Package 'nlmr' reference manual

Title:	Non-linear Mendelian randomisation
Description:	Non-linear Mendelian randomization analysis to investigate the shape of exposure-outcome relationships.
Authors:	James Staley [aut, cre]
Maintainer:	James Staley <[email protected]>
License:	GPL-3
Version:	1.0.3
Built:	2025-01-10 05:48:09 UTC
Source:	https://github.com/jrs95/nlmr

Fractional polynomial Mendelian randomization

Description

fracpoly_mr performs a Mendelian randomization (MR) analysis by fitting fractional polynomial models to localised average causal effects using meta-regression.

Usage

fracpoly_mr(
  y,
  x,
  g,
  covar = NULL,
  family = "gaussian",
  q = 10,
  xpos = "mean",
  method = "FE",
  d = 1,
  pd = 0.05,
  ci = "model_se",
  nboot = 100,
  fig = FALSE,
  ref = mean(x),
  pref_x = "x",
  pref_x_ref = "x",
  pref_y = "y",
  ci_type = "overall",
  ci_quantiles = 10,
  breaks = NULL
)
fracpoly_mr(
  y,
  x,
  g,
  covar = NULL,
  family = "gaussian",
  q = 10,
  xpos = "mean",
  method = "FE",
  d = 1,
  pd = 0.05,
  ci = "model_se",
  nboot = 100,
  fig = FALSE,
  ref = mean(x),
  pref_x = "x",
  pref_x_ref = "x",
  pref_y = "y",
  ci_type = "overall",
  ci_quantiles = 10,
  breaks = NULL
)

Arguments

`y`	vector of outcome values
`x`	vector of exposure values
`g`	the instrumental variable
`covar`	`data.frame` of covariates
`family`	a description of the error distribution and link function to be used in the model and is a `character` string naming either the gaussian (i.e. `"gaussian"` for continuous data) or binomial (i.e. `"binomial"` for binary data) family function (default: `"gaussian"`)
`q`	the number of quantiles the exposure distribution is to be split into within which a causal effect will be fitted, known as localised average causal effects (LACE) (default: `10`)
`xpos`	the position used to relate `x` to the localised average causal effect, this can either be the mean of the x-values within each quantile or a percentile (e.g. 0.5 corresponds to the median value) (default: `"mean"`)
`method`	meta-regression method parsed to the `metafor` package, e.g. the fixed-effects model (default: `"FE"`)
`d`	fractional polynomial degree, the options are: `1`, `2`, or `"both"` (default: `1`)
`pd`	p-value cut-off for choosing the best-fitting fractional polynomial of degree 2 over the best-fitting fractional polynomial degree 1, used only if `d = "both"` (default: `0.05`)
`ci`	the type of 95% confidence interval, there are three options: (i) using the model standard errors (`"model_se"`), (ii) using bootstrap standard errors (`"bootstrap_se"`), and (iii) using bootstrap percentile confidence intervals (`"bootstrap_per"`) (default: `"model_se"`)
`nboot`	the number of bootstrap replications (default: `100`)
`fig`	a `logical` statement as to whether the user wants the results displayed in a figure (default: `FALSE`)
`ref`	the reference point for the figure, this is the value of the function that represents the expected difference in the outcome compared with this reference value when the exposure is set to different values (default: `mean(x)`)
`pref_x`	the prefix/label for the x-axis (default: `"x"`)
`pref_x_ref`	the prefix for the reference value displayed on the y-axis (default: `"x"`)
`pref_y`	the prefix/label for the y-axis (default: `"y"`)
`ci_type`	the type of confidence interval to be displayed on the graph, where confidence intervals are either presented as bands across the range of x (option: `"overall"`) or as error bars at the mean in each quantile of x (option: `"quantile"`) (default:)
`ci_quantiles`	the number of quantiles at which confidence intervals are to be displayed (default: `10`)
`breaks`	breaks on the y-axis of the figure

Value

fracpoly_mr returns a list of non-linear MR results from the fractional polynomial MR approach:

