DMAR (version 1.0.0)

ss_aipe_smd_sensitivity: Sensitivity Analysis for Sample Size Given the Accuracy in Parameter Estimation Approach for the Standardized Mean Difference

Description

Performs sensitivity analysis for sample size determination for the standardized mean difference given a population and a standardized mean difference. Allows one to determine the effect of being wrong when estimating the population standardized mean difference in terms of the width of the obtained (two-sided) confidence intervals.

Usage

ss_aipe_smd_sensitivity(
  true_delta = NULL,
  estimated_delta = NULL,
  desired_width = NULL,
  n_per_group = NULL,
  assurance = NULL,
  conf_level = 0.95,
  G = 1000,
  print_iter = FALSE,
  filename = NULL
)

Value

A data.frame with columns term and value

summarizing the Monte Carlo sensitivity analysis across the G

replications. The term entries are: mean_smd, median_smd, sd_smd (summaries of the realized standardized mean difference); mean_ci_width, median_ci_width, sd_ci_width (summaries of the full interval widths); mean_ci_width_lower and mean_ci_width_upper (mean one-sided widths, measured from the observed standardized mean difference to each limit); pct_ci_less_w (proportion of intervals at or below the target width); pct_ci_miss_low and pct_ci_miss_high

(tail-specific empirical non-coverage of true_delta); total_type_I_error (overall empirical non-coverage, the sum of the two tails); and the input echoes n_per_group, total_N, true_delta, estimated_delta (NA when n_per_group was supplied instead), width, conf_level, and assurance (present only when an assurance was supplied). The proportion and Type I error rows are proportions on the 0 to 1 scale, not percentages.

Arguments

true_delta

population standardized mean difference

estimated_delta

estimated standardized mean difference; can be true_delta to perform standard simulations

desired_width

describe full width for the confidence interval around the population standardized mean difference

n_per_group

selected sample size to use in order to determine distributional properties of at a given value of sample size

assurance

parameter to ensure confidence interval width with a specified degree of certainty (must be NULL or between zero and unity)

conf_level

the desired degree of confidence (i.e., 1-Type I error rate)

G

number of generations (i.e., replications) of the simulation

print_iter

to print the current value of the iterations

filename

an optional path for a comma separated file recording every replication (the realized standardized mean difference, the full and the two one-sided interval widths, the three non-coverage indicators, and the two confidence limits): nothing is written when filename is NULL (the default), a new file with a header row is created otherwise, an existing file at that path is appended to, and a throwaway run should point it at tempfile(fileext = ".csv")

Author

Ken Kelley [email protected]

Details

For sensitivity analysis when planning sample size given the desire to obtain narrow confidence intervals for the population standardized mean difference. Given a population value and an estimated value, one can determine the effects of incorrectly specifying the population standardized mean difference (true_delta) on the obtained widths of the confidence intervals. Also, one can evaluate the percent of the confidence intervals that are less than the desired width (especially when modifying the assurance parameter); see ss_aipe_smd) Alternatively, one can specify n_per_group to determine the results at a particular sample size (when doing this estimated_delta cannot be specified).

References

Cumming, G., & Finch, S. (2001). A primer on the understanding, use, and calculation of confidence intervals that are based on central and noncentral distributions. Educational and Psychological Measurement, 61(4), 532--574. tools:::Rd_expr_doi("10.1177/0013164401614002")

Hedges, L. V. (1981). Distribution theory for Glass's Estimator of effect size and related estimators. Journal of Educational Statistics, 6(2), 107--128.

Kelley, K. (2005). The effects of nonnormal distributions on confidence intervals around the standardized mean difference: Bootstrap and parametric confidence intervals, Educational and Psychological Measurement, 65, 51--69. tools:::Rd_expr_doi("10.1177/0013164404264850")

Kelley, K., & Rausch, J. R. (2006). Sample size planning for the standardized mean difference: Accuracy in parameter estimation via narrow confidence intervals. Psychological Methods, 11(4), 363--385. tools:::Rd_expr_doi("10.1037/1082-989X.11.4.363")

Maxwell, S. E., Delaney, H. D., & Kelley, K. (2027). Designing experiments and analyzing data: A model comparison perspective (4th ed.). Routledge. (See Chapter 4 on individual comparisons and Chapter 3 on one-way ANOVA.)

Steiger, J. H., & Fouladi, R. T. (1997). Noncentrality interval estimation and the evaluation of statistical methods. In L. L. Harlow, S. A. Mulaik, & J. H. Steiger (Eds.), What if there were no significance tests? (pp. 221--257). Mahwah, NJ: Lawrence Erlbaum.

See Also

ss_aipe_smd

design_consequences for what a chosen design delivers: power, the Type S (sign) and Type M (exaggeration) errors of the significance filter, and the expected confidence interval width.

Examples

# Since 'true_delta' equals 'estimated_delta', this usage
# returns the results of a correctly specified situation.
# Note that 'G' should be large (50 is used to make the example run easily)
set.seed(113)
Res.1 <- ss_aipe_smd_sensitivity(true_delta=.5, estimated_delta=.5, desired_width=.30,
                                 assurance=NULL, conf_level=.95, G=50, print_iter=FALSE)

# Objects contained in the 'summary'.
Res.1$term

# True standardized mean difference is .4, but specified at .5.
# Change 'G' to some large number (e.g., G=5,000)
Res.2 <- ss_aipe_smd_sensitivity(true_delta=.4, estimated_delta=.5, desired_width=.30,
                                 assurance=NULL, conf_level=.95, G=50, print_iter=FALSE)

# The effect of the misspecification on mean confidence intervals is:
Res.2[1,]

# True standardized mean difference is .5, but specified at .4.
Res.3 <- ss_aipe_smd_sensitivity(true_delta=.5, estimated_delta=.4, desired_width=.30,
                                 assurance=NULL, conf_level=.95, G=50, print_iter=FALSE)

# The effect of the misspecification on mean confidence intervals is:
Res.3[1,]