Assess risk using the method of D'Agostino et al. (2008)

Description

Assess risk using the method of D'Agostino et al. (2008)

Usage

DAgostino_wrapper(
  sex,
  age,
  total_cholesterol,
  hdl,
  systolic,
  bp_treated,
  diabetes,
  smoker,
  points = TRUE
)

risk_DAgostino(
  age,
  total_cholesterol,
  hdl,
  systolic,
  age_points,
  tc_points,
  sbp_breaks,
  sbp_points,
  diabetes,
  smoker
)

get_risk(x, breaks, values)

DAgostino_raw(result, sex)

Arguments

Note

Parameter descriptions have been inherited from cvd_risk, but only direct scalar values (i.e., not column names) are allowed for this function

References

D'Agostino et al. (2008)

PAutilities: Streamline Physical Activity Research

Description

A collection of utilities that are useful for a broad range of tasks that are common in physical activity research. The main features (with associated functions in parentheses) are:

Details

* Bland-Altman plots (ba_plot) * Bout analysis for moderate-to-vigorous physical activity (bout_mvpa) * Formatted descriptive statistics descriptives * Demographic calculations (get_age and get_BMI_percentile) * Metabolic calculations (get_bmr, weir_equation, and get_kcal_vo2_conversion) * Analysis of bout detection algorithm performance (get_transition_info and associated methods, e.g. summary and plot)

Addition and subtraction for objects of class summaryTransition

Description

Addition and subtraction for objects of class summaryTransition

Usage

add_summaryTransition(e1, e2)

## S4 method for signature 'summaryTransition,summaryTransition'
e1 + e2

subtract_summaryTransition(e1, e2)

## S4 method for signature 'summaryTransition,summaryTransition'
e1 - e2

Arguments

Value

a summaryTransition object (see summary.transition

As("summaryTransition", "data.frame")

Description

As("summaryTransition", "data.frame")

As("summaryTransition", "list")

Perform Bland-Altman analysis on a data frame

Description

Perform Bland-Altman analysis on a data frame

Usage

ba_analysis(df, x_var, y_var, regress_against = c("Y", "XY_mean"), ...)

Arguments

Value

A data frame that has various summaries (means, standard deviations, and missing data details) plus mean bias (mean_bias column) and limits of agreement (lower_LOA and upper_LOA columns)

Examples

data(ex_data, package = "PAutilities")
ba_analysis(ex_data, "Axis1", "Vector.Magnitude", "XY_mean")
ba_analysis(
  ex_data, "Axis1", "Vector.Magnitude", "XY_mean",
  an_arbitrary_added_column = "Example of passing an extra column"
)

Create a Bland-Altman plot

Description

Create a Bland-Altman plot

Usage

ba_plot(plotdata, x_var, y_var, x_name, y_name, shape = 16, ...)

Arguments

Value

a Bland-Altman plot

References

Bland, J. M., & Altman, D. G. (1986). Statistical methods for assessing agreement between two methods of clinical measurement. lancet, 1(8476), 307-310.

See Also

ba_analysis

Examples

data(ex_data, package = "PAutilities")

# Reduce the number of data points (for illustration purposes) by isolating
# the 150 largest cases

illustration_threshold <-
    quantile(ex_data$Axis1, probs = 1 - (150 / nrow(ex_data)))
ex_data <- ex_data[ex_data$Axis1 > illustration_threshold, ]

# Generate the plot
my_ba <- ba_plot(
    ex_data,
    "(Axis1 + Axis3) / 2",
    "Axis1 - Axis3",
    "mean(Axis1, Axis3)",
    "Axis1 - Axis3"
)

my_ba


# You can add to the plot as you would a normal ggplot object
    my_ba +
      ggplot2::geom_text(
      x = 2000, y = 9000, label = "A",
      size = 8, fontface = "bold", colour = "blue"
      )

# With caution, you can change some automatic options (e.g. color of
# regression line) by overwriting in a new layer

    my_ba + ggplot2::geom_smooth(method = "lm", se = FALSE, colour = "blue")

Internal helper functions for get_BMI_percentile

Description

Internal helper functions for get_BMI_percentile

Usage

percentile_age(age_mos, age_yrs)

percentile_BMI(BMI, weight_kg, height_cm)

percentile_index(reference, age_mos)

percentile_lms(reference, colname, lesser_index, greater_index, increment)

percentile_reference(sex)

percentile_sex(sex = c("error", "male", "female"))

percentile_z(BMI, L, M, S)

percentile_back_calculate(p = 0.95, L, M, S)

Arguments

See Also

Flegal and Cole (2013)

Classify moderate-to-vigorous physical activity in bouts of a specific minimum length

Description

Classify moderate-to-vigorous physical activity in bouts of a specific minimum length

