Package 'MAIVE'

Draw a funnel plot (base graphics)

Description

High-level wrapper that accepts the original input data and the result returned by 'maive()' / 'waive()', prepares the necessary vectors/metadata, and draws the funnel plot on the currently active graphics device.

Usage

get_funnel_plot(dat, result, instrument = NULL, model_type = "MAIVE")

Arguments

dat	Data frame containing at least numeric columns 'bs' (effect sizes) and 'sebs' (standard errors).
result	Result list returned by 'maive()' or 'waive()'.
instrument	Optional indicator (0/1). If 'NULL', inferred from 'result'.
model_type	Label used for plot text/legend (e.g., '"MAIVE"' or '"WAIVE"').

Details

Device management (PNG/SVG/PDF, resolution, base64 encoding) is intentionally left to the caller.

Value

Invisibly returns 'NULL'.

---

R code for MAIVE

Description

R package for MAIVE: "Spurious Precision in Meta-Analysis of Observational Research" by Zuzana Irsova, Pedro Bom, Tomas Havranek, Petr Cala, and Heiko Rachinger.

Usage

maive(
  dat,
  method,
  weight,
  instrument,
  studylevel,
  SE,
  AR,
  first_stage = 1L,
  estimate = NULL,
  se = NULL,
  n = NULL,
  study_id = NULL,
  seed = 123
)

Arguments

dat	Data frame with columns bs, sebs, Ns, study_id (optional). Column names can be remapped with estimate, se, n, and study_id.
method	1 FAT-PET, 2 PEESE, 3 PET-PEESE, 4 EK.
weight	0 no weights, 1 standard weights, 2 MAIVE adjusted weights, 3 study weights.
instrument	1 yes, 0 no.
studylevel	Correlation at study level: 0 none, 1 fixed effects, 2 cluster.
SE	SE estimator: 0 CR0 (Huber-White), 1 CR1 (Standard empirical correction), 2 CR2 (Bias-reduced estimator), 3 wild bootstrap.
AR	Anderson Rubin corrected CI for weak instruments (available for unweighted and MAIVE-adjusted weight versions of PET, PEESE, PET-PEESE, not available for fixed effects): 0 no, 1 yes.
first_stage	First-stage specification for the variance model: 1 log (default), 0 levels. The log stage regresses log(sebs^2) on log(Ns) with a smearing retransformation, so the fitted variance is always positive. The levels stage regresses sebs^2 on 1/Ns and is the specification in the published paper; pass first_stage = 0 to reproduce it.
estimate	Optional column name to use instead of 'bs'
se	Optional column name to use instead of 'sebs'
n	Optional column name to use instead of 'Ns'
study_id	Optional column name for study identifiers. When not supplied, a column named study_id is used if present; otherwise, if dat has four or more columns, the fourth column is used as the study identifier and a warning names the column. Columns already mapped through estimate, se, or n are never picked: when the fourth column is one of them, the single remaining column is used instead, and when several remain an error asks for study_id (at studylevel = 0 the fallback is skipped silently, since no identifier is needed). Any fourth column (a moderator, a year) would otherwise drive the study dummies and clustering at every studylevel other than 0, so name the column explicitly or drop it. When studylevel is not 0 and no identifier can be found, a warning says the study-level options have no effect.
seed	Seed for the wild bootstrap when SE = 3. Use NULL to avoid setting a seed (results depend on the current RNG state). Default is 123 for historical reproducibility.

Details

Guided, interactive workflow available at https://www.easymeta.org.

Data dat can be imported from an Excel file via: dat <- read_excel("inputdata.xlsx") or from a csv file via: dat <- read.csv("inputdata.csv") It should contain:

• Estimates: bs

• Standard errors: sebs

• Number of observations: Ns

• Optional: study_id

Default option for MAIVE: MAIVE-PET-PEESE, unweighted, instrumented, cluster SE, wild bootstrap, AR, log first stage.

The levels first stage (first_stage = 0) regresses the squared standard errors on 1/N by ordinary least squares, so an individual fitted variance can be negative even when the intercept is not. Such an estimate has no instrumented standard error and is excluded from every quantity built on it: the MAIVE-adjusted weights, the second-stage regressions (PET, PEESE, PET-PEESE, EK), the first-stage F-test, the Hausman comparison, the Anderson-Rubin intervals, and the wild bootstrap. The first stage itself is fitted on all rows; every reported statistic then uses the same remaining rows. A warning reports the number of excluded estimates, which is also returned as n_excluded with their positions in excluded_rows. The log first stage (first_stage = 1) cannot fit a negative variance, so it never excludes an estimate.

