gscale standardizes variables by dividing them by 2 standard
deviations and mean-centering them by default. It contains options for
handling binary variables separately. gscale() is a fork of
rescale from the arm package—the key feature
difference is that gscale() will perform the same functions for
variables in svydesign objects. gscale() is
also more user-friendly in that it is more flexible in how it accepts input.
Usage
gscale(
data = NULL,
vars = NULL,
binary.inputs = "center",
binary.factors = FALSE,
n.sd = 2,
center.only = FALSE,
scale.only = FALSE,
weights = NULL,
apply.weighted.contrasts = getOption("jtools-weighted.contrasts", FALSE),
x = NULL,
messages = FALSE
)Arguments
- data
A data frame or survey design. Only needed if you would like to rescale multiple variables at once. If
x = NULL, all columns will be rescaled. Otherwise,xshould be a vector of variable names. Ifxis a numeric vector, this argument is ignored.- vars
If
datais a data.frame or similar, you can scale only select columns by providing a vector column names to this argument.- binary.inputs
Options for binary variables. Default is
center;0/1keeps original scale;-0.5/0.5rescales 0 as -0.5 and 1 as 0.5;centersubtracts the mean; andfullsubtracts the mean and divides by 2 sd.- binary.factors
Coerce two-level factors to numeric and apply scaling functions to them? Default is FALSE.
- n.sd
By how many standard deviations should the variables be divided by? Default for
gscaleis 2, likearm'srescale. 1 is the more typical standardization scheme.- center.only
A logical value indicating whether you would like to mean -center the values, but not scale them.
- scale.only
A logical value indicating whether you would like to scale the values, but not mean-center them.
- weights
A vector of weights equal in length to
x. If iterating over a data frame, the weights will need to be equal in length to all the columns to avoid errors. You may need to remove missing values before using the weights.- apply.weighted.contrasts
Factor variables cannot be scaled, but you can set the contrasts such that the intercept in a regression model will reflect the true mean (assuming all other variables are centered). If set to TRUE, the argument will apply weighted effects coding to all factors. This is similar to the R default effects coding, but weights according to how many observations are at each level. An adapted version of
contr.wec()from thewecpackage is used to do this. See that package's documentation and/or Grotenhuis et al. (2016) for more info.- x
Deprecated. Pass numeric vectors to
data. Pass vectors of column names tovars.- messages
Print messages when variables are not processed due to being non-numeric or all missing? Default is FALSE.
Details
This function is adapted from the rescale function of
the arm package. It is named gscale() after the
popularizer of this scaling method, Andrew Gelman. By default, it
works just like rescale. But it contains many additional options and
can also accept multiple types of input without breaking a sweat.
Only numeric variables are altered when in a data.frame or survey design. Character variables, factors, etc. are skipped.
For those dealing with survey data, if you provide a survey.design
object you can rest assured that the mean-centering and scaling is performed
with help from the svymean() and
svyvar() functions, respectively. It was among the
primary motivations for creating this function. gscale() will not
center or scale the weights variables defined in the survey design unless
the user specifically requests them in the x = argument.
References
Gelman, A. (2008). Scaling regression inputs by dividing by two standard deviations. Statistics in Medicine, 27, 2865–2873. http://www.stat.columbia.edu/~gelman/research/published/standardizing7.pdf
Grotenhuis, M. te, Pelzer, B., Eisinga, R., Nieuwenhuis, R., Schmidt-Catran, A., & Konig, R. (2017). When size matters: Advantages of weighted effect coding in observational studies. International Journal of Public Health, 62, 163–167. https://doi.org/10.1007/s00038-016-0901-1 ( open access)
See also
j_summ is a replacement for the summary function for
regression models. On request, it will center and/or standardize variables
before printing its output.