`n`	number of individuals
`model`	the model specifications: number of quantiles (`q`), position used to relate x to the LACE in each quantiles (`xpos`), type of confidence interval constructed (`ci`), number of bootstrap replications performed (`nboot`)
`powers`	the powers of the chosen polynomial
`coefficients`	the regression estimates: regression coefficients (`beta`), standard errors of regression coefficients (`se`), lower 95% confidence interval (`lci`), upper 95% confidence interval (`uci`), p-value (`pval`)
`lace`	the localised average causal effect estimate in each quantile: regression coefficients (`beta`), standard errors of regression coefficients (`se`), lower 95% confidence interval (`lci`), upper 95% confidence interval (`uci`), p-value (`pval`)
`xcoef`	the association between the instrument and the exposure in each quantile: regression coefficients (`beta`), standard errors of regression coefficients (`se`)
`p_tests`	the p-value of the non-linearity tests: p-value of the test between the fractional polynomial degrees (`fp_d1_d2`), p-value from the fractional polynomial non-linearity test (`fp`), p-value from the quadratic test (`quad`), p-value from the Cochran Q test (`Q`)
`p_heterogeneity`	the p-value of heterogeneity: p-value of the Cochran Q heterogeneity test (`Q`), p-value from the trend test (`trend`).

Author(s)

James Staley [email protected]

Examples

# IV (g), exposure (x) & outcome (y)
epsx <- rexp(10000)
u <- runif(10000, 0, 1)
g <- rbinom(10000, 2, 0.3)
epsy <- rnorm(10000)
ag <- 0.25
x <- 1 + ag * g + u + epsx
y <- 0.15 * x^2 + 0.8 * u + epsy

# Covariates (covar)
c1 <- rnorm(10000)
c2 <- rnorm(10000)
c3 <- rbinom(10000, 2, 0.33)
covar <- data.frame(c1 = c1, c2 = c2, c3 = as.factor(c3))

# Analyses
fp <- fracpoly_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, d = 1, ci = "model_se",
  fig = TRUE
)
summary(fp)
plm <- piecewise_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, nboot = 100,
  fig = TRUE
)
summary(plm)

# IV (g), exposure (x) & outcome (y)
epsx <- rexp(10000)
u <- runif(10000, 0, 1)
g <- rbinom(10000, 2, 0.3)
epsy <- rnorm(10000)
ag <- 0.25
x <- 1 + ag * g + u + epsx
y <- 0.15 * x^2 + 0.8 * u + epsy

# Covariates (covar)
c1 <- rnorm(10000)
c2 <- rnorm(10000)
c3 <- rbinom(10000, 2, 0.33)
covar <- data.frame(c1 = c1, c2 = c2, c3 = as.factor(c3))

# Analyses
fp <- fracpoly_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, d = 1, ci = "model_se",
  fig = TRUE
)
summary(fp)
plm <- piecewise_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, nboot = 100,
  fig = TRUE
)
summary(plm)

Localised average causal effects

Description

lace computes the localised average causal effect for each quantile.

Usage

lace(
  y,
  x,
  g,
  covar = NULL,
  q,
  x0q,
  xc_sub = TRUE,
  family = "gaussian",
  xpos = "mean"
)
lace(
  y,
  x,
  g,
  covar = NULL,
  q,
  x0q,
  xc_sub = TRUE,
  family = "gaussian",
  xpos = "mean"
)

Arguments

`y`	vector of outcome values
`x`	vector of exposure values
`g`	the instrumental variable
`covar`	`data.frame` of covariates
`q`	the number of quantiles the exposure distribution is to be split into within which a causal effect will be fitted, known as localised average causal effects (LACE) (default: `10`)
`x0q`	quantiles of x0 (the IV-free exposure)
`xc_sub`	compute the association between the exposure and the insturment in each quantile of x0
`family`	a description of the error distribution and link function to be used in the model and is a `character` string naming either the gaussian (i.e. `"gaussian"` for continuous data) or binomial (i.e. `"binomial"` for binary data) family function (default: `"gaussian"`)
`xpos`	the position used to relate `x` to the localised average causal effect, this can either be the mean of the x-values within each quantile or a percentile (e.g. 0.5 corresponds to the median value) (default: `"mean"`)

Value

lace returns a data.frame of the LACE for quantile:

`coef`	the LACE in each quantile
`coef_se`	the standard error of the LACE in each quantile
`xmean`	the mean of the exposure in each quantile
`xcoef_sub`	the association between the exposure and the instrument in each quantile
`xcoef_sub_se`	the standard error of the association between the exposure and the instrument in each quantile

Author(s)

James Staley [email protected]

Piecewise linear Mendelian randomization

Description

piecewise_mr performs a Mendelian randomization (MR) analysis by fitting a piecewise linear function to localised average causal effects.

