Skip to contents

Segmented level-change and slope-change effects for single-case data

level_slope_computation.Rd

Fits a segmented AB time-series model separately to each study-case series and returns the immediate intervention level change and change in time slope, with model-based variances and their covariance.

Usage

level_slope_computation(
  data,
  studyID,
  subjectID,
  outcome_name,
  phase_name,
  time_name,
  phase_order = NULL,
  improvement = c("increase", "decrease"),
  correlation = c("independence", "ar1"),
  na_option = "listwise"
)

Arguments

data

Data frame containing repeated observations.

studyID, subjectID, outcome_name, phase_name

Character strings naming the study, case, outcome, and phase columns.

time_name

Character string naming the ordered measurement-time column.

phase_order

Character vector giving the baseline and intervention labels, in that order. If NULL, factor-level or alphabetical order is used.

improvement

Whether an increase or decrease in the outcome is beneficial.

correlation

Either "independence" for ordinary least squares or "ar1" for feasible generalized least squares with an estimated AR(1) residual correlation.

na_option

Currently only "listwise" is supported.

Value

A data frame with two rows per study-case: level_change and slope_change. cov_level_slope is repeated on both rows to allow the two estimates to be retained as dependent effects in later synthesis.

Details

This function supports a single transition from baseline to intervention: all baseline times must precede all intervention times. The AR(1) option estimates rho from ordinary least-squares residuals; its reported variance treats that estimated rho as fixed and is therefore approximate.

Examples

dat <- data.frame(study = "S1", case = "A", time = 1:8,
                  phase = rep(c("A", "B"), each = 4),
                  outcome = c(1, 2, 2, 3, 5, 6, 7, 8))
level_slope_computation(dat, "study", "case", "outcome", "phase", "time")
#>                   study_id case_id    effect_id       metric  yi   vi
#> S1.A.level_change       S1       A level_change level_change 1.5 0.11
#> S1.A.slope_change       S1       A slope_change slope_change 0.4 0.02
#>                   cov_level_slope residual_df autocorrelation  correlation
#> S1.A.level_change            0.01           4              NA independence
#> S1.A.slope_change            0.01           4              NA independence