Usage

bout_mvpa(
  intensity,
  var_type = c("METs", "Intensity"),
  min_duration = 10,
  termination = 3,
  MoreArgs = list(breaks = c(-Inf, 1.51, 3, Inf), labels = c("SB", "LPA", "MVPA"), right
    = FALSE),
  ...,
  timestamps = NULL,
  output_var = c("is_MVPA", "bout_tracker")
)

Arguments

Value

based on the setting of output_var, one or both of is_MVPA and bout_tracker will be returned, the former being a vector of indicators (1 or 0) specifying whether a minute is part of a valid MVPA bout, and the latter being a collapsed data frame giving only the valid bouts of MVPA and the relevant information (i.e., duration of the bout, minutes of MVPA, and percentage of time spent in MVPA within the bout). If both are selected, they are returned in a list.

Examples

data(ex_data, package = "PAutilities")
ex_data$DateTime <- as.POSIXct(ex_data$DateTime, "UTC")


# Runs with a warning

bout_mvpa(ex_data$METs, "METs")

bout_mvpa(ex_data$METs, "METs", timestamps = ex_data$DateTime)


# Recommended usage
lapply(split(ex_data, strftime(ex_data$DateTime, "%Y-%m-%d", "UTC")),
function(x) {
bout_mvpa(x$METs, "METs", timestamps = x$DateTime)
})

lapply(split(ex_data, strftime(ex_data$DateTime, "%Y-%m-%d", "UTC")),
function(x) {
bout_mvpa(x$METs,
"METs",
timestamps = x$DateTime,
output_var = "is_MVPA")
})

lapply(split(ex_data, strftime(ex_data$DateTime, "%Y-%m-%d", "UTC")),
function(x) {
bout_mvpa(x$METs,
"METs",
timestamps = x$DateTime,
output_var = "bout_tracker")
})

Calculate risk of cardiovascular disease

Description

Calculate risk of cardiovascular disease

Usage

cvd_risk(
  x = NULL,
  method = "D'Agostino_2008",
  sex,
  age,
  total_cholesterol,
  hdl,
  systolic,
  bp_treated,
  diabetes,
  smoker,
  points = TRUE,
  ...
)

## Default S3 method:
cvd_risk(
  x = NULL,
  method = "D'Agostino_2008",
  sex,
  age,
  total_cholesterol,
  hdl,
  systolic,
  bp_treated,
  diabetes,
  smoker,
  points = TRUE,
  ...
)

## S3 method for class 'data.frame'
cvd_risk(
  x = NULL,
  method = "D'Agostino_2008",
  sex,
  age,
  total_cholesterol,
  hdl,
  systolic,
  bp_treated,
  diabetes,
  smoker,
  points = TRUE,
  combine = TRUE,
  ...
)

Arguments

Value

One or more risk profiles (for default method with points = TRUE, or for data frames with combine = FALSE & points = TRUE). Otherwise numeric risk percentage (for points = FALSE, scalars and data frames) or an integer vector (for data frames with combine = TRUE & points = FALSE)

References

D'Agostino et al. (2008)

Examples

cvd_risk(sex = "Female", age = 111, total_cholesterol = 111, systolic = 111,
hdl = 11, bp_treated = FALSE, diabetes = TRUE, smoker = TRUE)


df <- data.frame(
  sex = sample(c("Male", "Female"), 5, TRUE),
  age = sample(30:100, 5, TRUE),
  tc = sample(150:300, 5, TRUE),
  hdl = sample(30:70, 5, TRUE),
  sbp = sample(100:180, 5, TRUE),
  bpmed = sample(c(TRUE, FALSE), 5, TRUE),
  diabetes = sample(c(TRUE, FALSE), 5, TRUE),
  smoker = sample(c(TRUE, FALSE), 5, TRUE)
)

cvd_risk(
  df, sex = "sex", age = "age",
  total_cholesterol = "tc", hdl = "hdl",
  systolic = "sbp", bp_treated = "bpmed",
  diabetes = "diabetes", smoker = "smoker",
  combine = FALSE
)

Compute descriptive statistics for a variable in the metabolic data set

Description

Compute descriptive statistics for a variable in the metabolic data set

Usage

descriptives(dataset, variable, group = NULL)

Arguments

Value

a data frame of formatted summary statistics

Examples

data(ex_data, package = "PAutilities")
ex_data$group_var <- rep(
 c("One", "Two", "Three"),
 each = ceiling(nrow(ex_data)/3)
)[seq(nrow(ex_data))]
descriptives(ex_data, "Axis1", "group_var")

Check if a dataframe is continuous

Description

Check if a dataframe is continuous

Usage

df_continuous(df, time_var = "Timestamp", digits = 6, ...)