Usage

piecewise_mr(
  y,
  x,
  g,
  covar = NULL,
  family = "gaussian",
  q = 10,
  xpos = "mean",
  nboot = 100,
  fig = TRUE,
  ref = mean(x),
  pref_x = "x",
  pref_x_ref = "x",
  pref_y = "y",
  ci_quantiles = 10,
  breaks = NULL
)
piecewise_mr(
  y,
  x,
  g,
  covar = NULL,
  family = "gaussian",
  q = 10,
  xpos = "mean",
  nboot = 100,
  fig = TRUE,
  ref = mean(x),
  pref_x = "x",
  pref_x_ref = "x",
  pref_y = "y",
  ci_quantiles = 10,
  breaks = NULL
)

Arguments

`y`	vector of outcome values
`x`	vector of exposure values
`g`	the instrumental variable
`covar`	`data.frame` of covariates
`family`	a description of the error distribution and link function to be used in the model and is a `character` string naming either the gaussian (i.e. `"gaussian"` for continuous data) or binomial (i.e. `"binomial"` for binary data) family function (default: `"gaussian"`)
`q`	the number of quantiles the exposure distribution is to be split into within which a causal effect will be fitted, known as localised average causal effects (LACE) (default: `10`)
`nboot`	the number of bootstrap replications (default: `100`)
`fig`	a `logical` statement as to whether the user wants the results displayed in a figure (default: `TRUE`)
`ref`	the reference point for the figure, this is the value of the function that represents the expected difference in the outcome compared with this reference value when the exposure is set to different values (default: `mean(x)`)
`pref_x`	the prefix/label for the x-axis (default: `"x"`)
`pref_x_ref`	the prefix for the reference value displayed on the y-axis (default: `"x"`)
`pref_y`	the prefix/label for the y-axis (default: `"y"`)
`ci_quantiles`	the number of quantiles at which confidence intervals are to be displayed (default: `10`)
`breaks`	breaks on the y-axis of the figure

Value

piecewise_mr returns a list of non-linear MR results from the piecewise linear function MR approach:

`n`	number of individuals
`model`	the model specifications: number of quantiles (`q`), number of bootstrap replications performed (`nboot`)
`coefficients`	the regression estimates: regression coefficients (`beta`), standard errors of regression coefficients (`se`), lower 95% confidence interval (`lci`), upper 95% confidence interval (`uci`), p-value (`pval`)
`lace`	the localised average causal effect estimate in each quantile: regression coefficients (`beta`), standard errors of regression coefficients (`se`), lower 95% confidence interval (`lci`), upper 95% confidence interval (`uci`), p-value (`pval`)
`xcoef`	the association between the instrument and the exposure in each quantile: regression coefficients (`beta`), standard errors of regression coefficients (`se`)
`p_tests`	the p-value of the non-linearity tests: p-value from the quadratic test (`quad`), p-value from the Cochran Q test (`Q`)
`p_heterogeneity`	the p-value of heterogeneity: p-value of the Cochran Q heterogeneity test (`Q`), p-value from the trend test (`trend`).

