Marginal effects, adjusted predictions and estimated marginal means from regression models

The ggeffects package computes estimated marginal means (predicted values) for the response, at the margin of specific values or levels from certain model terms, i.e. it generates predictions by a model by holding the non-focal variables constant and varying the focal variable(s).

ggpredict() uses predict() for generating predictions, while ggeffect() computes marginal effects by internally calling effects::Effect() and ggemmeans() uses emmeans::emmeans(). The result is returned as consistent data frame.

Usage

# S3 method for ggeffects
as.data.frame(
  x,
  row.names = NULL,
  optional = FALSE,
  ...,
  stringsAsFactors = FALSE,
  terms_to_colnames = FALSE
)

ggeffect(model, terms, ci.lvl = 0.95, verbose = TRUE, ...)

ggemmeans(
  model,
  terms,
  ci.lvl = 0.95,
  type = "fixed",
  typical = "mean",
  condition = NULL,
  back.transform = TRUE,
  interval = "confidence",
  verbose = TRUE,
  ...
)

ggpredict(
  model,
  terms,
  ci.lvl = 0.95,
  type = "fixed",
  typical = "mean",
  condition = NULL,
  back.transform = TRUE,
  ppd = FALSE,
  vcov.fun = NULL,
  vcov.type = NULL,
  vcov.args = NULL,
  interval,
  verbose = TRUE,
  ...
)

Arguments

x

An object of class ggeffects, as returned by ggpredict(), ggeffect() or ggemmeans().

row.names

NULL or a character vector giving the row names for the data frame. Missing values are not allowed.

optional

logical. If TRUE, setting row names and converting column names (to syntactic names: see make.names) is optional. Note that all of R's base package as.data.frame() methods use optional only for column names treatment, basically with the meaning of data.frame(*, check.names = !optional). See also the make.names argument of the matrix method.

...

For ggpredict(), further arguments passed down to predict(); for ggeffect(), further arguments passed down to effects::Effect(); and for ggemmeans(), further arguments passed down to emmeans::emmeans(). If type = "sim", ... may also be used to set the number of simulation, e.g. nsim = 500.

stringsAsFactors

logical: should the character vector be converted to a factor?

terms_to_colnames

Logical, if TRUE, standardized column names (like "x", "group" or "facet") are replaced by the variable names of the focal predictors specified in terms.

model

A fitted model object, or a list of model objects. Any model that supports common methods like predict(), family() or model.frame() should work. For ggeffect(), any model that is supported by effects should work, and for ggemmeans(), all models supported by emmeans should work.

terms

Character vector, (or a named list or a formula) with the names of those terms from model, for which predictions should be displayed. At least one term is required to calculate effects for certain terms, maximum length is four terms, where the second to fourth term indicate the groups, i.e. predictions of first term are grouped at the values or levels of the remaining terms. If terms is missing or NULL, adjusted predictions for each model term are calculated. It is also possible to define specific values for terms, at which adjusted predictions should be calculated (see 'Details'). All remaining covariates that are not specified in terms are held constant (see 'Details'). See also arguments condition and typical.

ci.lvl

Numeric, the level of the confidence intervals. For ggpredict(), use ci.lvl = NA, if confidence intervals should not be calculated (for instance, due to computation time). Typically, confidence intervals based on the standard errors as returned by the predict() function are returned, assuming normal distribution (i.e. +/- 1.96 * SE). See introduction of this vignette for more details.

verbose

Toggle messages or warnings.

type

Character, only applies for survival models, mixed effects models and/or models with zero-inflation. Note: For brmsfit-models with zero-inflation component, there is no type = "zero_inflated" nor type = "zi_random"; predicted values for MixMod-models from GLMMadaptive with zero-inflation component always condition on the zero-inflation part of the model (see 'Details').

"fixed" (or "fe" or "count")

Predicted values are conditioned on the fixed effects or conditional model only (for mixed models: predicted values are on the population-level and confidence intervals are returned). For instance, for models fitted with zeroinfl from pscl, this would return the predicted mean from the count component (without zero-inflation). For models with zero-inflation component, this type calls predict(..., type = "link") (however, predicted values are back-transformed to the response scale).
"random" (or "re")

This only applies to mixed models, and type = "random" does not condition on the zero-inflation component of the model. type = "random" still returns population-level predictions, however, unlike type = "fixed", intervals also consider the uncertainty in the variance parameters (the mean random effect variance, see Johnson et al. 2014 for details) and hence can be considered as prediction intervals. For models with zero-inflation component, this type calls predict(..., type = "link") (however, predicted values are back-transformed to the response scale).