Arguments

Value

a logical scalar indicating whether the dataframe reflects a continuous time series

Examples

data(ex_data, package = "PAutilities")
df_continuous(ex_data, "DateTime", tz = "UTC")
df_continuous(ex_data[-c(300:500), ], "DateTime", tz = "UTC")

Reorder the columns of a data frame

Description

Reorder the columns of a data frame

Usage

df_reorder(df, columns, after)

Arguments

Value

The reordered data frame

Examples

df <- data.frame(a = 1:10, b = 11:20, c = 21:30, d = 31:40)
df_reorder(df, 2:3, "d")
df_reorder(df, c("c", "d"), "a")

Account for cases that refuse all matches

Description

To run the college admissions algorithm, it is assumed that each student/college has at least one possible match. In the activity transition application, possible matches are restricted to "nearby" cases, i.e. within some specified window_size. Thus, if there are no matches close by, there are no possible matches, and the case needs to be removed from the analysis in the college admissions algorithm. It needs to be re-inserted afterwards and labeled as a false positive or false negative, depending on whether it was a college (i.e., a predicted transition) or a student (i.e., an actual transition), respectively.

Usage

dim_check(x)

prune_prefs(prefs)

Arguments

Value

A pruned list of matrices containing only cases with at least one possible match

Determine epoch length in seconds

Description

Determine epoch length in seconds

Usage

epoch_length_sec(timestamps, digits = 6)

Arguments

Details

The function is designed to work even when the epoch length is less than one second (e.g., for raw accelerometry data). Thus, it is not possible to base the code on convenient difftime methods. Instead, numeric operations are performed after running unclass on the input. This sometimes results in minuscule fluctuations of the calculated epoch length (e.g., +/- 0.0000002). Thus, the code rounds everything to the precision indicated by digits. For most applications, the default value (digits = 6) should be well past the range of meaningful fluctuations and lead to a favorable outcome. But the digits argument can also be adjusted if greater assurance is needed.

After rounding, the code checks for the existence of multiple epoch lengths. If they are detected (e.g., due to a discontinuity in the file), a warning is issued and the most prevalent epoch length is returned. The warning will specify all the different epoch lengths that were detected, which may be useful information for troubleshooting.

Value

The epoch length of the data, in seconds

Examples

epoch_length_sec(Sys.time() + 0:5)
epoch_length_sec(Sys.time() + seq(0, 25, 5))

Determine the minimum equivalence zone necessary for establishing equivalence in a paired equivalence test

Description

Paired equivalence tests are conducted based on a pre-specified zone of equivalence. Following the test, it is useful to know how minimally small or large the zone would have needed to be in order for the test to indicate equivalence.

Usage

equivalent_at(result)

get_absolute_equivalent_at(result)

get_relative_equivalent_at(result)

Arguments

Example data for calculating bouts of moderate-to-vigorous physical activity

Description

A dataset containing accelerometer data and predicted energy expenditure in metabolic equivalents (METs) that can be used to classify moderate-to-vigorous physical activity in continuous bouts.

Usage

ex_data

Format

A data frame with 10080 rows and 12 variables:

FileID

character. Name of the file originating the data

Date

character giving the date ("%m/%d/%Y")

Time

character giving the time ("%H:%M:%S")

DateTime

full timestamp (%Y-%m-%d %H:%M:%S) given as character

dayofyear

numeric day of the year (i.e., julian date)

minofday

numeric minute of the day (i.e., 0 for midnight and 1439 for 11:59)

Axis1

activity counts for the device's first axis

Axis2

activity counts for the device's second axis

Axis3

activity counts for the device's third axis

Steps

number of steps taken

Vector.Magnitude

vector magnitude (Euclidian norm) of the activity counts from the three axes

METs

predicted energy expenditure, in metabolic equivalents

Drop incomplete days from a dataset

Description

Drop incomplete days from a dataset

Usage

full_days(
  df,
  time_var = "Timestamp",
  drop = c("all", "leading", "trailing", "label"),
  epoch_length_sec = NULL,
  label_name = "is_full_day",
  digits = 6,
  check_continuous = TRUE,
  discontinuous_action = c("stop", "warn"),
  ...
)

Arguments

Value

an updated copy of df, in which incomplete days are addressed according to the selected value of drop.