standardization, scaling, and centering tools
center(),
center_mod(),
scale_mod(),
standardize()
Author
Jacob Long jacob.long@sc.edu
Examples
x <- rnorm(10, 2, 1)
x2 <- rbinom(10, 1, .5)
# Basic use
gscale(x)
#> [1] -0.42887747 0.31166952 -0.89289131 0.19495774 0.47550979 0.71120693
#> [7] -0.61756360 0.08680595 0.08820427 0.07097818
# Normal standardization
gscale(x, n.sd = 1)
#> [1] -0.8577549 0.6233390 -1.7857826 0.3899155 0.9510196 1.4224139
#> [7] -1.2351272 0.1736119 0.1764085 0.1419564
# Scale only
gscale(x, scale.only = TRUE)
#> [1] 0.26839830 1.00894529 -0.19561554 0.89223351 1.17278556 1.40848270
#> [7] 0.07971218 0.78408172 0.78548004 0.76825396
# Center only
gscale(x, center.only = TRUE)
#> [1] -0.9586790 0.6966816 -1.9958991 0.4357932 1.0629172 1.5897761
#> [7] -1.3804532 0.1940392 0.1971649 0.1586591
# Binary inputs
gscale(x2, binary.inputs = "0/1")
#> [1] 0 1 1 0 1 1 0 1 1 1
gscale(x2, binary.inputs = "full") # treats it like a continous var
#> [1] -0.7245688 0.3105295 0.3105295 -0.7245688 0.3105295 0.3105295
#> [7] -0.7245688 0.3105295 0.3105295 0.3105295
gscale(x2, binary.inputs = "-0.5/0.5") # keep scale, center at zero
#> [1] -0.5 0.5 0.5 -0.5 0.5 0.5 -0.5 0.5 0.5 0.5
gscale(x2, binary.inputs = "center") # mean center it
#> [1] -0.7 0.3 0.3 -0.7 0.3 0.3 -0.7 0.3 0.3 0.3
# Data frame as input
# loops through each numeric column
gscale(data = mtcars, binary.inputs = "-0.5/0.5")
#> mpg cyl disp hp drat
#> Mazda RX4 0.07544241 -0.0524939 -0.28530991 -0.26754642 0.28375684
#> Mazda RX4 Wag 0.07544241 -0.0524939 -0.28530991 -0.26754642 0.28375684
#> Datsun 710 0.22477172 -0.6124289 -0.49509105 -0.39152023 0.23699979
#> Hornet 4 Drive 0.10862670 -0.0524939 0.11004685 -0.26754642 -0.48305877
#> Hornet Sportabout -0.11536726 0.5074411 0.52154061 0.20647109 -0.41759890
#> Valiant -0.16514370 -0.0524939 -0.02308349 -0.30400931 -0.78230388
#> Duster 360 -0.48039447 0.5074411 0.52154061 0.71695148 -0.36149044
#> Merc 240D 0.35750889 -0.6124289 -0.33896547 -0.61759012 0.08737724
#> Merc 230 0.22477172 -0.6124289 -0.36276756 -0.37693508 0.30245966
#> Merc 280 -0.07388690 -0.0524939 -0.25464959 -0.17274292 0.30245966
#> Merc 280C -0.19003192 -0.0524939 -0.25464959 -0.17274292 0.30245966
#> Merc 450SE -0.30617694 0.5074411 0.18185654 0.24293397 -0.49241018
#> Merc 450SL -0.23151228 0.5074411 0.18185654 0.24293397 -0.49241018
#> Merc 450SLC -0.40572981 0.5074411 0.18185654 0.24293397 -0.49241018
#> Cadillac Fleetwood -0.80394131 0.5074411 0.97337691 0.42524840 -0.62332991
#> Lincoln Continental -0.80394131 0.5074411 0.92496588 0.49817417 -0.55787004
#> Chrysler Imperial -0.44721018 0.5074411 0.84428082 0.60756282 -0.34278762
#> Fiat 128 1.02119472 -0.6124289 -0.61329465 -0.58841981 0.45208222
#> Honda Civic 0.85527326 -0.6124289 -0.62539740 -0.69051589 1.24695206
