afex (version 0.2-26)

aov.car: Convenience wrappers for car::Anova using either a formula or factor based interface.

Description

These functions allow convenient access to Anova (from the car package) for data in the long format (i.e., one observation per row), possibly aggregating the data if there is more than one obersvation per individuum and cell. Hence, mixed between-within ANOVAs can be calculated conveniently without using the rather unhandy format of car::Anova. aov.car can be called using a formula similar to aov specifying an error strata for the within-subject factor(s). ez.glm is called specifying the factors as character vectors.

Usage

aov.car(formula, data, fun.aggregate = NULL, type = 3,
    ...)

  ez.glm(id, dv, data, between = NULL, within = NULL,
    covariate = NULL, fun.aggregate = NULL, type = 3, ...,
    print.formula = FALSE)

  univariate(object)

Arguments

formula

A formula specifying the ANOVA model similar to aov. Should include an error term (i.e., Error( / )). Note that the within-subject factors do not need to be outside the Error term (this

id

character vector (of length 1) indicating the subject identifier column in data.

dv

character vector (of length 1) indicating the column containing the dependent variable in data.

between

character vector indicating the between-subject(s) factor(s)/column(s) in data. Default is NULL indicating no between-subjects factors.

within

character vector indicating the within-subject(s) factor(s)/column(s) in data. Default is NULL indicating no within-subjects factors.

covariate

character vector indicating the between-subject(s) covariate(s) (i.e., column(s)) in data. Default is NULL indicating no covariates.

data

A data.frame containing the data. Mandatory.

fun.aggregate

The function for aggregating the data before running the ANOVA if there is more than one obervation per individuum and cell of the design. The default NULL issues a warning if aggregation is necessary and uses

type

The type of sums of squares for the ANOVA. Defaults to 3. Passed to Anova. Possible values are "II", "III", 2, or 3.

print.formula

ez.glm is a wrapper for aov.car. This boolean argument indicates whether the formula in the call to car.aov should be printed.

...

Further arguments passed to fun.aggregate.

object

An object of class Anova.mlm as returned by aov.car, ez.glm, or Anova.

Value

• aov.car and ez.glm are wrappers and therfore return the same as Anova. Usually an object of class "Anova.mlm" (with within-subjects factors) or of class c("anova", "data.frame"). univariate returns a list of data.frames containing the univariate results (i.e., the classical ANOVA results) from an object of class "Anova.mlm". This is essentially the output from summary.Anova.mlm with multivariate = FALSE, e.g. summary(aov.car(...), multivriate = FALSE), as a list instead of printed to the console. For objects of class "anova" (i.e., the object returned by car::Anova for a purely between-subjects ANOVA) the object is returned unaltered. The elements of the list returned by univariate are: anova, mauchly, and spehricity.correction (containing both, Greenhouse-Geisser and Hyundt-Feldt correction).

Details

Type 3 sums of squares are default in afex. Note that type 3 sums of squares are said to be dangerous and/or problematic. On the other side they are the default in in SPSS and SAS and recommended by e.g. Maxwell and Delaney (2004). For a brief discussion see http://stats.stackexchange.com/q/6208/442{here}. However, note that lower order effects (e.g., main effects) in type 3 ANOVAs are only meaningful with http://www.ats.ucla.edu/stat/mult_pkg/faq/general/effect.htm{effects coding}. That is, contrasts should be set to contr.sum via options(contrasts=c('contr.sum','contr.poly')). This should be done automatically when loading afex and afex will issue a warning when running type 3 SS and http://www.ats.ucla.edu/stat/r/library/contrast_coding.htm{other coding schemes}. You can check the coding with options("contrasts"). The formula for aov.car must contain a single Error term specyfying the ID column and potential within-subject factors (you may use mixed with multiple error terms). Factors outside the Error term are treated as between-subject factors (the within-subject factors specified in the Error term are ignored outside the Error term, i.e., it is not necessary to specify them outside the Error term, see Examples). Suppressing the intercept (i.e, via 0 + or - 1) is ignored. Specific specifications of effects (e.g., excluding terms with - or using ^) could be okay but is not tested. Using the I or poly function within the formula is not tested and not supported! For ez.glm either between or within must not be NULL. ez.glm will concatante all between-subject factors using * (i.e., producing all main effects and interactions) and all covariates by + (i.e., adding only the main effects to the existing between-subject factors). The within-subject factors do fully interact with all between-subject factors and covariates. This is essentially identical to the behavior of SPSS's glm function.

References

Maxwell, S. E., & Delaney, H. D. (2004). Designing Experiments and Analyzing Data: A Model-Comparisons Perspective. Mahwah, N.J.: Lawrence Erlbaum Associates.