See Also

df_continuous

Examples

data(ex_data, package = "PAutilities")
ex_data <- full_days(
  ex_data, "DateTime", "label", 60,
  "full_day_indicator", tz = "UTC"
)
head(ex_data)

Calculate youth BMI percentile from CDC standards

Description

Calculate youth BMI percentile from CDC standards

Usage

get_BMI_percentile(
  weight_kg,
  height_cm,
  age_yrs = NULL,
  age_mos = NULL,
  sex = c("Male", "Female"),
  BMI = NULL,
  df = NULL,
  output = c("percentile", "classification", "both", "summary")
)

percentile_df(
  df,
  weight_kg = "default",
  height_cm = "default",
  age_yrs = "default",
  age_mos = "default",
  sex = "default",
  BMI = "default",
  output = c("percentile", "classification", "both", "summary")
)

Arguments

Details

Only one of age_mos and age_yrs is required. The former will be used if both are provided. If age_mos is not provided, it will be calculated based on age_yrs, assuming 365.2425 days per year and 30.4375 days per month. Depending on how the initial age calculation was made, rounding error will occur. Thus, use of the get_age function is recommended, with units = "months". If BMI is provided, there is no need to pass weight_kg or height_cm.

Value

One of: A numeric scalar giving the BMI percentile (for output = "percentile"); a factor scalar giving the weight status (for output = "classification"); a list with the percentile and classification (for output = "both"); or a list with the BMI, percentile, classification, and severe obesity cutoff (for output = "summary").

References

This function was developed with reference to public domain resources provided by the Centers for Disease Control and Prevention. For more information, see:

https://www.cdc.gov/bmi/adult-calculator/bmi-categories.html

https://www.cdc.gov/growthcharts/cdc_charts.htm

See Also

doi:10.3945/ajcn.2009.28335 Kelly et al. (2013)

Examples

get_BMI_percentile(39.4, 144.5, 12.35, sex = "Male")

Calculate age

Description

Takes two Date objects and calculates age based on difftime (in days) divided by 365.2425 days per year (for age in years) or 30.4375 days per month (for age in months).

Usage

get_age(birthdate, current_date, units = c("years", "months"))

Arguments

Value

Numeric value giving age in the specified units.

Examples

get_age(as.Date("2000-01-01"), Sys.Date(), "years")

Calculate body mass index

Description

Calculate body mass index

Usage

get_bmi(
  wt,
  wt_unit = c("kg", "lb", "oz", "st"),
  ht,
  ht_unit = c("cm", "m", "in", "ft"),
  target = NULL
)

get_wt_kg(wt, wt_unit = c("kg", "lb", "oz", "st"))

get_ht_m2(ht, ht_unit = c("cm", "m", "in", "ft"))

bmi_check(bmi)

target_wt(
  target,
  ht,
  ht_unit = c("cm", "m", "in", "ft"),
  wt_unit = c("kg", "lb", "oz", "st")
)

Arguments

Value

If target is NULL (default), the function returns the body mass index. If target is provided, the function will use target and ht to back-calculate a target body mass in the units defined by wt_unit (kg by default).

Examples

get_bmi(160, "lb", 180, "cm")
get_bmi(ht = 5.90, ht_unit = "ft", target = 24, wt_unit = "st")
get_bmi(wt = c(60:79, NA), ht = c(NA, 160:179))

Retrieve estimated basal metabolic rate for an individual

Description

Retrieve estimated basal metabolic rate for an individual

Usage

get_bmr(
  Sex = c("M", "F"),
  Ht = NULL,
  Wt,
  Age,
  verbose = FALSE,
  RER = NULL,
  equation = c("ht_wt", "wt", "both"),
  kcal_table = c("Lusk", "Peronnet", "both"),
  method = c("Schofield", "FAO", "both"),
  MJ_conversion = c("thermochemical", "dry", "convenience", "all"),
  kcal_conversion = 5
)

Arguments

Value

a data frame containing predictions of basal metabolic rate in one column, along with additional columns that indicate how the predictions were obtained (e.g., which sources and conversions were applied)

References

Schofield, W. N. (1985). Predicting basal metabolic rate, new standards and review of previous work. Human nutrition. Clinical nutrition, 39, 5-41.

Examples

# Get BMR for an imaginary 900-year-old person (Age is only
# used to determine which equations to use, in this case the
# equations for someone older than 60)

get_bmr(
  Sex = "M", Ht = 1.5, Wt = 80, Age = 900, equation = "both",
  method = "both", RER = 0.865, kcal_table = "both",
  MJ_conversion = c("all")
)

get_bmr(
  Sex = "M", Ht = 1.5, Wt = 80, Age = 900, MJ_conversion = "all",
  kcal_conversion = 4.86
)

get_bmr(
  Sex = "M", Ht = 1.5, Wt = 80, Age = 900, method = "FAO",
  kcal_conversion = 4.86
)

Retrieve indices for a rolling window analysis

Description

Retrieve indices for a rolling window analysis

Usage

get_indices(y_var, window_size = 15L)

Arguments

Value

a list in which each element contains window_size consecutive integers that indicate which elements of y_var would be extracted for that roll of the window

Note

For this function, the output elements contain positions (i.e., indices) from y_var, whereas for rolling_groups the output elements contain the raw values found at each index

See Also

rolling_groups

Examples

result <- get_indices(1:100, 10)
head(result)
tail(result)

Classify activity intensity

Description

Supports intensity classification via energy expenditure with or without additional posture requirements (i.e., for sedentary behavior to be in lying/seated posture)

Usage

get_intensity(mets, posture = NULL, ...)