To get predicted values for each level of the random effects groups, add the name of the related random effect term to the terms-argument (for more details, see this vignette).
"zero_inflated" (or "fe.zi" or "zi")

Predicted values are conditioned on the fixed effects and the zero-inflation component. For instance, for models fitted with zeroinfl from pscl, this would return the predicted response (mu*(1-p)) and for glmmTMB, this would return the expected value mu*(1-p) without conditioning on random effects (i.e. random effect variances are not taken into account for the confidence intervals). For models with zero-inflation component, this type calls predict(..., type = "response"). See 'Details'.
"zi_random" (or "re.zi" or "zero_inflated_random")

Predicted values are conditioned on the zero-inflation component and take the random effects uncertainty into account. For models fitted with glmmTMB(), hurdle() or zeroinfl(), this would return the expected value mu*(1-p). For glmmTMB, prediction intervals also consider the uncertainty in the random effects variances. This type calls predict(..., type = "response"). See 'Details'.
"zi_prob" (or "zi.prob")

Predicted zero-inflation probability. For glmmTMB models with zero-inflation component, this type calls predict(..., type = "zlink"); models from pscl call predict(..., type = "zero") and for GLMMadaptive, predict(..., type = "zero_part") is called.
"simulate" (or "sim")

Predicted values and confidence resp. prediction intervals are based on simulations, i.e. calls to simulate(). This type of prediction takes all model uncertainty into account, including random effects variances. Currently supported models are objects of class lm, glm, glmmTMB, wbm, MixMod and merMod. See ... for details on number of simulations.
"survival" and "cumulative_hazard" (or "surv" and "cumhaz")

Applies only to coxph-objects from the survial-package and calculates the survival probability or the cumulative hazard of an event.

typical

Character vector, naming the function to be applied to the covariates over which the effect is "averaged". The default is "mean". See ?sjmisc::typical_value for options.

condition

Named character vector, which indicates covariates that should be held constant at specific values. Unlike typical, which applies a function to the covariates to determine the value that is used to hold these covariates constant, condition can be used to define exact values, for instance condition = c(covariate1 = 20, covariate2 = 5). See 'Examples'.

back.transform

Logical, if TRUE (the default), predicted values for log- or log-log transformed responses will be back-transformed to original response-scale.

interval

Type of interval calculation, can either be "confidence" (default) or "prediction". May be abbreviated. Unlike confidence intervals, prediction intervals include the residual variance (sigma^2). For mixed models, interval = "prediction" is the default for type = "random". When type = "fixed", the default is interval = "confidence". Note that prediction intervals are not available for all models, but only for models that work with insight::get_sigma().

ppd

Logical, if TRUE, predictions for Stan-models are based on the posterior predictive distribution rstantools::posterior_predict(). If FALSE (the default), predictions are based on posterior draws of the linear predictor rstantools::posterior_linpred().

vcov.fun

Variance-covariance matrix used to compute uncertainty estimates (e.g., for confidence intervals based on robust standard errors). This argument accepts a covariance matrix, a function which returns a covariance matrix, or a string which identifies the function to be used to compute the covariance matrix.

A covariance matrix
A function which returns a covariance matrix (e.g., stats::vcov())
A string which indicates the name of the vcov*()-function from the sandwich or clubSandwich-package, e.g. vcov.fun = "vcovCL", which is used to compute (cluster) robust standard errors for predictions. If NULL, standard errors (and confidence intervals) for predictions are based on the standard errors as returned by the predict()-function. Note that probably not all model objects that work with ggpredict() are also supported by the sandwich or clubSandwich-package.

vcov.type

Character vector, specifying the estimation type for the robust covariance matrix estimation (see ?sandwich::vcovHC or ?clubSandwich::vcovCR for details). Only used when vcov.fun is a character string.

vcov.args

List of named vectors, used as additional arguments that are passed down to vcov.fun.

