Type:	Package
Title:	Statistical Quality-Assured Integrated Response Estimation
Version:	1.0.0
Author:	Richard A. Feiss [aut, cre]
Maintainer:	Richard A. Feiss <feiss026@umn.edu>
Description:	Implements statistically validated biological parameter optimization that combines automated parameter type detection with rigorous statistical quality assurance. Unlike conventional optimizers that fit parameters to any data, 'SQUIRE' first validates whether statistically significant biological effects exist before proceeding with parameter estimation. Uses trust region methods from Conn et al. (2000) <doi:10.1137/S1052623497325107>, ANOVA-based validation following Fisher (1925) <doi:10.1007/978-1-4612-4380-9_6>, and effect size calculations per Cohen (1988, ISBN:0805802835). Automatically distinguishes rate-based, positive-constrained, and unconstrained variables, applying geometry-appropriate optimization methods while preventing over-fitting to noise through built-in statistical validation, effect size assessment, and data quality requirements. Designed for complex biological and environmental models including germination studies, dose-response curves, and survival analysis. Enhanced successor to the 'GALAHAD' optimization framework with integrated statistical gatekeeping. Developed at the Minnesota Center for Prion Research and Outreach at the University of Minnesota.
License:	MIT + file LICENSE
Encoding:	UTF-8
Depends:	R (≥ 4.2.0)
Imports:	stats
Suggests:	testthat (≥ 3.0.0)
RoxygenNote:	7.3.3
Config/testthat/edition:	3
NeedsCompilation:	no
Packaged:	2025-11-14 00:12:06 UTC; feiss026
Repository:	CRAN
Date/Publication:	2025-11-19 18:00:02 UTC

SQUIRE: Statistical Quality-Assured Integrated Response Estimation

Description

Geometry-adaptive biological parameter estimation with built-in statistical validation. Implements two-cycle optimization: statistical validation followed by GALAHAD-calibrated parameter estimation.

Usage

SQUIRE(
  data,
  treatments,
  control_treatment = treatments[1],
  response_type = c("germination", "growth", "survival"),
  validation_level = 0.05,
  min_timepoints = 5,
  min_replicates = 3,
  galahad_config = NULL,
  verbose = TRUE
)

Arguments

Details

SQUIRE implements a two-stage validation process:

Stage 1: Statistical Validation

• Tests for significant treatment effects using ANOVA

• Checks data quality requirements (timepoints, replication)

• Only proceeds to optimization if biological signals detected

Stage 2: Validated Optimization

• Calibrates GALAHAD geometry parameters on significant effects

• Applies optimized parameters with uncertainty quantification

• Validates that optimized parameters are statistically meaningful

Value

List with statistical validation results, optimized parameters, and biological interpretation (only if statistically justified)

Examples

# Quick data setup example (fast execution)
n_time <- 5
n_rep <- 3

# Simulate example data
example_data <- data.frame(
  time = rep(1:n_time, times = 3 * n_rep),
  treatment = rep(c("Control", "Treatment_A", "Treatment_B"), 
                  each = n_time * n_rep),
  replicate = rep(rep(1:n_rep, each = n_time), times = 3),
  response = c(
    cumsum(rbinom(n_time * n_rep, 1, 0.1)),  # Control
    cumsum(rbinom(n_time * n_rep, 1, 0.15)), # Treatment A  
    cumsum(rbinom(n_time * n_rep, 1, 0.2))   # Treatment B
  )
)

# Inspect data structure (this runs quickly)
head(example_data)
table(example_data$treatment)


# Full analysis (longer computation)
results <- SQUIRE(
  data = example_data,
  treatments = c("Control", "Treatment_A", "Treatment_B"),
  control_treatment = "Control",
  response_type = "germination",
  verbose = FALSE
)

# Check results
if(results$optimization_performed) {
  print("Optimization was justified")
  print(results$parameters)
} else {
  print("No significant effects detected")
  print(results$statistical_advice)
}

Assess Data Quality

Description

Check data quality requirements for optimization

Usage

assess_data_quality(data, treatments, min_timepoints, min_replicates)

Arguments

Value

List with data quality assessment

Calculate Response Metric

Description

Calculate appropriate response metric for statistical testing

Usage

calculate_response_metric(data)

Arguments

Value

Vector of response metrics

Calibrate GALAHAD Parameters

Description

Two-cycle parameter calibration for geometry-adaptive optimization

Usage

calibrate_galahad_parameters(
  data,
  treatments,
  response_type,
  validation_results,
  verbose = FALSE
)

Arguments

Value

Calibrated GALAHAD configuration

Calibrate Optimization Parameters

Description

Calibrate numerical parameters for optimization

Usage

calibrate_optimization_parameters(data, geometry_config)

Arguments

Value

Optimization configuration

Compile Optimization Results

Description

Compile results from multiple treatment optimizations

Usage

compile_optimization_results(treatment_parameters, treatments)

Arguments

Value

Compiled optimization results

Describe Treatment Effects

Description

Describe how treatments affect each parameter

Usage

describe_treatment_effects(param_values, param_name)

Arguments

Value

Treatment effect description

Determine Geometry Partitioning

Description

Determine parameter types for geometry-adaptive optimization

Usage

determine_geometry_partitioning(data, response_type)

Arguments

Value

Geometry configuration

Fit Biological Model

Description

Fit biological model to single treatment data

Usage

fit_biological_model(data, response_type, galahad_config, verbose = FALSE)

Arguments

Value

Model fitting results

Fit Germination Model

Description

Fit germination-specific model

Usage

fit_germination_model(data, galahad_config, verbose = FALSE)

Arguments

Value

Germination model results

Generate Biological Interpretation

Description

Create biological interpretation of optimization results

Usage

generate_biological_interpretation(
  optimization_results,
  parameter_validation,
  response_type
)

Arguments

Value

Biological interpretation

Generate Recommendations

Description

Provide methodological and experimental recommendations

Usage

generate_recommendations(validation_results, parameter_validation)

Arguments

Value

Recommendations list

Get Biological Meaning

Description

Translate parameter names to biological interpretation

Usage

get_biological_meaning(param_name, response_type)

Arguments

Value

Biological meaning description

Perform Validated Optimization

Description

Execute parameter optimization with statistical validation

Usage

perform_validated_optimization(
  data,
  treatments,
  galahad_config,
  validation_results,
  response_type,
  verbose = FALSE
)

Arguments

Value

Optimization results

Summarize Biological Effects

Description

Create overall biological summary

Usage

summarize_biological_effects(interpretation, response_type)

Arguments

Value

Biological summary text

SQUIRE Summary Method

Description

Print method for SQUIRE results

Usage

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

Arguments

Value

No return value, called for side effects (prints summary to console)

Test Treatment Effects

Description

Statistical test for treatment differences

Usage

test_treatment_effects(data, treatments, alpha = 0.05, verbose = FALSE)

Arguments

Value

List with statistical test results

Validate Biological Effects

Description

Test for statistically significant treatment effects before optimization

Usage

validate_biological_effects(
  data,
  treatments,
  control_treatment,
  response_type,
  alpha,
  min_timepoints,
  min_replicates,
  verbose
)

Arguments

Value

List with validation results

Validate Optimized Parameters

Description

Test statistical significance of optimized parameters

Usage

validate_optimized_parameters(
  optimization_results,
  treatments,
  control_treatment,
  alpha = 0.05,
  verbose = FALSE
)

Arguments

Value

Parameter validation results