#> Toyota Corolla 1.14563581 -0.6124289 -0.64395497 -0.59571239 0.58300196
#> Toyota Corona 0.11692278 -0.6124289 -0.44627659 -0.36234992 0.09672865
#> Dodge Challenger -0.38084159 0.5074411 0.35210200 0.02415666 -0.78230388
#> AMC Javelin -0.40572981 0.5074411 0.29562247 0.02415666 -0.41759890
#> Camaro Z28 -0.56335520 0.5074411 0.48119809 0.71695148 0.12478288
#> Pontiac Firebird -0.07388690 0.5074411 0.68291072 0.20647109 -0.48305877
#> Fiat X1-9 0.59809500 -0.6124289 -0.61208437 -0.58841981 0.45208222
#> Porsche 914-2 0.49024605 -0.6124289 -0.44546974 -0.40610538 0.77938156
#> Lotus Europa 0.85527326 -0.6124289 -0.54713290 -0.24566869 0.16218851
#> Ford Pantera L -0.35595337 0.5074411 0.48523234 0.85551044 0.58300196
#> Ferrari Dino -0.03240653 -0.0524939 -0.34582370 0.20647109 0.02191737
#> Maserati Bora -0.42232196 0.5074411 0.28351971 1.37328341 -0.05289391
#> Volvo 142E 0.10862670 -0.6124289 -0.44264576 -0.27483900 0.48013645
#> wt qsec vs am gear carb
#> Mazda RX4 -0.305199784 -0.388582573 -0.5 0.5 0.2117771 0.36760154
#> Mazda RX4 Wag -0.174892635 -0.231890410 -0.5 0.5 0.2117771 0.36760154
#> Datsun 710 -0.458502312 0.213003408 0.5 0.5 0.2117771 -0.56107604
#> Hornet 4 Drive -0.001149769 0.445243578 0.5 -0.5 -0.4659096 -0.56107604
#> Hornet Sportabout 0.113827127 -0.231890410 -0.5 -0.5 -0.4659096 -0.25151684
#> Valiant 0.124047296 0.663493376 0.5 -0.5 -0.4659096 -0.56107604
#> Duster 360 0.180258223 -0.562063181 -0.5 -0.5 -0.4659096 0.36760154
#> Merc 240D -0.013924980 0.601935740 0.5 -0.5 0.2117771 -0.25151684
#> Merc 230 -0.034365317 1.413377296 0.5 -0.5 0.2117771 -0.25151684
#> Merc 280 0.113827127 0.126263104 0.5 -0.5 0.2117771 0.36760154
#> Merc 280C 0.113827127 0.294147564 0.5 -0.5 0.2117771 0.36760154
#> Merc 450SE 0.435762437 -0.125563586 -0.5 -0.5 -0.4659096 0.05804235
#> Merc 450SL 0.262019572 -0.069602099 -0.5 -0.5 -0.4659096 0.05804235
#> Merc 450SLC 0.287569993 0.042320874 -0.5 -0.5 -0.4659096 0.05804235
#> Cadillac Fleetwood 1.038752382 0.036724726 -0.5 -0.5 -0.4659096 0.36760154
#> Lincoln Continental 1.127667849 -0.008044464 -0.5 -0.5 -0.4659096 0.36760154
#> Chrysler Imperial 1.087298183 -0.119967437 -0.5 -0.5 -0.4659096 0.36760154
#> Fiat 128 -0.519823324 0.453637801 0.5 0.5 0.2117771 -0.56107604
#> Honda Civic -0.818763254 0.187820739 0.5 0.5 0.2117771 -0.25151684
#> Toyota Corolla -0.706341400 0.573954997 0.5 0.5 0.2117771 -0.56107604
#> Toyota Corona -0.384406090 0.604733815 0.5 -0.5 -0.4659096 -0.56107604
#> Dodge Challenger 0.154707802 -0.273861525 -0.5 -0.5 -0.4659096 -0.25151684
#> AMC Javelin 0.111272085 -0.153544329 -0.5 -0.5 -0.4659096 -0.25151684
#> Camaro Z28 0.318230499 -0.682380377 -0.5 -0.5 -0.4659096 0.36760154
#> Pontiac Firebird 0.320785541 -0.223496187 -0.5 -0.5 -0.4659096 -0.25151684