Value

A data frame (with ggeffects class attribute) with consistent data columns:

"x": the values of the first term in terms, used as x-position in plots.
"predicted": the predicted values of the response, used as y-position in plots.
"std.error": the standard error of the predictions. Note that the standard errors are always on the link-scale, and not back-transformed for non-Gaussian models!
"conf.low": the lower bound of the confidence interval for the predicted values.
"conf.high": the upper bound of the confidence interval for the predicted values.
"group": the grouping level from the second term in terms, used as grouping-aesthetics in plots.
"facet": the grouping level from the third term in terms, used to indicate facets in plots.

The estimated marginal means (or predicted values) are always on the response scale!

For proportional odds logistic regression (see ?MASS::polr) resp. cumulative link models (e.g., see ?ordinal::clm), an additional column "response.level" is returned, which indicates the grouping of predictions based on the level of the model's response.

Note that for convenience reasons, the columns for the intervals are always named "conf.low" and "conf.high", even though for Bayesian models credible or highest posterior density intervals are returned.

Details

Supported Models

A list of supported models can be found at https://github.com/strengejacke/ggeffects. Support for models varies by function, i.e. although ggpredict(), ggemmeans() and ggeffect() support most models, some models are only supported exclusively by one of the three functions.

Difference between ggpredict() and ggeffect() or ggemmeans()

ggpredict() calls predict(), while ggeffect() calls effects::Effect() and ggemmeans() calls emmeans::emmeans() to compute predicted values. Thus, effects returned by ggpredict() can be described as conditional effects (i.e. these are conditioned on certain (reference) levels of factors), while ggemmeans() and ggeffect() return marginal means, since the effects are "marginalized" (or "averaged") over the levels of factors (or values of character vectors). Therefore, ggpredict() and ggeffect() resp. ggemmeans() differ in how factors and character vectors are held constant: ggpredict() uses the reference level (or "lowest" value in case of character vectors), while ggeffect() and ggemmeans() compute a kind of "average" value, which represents the proportions of each factor's category. Use condition to set a specific level for factors in ggemmeans(), so factors are not averaged over their categories, but held constant at a given level.

Marginal Effects and Adjusted Predictions at Specific Values

Specific values of model terms can be specified via the terms-argument. Indicating levels in square brackets allows for selecting only specific groups or values resp. value ranges. Term name and the start of the levels in brackets must be separated by a whitespace character, e.g. terms = c("age", "education [1,3]"). Numeric ranges, separated with colon, are also allowed: terms = c("education", "age [30:60]"). The stepsize for range can be adjusted using by, e.g. terms = "age [30:60 by=5]".

The terms-argument also supports the same shortcuts as the values-argument in values_at(). So terms = "age [meansd]" would return predictions for the values one standard deviation below the mean age, the mean age and one SD above the mean age. terms = "age [quart2]" would calculate predictions at the value of the lower, median and upper quartile of age.

Furthermore, it is possible to specify a function name. Values for predictions will then be transformed, e.g. terms = "income [exp]". This is useful when model predictors were transformed for fitting the model and should be back-transformed to the original scale for predictions. It is also possible to define own functions (see this vignette).

Instead of a function, it is also possible to define the name of a variable with specific values, e.g. to define a vector v = c(1000, 2000, 3000) and then use terms = "income [v]".

You can take a random sample of any size with sample=n, e.g terms = "income [sample=8]", which will sample eight values from all possible values of the variable income. This option is especially useful for plotting predictions at certain levels of random effects group levels, where the group factor has many levels that can be completely plotted. For more details, see this vignette.

Finally, numeric vectors for which no specific values are given, a "pretty range" is calculated (see pretty_range()), to avoid memory allocation problems for vectors with many unique values. If a numeric vector is specified as second or third term (i.e. if this vector represents a grouping structure), representative values (see values_at()) are chosen (unless other values are specified). If all values for a numeric vector should be used to compute predictions, you may use e.g. terms = "age [all]". See also package vignettes.

To create a pretty range that should be smaller or larger than the default range (i.e. if no specific values would be given), use the n-tag, e.g. terms="age [n=5]" or terms="age [n=12]". Larger values for n return a larger range of predicted values.

