Function to identify sudden gains in longitudinal data structured in wide format.
identify_sg(
data,
id_var_name,
sg_var_list,
sg_crit1_cutoff,
sg_crit2_pct = 0.25,
sg_crit3 = TRUE,
sg_crit3_alpha = 0.05,
sg_crit3_adjust = TRUE,
sg_crit3_critical_value = 2.776,
identify_sg_1to2 = FALSE,
crit123_details = FALSE
)
A wide data set indicating whether sudden gains are present for each session to session interval for all cases in data
.
A data set in wide format including an ID variable and variables for each measurement point.
String, specifying the name of the ID variable. Each row should have a unique value.
Vector, specifying the variable names of each measurement point sequentially.
Numeric, specifying the cut-off value to be used for the first sudden gains criterion.
The function define_crit1_cutoff
can be used to calculate a cutoff value based on the Reliable Change Index (RCI; Jacobson & Truax, 1991).
If set to NULL
the first criterion wont be applied.
Numeric, specifying the percentage change to be used for the second sudden gains criterion.
If set to NULL
the second criterion wont be applied.
If set to TRUE
the third criterion will be applied automatically adjusting the critical value for missingness.
If set to FALSE
the third criterion wont be applied.
Numeric, alpha for the two-tailed student t-test to determine the critical value to be used for the third criterion. Degrees of freedom are based on the number of available data in the three sessions preceding the gain and the three sessions following the gain.
Logical, specify whether critical value gets adjusted for missingness, see Lutz et al. (2013) and the documentation of this R package for further details.
This argument is set to TRUE
by default adjusting the critical value for missingness as described in the package documentation and Lutz et al. (2013):
A critical value of 2.776 is used when all three data points before and after a potential gain are available,
where one data point is missing either before or after a potential gain a critical value of 3.182 is used,
and where one data point is missing both before and after the gain a critical value of 4.303 is used (for sg_crit3_alpha = 0.05).
If set to FALSE
the critical value set in sg_crit3_critical_value
will instead be used for all comparisons, regardless of missingnes in the sequence of data points that are investigated for potential sudden gains.
Numeric, specifying the critical value to instead be used for all comparisons, regardless of missingnes in the sequence of data points that are investigated for potential sudden gains.
Logical, indicating whether to identify sudden gains from measurement point 1 to 2.
If set to TRUE, this implies that the first variable specified in sg_var_list
represents a baseline measurement point, e.g. pre-intervention assessment.
Logical, if set to TRUE
this function returns information about which of the three criteria (e.g. "sg_crit1_2to3", "sg_crit2_2to3", and "sg_crit3_2to3") are met for each session to session interval for all cases.
Variables named "sg_2to3", "sg_3to4" summarise all criteria that were selected to identify sudden gains.
Lutz, W., Ehrlich, T., Rubel, J., Hallwachs, N., Röttger, M.-A., Jorasz, C., … Tschitsaz-Stucki, A. (2013). The ups and downs of psychotherapy: Sudden gains and sudden losses identified with session reports. Psychotherapy Research, 23(1), 14–24. tools:::Rd_expr_doi("10.1080/10503307.2012.693837").
Tang, T. Z., & DeRubeis, R. J. (1999). Sudden gains and critical sessions in cognitive-behavioral therapy for depression. Journal of Consulting and Clinical Psychology, 67(6), 894–904. tools:::Rd_expr_doi("10.1037/0022-006X.67.6.894").
# Identify sudden gains
identify_sg(data = sgdata,
sg_crit1_cutoff = 7,
id_var_name = "id",
sg_var_list = c("bdi_s1", "bdi_s2", "bdi_s3",
"bdi_s4", "bdi_s5", "bdi_s6",
"bdi_s7", "bdi_s8", "bdi_s9",
"bdi_s10", "bdi_s11", "bdi_s12"))
Run the code above in your browser using DataLab