Skip to main content

Table 6 Sensitivity and false discovery rate (FDR) for the likelihood ratio test (LRT), normal approximation, proportional reporting ratio (PRR), and reporting odds ratio methods while using the Max-Stat method for adjustment of multiple testing under different parameter settings. The simulation takes counts from 250 random AEs from each \(n_i.\) size category and randomly assigns \(20\%\) of drugs from each AE to follow a proportion that differs from the null hypothesis proportion by a value of \(\Delta\)

From: Statistical methods for exploring spontaneous adverse event reporting databases for drug-host factor interactions

 

\({\boldsymbol n}_{\boldsymbol i\cdot}\) size

\(\Delta\)

LRT

Normal approx.

PRR

ROR

sensitivity

small

0.025

0.00925

0.00999

0.0279

0.0168

small

0.05

0.0158

0.0183

0.0424

0.0237

small

0.1

0.0523

0.0600

0.103

0.0652

small

0.2

0.250

0.268

0.338

0.290

medium

0.025

0.00684

0.00783

0.0217

0.0112

medium

0.05

0.0152

0.0184

0.0401

0.0176

medium

0.1

0.0643

0.0740

0.120

0.0645

medium

0.2

0.293

0.311

0.402

0.301

large

0.025

0.00311

0.0039

0.0132

0.00555

large

0.05

0.0133

0.0162

0.0328

0.0142

large

0.1

0.0644

0.0726

0.115

0.0650

large

0.2

0.240

0.260

0.369

0.257

FDR

small

0.0250

0.0382

0.0340

0.110

0.0863

small

0.05

0.0380

0.0338

0.109

0.0865

small

0.1

0.0370

0.0330

0.104

0.0838

small

0.2

0.0329

0.0287

0.0911

0.0723

medium

0.025

0.0385

0.0333

0.128

0.102

medium

0.05

0.0381

0.0329

0.125

0.101

medium

0.1

0.0366

0.0311

0.116

0.0967

medium

0.2

0.0281

0.0235

0.0871

0.0732

large

0.025

0.0389

0.0299

0.256

0.211

large

0.05

0.0368

0.0277

0.230

0.198

large

0.1

0.0290

0.0213

0.162

0.148

large

0.2

0.0152

0.0111

0.087

0.0679