Arguments

Details

If breaks and labels arguments are not provided, default values are <= 1.5 METs for sedentary behavior, 1.51-2.99 METs for light physical activity, and >= 3.0 METs for moderate-to-vigorous physical activity.

It is expected for the elements of posture to be one of c("lie", "sit", "stand", "other"). The function will run (with a warning) if that requirement is not met, but the output will likely be incorrect.

Value

a factor giving intensity classifications for each element of mets

Examples

mets <- seq(1, 8, 0.2)
posture <- rep(
c("lie", "sit", "stand", "other"), 9
)

intensity_no_posture <- get_intensity(mets)
intensity_posture <- get_intensity(mets, posture)
head(intensity_no_posture)
head(intensity_posture)

Retrieve conversion factors from kilocalories to oxygen consumption

Description

Retrieve conversion factors from kilocalories to oxygen consumption

Usage

get_kcal_vo2_conversion(RER, kcal_table = c("Lusk", "Peronnet", "both"))

Arguments

Details

RER values are matched to the table entries based on the minimum absolute difference. If there is a tie, the lower RER is taken.

Value

numeric vector giving the conversion factor from the specified table(s)

References

Peronnet, F., & Massicotte, D. (1991). Table of nonprotein respiratory quotient: an update. Can J Sport Sci, 16(1), 23-29.

Lusk, G. (1924). Analysis of the oxidation of mixtures of carbohydrate and fat: a correction. Journal of Biological Chemistry, 59, 41-42.

Examples

get_kcal_vo2_conversion(0.85, "both")

Obtain the matchings for predicted and actual activity transitions using the college admissions algorithm

Description

Obtain the matchings for predicted and actual activity transitions using the college admissions algorithm

Usage

get_matchings(prefs)

Arguments

Value

A data frame giving the relative and absolute indices of the matchings, based on optimal outcomes for the students (i.e., the actual transitions)

Obtain preference lists for predicted and actual (reference) activity transitions

Description

When predicting activity transitions, the behavior of the predictor is not known a priori. It may predict too many or too few transitions, and its "intent" is also unknown. Therefore, some method is necessary in order to determine which predictions (if any) should be taken to correspond to a reference transition. There should also be a record of false positives and false negatives. The problem is treated as an instance of the college admissions problem, wherein both parties give their preferences for who they would like to be matched with, and a stable arrangement is sought. This function supports the overall goal by assigning the preferences based on the temporal proximity of predicted and actual transitions. Preferences beyond a specified window_size are not allowed.

Usage

get_preferences(predictions, references, window_size, missing_info)

## S3 method for class 'transition'
summary(object, ...)

Arguments

Value

A list of matrices giving distance-based preferences for both the predicted and reference transitions, formatted to pass directly to hri

a data frame containing indicators that reflect, in different ways, the effectiveness of predicted transitions compared to the set of actual (reference) transitions

Examples

predictions <- (sample(1:100)%%2)
references  <- (sample(1:100)%%2)
window_size <- 7
if (isTRUE(requireNamespace("matchingMarkets", quietly = TRUE))){
  transitions <- get_transition_info(
    predictions, references, window_size
  )
  summary(transitions)
}

Rank preferences for an arbitrary proposer and rejecter, based on distance (i.e., difference) between them

Description

Rank preferences for an arbitrary proposer and rejecter, based on distance (i.e., difference) between them

Usage

get_proposer_rank(proposer, rejecter, window_size)

Arguments

Value

A matrix with length(proposer) columns and length(rejecter) rows, giving ordered preferences for the proposer, based on the absolute difference between the ith proposer index and the rejecter indices, where differences larger than window_size are treated as omitted preferences, i.e., non-possibilities.

Calculate resting energy expenditure

Description

Calculate resting energy expenditure

Usage

get_ree(
  method = c("harris_benedict", "schofield_wt", "schofield_wt_ht", "fao", "muller_wt_ht",
    "muller_ffm"),
  sex,
  age_yr = NA,
  ...,
  output = c("default", "mj_day", "kcal_day", "vo2_ml_min"),
  calorie = c("thermochemical", "convenience", "dry"),
  RER = 0.86,
  kcal_table = c("Lusk", "Peronnet", "both"),
  df = NULL
)

Arguments

Value

Calculated resting energy expenditure

Examples

get_ree("schofield_wt_ht", "female", 57.8, wt_kg = 80, ht_m = 1.50)