#> Fiat X1-9 -0.655240557 0.294147564 0.5 0.5 0.2117771 -0.56107604
#> Porsche 914-2 -0.550483829 -0.321428789 -0.5 0.5 0.8894638 -0.25151684
#> Lotus Europa -0.870886114 -0.265467302 0.5 0.5 0.8894638 -0.25151684
#> Ford Pantera L -0.024145148 -0.937005142 -0.5 0.5 0.8894638 0.36760154
#> Ferrari Dino -0.228548520 -0.657197709 -0.5 0.5 0.8894638 0.98671992
#> Maserati Bora 0.180258223 -0.909024398 -0.5 0.5 0.8894638 1.60583831
#> Volvo 142E -0.223438435 0.210205334 0.5 0.5 0.2117771 -0.25151684
# Specified vars in data frame
gscale(mtcars, vars = c("hp", "wt", "vs"), binary.inputs = "center")
#> mpg cyl disp hp drat wt qsec vs
#> Mazda RX4 21.0 6 160.0 -0.26754642 3.90 -0.305199784 16.46 -0.4375
#> Mazda RX4 Wag 21.0 6 160.0 -0.26754642 3.90 -0.174892635 17.02 -0.4375
#> Datsun 710 22.8 4 108.0 -0.39152023 3.85 -0.458502312 18.61 0.5625
#> Hornet 4 Drive 21.4 6 258.0 -0.26754642 3.08 -0.001149769 19.44 0.5625
#> Hornet Sportabout 18.7 8 360.0 0.20647109 3.15 0.113827127 17.02 -0.4375
#> Valiant 18.1 6 225.0 -0.30400931 2.76 0.124047296 20.22 0.5625
#> Duster 360 14.3 8 360.0 0.71695148 3.21 0.180258223 15.84 -0.4375
#> Merc 240D 24.4 4 146.7 -0.61759012 3.69 -0.013924980 20.00 0.5625
#> Merc 230 22.8 4 140.8 -0.37693508 3.92 -0.034365317 22.90 0.5625
#> Merc 280 19.2 6 167.6 -0.17274292 3.92 0.113827127 18.30 0.5625
#> Merc 280C 17.8 6 167.6 -0.17274292 3.92 0.113827127 18.90 0.5625
#> Merc 450SE 16.4 8 275.8 0.24293397 3.07 0.435762437 17.40 -0.4375
#> Merc 450SL 17.3 8 275.8 0.24293397 3.07 0.262019572 17.60 -0.4375
#> Merc 450SLC 15.2 8 275.8 0.24293397 3.07 0.287569993 18.00 -0.4375
#> Cadillac Fleetwood 10.4 8 472.0 0.42524840 2.93 1.038752382 17.98 -0.4375
#> Lincoln Continental 10.4 8 460.0 0.49817417 3.00 1.127667849 17.82 -0.4375
#> Chrysler Imperial 14.7 8 440.0 0.60756282 3.23 1.087298183 17.42 -0.4375
#> Fiat 128 32.4 4 78.7 -0.58841981 4.08 -0.519823324 19.47 0.5625
#> Honda Civic 30.4 4 75.7 -0.69051589 4.93 -0.818763254 18.52 0.5625
#> Toyota Corolla 33.9 4 71.1 -0.59571239 4.22 -0.706341400 19.90 0.5625
#> Toyota Corona 21.5 4 120.1 -0.36234992 3.70 -0.384406090 20.01 0.5625
#> Dodge Challenger 15.5 8 318.0 0.02415666 2.76 0.154707802 16.87 -0.4375
#> AMC Javelin 15.2 8 304.0 0.02415666 3.15 0.111272085 17.30 -0.4375
#> Camaro Z28 13.3 8 350.0 0.71695148 3.73 0.318230499 15.41 -0.4375
#> Pontiac Firebird 19.2 8 400.0 0.20647109 3.08 0.320785541 17.05 -0.4375
#> Fiat X1-9 27.3 4 79.0 -0.58841981 4.08 -0.655240557 18.90 0.5625
#> Porsche 914-2 26.0 4 120.3 -0.40610538 4.43 -0.550483829 16.70 -0.4375
#> Lotus Europa 30.4 4 95.1 -0.24566869 3.77 -0.870886114 16.90 0.5625
#> Ford Pantera L 15.8 8 351.0 0.85551044 4.22 -0.024145148 14.50 -0.4375
#> Ferrari Dino 19.7 6 145.0 0.20647109 3.62 -0.228548520 15.50 -0.4375
#> Maserati Bora 15.0 8 301.0 1.37328341 3.54 0.180258223 14.60 -0.4375