Value

• beta: MAIVE meta-estimate

• SE: MAIVE standard error

• F-test: heteroskedastic robust F-test of the first step instrumented SEs

• beta_standard: point estimate from the conventional (non-instrumented, inverse-variance weighted) fit of the method chosen

• SE_standard: standard error from the same conventional fit as beta_standard

• Hausman: Hausman type test: comparison between MAIVE and standard version

• Chi2: 5

• SE_instrumented: instrumented standard errors, one per input row; NA for estimates excluded because their fitted variance was not positive

• AR_CI: Anderson-Rubin confidence interval for weak instruments

• pub bias p-value: p-value of test for publication bias / p-hacking based on instrumented FAT

• egger_coef: Egger Coefficient (PET estimate)

• egger_se: Egger Standard Error (PET standard error)

• egger_boot_ci: Confidence interval for the Egger coefficient using the selected resampling scheme

• egger_ar_ci: Anderson-Rubin confidence interval for the Egger coefficient (when available)

• is_quadratic_fit: Details on quadratic selection and slope behaviour

• ek_structure: Structure of the fitted EK model when method=4: "kink", "linear", or "intercept" (intercept-only degenerate fit); NA for other methods

• boot_result: Boot result

• slope_coef: Slope coefficient

• petpeese_selected: Which model (PET or PEESE) was selected when method=3 (NA otherwise)

• peese_se2_coef: Coefficient on SE^2 when PEESE is the final model (NA otherwise)

• peese_se2_se: Standard error of the PEESE SE^2 coefficient (NA otherwise)

• weights: second-stage row scale, one per input row; NA for excluded estimates. Each row of the second-stage regressions is divided by it, so the least-squares weight of an estimate is 1 / weights^2. In waive() it is also divided by the square root of the exponential-decay weight, so with weight = 0, 1 / weights^2 is the decay weight itself

• instrument_strength: "strong", "weak", "very_weak", "unknown", or "not_applicable", from the first-stage F-test

• n_excluded: number of estimates excluded because the first stage fitted a non-positive variance for them (0 with the log first stage)

• excluded_rows: positions of the excluded estimates in the input data (after completely empty rows are dropped); integer(0) when none

Examples

dat <- data.frame(
  bs = c(0.5, 0.45, 0.55, 0.6),
  sebs = c(0.25, 0.2, 0.22, 0.27),
  Ns = c(50, 80, 65, 90)
)

result <- maive(dat,
  method = 3, weight = 0, instrument = 1,
  studylevel = 0, SE = 0, AR = 0
)

# first_stage = 0 uses the levels first stage from the published paper
result_levels <- maive(dat,
  method = 3, weight = 0, instrument = 1,
  studylevel = 0, SE = 0, AR = 0, first_stage = 0
)

---

Convert metafor objects into MAIVE input data

Description

Builds the data frame that maive() and waive() expect (columns bs, sebs, Ns, and optionally study_id) from a metafor escalc data frame or an rma.uni model fit.

Usage

maive_from_metafor(x, ni = NULL, study_id = NULL)

Arguments

x	An escalc data frame (or any data frame with yi and vi columns) or an rma.uni fit.
ni	Optional sample sizes: a numeric vector, or the name of a column in x (or in the data stored with the fit). Overrides any sample sizes carried by x.
study_id	Optional study identifiers: a vector, or the name of a column in x (or in the data stored with the fit). Vectors may have either the length of the original data or the number of rows the fit kept.

Details

The conversion takes the standard error as sqrt(vi), so metafor's sampling variance cannot end up in the sebs slot by mistake. Sample sizes are never inferred from the variances; doing so would reintroduce the spurious precision that MAIVE corrects for. They are resolved, in order, from the ni argument, an ni column (or the fit's ni), the ni attribute that escalc() stamps on the effect size column, and finally the exact two-group total n1i + n2i. The column and the attribute are only used when they agree with n1i + n2i wherever both are present: the attribute does not follow a reorder such as dplyr::arrange() and rma() copies it into the fit, so a stale vector of the right length falls through to the two-group total instead of binding every sample size to the wrong estimate. When none of these is available the function stops and names what it needs.

For rma.uni fits the effect sizes, variances, sample sizes, and any vector supplied through ni or study_id are taken through the same subset and missing-value masks the fit applied, so the rows stay aligned. Multivariate (rma.mv), GLMM (rma.glmm), and other rma subclasses are refused rather than silently flattened, and so are metafor::trimfill() fits: their imputed studies would enter MAIVE as observed estimates, so pass the original rma() fit.