Internal functions for calculating resting energy expenditure

Description

Internal functions for calculating resting energy expenditure

Usage

get_ree_dataframe(df, method, sex, age_yr, ...)

get_ree_default(method, sex, age_yr, ...)

ree_single(
  sex = c("female", "male"),
  age_yr,
  method,
  breaks = c(-Inf, 3, 10, 18, 30, 60, Inf),
  labels = c("less3", "3to10", "10to18", "18to30", "30to60", "over60"),
  ...
)

get_stratum(method, sex = c("female", "male"), age_yr, breaks, labels)

get_ree_single_setting(method, sex, age_yr, ..., df)

get_ree_grid(method, output, calorie, RER, kcal_table)

ree_profile(settings)

Arguments

Invoke the Transition Pairing Method

Description

Invoke the Transition Pairing Method

Usage

get_transition_info(predictions, references, window_size = 1, ...)

validate_transition_info_input(predictions, references)

impute_trans(x, out_length)

recode_trans_names(x)

Arguments

Value

an object of class transition that contains necessary information for evaluating the effectiveness of the predictions.

Note

If the lengths of predictions and references differ, a warning is issued, and the shorter vector will be expanded to match the length of the longer, using the original relative/proportional positions of the transitions to determine where they should be placed in the expanded vector. The relative position could be determined different ways, each having unique implications for how well aligned predictions and references are. Therefore, while this function is not unusable when the lengths differ, you should make sure you know what you're doing if you want to use it that way. The safest solution is to expand the shorter vector yourself.

See Also

summary.transition

Examples

set.seed(100)
predictions <- (sample(1:100)%%2)
references  <- (sample(1:100)%%2)
window_size <- 7
if (isTRUE(requireNamespace("matchingMarkets", quietly = TRUE))) {
  get_transition_info(predictions, references, window_size)
}

Run length encoding with indices

Description

Run length encoding with indices

Usage

index_runs(x, zero_index = FALSE)

Arguments

Value

A data frame with information about the runs and start/stop indices

Examples

x <- c(
  FALSE, TRUE, FALSE, FALSE, FALSE, TRUE,
  FALSE, TRUE, TRUE, FALSE, TRUE, FALSE,
  FALSE, FALSE, FALSE, FALSE, TRUE, TRUE,
  FALSE, TRUE
)
head(index_runs(x))

Printing and timing utility for managing processes

Description

Printing and timing utility for managing processes

Usage

manage_procedure(part = c("Start", "End"), ..., timer = NULL, verbose = TRUE)

get_duration(timer)

Arguments

Value

For part = "Start", a proc_time object (i.e., a timer passable to an eventual part = "End" command); for part = "End", invisible

Examples

manage_procedure("Start", "String will be printed\n")
timer <- manage_procedure(
"Start", "Printing a string is optional", verbose = FALSE
)

## Default starting message
manage_procedure("Start")

## Default ending message
manage_procedure("End", timer = timer)

## Other examples
get_duration(timer)
manage_procedure("End", "Custom ending message")

Compute the mean and standard deviation of a vector, returning a formatted string containing the values as 'M +/- SD'

Description

Compute the mean and standard deviation of a vector, returning a formatted string containing the values as 'M +/- SD'

Usage

mean_sd(
  x = NULL,
  MoreArgs = NULL,
  give_df = TRUE,
  ...,
  mean_x = NULL,
  sd_x = NULL
)

## Default S3 method:
mean_sd(
  x = NULL,
  MoreArgs = NULL,
  give_df = TRUE,
  ...,
  mean_x = NULL,
  sd_x = NULL
)

## S3 method for class 'data.frame'
mean_sd(
  x = NULL,
  MoreArgs = NULL,
  give_df = TRUE,
  ...,
  mean_x = NULL,
  sd_x = NULL
)

Arguments

Value

either a formatted character scalar (if give_df == FALSE), or else a data frame containing columns for the mean value, standard deviation, and formatted character string combining the two.

Examples

mean_sd(rnorm(100, 50))

Dispatch resting metabolic rate calculations based on data frame input that specifies conversions etc.

Description

Dispatch resting metabolic rate calculations based on data frame input that specifies conversions etc.

