STMr (version 0.1.7)

estimate_functions_quantile: Estimate relationship between reps and weight using the non-linear quantile regression

Description

These functions provide estimate 1RM and parameter values using the quantile regression. By default, target variable is the reps performed, while the predictors is the perc_1RM or weight. To reverse this, use the reverse = TRUE argument

Usage

estimate_k_quantile(
  perc_1RM,
  reps,
  eRIR = 0,
  tau = 0.5,
  reverse = FALSE,
  control = quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0),
  ...
)
estimate_k_generic_1RM_quantile(
  weight,
  reps,
  eRIR = 0,
  k = 0.0333,
  tau = 0.5,
  reverse = FALSE,
  control = quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0),
  ...
)
estimate_k_1RM_quantile(
  weight,
  reps,
  eRIR = 0,
  tau = 0.5,
  reverse = FALSE,
  control = quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0),
  ...
)
estimate_kmod_quantile(
  perc_1RM,
  reps,
  eRIR = 0,
  tau = 0.5,
  reverse = FALSE,
  control = quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0),
  ...
)
estimate_kmod_1RM_quantile(
  weight,
  reps,
  eRIR = 0,
  tau = 0.5,
  reverse = FALSE,
  control = quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0),
  ...
)
estimate_klin_quantile(
  perc_1RM,
  reps,
  eRIR = 0,
  tau = 0.5,
  reverse = FALSE,
  control = quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0),
  ...
)
estimate_klin_1RM_quantile(
  weight,
  reps,
  eRIR = 0,
  tau = 0.5,
  reverse = FALSE,
  control = quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0),
  ...
)

Value

nlrq object

Arguments

perc_1RM

%1RM

reps

Number of repetitions done

eRIR

Subjective estimation of reps-in-reserve (eRIR)

tau

Vector of quantiles to be estimated. Default is 0.5

reverse

Logical, default is FALSE. Should reps be used as predictor instead as a target?

control

Control object for the nlrq function. Default is: quantreg::nlrq.control(maxiter = 10^4, InitialStepSize = 0)

...

Forwarded to nlrq function

weight

Weight used

k

Value for the generic Epley's equation, which is by default equal to 0.0333

Functions

• estimate_k_quantile(): Estimate the parameter k in the Epley's equation

• estimate_k_generic_1RM_quantile(): Provides the model with generic k parameter, as well as estimated 1RM. This is a novel estimation function that uses the absolute weights

• estimate_k_1RM_quantile(): Estimate the parameter k in the Epley's equation, as well as 1RM. This is a novel estimation function that uses the absolute weights

• estimate_kmod_quantile(): Estimate the parameter kmod in the modified Epley's equation

• estimate_kmod_1RM_quantile(): Estimate the parameter kmod in the modified Epley's equation, as well as 1RM. This is a novel estimation function that uses the absolute weights

• estimate_klin_quantile(): Estimate the parameter klin in the Linear/Brzycki equation

• estimate_klin_1RM_quantile(): Estimate the parameter klin in the Linear/Brzycki equation, as well as 1RM. This is a novel estimation function that uses the absolute weights

Examples

# ---------------------------------------------------------
# Epley's model
m1 <- estimate_k_quantile(
  perc_1RM = c(0.7, 0.8, 0.9),
  reps = c(10, 5, 3)
)

coef(m1)
# ---------------------------------------------------------
# Epley's model that also estimates 1RM
m1 <- estimate_k_generic_1RM_quantile(
  weight = c(70, 110, 140),
  reps = c(10, 5, 3)
)

coef(m1)
# ---------------------------------------------------------
# Epley's model that also estimates 1RM
m1 <- estimate_k_1RM_quantile(
  weight = c(70, 110, 140),
  reps = c(10, 5, 3)
)

coef(m1)
# ---------------------------------------------------------
# Modified Epley's model
m1 <- estimate_kmod_quantile(
  perc_1RM = c(0.7, 0.8, 0.9),
  reps = c(10, 5, 3)
)

coef(m1)
# ---------------------------------------------------------
# Modified Epley's model that also estimates 1RM
m1 <- estimate_kmod_1RM_quantile(
  weight = c(70, 110, 140),
  reps = c(10, 5, 3)
)

coef(m1)
# ---------------------------------------------------------
# Linear/Brzycki model
m1 <- estimate_klin_quantile(
  perc_1RM = c(0.7, 0.8, 0.9),
  reps = c(10, 5, 3)
)

coef(m1)
# ---------------------------------------------------------
# Linear/Brzycki model thal also estimates 1RM
m1 <- estimate_klin_1RM_quantile(
  weight = c(70, 110, 140),
  reps = c(10, 5, 3)
)

coef(m1)