Value

A data frame with columns bs, sebs, Ns, and, when identifiers were supplied, study_id, ready for maive() or waive().

Examples

dat <- metafor::escalc(
  measure = "SMD",
  m1i = c(2.1, 2.5, 1.9, 2.4, 2.2, 2.6),
  sd1i = c(1.0, 1.2, 0.9, 1.1, 1.0, 1.3),
  n1i = c(40, 50, 30, 45, 60, 35),
  m2i = c(1.8, 2.0, 1.7, 2.1, 1.9, 2.2),
  sd2i = c(1.0, 1.1, 1.0, 1.0, 1.1, 1.2),
  n2i = c(42, 55, 33, 48, 58, 37)
)
maive_dat <- maive_from_metafor(dat)
head(maive_dat)

fit <- metafor::rma(yi, vi, data = dat)
identical(maive_from_metafor(fit), maive_dat)

result <- maive(maive_dat,
  method = 3, weight = 0, instrument = 1,
  studylevel = 0, SE = 0, AR = 0
)

---

WAIVE: More Aggressive Correction for P-Hacking and Spurious Precision

Description

WAIVE (Weighted Adjusted Instrumental Variable Estimator) provides a more aggressive correction for p-hacking and spurious precision by extending MAIVE with exponential-decay weights that downweight both spuriously precise estimates and extreme outliers.

Usage

waive(
  dat,
  method,
  weight,
  instrument,
  studylevel,
  SE,
  AR,
  first_stage = 1L,
  estimate = NULL,
  se = NULL,
  n = NULL,
  study_id = NULL,
  seed = 123
)

Arguments

dat	Data frame with columns bs, sebs, Ns, study_id (optional). Column names can be remapped with estimate, se, n, and study_id.
method	1 FAT-PET, 2 PEESE, 3 PET-PEESE, 4 EK.
weight	0 no weights, 1 standard weights, 2 MAIVE adjusted weights, 3 study weights.
instrument	1 yes, 0 no.
studylevel	Correlation at study level: 0 none, 1 fixed effects, 2 cluster.
SE	SE estimator: 0 CR0 (Huber-White), 1 CR1 (Standard empirical correction), 2 CR2 (Bias-reduced estimator), 3 wild bootstrap.
AR	Anderson Rubin corrected CI for weak instruments (available for unweighted and MAIVE-adjusted weight versions of PET, PEESE, PET-PEESE, not available for fixed effects): 0 no, 1 yes.
first_stage	First-stage specification for the variance model: 1 log (default), 0 levels. The log stage regresses log(sebs^2) on log(Ns) with a smearing retransformation, so the fitted variance is always positive. The levels stage regresses sebs^2 on 1/Ns and is the specification in the published paper; pass first_stage = 0 to reproduce it.
estimate	Optional column name to use instead of 'bs'
se	Optional column name to use instead of 'sebs'
n	Optional column name to use instead of 'Ns'
study_id	Optional column name for study identifiers. When not supplied, a column named study_id is used if present; otherwise, if dat has four or more columns, the fourth column is used as the study identifier and a warning names the column. Columns already mapped through estimate, se, or n are never picked: when the fourth column is one of them, the single remaining column is used instead, and when several remain an error asks for study_id (at studylevel = 0 the fallback is skipped silently, since no identifier is needed). Any fourth column (a moderator, a year) would otherwise drive the study dummies and clustering at every studylevel other than 0, so name the column explicitly or drop it. When studylevel is not 0 and no identifier can be found, a warning says the study-level options have no effect.
seed	Seed for the wild bootstrap when SE = 3. Use NULL to avoid setting a seed (results depend on the current RNG state). Default is 123 for historical reproducibility.

Details

Guided, interactive workflow available at https://www.easymeta.org.

For technical details on WAIVE methodology, see: https://meta-analysis.cz/waive_ottawa.pdf

WAIVE combines variance instrumentation (as in MAIVE) with robust downweighting based on first-stage residuals. Studies with negative residuals (spurious precision) or extreme residuals (outliers) receive exponentially reduced influence in the meta-analytic estimate. This makes WAIVE more aggressive than standard MAIVE at correcting for p-hacking and handling outliers.

Value

List with the same structure as maive(). See ?maive for details.

Examples

dat <- data.frame(
  bs = c(0.5, 0.45, 0.55, 0.6),
  sebs = c(0.25, 0.2, 0.22, 0.27),
  Ns = c(50, 80, 65, 90)
)

result <- waive(dat,
  method = 3, weight = 0, instrument = 1,
  studylevel = 0, SE = 0, AR = 0
)

---