Usage

metabolic_row_wise(calculation, weights)

assemble_wt_ht(calculation, weights)

assemble_wt(calculation, weights)

assemble_fao(calculation, weights)

Arguments

Determine the number of temporal conflicts among the pairs assigned by the Gale-Shapley algorithm

Description

Determine the number of temporal conflicts among the pairs assigned by the Gale-Shapley algorithm

Usage

n_crossings(matchings)

Arguments

Value

integer vector specifying the number of conflicts for each pairing

A combined constructor and validator for paired_equivalence objects

Description

A combined constructor and validator for paired_equivalence objects

Usage

new_paired_equivalence(
  x,
  y,
  y_type = c("both", "criterion", "comparison"),
  alpha = 0.05,
  na.rm = TRUE,
  scale = c("relative", "absolute"),
  absolute_region_width = NULL,
  relative_region_width = NULL
)

Arguments

Value

an initialized paired_equivalence object

Perform equivalence testing on paired samples

Description

Perform equivalence testing on paired samples

Usage

## S3 method for class 'data.frame'
paired_equivalence_test(
  x,
  y,
  y_type = c("both", "criterion", "comparison"),
  alpha = 0.05,
  na.rm = TRUE,
  scale = c("relative", "absolute"),
  absolute_region_width = NULL,
  relative_region_width = NULL,
  ...
)

## Default S3 method:
paired_equivalence_test(
  x,
  y,
  y_type = c("both", "criterion", "comparison"),
  alpha = 0.05,
  na.rm = TRUE,
  scale = c("relative", "absolute"),
  absolute_region_width = NULL,
  relative_region_width = NULL,
  ...
)

paired_equivalence_test(
  x,
  y,
  y_type = c("both", "criterion", "comparison"),
  alpha = 0.05,
  na.rm = TRUE,
  scale = c("relative", "absolute"),
  absolute_region_width = NULL,
  relative_region_width = NULL,
  ...
)

Arguments

Value

a 'paired_equivalence' object summarizing the test input and results

Note

If a value is not specified for the region width that corresponds with scale, a default value will be assigned with a warning.

References

Dixon et al.

Examples

set.seed(1544)
x <- data.frame(
  var1 = rnorm(500, 15, 4),
  var2 = rnorm(500, 23, 7.3)
)
y <- rnorm(500, 17.4, 9)

test_result <- paired_equivalence_test(
  x, y, relative_region_width = 0.25
)

lapply(test_result, head)

A template function for conducting a paired equivalence test

Description

A template function for conducting a paired equivalence test

Usage

paired_equivalence_wrapper(
  x,
  y,
  y_type,
  width,
  epsilon,
  alpha,
  scale,
  na.rm,
  do_test = TRUE
)

Arguments

Plot the outcome of a paired equivalence test

Description

Plot the outcome of a paired equivalence test

Usage

## S3 method for class 'paired_equivalence'
plot(x, shade = "auto", ...)

shaded_equivalence_plot(results, ...)

unshaded_equivalence_plot(results, ...)

Arguments

Details

shaded_equivalence_plot plots the results of an equivalence test in which a single equivalence region applies to all variables. In that case, the equivalence region is displayed as a shaded region. unshaded_equivalence_plot plots the results of an equivalence test in which variables have unique equivalence regions. In that case, the equivalence regions are displayed as dodged "confidence intervals".

Value

A plot of the equivalence test

Examples

set.seed(1544)
y <- rnorm(500, 17.4, 9)
z <- data.frame(
  var1 = rnorm(500, 15, 4),
  var2 = rnorm(500, 23, 7.3)
)

# Optionally create artificial missing values to trigger unshaded plot
missing_indices <- sample(seq(nrow(z)), 250)
z$var1[missing_indices] <- NA

x <- paired_equivalence_test(
  z, y, "criterion", scale = "relative",
  relative_region_width = 0.25
)

plot(x)

Plot a spurious curve

Description

Plot a spurious curve

Usage

## S3 method for class 'spurious_curve'
plot(x, ...)

Arguments

Value

a plot of the object

See Also

spurious_curve

Examples

set.seed(100)
predictions <- (sample(1:100)%%2)
references  <- (sample(1:100)%%2)

trans <- get_transition_info(
  predictions, references, 7
)
result <- spurious_curve(trans)
plot(result)

Plot the transitions and matchings from a transition object

Description

Plot the transitions and matchings from a transition object

Usage

## S3 method for class 'transition'
plot(x, ...)

Arguments

Value

A plot of the predicted and actual transitions in a transition object, as well as the matchings between them

Examples

predictions <- (sample(1:100)%%2)
references  <- (sample(1:100)%%2)
window_size <- 7
if (isTRUE(requireNamespace("matchingMarkets", quietly = TRUE))){
  transitions <- get_transition_info(
    predictions, references, window_size
  )
  plot(transitions)
}

Impute placeholder values into a transition object

Description

If missing values are passed to get_transition_info, the prediction and criterion data streams become irregularly spaced. This fixes the spacing issue.

Usage

reconstruct_transitions(x)

Arguments

Perform residual adjustment on an epidemiologic variable

Description

Perform residual adjustment on an epidemiologic variable

Usage

residual_adjust(d, variable, confounder, label, verbose = FALSE)

Arguments

Value

The original d object, with an extra column reflecting residual adjustments on the selected variable.

