020-03-31 [1]
## 2.3.1 2020-06-01 [1]
## 0.9 2021-04-16 [1]
## 4.5-0 2021-02-28 [1]
## 1.0.0 2021-01-13 [1]
## 2.1.0 2020-09-16 [1]
## 0.5.1.1 2021-01-22 [1]
## 1.5.3 2020-12-10 [1]
## 1.5.5 2021-01-13 [1]
## 1.4.2 2020-07-20 [1]
## 1.2.6 2020-10-06 [1]
## 0.1.0 2019-03-07 [1]
## 1.0.13 2020-10-15 [1]
## 0.1-8.1 2019-10-24 [1]
## 0.1.3 2020-12-17 [1]
## 1.7.2 2020-12-09 [1]
## 1.32 2021-04-14 [1]
## 0.4.2 2020-10-20 [1]
## 1.1.0.1 2020-06-05 [1]
## 0.20-41 2020-04-02 [2]
## 0.6-29 2019-12-19 [1]
## 0.6-8 2021-03-10 [1]
## 3.1 2020-01-16 [1]
## 1.0.0 2021-02-15 [1]
## 0.9-38 2020-09-09 [1]
## 1.5-9.4 2020-03-25 [1]
## 1.7.10 2021-02-26 [1]
## 2.7.1 2021-03-20 [1]
## 2.0.1 2020-11-17 [1]
## 7.3-53.1 2021-02-12 [2]
## 1.3-2 2021-01-06 [2]
## 2.0.0 2021-01-26 [1]
## 1.8-34 2021-02-16 [2]
## 0.10 2021-02-13 [1]
## 2.0.2 2020-09-01 [1]
## 0.1.8 2020-05-19 [1]
## 0.5.0 2018-06-12 [1]
## 3.1-152 2021-02-04 [2]
## 7.3-15 2021-01-24 [2]
## 0.6.3 2018-11-06 [1]
## 1.1.1 2020-12-17 [1]
## 1.4-3 2020-08-18 [1]
## 0.6.0 2015-01-23 [1]
## 0.9-5 2019-03-12 [1]
## 1.6.0 2021-04-13 [1]
## 1.2.0 2020-12-15 [1]
## 2.0.3 2019-09-22 [1]
## 1.2.1 2021-04-06 [1]
## 1.8.6 2020-03-03 [1]
## 0.1-7 2013-12-03 [1]
## 1.1.1 2020-01-24 [1]
## 3.5.1 2021-04-04 [1]
## 1.2.0.1 2021-02-11 [1]
## 0.4-25 2021-03-05 [1]
## 1.6.0 2021-02-28 [1]
## 2.1.3 2021-03-27 [1]
## 0.3.4 2020-04-17 [1]
## 1.6.9 2021-01-28 [1]
## 1.5-8 2019-11-20 [1]
## 0.4.18 2020-12-09 [1]
## 2.5.0 2020-10-28 [1]
## 1.0 2014-11-17 [1]
## 1.1-2 2014-12-07 [1]
## 1.0.6 2021-01-15 [1]
## 1.4.0 2020-10-05 [1]
## 1.3.1 2019-03-13 [1]
## 2.3.0 2021-04-01 [1]
## 2.0.0 2021-04-02 [1]
## 1.4.4 2020-04-09 [1]
## 0.4.10 2020-12-30 [1]
## 2.7 2021-02-19 [1]
## 4.1-15 2019-04-12 [2]
## 2.0.2 2020-11-15 [1]
## 0.13 2020-11-12 [1]
## 0.1.8 2020-03-01 [1]
## 1.0.0 2021-03-09 [1]
## 0.3.1 2021-01-24 [1]
## 1.1.1 2020-05-11 [1]
## 1.1.1 2018-11-05 [1]
## 1.6.0 2021-01-25 [1]
## 0.7-1 2016-09-12 [1]
## 1.5.3 2020-09-09 [1]
## 1.4.0 2019-02-10 [1]
## 3.2-10 2021-03-16 [2]
## 3.0.2 2021-02-14 [1]
## 3.1.1 2021-04-18 [1]
## 1.1.3 2021-03-03 [1]
## 1.1.0 2020-05-11 [1]
## 1.3.1 2021-04-15 [1]
## 3043.102 2018-02-21 [1]
## 1.0-2 2016-12-15 [1]
## 1.3 2020-09-13 [1]
## 0.10-48 2020-12-04 [1]
## 0.24.2 2020-09-01 [1]
## 1.3-0 2016-09-06 [1]
## 2.0.1 2021-02-10 [1]
## 1.2.1 2021-03-12 [1]
## 0.3.7 2021-03-29 [1]
## 0.3.0 2018-02-01 [1]
## 2.4.2 2021-04-18 [1]
## 0.22 2021-03-11 [1]
## 1.3.2 2020-04-23 [1]
## 1.8-4 2019-04-21 [1]
## 0.12.1 2020-09-09 [1]
## 2.2.1 2020-02-01 [1]
## 1.8-9 2021-03-09 [1]
## source
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## Github (tidymodels/broom@0f4c1ca)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.4)
## Github (fredhasselman/casnet@bb112ee)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.4)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.4)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.4)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.4)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.3)
## CRAN (R 4.0.4)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.4)
## CRAN (R 4.0.3)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.5)
## CRAN (R 4.0.4)
## CRAN (R 4.0.5)
##
## [1] C:/rlibs/4.0.5
## [2] C:/Program Files/R/R-4.0.5/library
pander::pander(sessionInfo())R version 4.0.5 (2021-03-31)