#> Volvo 142E 21.4 4 121.0 -0.27483900 4.11 -0.223438435 18.60 0.5625
#> am gear carb
#> Mazda RX4 1 4 4
#> Mazda RX4 Wag 1 4 4
#> Datsun 710 1 4 1
#> Hornet 4 Drive 0 3 1
#> Hornet Sportabout 0 3 2
#> Valiant 0 3 1
#> Duster 360 0 3 4
#> Merc 240D 0 4 2
#> Merc 230 0 4 2
#> Merc 280 0 4 4
#> Merc 280C 0 4 4
#> Merc 450SE 0 3 3
#> Merc 450SL 0 3 3
#> Merc 450SLC 0 3 3
#> Cadillac Fleetwood 0 3 4
#> Lincoln Continental 0 3 4
#> Chrysler Imperial 0 3 4
#> Fiat 128 1 4 1
#> Honda Civic 1 4 2
#> Toyota Corolla 1 4 1
#> Toyota Corona 0 3 1
#> Dodge Challenger 0 3 2
#> AMC Javelin 0 3 2
#> Camaro Z28 0 3 4
#> Pontiac Firebird 0 3 2
#> Fiat X1-9 1 4 1
#> Porsche 914-2 1 5 2
#> Lotus Europa 1 5 2
#> Ford Pantera L 1 5 4
#> Ferrari Dino 1 5 6
#> Maserati Bora 1 5 8
#> Volvo 142E 1 4 2
# Weighted inputs
wts <- runif(10, 0, 1)
gscale(x, weights = wts)
#> [1] -0.43125470 0.26464991 -0.86729640 0.15497386 0.41861339 0.64010201
#> [7] -0.60856626 0.05334179 0.05465581 0.03846817
# If using a weights column of data frame, give its name
mtcars$weights <- runif(32, 0, 1)
gscale(mtcars, weights = weights) # will skip over mtcars$weights
#> mpg cyl disp hp
#> Mazda RX4 0.06424156 0.01615019 -0.259872325 -0.22222143
#> Mazda RX4 Wag 0.06424156 0.01615019 -0.259872325 -0.22222143
#> Datsun 710 0.21520704 -0.53517597 -0.470660639 -0.34614194
#> Hornet 4 Drive 0.09778944 0.01615019 0.137382575 -0.22222143
#> Hornet Sportabout -0.12865877 0.56747635 0.550851960 0.25159228
#> Valiant -0.17898060 0.01615019 0.003613068 -0.25866864
#> Duster 360 -0.49768550 0.56747635 0.550851960 0.76185320
#> Merc 240D 0.34939858 -0.53517597 -0.313785490 -0.57211463
#> Merc 230 0.21520704 -0.53517597 -0.337701856 -0.33156305
#> Merc 280 -0.08672392 0.01615019 -0.229064802 -0.12745869
#> Merc 280C -0.20414151 0.01615019 -0.229064802 -0.12745869
#> Merc 450SE -0.32155911 0.56747635 0.209537036 0.28803949
#> Merc 450SL -0.24607637 0.56747635 0.209537036 0.28803949
#> Merc 450SLC -0.42220276 0.56747635 0.209537036 0.28803949
#> Cadillac Fleetwood -0.82477737 0.56747635 1.004857560 0.47027553
#> Lincoln Continental -0.82477737 0.56747635 0.956214103 0.54316995
#> Chrysler Imperial -0.46413761 0.56747635 0.875141674 0.65251157
#> Fiat 128 1.02035626 -0.53517597 -0.589431747 -0.54295686
#> Honda Civic 0.85261684 -0.53517597 -0.601592611 -0.64500905
#> Toyota Corolla 1.14616082 -0.53517597 -0.620239269 -0.55024631
#> Toyota Corona 0.10617642 -0.53517597 -0.421611820 -0.31698417
#> Dodge Challenger -0.39704185 0.56747635 0.380599860 0.06935624
#> AMC Javelin -0.42220276 0.56747635 0.323849160 0.06935624
#> Camaro Z28 -0.58155521 0.56747635 0.510315746 0.76185320
#> Pontiac Firebird -0.08672392 0.56747635 0.712996817 0.25159228
#> Fiat X1-9 0.59262074 -0.53517597 -0.588215660 -0.54295686