Author(s)

James Staley [email protected]

Examples

# IV (g), exposure (x) & outcome (y)
epsx <- rexp(10000)
u <- runif(10000, 0, 1)
g <- rbinom(10000, 2, 0.3)
epsy <- rnorm(10000)
ag <- 0.25
x <- 1 + ag * g + u + epsx
y <- 0.15 * x^2 + 0.8 * u + epsy

# Covariates (covar)
c1 <- rnorm(10000)
c2 <- rnorm(10000)
c3 <- rbinom(10000, 2, 0.33)
covar <- data.frame(c1 = c1, c2 = c2, c3 = as.factor(c3))

# Analyses
fp <- fracpoly_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, d = 1, ci = "model_se",
  fig = TRUE
)
summary(fp)
plm <- piecewise_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, nboot = 100,
  fig = TRUE
)
summary(plm)

# IV (g), exposure (x) & outcome (y)
epsx <- rexp(10000)
u <- runif(10000, 0, 1)
g <- rbinom(10000, 2, 0.3)
epsy <- rnorm(10000)
ag <- 0.25
x <- 1 + ag * g + u + epsx
y <- 0.15 * x^2 + 0.8 * u + epsy

# Covariates (covar)
c1 <- rnorm(10000)
c2 <- rnorm(10000)
c3 <- rbinom(10000, 2, 0.33)
covar <- data.frame(c1 = c1, c2 = c2, c3 = as.factor(c3))

# Analyses
fp <- fracpoly_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, d = 1, ci = "model_se",
  fig = TRUE
)
summary(fp)
plm <- piecewise_mr(
  y = y, x = x, g = g, covar = covar,
  family = "gaussian", q = 10, nboot = 100,
  fig = TRUE
)
summary(plm)

Print fracpoly_mr

Description

print method for class "fracpoly_mr".

Usage

## S3 method for class 'fracpoly_mr'
print(x, ...)
## S3 method for class 'fracpoly_mr'
print(x, ...)

Arguments

`x`	an object of class `"fracpoly_mr"`

Author(s)

James Staley [email protected]

Print piecewise_mr

Description

print method for class "piecewise_mr".

Usage

## S3 method for class 'piecewise_mr'
print(x, ...)
## S3 method for class 'piecewise_mr'
print(x, ...)

Arguments

`x`	an object of class `"piecewise_mr"`

Author(s)

James Staley [email protected]

Print summary of fracpoly_mr

Description

print.summary method for class "fracpoly_mr".

Usage

## S3 method for class 'summary.fracpoly_mr'
print(x, ...)
## S3 method for class 'summary.fracpoly_mr'
print(x, ...)

Arguments

`x`	an object of class `"fracpoly_mr"`

Author(s)

James Staley [email protected]

Print summary of piecewise_mr

Description

print.summary method for class "piecewise_mr".

Usage

## S3 method for class 'summary.piecewise_mr'
print(x, ...)
## S3 method for class 'summary.piecewise_mr'
print(x, ...)

Arguments

`x`	an object of class `"piecewise_mr"`.

Author(s)

James Staley [email protected]

Summary of fracpoly_mr

Description

summary method for class "fracpoly_mr".

Usage

## S3 method for class 'fracpoly_mr'
summary(x, ...)
## S3 method for class 'fracpoly_mr'
summary(x, ...)

Arguments

`x`	an object of class `"fracpoly_mr"`

Author(s)

James Staley [email protected]

Summary of piecewise_mr

Description

summary method for class "piecewise_mr".

Usage

## S3 method for class 'piecewise_mr'
summary(x, ...)
## S3 method for class 'piecewise_mr'
summary(x, ...)

Arguments

`x`	an object of class `"piecewise_mr"`

Author(s)

James Staley [email protected]

Package 'nlmr'

Help Index

Fractional polynomial Mendelian randomization

Description

Usage

Arguments

Value

Author(s)

Examples

Localised average causal effects

Description

Usage

Arguments

Value

Author(s)

Piecewise linear Mendelian randomization

Description

Usage

Arguments

Value

Author(s)

Examples

Print fracpoly_mr

Description

Usage

Arguments

Author(s)

Print piecewise_mr

Description

Usage

Arguments

Author(s)

Print summary of fracpoly_mr

Description

Usage

Arguments

Author(s)

Print summary of piecewise_mr

Description

Usage

Arguments

Author(s)

Summary of fracpoly_mr

Description

Usage

Arguments

Author(s)

Summary of piecewise_mr

Description

Usage

Arguments

Author(s)