See Also

nice.anova is a function for creating nice ANOVA tables (including sphercitiy corrections) from objects returned by ez.glm and aov.car. mixed provides a (formula) interface for obtaining p-values for mixed-models via lme4. obk.long describes the long version of the OBrienKaiser dataset used in the examples.

Examples

# exampel using obk.long (see ?obk.long), a long version of the OBrienKaiser dataset from car.
data(obk.long)

# run univariate mixed ANCOVA for the full design:
univariate(aov.car(value ~ treatment * gender + age + Error(id/phase*hour), data = obk.long))
univariate(ez.glm("id", "value", obk.long, c("treatment", "gender"), c("phase", "hour"), "age"))

# both calls return the same:

## $anova
##                                      SS num Df  Error SS den Df           F       Pr(>F)
## (Intercept)                 6454.236987      1 215.65658      9 269.3547893 5.152317e-08
## treatment                    171.399953      2 215.65658      9   3.5765187 7.193619e-02
## gender                        94.598340      1 215.65658      9   3.9478742 7.818280e-02
## age                           12.398975      1 215.65658      9   0.5174466 4.901885e-01
## treatment:gender              61.531858      2 215.65658      9   1.2839551 3.231798e-01
## phase                        134.586005      2  59.72439     18  20.2810632 2.448505e-05
## treatment:phase               80.604542      4  59.72439     18   6.0732385 2.826803e-03
## gender:phase                   1.634246      2  59.72439     18   0.2462681 7.843036e-01
## age:phase                     20.553392      2  59.72439     18   3.0972362 6.982439e-02
## treatment:gender:phase        21.254421      4  59.72439     18   1.6014379 2.170946e-01
## hour                         108.513510      4  47.59543     36  20.5192290 7.001584e-09
## treatment:hour                 7.547869      8  47.59543     36   0.7136275 6.779072e-01
## gender:hour                    3.746135      4  47.59543     36   0.7083708 5.915285e-01
## age:hour                      14.904567      4  47.59543     36   2.8183608 3.926421e-02
## treatment:gender:hour          6.235198      8  47.59543     36   0.5895186 7.798264e-01
## phase:hour                     9.762579      8  88.62706     72   0.9913814 4.501348e-01
## treatment:phase:hour           6.579092     16  88.62706     72   0.3340505 9.915014e-01
## gender:phase:hour              8.851396      8  88.62706     72   0.8988515 5.222336e-01
## age:phase:hour                 7.539611      8  88.62706     72   0.7656409 6.339004e-01
## treatment:gender:phase:hour   12.822199     16  88.62706     72   0.6510416 8.307936e-01
##
## $mauchly
##                             Test statistic    p-value
## phase                         0.8217571566 0.45600959
## treatment:phase               0.8217571566 0.45600959
## gender:phase                  0.8217571566 0.45600959
## age:phase                     0.8217571566 0.45600959
## treatment:gender:phase        0.8217571566 0.45600959
## hour                          0.0966749877 0.04923980
## treatment:hour                0.0966749877 0.04923980
## gender:hour                   0.0966749877 0.04923980
## age:hour                      0.0966749877 0.04923980
## treatment:gender:hour         0.0966749877 0.04923980
## phase:hour                    0.0002379741 0.08651564
## treatment:phase:hour          0.0002379741 0.08651564
## gender:phase:hour             0.0002379741 0.08651564
## age:phase:hour                0.0002379741 0.08651564
## treatment:gender:phase:hour   0.0002379741 0.08651564
##
## $sphericity.correction
##                                GG eps   Pr(>F[GG])    HF eps   Pr(>F[HF])
## phase                       0.8487215 8.383485e-05 1.0252867 2.448505e-05
## treatment:phase             0.8487215 5.159591e-03 1.0252867 2.826803e-03
## gender:phase                0.8487215 7.493990e-01 1.0252867 7.843036e-01
## age:phase                   0.8487215 8.073373e-02 1.0252867 6.982439e-02
## treatment:gender:phase      0.8487215 2.279698e-01 1.0252867 2.170946e-01
## hour                        0.5341747 1.302016e-05 0.7054545 8.046331e-07
## treatment:hour              0.5341747 6.010781e-01 0.7054545 6.342676e-01
## gender:hour                 0.5341747 5.137213e-01 0.7054545 5.478398e-01
## age:hour                    0.5341747 8.155027e-02 0.7054545 6.211130e-02
## treatment:gender:hour       0.5341747 6.843526e-01 0.7054545 7.263729e-01
## phase:hour                  0.4355822 4.186799e-01 0.7444364 4.402119e-01
## treatment:phase:hour        0.4355822 9.317848e-01 0.7444364 9.787985e-01
## gender:phase:hour           0.4355822 4.651930e-01 0.7444364 5.020890e-01
## age:phase:hour              0.4355822 5.395151e-01 0.7444364 5.992844e-01
## treatment:gender:phase:hour 0.4355822 7.100921e-01 0.7444364 7.878433e-01
##
## Warning message:
## In univariate(aov.car(value ~ treatment * gender + age + Error(id/phase *  :
##   HF eps > 1 treated as 1