Platform: x86_64-w64-mingw32/x64 (64-bit)
locale: LC_COLLATE=Finnish_Finland.1252, LC_CTYPE=Finnish_Finland.1252, LC_MONETARY=Finnish_Finland.1252, LC_NUMERIC=C and LC_TIME=Finnish_Finland.1252
attached base packages: stats, graphics, grDevices, utils, datasets, methods and base
other attached packages: patchwork(v.1.1.1), bookdown(v.0.21), knitr(v.1.32), shiny(v.1.6.0), forcats(v.0.5.1), stringr(v.1.4.0), dplyr(v.1.0.5), purrr(v.0.3.4), readr(v.1.4.0), tidyr(v.1.1.3), tibble(v.3.1.1), ggplot2(v.3.3.3) and tidyverse(v.1.3.1)
loaded via a namespace (and not attached): readxl(v.1.3.1), backports(v.1.2.1), Hmisc(v.4.5-0), plyr(v.1.8.6), igraph(v.1.2.6), splines(v.4.0.5), crosstalk(v.1.1.1), usethis(v.2.0.1), digest(v.0.6.27), foreach(v.1.5.1), casnet(v.0.1.6), htmltools(v.0.5.1.1), magick(v.2.7.1), fansi(v.0.4.2), magrittr(v.2.0.1), checkmate(v.2.0.0), memoise(v.2.0.0), cluster(v.2.1.1), doParallel(v.1.0.16), remotes(v.2.3.0), modelr(v.0.1.8), stabledist(v.0.7-1), xts(v.0.12.1), forecast(v.8.14), tseries(v.0.10-48), prettyunits(v.1.1.1), jpeg(v.0.1-8.1), colorspace(v.2.0-0), rvest(v.1.0.0), haven(v.2.3.1), xfun(v.0.22), callr(v.3.6.0), crayon(v.1.4.1), jsonlite(v.1.7.2), survival(v.3.2-10), zoo(v.1.8-9), iterators(v.1.0.13), glue(v.1.4.2), gtable(v.0.3.0), pkgbuild(v.1.2.0), DirectedClustering(v.0.1.1), quantmod(v.0.4.18), abind(v.1.4-5), scales(v.1.1.1), DBI(v.1.1.1), Rcpp(v.1.0.6), xtable(v.1.8-4), viridisLite(v.0.3.0), htmlTable(v.2.1.0), tmvnsim(v.1.0-2), gridGraphics(v.0.5-1), foreign(v.0.8-81), proxy(v.0.4-25), brainGraph(v.3.0.0), Formula(v.1.2-4), randtests(v.1.0), DT(v.0.18), stats4(v.4.0.5), htmlwidgets(v.1.5.3), httr(v.1.4.2), lavaan(v.0.6-8), RColorBrewer(v.1.1-2), ellipsis(v.0.3.1), pkgconfig(v.2.0.3), farver(v.2.1.0), sass(v.0.3.1), nnet(v.7.3-15), invctr(v.0.1.0), dbplyr(v.2.1.1), locfit(v.1.5-9.4), utf8(v.1.2.1), later(v.1.1.0.1), ggplotify(v.0.0.5), tidyselect(v.1.1.0), labeling(v.0.4.2), rlang(v.0.4.10), reshape2(v.1.4.4), munsell(v.0.5.0), cellranger(v.1.1.0), tools(v.4.0.5), cachem(v.1.0.4), cli(v.2.4.0), generics(v.0.1.0), devtools(v.2.4.0), broom(v.0.7.6.9001), fdrtool(v.1.2.16), evaluate(v.0.14), fastmap(v.1.1.0), yaml(v.2.2.1), processx(v.3.5.1), fs(v.1.5.0), pander(v.0.6.3), glasso(v.1.11), pbapply(v.1.4-3), nlme(v.3.1-152), mime(v.0.10), leaps(v.3.1), xml2(v.1.3.2), compiler(v.4.0.5), rstudioapi(v.0.13), curl(v.4.3), png(v.0.1-7), testthat(v.3.0.2), reprex(v.2.0.0), bslib(v.0.2.4), pbivnorm(v.0.6.0), stringi(v.1.5.3), ggimage(v.0.2.8), highr(v.0.9), ps(v.1.6.0), TSA(v.1.3), qgraph(v.1.6.9), desc(v.1.3.0), lattice(v.0.20-41), Matrix(v.1.3-2), psych(v.2.1.3), urca(v.1.3-0), permute(v.0.9-5), vctrs(v.0.3.7), pillar(v.1.6.0), lifecycle(v.1.0.0), BiocManager(v.1.30.12), lmtest(v.0.9-38), jquerylib(v.0.1.3), data.table(v.1.14.0), cowplot(v.1.1.1), corpcor(v.1.6.9), httpuv(v.1.5.5), R6(v.2.5.0), latticeExtra(v.0.6-29), promises(v.1.2.0.1), gridExtra(v.2.3), sessioninfo(v.1.1.1), codetools(v.0.2-18), gtools(v.3.8.2), MASS(v.7.3-53.1), assertthat(v.0.2.1), pkgload(v.1.2.1), rprojroot(v.2.0.2), withr(v.2.4.2), fracdiff(v.1.5-1), mnormt(v.2.0.2), mgcv(v.1.8-34), parallel(v.4.0.5), hms(v.1.0.0), timeDate(v.3043.102), quadprog(v.1.5-8), grid(v.4.0.5), rpart(v.4.1-15), rmarkdown(v.2.7), rvcheck(v.0.1.8), TTR(v.0.24.2), lubridate(v.1.7.10) and base64enc(v.0.1-3)