Holding covariates at constant values

For ggpredict(), expand.grid() is called on all unique combinations of model.frame(model)[, terms] and used as newdata-argument for predict(). In this case, all remaining covariates that are not specified in terms are held constant: Numeric values are set to the mean (unless changed with the condition or typical-argument), integer values are set to their median, factors are set to their reference level (may also be changed with condition) and character vectors to their mode (most common element).

ggeffect() and ggemmeans(), by default, set remaining numeric covariates to their mean value, while for factors, a kind of "average" value, which represents the proportions of each factor's category, is used. The same applies to character vectors: ggemmeans() averages over the distribution of unique values in a character vector, similar to how factors are treated. For ggemmeans(), use condition to set a specific level for factors so that these are not averaged over their categories, but held constant at the given level.

Bayesian Regression Models

ggpredict() also works with Stan-models from the rstanarm or brms-packages. The predicted values are the median value of all drawn posterior samples. The confidence intervals for Stan-models are Bayesian predictive intervals. By default (i.e. ppd = FALSE), the predictions are based on rstantools::posterior_linpred() and hence have some limitations: the uncertainty of the error term is not taken into account. The recommendation is to use the posterior predictive distribution (rstantools::posterior_predict()).

Zero-Inflated and Zero-Inflated Mixed Models with brms

Models of class brmsfit always condition on the zero-inflation component, if the model has such a component. Hence, there is no type = "zero_inflated" nor type = "zi_random" for brmsfit-models, because predictions are based on draws of the posterior distribution, which already account for the zero-inflation part of the model.

Zero-Inflated and Zero-Inflated Mixed Models with glmmTMB

If model is of class glmmTMB, hurdle, zeroinfl or zerotrunc, simulations from a multivariate normal distribution (see ?MASS::mvrnorm) are drawn to calculate mu*(1-p). Confidence intervals are then based on quantiles of these results. For type = "zi_random", prediction intervals also take the uncertainty in the random-effect paramters into account (see also Brooks et al. 2017, pp.391-392 for details).

An alternative for models fitted with glmmTMB that take all model uncertainties into account are simulations based on simulate(), which is used when type = "sim" (see Brooks et al. 2017, pp.392-393 for details).

MixMod-models from GLMMadaptive

Predicted values for the fixed effects component (type = "fixed" or type = "zero_inflated") are based on predict(..., type = "mean_subject"), while predicted values for random effects components (type = "random" or type = "zi_random") are calculated with predict(..., type = "subject_specific") (see ?GLMMadaptive::predict.MixMod for details). The latter option requires the response variable to be defined in the newdata-argument of predict(), which will be set to its typical value (see ?sjmisc::typical_value).

Note

Multinomial Models

polr-, clm-models, or more generally speaking, models with ordinal or multinominal outcomes, have an additional column response.level, which indicates with which level of the response variable the predicted values are associated.

Printing Results

The print()-method gives a clean output (especially for predictions by groups), and indicates at which values covariates were held constant. Furthermore, the print()-method has the arguments digits and n to control number of decimals and lines to be printed, and an argument x.lab to print factor-levels instead of numeric values if x is a factor.

Limitations

The support for some models, for example from package MCMCglmm, is rather experimental and may fail for certain models. If you encounter any errors, please file an issue at https://github.com/strengejacke/ggeffects/issues.

References

Brooks ME, Kristensen K, Benthem KJ van, Magnusson A, Berg CW, Nielsen A, et al. glmmTMB Balances Speed and Flexibility Among Packages for Zero-inflated Generalized Linear Mixed Modeling. The R Journal. 2017;9: 378-400.
Johnson PC, O'Hara RB. 2014. Extension of Nakagawa & Schielzeth's R2GLMM to random slopes models. Methods Ecol Evol, 5: 944-946.