#> Porsche 914-2 0.48359011 -0.53517597 -0.420801095 -0.36072082
#> Lotus Europa 0.85261684 -0.53517597 -0.522952355 -0.20035310
#> Ford Pantera L -0.37188093 0.56747635 0.514369367 0.90035259
#> Ferrari Dino -0.04478906 0.01615019 -0.320676646 0.25159228
#> Maserati Bora -0.43897670 0.56747635 0.311688296 1.41790295
#> Volvo 142E 0.09778944 -0.53517597 -0.417963560 -0.22951087
#> drat wt qsec vs am
#> Mazda RX4 0.30386980 -0.307380611 -0.41003825 -0.4819734 0.6191224
#> Mazda RX4 Wag 0.30386980 -0.172587401 -0.27285304 -0.4819734 0.6191224
#> Datsun 710 0.25426903 -0.465960859 0.11665499 0.5180266 0.6191224
#> Hornet 4 Drive -0.50958280 0.007136879 0.31998307 0.5180266 -0.3808776
#> Hornet Sportabout -0.44014172 0.126072065 -0.27285304 -0.4819734 -0.3808776
#> Valiant -0.82702771 0.136644081 0.51106248 0.5180266 -0.3808776
#> Duster 360 -0.38062080 0.194790172 -0.56192188 -0.4819734 -0.3808776
#> Merc 240D 0.09554657 -0.006078141 0.45716829 0.5180266 -0.3808776
#> Merc 230 0.32371011 -0.027222174 1.16759173 0.5180266 -0.3808776
#> Merc 280 0.32371011 0.126072065 0.04071317 0.5180266 -0.3808776
#> Merc 280C 0.32371011 0.126072065 0.18769733 0.5180266 -0.3808776
#> Merc 450SE -0.51950295 0.459090584 -0.17976307 -0.4819734 -0.3808776
#> Merc 450SL -0.51950295 0.279366304 -0.13076835 -0.4819734 -0.3808776
#> Merc 450SLC -0.51950295 0.305796345 -0.03277891 -0.4819734 -0.3808776
#> Cadillac Fleetwood -0.65838510 1.082839558 -0.03767838 -0.4819734 -0.3808776
#> Lincoln Continental -0.58894402 1.174816101 -0.07687416 -0.4819734 -0.3808776
#> Chrysler Imperial -0.36078049 1.133056636 -0.17486360 -0.4819734 -0.3808776
#> Fiat 128 0.48243256 -0.529392958 0.32733228 0.5180266 0.6191224
#> Honda Civic 1.32564562 -0.838624440 0.09460736 0.5180266 0.6191224
#> Toyota Corolla 0.62131471 -0.722332259 0.43267093 0.5180266 0.6191224
#> Toyota Corona 0.10546673 -0.389313739 0.45961802 0.5180266 -0.3808776
#> Dodge Challenger -0.82702771 0.168360131 -0.30959908 -0.4819734 -0.3808776
#> AMC Javelin -0.44014172 0.123429061 -0.20426043 -0.4819734 -0.3808776
#> Camaro Z28 0.13522719 0.337512395 -0.66726053 -0.4819734 -0.3808776
#> Pontiac Firebird -0.50958280 0.340155399 -0.26550383 -0.4819734 -0.3808776
#> Fiat X1-9 0.48243256 -0.669472176 0.18769733 0.5180266 0.6191224
#> Porsche 914-2 0.82963794 -0.561109007 -0.35124459 -0.4819734 0.6191224
#> Lotus Europa 0.17490780 -0.892541725 -0.30224987 0.5180266 0.6191224
#> Ford Pantera L 0.62131471 -0.016650158 -0.89018651 -0.4819734 0.6191224
#> Ferrari Dino 0.02610550 -0.228090488 -0.64521291 -0.4819734 0.6191224
#> Maserati Bora -0.05325573 0.194790172 -0.86568915 -0.4819734 0.6191224
#> Volvo 142E 0.51219302 -0.222804480 0.11420525 0.5180266 0.6191224
#> gear carb weights
#> Mazda RX4 0.1858306 0.4200398 0.09608644
#> Mazda RX4 Wag 0.1858306 0.4200398 -0.29173217