Examples

d <- data.frame(
  VARIABLE = rnorm(100, 10, 2),
  CONFOUNDER = rnorm(100, 3, 7)
)
result <- residual_adjust(d, "VARIABLE", "CONFOUNDER", "ADJUSTED")

head(d)
head(result)

Calculate resting metabolic rate using a sliding window method

Description

Calculate resting metabolic rate using a sliding window method

Usage

rmr_sliding(
  vo2_values,
  vo2_timestamps,
  start_time,
  stop_time,
  window_size_minutes = 5
)

Arguments

Value

A data frame giving the oxygen consumption from the lowest window, as well as the time difference from first to last breath in the same window.

Examples

set.seed(144)
fake_start_time <- Sys.time()
fake_stop_time <- fake_start_time + 1800
fake_timestamps <- fake_start_time + cumsum(sample(1:3, 500, TRUE))
fake_timestamps <- fake_timestamps[fake_timestamps <= fake_stop_time]
fake_breaths <- rnorm(length(fake_timestamps), 450, 0.5)
window_size <- 5

rmr_sliding(
  fake_breaths, fake_timestamps,
  fake_start_time, fake_stop_time,
  window_size
)

Loop along a vector, returning n elements at a time in a list

Description

Loop along a vector, returning n elements at a time in a list

Usage

rolling_groups(values, n = 2L)

Arguments

Value

a list in which each element contains n elements from values

Note

For this function, the output elements contain raw values from values, whereas for get_indices the output elements contain the positions (i.e., indices) rather than the raw values

See Also

get_indices

Examples

groups <- rolling_groups(0:50, 3)
head(groups)
tail(groups)

Label matchings for rejection if the assignment violates sequential nature of the data

Description

Label matchings for rejection if the assignment violates sequential nature of the data

Usage

sequence_check(prefs)

Arguments

Value

a list ready for assignment as class transition

Perform a spurious curve analysis

Description

Assess performance using the Transition Pairing Method when the spurious pairing threshold is varied

Usage

spurious_curve(trans, predictions, references, thresholds = 1:20)

Arguments

Value

an object with class spurious_curve

Examples

set.seed(100)
predictions <- (sample(1:100)%%2)
references  <- (sample(1:100)%%2)

trans <- get_transition_info(
  predictions, references, 7
)
head(spurious_curve(trans))

An S4 class containing summary information about a transition object

Description

An S4 class containing summary information about a transition object

Slots

result

a data frame with the summary information

Compare numeric variables in a data frame based on root-squared differences

Description

Compare numeric variables in a data frame based on root-squared differences

Usage

test_errors(
  reference,
  target,
  vars,
  tolerance = 0.001005,
  return_logical = TRUE
)

Arguments

Value

If return_logical = TRUE, a named logical vector with one element per variable compared, indicating whether the maximum and root-mean-squared differences fall within the tolerance. If return_logical = FALSE, a data frame indicating the variables compared and the maximum and root-mean-squared differences.

Note

It is assumed that reference and target have equal numbers of rows.

Examples

reference <- data.frame(
a = 1:100, b = 75:174
)

target <- data.frame(
  a = 0.001 + (1:100),
  b = 76:175
)

test_errors(reference, target, c("a", "b"))
test_errors(reference, target, c("a", "b"), return_logical = FALSE)

Determine weight status from body mass index

Description

Allows users to determine weight status from body mass index (BMI). The function is designed to classify adult weight status, with default settings yielding weight classes defined by the Centers for Disease Control and Prevention (see reference below). Alternatively, the function can be used as a wrapper for get_BMI_percentile to obtain classifications for youth.

Usage

weight_status(BMI = NULL, breaks = c(-Inf, 18.5, 25, 30, 35, 40, Inf),
  labels = c("Underweight", "Healthy Weight", "Overweight", "Class 1 Obese",
  "Class 2 Obese", "Class 3 Obese"), right = FALSE, youth = FALSE, ...)

#get_BMI_percentile(weight_kg, height_cm, age_yrs = NULL, age_mos = NULL,
  #sex = c("Male", "Female"), BMI = NULL, df = NULL,
  #output = c("percentile", "classification", "both", "summary"))

Arguments

Value

a factor reflecting weight status

References

https://www.cdc.gov/bmi/adult-calculator/bmi-categories.html

Examples

weight_status(17:42)

Calculate energy expenditure using the Weir equation

Description

Calculate energy expenditure using the Weir equation

Usage

weir_equation(VO2, VCO2, epochSecs)

Arguments

Value

numeric scalar indicating predicted energy expenditure from the Weir equation, based on the inputs

References

De V Weir, J. B. (1949). New methods for calculating metabolic rate with special reference to protein metabolism. The Journal of physiology, 109(1-2), 1.

Examples

weir_equation(3.5, 3.1, 60)