Examples

library(sjlabelled)
#> 
#> Attaching package: ‘sjlabelled’
#> The following object is masked from ‘package:ggplot2’:
#> 
#>     as_label
data(efc)
fit <- lm(barthtot ~ c12hour + neg_c_7 + c161sex + c172code, data = efc)

ggpredict(fit, terms = "c12hour")
#> # Predicted values of Total score BARTHEL INDEX
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.44 | [73.25, 77.63]
#>      20 |     70.38 | [68.56, 72.19]
#>      45 |     64.05 | [62.39, 65.70]
#>      65 |     58.98 | [57.15, 60.80]
#>      85 |     53.91 | [51.71, 56.12]
#>     105 |     48.85 | [46.14, 51.55]
#>     125 |     43.78 | [40.51, 47.05]
#>     170 |     32.38 | [27.73, 37.04]
#> 
#> Adjusted for:
#> *  neg_c_7 = 11.84
#> *  c161sex =  1.76
#> * c172code =  1.97
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.
ggpredict(fit, terms = c("c12hour", "c172code"))
#> # Predicted values of Total score BARTHEL INDEX
#> 
#> # c172code = low level of education
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     74.75 | [71.26, 78.23]
#>      30 |     67.15 | [64.03, 70.26]
#>      55 |     60.81 | [57.77, 63.86]
#>      85 |     53.22 | [49.95, 56.48]
#>     115 |     45.62 | [41.86, 49.37]
#>     170 |     31.69 | [26.59, 36.78]
#> 
#> # c172code = intermediate level of education
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.46 | [73.28, 77.65]
#>      30 |     67.87 | [66.16, 69.57]
#>      55 |     61.53 | [59.82, 63.25]
#>      85 |     53.93 | [51.72, 56.14]
#>     115 |     46.34 | [43.35, 49.32]
#>     170 |     32.40 | [27.74, 37.07]
#> 
#> # c172code = high level of education
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     76.18 | [72.81, 79.55]
#>      30 |     68.58 | [65.41, 71.76]
#>      55 |     62.25 | [59.00, 65.50]
#>      85 |     54.65 | [51.03, 58.27]
#>     115 |     47.05 | [42.85, 51.26]
#>     170 |     33.12 | [27.50, 38.74]
#> 
#> Adjusted for:
#> * neg_c_7 = 11.84
#> * c161sex =  1.76
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.
ggpredict(fit, terms = c("c12hour", "c172code", "c161sex"))
#> # Predicted values of Total score BARTHEL INDEX
#> 
#> # c172code = low level of education
#> #  c161sex = [1] Male
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     73.95 | [69.35, 78.56]
#>      45 |     62.56 | [58.22, 66.89]
#>      85 |     52.42 | [47.89, 56.96]
#>     170 |     30.89 | [24.84, 36.95]
#> 
#> # c172code = intermediate level of education
#> #  c161sex = [1] Male
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     74.67 | [71.05, 78.29]
#>      45 |     63.27 | [59.88, 66.67]
#>      85 |     53.14 | [49.39, 56.89]
#>     170 |     31.61 | [25.97, 37.25]
#> 
#> # c172code = high level of education
#> #  c161sex = [1] Male
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.39 | [71.03, 79.75]
#>      45 |     63.99 | [59.72, 68.26]
#>      85 |     53.86 | [49.22, 58.50]
#>     170 |     32.33 | [25.94, 38.72]
#> 
#> # c172code = low level of education
#> #  c161sex = [2] Female
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.00 | [71.40, 78.59]
#>      45 |     63.60 | [60.45, 66.74]
#>      85 |     53.46 | [50.12, 56.80]
#>     170 |     31.93 | [26.82, 37.05]
#> 
#> # c172code = intermediate level of education
#> #  c161sex = [2] Female
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.71 | [73.31, 78.12]
#>      45 |     64.32 | [62.41, 66.22]
#>      85 |     54.18 | [51.81, 56.56]
#>     170 |     32.65 | [27.94, 37.37]
#> 
#> # c172code = high level of education
#> #  c161sex = [2] Female
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     76.43 | [72.88, 79.98]
#>      45 |     65.03 | [61.67, 68.39]
#>      85 |     54.90 | [51.15, 58.65]
#>     170 |     33.37 | [27.69, 39.05]
#> 
#> Adjusted for:
#> * neg_c_7 = 11.84
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.