#> Datsun 710 0.1858306 -0.5246565 0.01377414
#> Hornet 4 Drive -0.4754387 -0.5246565 0.05356828
#> Hornet Sportabout -0.4754387 -0.2097577 -1.15332479
#> Valiant -0.4754387 -0.5246565 0.27882770
#> Duster 360 -0.4754387 0.4200398 0.28754293
#> Merc 240D 0.1858306 -0.2097577 0.76031886
#> Merc 230 0.1858306 -0.2097577 0.71713156
#> Merc 280 0.1858306 0.4200398 -0.52628944
#> Merc 280C 0.1858306 0.4200398 -0.37228111
#> Merc 450SE -0.4754387 0.1051410 -0.68444146
#> Merc 450SL -0.4754387 0.1051410 -0.98509702
#> Merc 450SLC -0.4754387 0.1051410 -0.22173057
#> Cadillac Fleetwood -0.4754387 0.4200398 -0.30287280
#> Lincoln Continental -0.4754387 0.4200398 0.30814866
#> Chrysler Imperial -0.4754387 0.4200398 -0.92199439
#> Fiat 128 0.1858306 -0.5246565 0.16717124
#> Honda Civic 0.1858306 -0.2097577 -1.21921995
#> Toyota Corolla 0.1858306 -0.5246565 -0.60109934
#> Toyota Corona -0.4754387 -0.5246565 0.40630423
#> Dodge Challenger -0.4754387 -0.2097577 -0.77304198
#> AMC Javelin -0.4754387 -0.2097577 -0.13944428
#> Camaro Z28 -0.4754387 0.4200398 -0.64064262
#> Pontiac Firebird -0.4754387 -0.2097577 -0.08336709
#> Fiat X1-9 0.1858306 -0.5246565 -0.94907346
#> Porsche 914-2 0.8470999 -0.2097577 0.66845681
#> Lotus Europa 0.8470999 -0.2097577 -0.19840193
#> Ford Pantera L 0.8470999 0.4200398 -0.19386109
#> Ferrari Dino 0.8470999 1.0498372 -0.76282040
#> Maserati Bora 0.8470999 1.6796347 -0.40326085
#> Volvo 142E 0.1858306 -0.2097577 -0.56408708
# If using a weights column of data frame, can still select variables
gscale(mtcars, vars = c("hp", "wt", "vs"), weights = weights)
#> mpg cyl disp hp drat wt qsec
#> Mazda RX4 21.0 6 160.0 -0.22222143 3.90 -0.307380611 16.46
#> Mazda RX4 Wag 21.0 6 160.0 -0.22222143 3.90 -0.172587401 17.02
#> Datsun 710 22.8 4 108.0 -0.34614194 3.85 -0.465960859 18.61
#> Hornet 4 Drive 21.4 6 258.0 -0.22222143 3.08 0.007136879 19.44
#> Hornet Sportabout 18.7 8 360.0 0.25159228 3.15 0.126072065 17.02
#> Valiant 18.1 6 225.0 -0.25866864 2.76 0.136644081 20.22
#> Duster 360 14.3 8 360.0 0.76185320 3.21 0.194790172 15.84
#> Merc 240D 24.4 4 146.7 -0.57211463 3.69 -0.006078141 20.00
#> Merc 230 22.8 4 140.8 -0.33156305 3.92 -0.027222174 22.90
#> Merc 280 19.2 6 167.6 -0.12745869 3.92 0.126072065 18.30
#> Merc 280C 17.8 6 167.6 -0.12745869 3.92 0.126072065 18.90
#> Merc 450SE 16.4 8 275.8 0.28803949 3.07 0.459090584 17.40
#> Merc 450SL 17.3 8 275.8 0.28803949 3.07 0.279366304 17.60
#> Merc 450SLC 15.2 8 275.8 0.28803949 3.07 0.305796345 18.00
#> Cadillac Fleetwood 10.4 8 472.0 0.47027553 2.93 1.082839558 17.98
#> Lincoln Continental 10.4 8 460.0 0.54316995 3.00 1.174816101 17.82
#> Chrysler Imperial 14.7 8 440.0 0.65251157 3.23 1.133056636 17.42
#> Fiat 128 32.4 4 78.7 -0.54295686 4.08 -0.529392958 19.47
#> Honda Civic 30.4 4 75.7 -0.64500905 4.93 -0.838624440 18.52