# To get a nicer ANOVA table use function nice.anova (see ?noce.anova):
nice.anova(ez.glm("id", "value", obk.long, c("treatment", "gender"), c("phase", "hour"), "age"))

##                         Effect          df   MSE         F     p
## 1                    treatment        2, 9 23.96    3.58 +   .07
## 2                       gender        1, 9 23.96    3.95 +   .08
## 3                          age        1, 9 23.96      0.52   .49
## 4             treatment:gender        2, 9 23.96      1.28   .32
## 5                        phase  1.7, 15.28  3.91 20.28 *** <.001
## 6              treatment:phase 3.39, 15.28  3.91   6.07 **  .005
## 7                 gender:phase  1.7, 15.28  3.91      0.25   .75
## 8                    age:phase  1.7, 15.28  3.91    3.10 +   .08
## 9       treatment:gender:phase 3.39, 15.28  3.91      1.60   .23
## 10                        hour 2.14, 19.23  2.48 20.52 *** <.001
## 11              treatment:hour 4.27, 19.23  2.48      0.71   .60
## 12                 gender:hour 2.14, 19.23  2.48      0.71   .51
## 13                    age:hour 2.14, 19.23  2.48    2.82 +   .08
## 14       treatment:gender:hour 4.27, 19.23  2.48      0.59   .68
## 15                  phase:hour 3.48, 31.36  2.83      0.99   .42
## 16        treatment:phase:hour 6.97, 31.36  2.83      0.33   .93
## 17           gender:phase:hour 3.48, 31.36  2.83      0.90   .47
## 18              age:phase:hour 3.48, 31.36  2.83      0.77   .54
## 19 treatment:gender:phase:hour 6.97, 31.36  2.83      0.65   .71

# replicating ?Anova using aov.car:
aov.car(value ~ treatment * gender + Error(id/phase*hour), data = obk.long, type = 2)
# in contrast to aov you do not need the within-subject factors outside Error()

# replicating ?Anova using ez.glm:
ez.glm("id", "value", obk.long, c("treatment", "gender"), c("phase", "hour"), type = 2)

#both return:
## Type II Repeated Measures MANOVA Tests: Pillai test statistic
##                             Df test stat approx F num Df den Df       Pr(>F)
## (Intercept)                  1     0.970      318      1     10 0.0000000065 ***
## treatment                    2     0.481        5      2     10      0.03769 *
## gender                       1     0.204        3      1     10      0.14097
## treatment:gender             2     0.364        3      2     10      0.10447
## phase                        1     0.851       26      2      9      0.00019 ***
## treatment:phase              2     0.685        3      4     20      0.06674 .
## gender:phase                 1     0.043        0      2      9      0.82000
## treatment:gender:phase       2     0.311        1      4     20      0.47215
## hour                         1     0.935       25      4      7      0.00030 ***
## treatment:hour               2     0.301        0      8     16      0.92952
## gender:hour                  1     0.293        1      4      7      0.60237
## treatment:gender:hour        2     0.570        1      8     16      0.61319
## phase:hour                   1     0.550        0      8      3      0.83245
## treatment:phase:hour         2     0.664        0     16      8      0.99144
## gender:phase:hour            1     0.695        1      8      3      0.62021
## treatment:gender:phase:hour  2     0.793        0     16      8      0.97237
## ---
## Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1


# aggregating over one within-subjects factor (phase) with warning:

aov.car(value ~ treatment * gender + age + Error(id/hour), data = obk.long)

ez.glm("id", "value", obk.long, c("treatment", "gender"), "hour", "age")


# runs with "numeric" factors
obk.long$hour2 <- as.numeric(as.character(obk.long$hour))

aov.car(value ~ treatment * gender + Error(id/hour2), data = obk.long, type = 2)

# only between
aov.car(value ~ treatment * gender + age + Error(id), data = obk.long, type = 2)
aov.car(value ~ treatment * gender + Error(id), data = obk.long, type = 2)

ez.glm("id", "value", obk.long, c("treatment", "gender"), within = NULL, covariate = "age", type = 2, print.formula = TRUE)

ez.glm("id", "value", obk.long, c("treatment", "gender"), within = NULL, type = 2, print.formula = TRUE)

# only within

univariate(aov.car(value ~ Error(id/phase*hour), data = obk.long, type = 2))

univariate(ez.glm("id", "value", obk.long,  NULL, c("phase", "hour"), type = 2, print.formula = TRUE))