# specified as formula
ggpredict(fit, terms = ~ c12hour + c172code + c161sex)
#> # Predicted values of Total score BARTHEL INDEX
#> 
#> # c172code = low level of education
#> #  c161sex = [1] Male
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     73.95 | [69.35, 78.56]
#>      45 |     62.56 | [58.22, 66.89]
#>      85 |     52.42 | [47.89, 56.96]
#>     170 |     30.89 | [24.84, 36.95]
#> 
#> # c172code = intermediate level of education
#> #  c161sex = [1] Male
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     74.67 | [71.05, 78.29]
#>      45 |     63.27 | [59.88, 66.67]
#>      85 |     53.14 | [49.39, 56.89]
#>     170 |     31.61 | [25.97, 37.25]
#> 
#> # c172code = high level of education
#> #  c161sex = [1] Male
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.39 | [71.03, 79.75]
#>      45 |     63.99 | [59.72, 68.26]
#>      85 |     53.86 | [49.22, 58.50]
#>     170 |     32.33 | [25.94, 38.72]
#> 
#> # c172code = low level of education
#> #  c161sex = [2] Female
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.00 | [71.40, 78.59]
#>      45 |     63.60 | [60.45, 66.74]
#>      85 |     53.46 | [50.12, 56.80]
#>     170 |     31.93 | [26.82, 37.05]
#> 
#> # c172code = intermediate level of education
#> #  c161sex = [2] Female
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     75.71 | [73.31, 78.12]
#>      45 |     64.32 | [62.41, 66.22]
#>      85 |     54.18 | [51.81, 56.56]
#>     170 |     32.65 | [27.94, 37.37]
#> 
#> # c172code = high level of education
#> #  c161sex = [2] Female
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>       0 |     76.43 | [72.88, 79.98]
#>      45 |     65.03 | [61.67, 68.39]
#>      85 |     54.90 | [51.15, 58.65]
#>     170 |     33.37 | [27.69, 39.05]
#> 
#> Adjusted for:
#> * neg_c_7 = 11.84
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.

# only range of 40 to 60 for variable 'c12hour'
ggpredict(fit, terms = "c12hour [40:60]")
#> # Predicted values of Total score BARTHEL INDEX
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>      40 |     65.31 | [63.66, 66.96]
#>      43 |     64.55 | [62.90, 66.20]
#>      45 |     64.05 | [62.39, 65.70]
#>      47 |     63.54 | [61.88, 65.20]
#>      50 |     62.78 | [61.11, 64.45]
#>      53 |     62.02 | [60.33, 63.71]
#>      55 |     61.51 | [59.80, 63.22]
#>      60 |     60.25 | [58.49, 62.01]
#> 
#> Adjusted for:
#> *  neg_c_7 = 11.84
#> *  c161sex =  1.76
#> * c172code =  1.97
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.

# terms as named list
ggpredict(fit, terms = list(c12hour = 40:60))
#> # Predicted values of Total score BARTHEL INDEX
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>      40 |     65.31 | [63.66, 66.96]
#>      43 |     64.55 | [62.90, 66.20]
#>      45 |     64.05 | [62.39, 65.70]
#>      47 |     63.54 | [61.88, 65.20]
#>      50 |     62.78 | [61.11, 64.45]
#>      53 |     62.02 | [60.33, 63.71]
#>      55 |     61.51 | [59.80, 63.22]
#>      60 |     60.25 | [58.49, 62.01]
#> 
#> Adjusted for:
#> *  neg_c_7 = 11.84
#> *  c161sex =  1.76
#> * c172code =  1.97
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.

# covariate "neg_c_7" is held constant at a value of 11.84 (its mean value).
# To use a different value, use "condition"
ggpredict(fit, terms = "c12hour [40:60]", condition = c(neg_c_7 = 20))
#> # Predicted values of Total score BARTHEL INDEX
#> 
#> c12hour | Predicted |         95% CI
#> ------------------------------------
#>      40 |     46.56 | [42.58, 50.55]
#>      43 |     45.80 | [41.84, 49.76]
#>      45 |     45.30 | [41.35, 49.24]
#>      47 |     44.79 | [40.86, 48.72]
#>      50 |     44.03 | [40.11, 47.94]
#>      53 |     43.27 | [39.37, 47.17]
#>      55 |     42.76 | [38.87, 46.65]
#>      60 |     41.50 | [37.62, 45.37]
#> 
#> Adjusted for:
#> *  c161sex = 1.76
#> * c172code = 1.97
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.