#> Toyota Corolla 33.9 4 71.1 -0.55024631 4.22 -0.722332259 19.90
#> Toyota Corona 21.5 4 120.1 -0.31698417 3.70 -0.389313739 20.01
#> Dodge Challenger 15.5 8 318.0 0.06935624 2.76 0.168360131 16.87
#> AMC Javelin 15.2 8 304.0 0.06935624 3.15 0.123429061 17.30
#> Camaro Z28 13.3 8 350.0 0.76185320 3.73 0.337512395 15.41
#> Pontiac Firebird 19.2 8 400.0 0.25159228 3.08 0.340155399 17.05
#> Fiat X1-9 27.3 4 79.0 -0.54295686 4.08 -0.669472176 18.90
#> Porsche 914-2 26.0 4 120.3 -0.36072082 4.43 -0.561109007 16.70
#> Lotus Europa 30.4 4 95.1 -0.20035310 3.77 -0.892541725 16.90
#> Ford Pantera L 15.8 8 351.0 0.90035259 4.22 -0.016650158 14.50
#> Ferrari Dino 19.7 6 145.0 0.25159228 3.62 -0.228090488 15.50
#> Maserati Bora 15.0 8 301.0 1.41790295 3.54 0.194790172 14.60
#> Volvo 142E 21.4 4 121.0 -0.22951087 4.11 -0.222804480 18.60
#> vs am gear carb weights
#> Mazda RX4 -0.4819734 1 4 4 0.68016292
#> Mazda RX4 Wag -0.4819734 1 4 4 0.49884561
#> Datsun 710 0.5180266 1 4 1 0.64167935
#> Hornet 4 Drive 0.5180266 0 3 1 0.66028435
#> Hornet Sportabout -0.4819734 0 3 2 0.09602416
#> Valiant 0.5180266 0 3 1 0.76560016
#> Duster 360 -0.4819734 0 3 4 0.76967480
#> Merc 240D 0.5180266 0 4 2 0.99071231
#> Merc 230 0.5180266 0 4 2 0.97052090
#> Merc 280 0.5180266 0 4 4 0.38918276
#> Merc 280C 0.5180266 0 4 4 0.46118646
#> Merc 450SE -0.4819734 0 3 3 0.31524175
#> Merc 450SL -0.4819734 0 3 3 0.17467589
#> Merc 450SLC -0.4819734 0 3 3 0.53157354
#> Cadillac Fleetwood -0.4819734 0 3 4 0.49363702
#> Lincoln Continental -0.4819734 0 3 4 0.77930863
#> Chrysler Imperial -0.4819734 0 3 4 0.20417834
#> Fiat 128 0.5180266 1 4 1 0.71339728
#> Honda Civic 0.5180266 1 4 2 0.06521611
#> Toyota Corolla 0.5180266 1 4 1 0.35420680
#> Toyota Corona 0.5180266 0 3 1 0.82519942
#> Dodge Challenger -0.4819734 0 3 2 0.27381825
#> AMC Javelin -0.4819734 0 3 2 0.57004495
#> Camaro Z28 -0.4819734 0 3 4 0.33571908
#> Pontiac Firebird -0.4819734 0 3 2 0.59626279
#> Fiat X1-9 0.5180266 1 4 1 0.19151803
#> Porsche 914-2 -0.4819734 1 5 2 0.94776394
#> Lotus Europa 0.5180266 1 5 2 0.54248041
#> Ford Pantera L -0.4819734 1 5 4 0.54460339
#> Ferrari Dino -0.4819734 1 5 6 0.27859715
#> Maserati Bora -0.4819734 1 5 8 0.44670247
#> Volvo 142E 0.5180266 1 4 2 0.37151118
# Survey designs
if (requireNamespace("survey")) {
library(survey)
data(api)
## Create survey design object
dstrat <- svydesign(id = ~1, strata = ~stype, weights = ~pw,
data = apistrat, fpc=~fpc)
# Creating test binary variable
dstrat$variables$binary <- rbinom(200, 1, 0.5)
gscale(data = dstrat, binary.inputs = "-0.5/0.5")
gscale(data = dstrat, vars = c("api00","meals","binary"),
binary.inputs = "-0.5/0.5")
}
#> Stratified Independent Sampling design
#> dstrat <- svydesign(id = ~1, strata = ~stype, weights = ~pw,
#> data = apistrat, fpc=~fpc)