# to plot ggeffects-objects, you can use the 'plot()'-function.
# the following examples show how to build your ggplot by hand.

if (FALSE) {
# plot predicted values, remaining covariates held constant
library(ggplot2)
mydf <- ggpredict(fit, terms = "c12hour")
ggplot(mydf, aes(x, predicted)) +
  geom_line() +
  geom_ribbon(aes(ymin = conf.low, ymax = conf.high), alpha = .1)

# three variables, so we can use facets and groups
mydf <- ggpredict(fit, terms = c("c12hour", "c161sex", "c172code"))
ggplot(mydf, aes(x = x, y = predicted, colour = group)) +
  stat_smooth(method = "lm", se = FALSE) +
  facet_wrap(~facet, ncol = 2)

# select specific levels for grouping terms
mydf <- ggpredict(fit, terms = c("c12hour", "c172code [1,3]", "c161sex"))
ggplot(mydf, aes(x = x, y = predicted, colour = group)) +
  stat_smooth(method = "lm", se = FALSE) +
  facet_wrap(~facet) +
  labs(
    y = get_y_title(mydf),
    x = get_x_title(mydf),
    colour = get_legend_title(mydf)
  )

# level indication also works for factors with non-numeric levels
# and in combination with numeric levels for other variables
data(efc)
efc$c172code <- sjlabelled::as_label(efc$c172code)
fit <- lm(barthtot ~ c12hour + neg_c_7 + c161sex + c172code, data = efc)
ggpredict(fit, terms = c("c12hour",
  "c172code [low level of education, high level of education]",
  "c161sex [1]"))

# when "terms" is a named list
ggpredict(fit, terms = list(
  c12hour = seq(0, 170, 30),
  c172code = c("low level of education", "high level of education"),
  c161sex = 1)
)

# use categorical value on x-axis, use axis-labels, add error bars
dat <- ggpredict(fit, terms = c("c172code", "c161sex"))
ggplot(dat, aes(x, predicted, colour = group)) +
  geom_point(position = position_dodge(.1)) +
  geom_errorbar(
    aes(ymin = conf.low, ymax = conf.high),
    position = position_dodge(.1)
  ) +
  scale_x_discrete(breaks = 1:3, labels = get_x_labels(dat))

# 3-way-interaction with 2 continuous variables
data(efc)
# make categorical
efc$c161sex <- as_factor(efc$c161sex)
fit <- lm(neg_c_7 ~ c12hour * barthtot * c161sex, data = efc)
# select only levels 30, 50 and 70 from continuous variable Barthel-Index
dat <- ggpredict(fit, terms = c("c12hour", "barthtot [30,50,70]", "c161sex"))
ggplot(dat, aes(x = x, y = predicted, colour = group)) +
  stat_smooth(method = "lm", se = FALSE, fullrange = TRUE) +
  facet_wrap(~facet) +
  labs(
    colour = get_legend_title(dat),
    x = get_x_title(dat),
    y = get_y_title(dat),
    title = get_title(dat)
  )

# or with ggeffects' plot-method
plot(dat, ci = FALSE)}

# predictions for polynomial terms
data(efc)
fit <- glm(
  tot_sc_e ~ c12hour + e42dep + e17age + I(e17age^2) + I(e17age^3),
  data = efc,
  family = poisson()
)
ggeffect(fit, terms = "e17age")
#> # Predicted counts of Services for elderly
#> 
#> e17age | Predicted |       95% CI
#> ---------------------------------
#>     64 |      1.37 | [1.04, 1.80]
#>     70 |      0.94 | [0.84, 1.06]
#>     74 |      0.90 | [0.80, 1.01]
#>     78 |      0.94 | [0.85, 1.04]
#>     84 |      1.04 | [0.94, 1.15]
#>     90 |      1.01 | [0.88, 1.15]
#>     94 |      0.82 | [0.65, 1.04]
#>    104 |      0.17 | [0.04, 0.67]
#> 
#> Not all rows are shown in the ouput. Use `print(..., n = Inf)` to show
#>   all rows.