You are on page 1of 14

Biostatistics (2007), 8, 1, pp.

Advance Access publication on April 5, 2006

The logistic transform for bounded outcome scores

Biostatistical Centre, Catholic University of Leuven,
U.Z. St. Rafaël, Kapucijnenvoer 35, B–3000 Leuven, Belgium

Downloaded from by guest on February 7, 2011

The logistic transformation, originally suggested by Johnson (1949), is applied to analyze responses that
are restricted to a finite interval (e.g. (0, 1)), so-called bounded outcome scores. Bounded outcome scores
often have a non-standard distribution, e.g. J - or U -shaped, precluding classical parametric statistical
approaches for analysis. Applying the logistic transformation on a normally distributed random variable,
gives rise to a logit-normal (LN) distribution. This distribution can take a variety of shapes on (0, 1).
Further, the model can be extended to correct for (baseline) covariates. Therefore, the method could be
useful for comparative clinical trials. Bounded outcomes can be found in many research areas, e.g. drug
compliance research, quality-of-life studies, and pain (and pain relief) studies using visual analog scores,
but all these scores can attain the boundary values 0 or 1. A natural extension of the above approach is
therefore to assume a latent score on (0, 1) having a LN distribution. Two cases are considered: (a) the
bounded outcome score is a proportion where the true probabilities have a LN distribution on (0, 1) and
(b) the bounded outcome score on [0, 1] is a coarsened version of a latent score with a LN distribution
on (0, 1). We also allow the variance (on the transformed scale) to depend on treatment. The usefulness
of our approach for comparative clinical trials will be assessed in this paper. It turns out to be important
to distinguish the case of equal and unequal variances. For a bounded outcome score of the second type
and with equal variances, our approach comes close to ordinal probit (OP) regression. However, ignoring
the inequality of variances can lead to highly biased parameter estimates. A simulation study compares
the performance of our approach with the two-sample Wilcoxon test and with OP regression. Finally, the
different methods are illustrated on two data sets.

Keywords: Barthel index; Bounded outcome scores; Compliance research; Logistic-transform, Ordinal probit

Bounded outcome scores are measurements that are restricted to a finite interval, which can be closed,
open, or half-closed. Examples of bounded outcome scores can be found in many medical disciplines.
For instance, in compliance research one measures the proportion of days that patients correctly take
their drug, hereafter denoted as “pdays.” Another example is the Barthel index (Mahoney and Barthel,
1965) which is an Activities on Daily Living scale that (in one version) jumps with steps of 5 from 0

∗ To whom correspondence should be addressed.

c The Author 2006. Published by Oxford University Press. All rights reserved. For permissions, please e-mail:
The logistic transform for bounded outcome scores 73

(death or completely immobilized) to 100 (able to perform all daily activities independently). This scale
is often used in stroke trials to measure the recovery of a patient after an acute stroke. Finally, in pain and
pain-relief studies, a visual analog score (VAS) is used to measure the psychological state of the subject.
Bounded outcome scores show a variety of distributions, from unimodal to J - and U -shaped. These
peculiar shapes often motivate the use of non-parametric methods, like the Wilcoxon test (Lesaffre and
others, 1993) when comparing two treatments. However, possibilities for statistical modeling, e.g. when
covariate adjustment is envisaged, are then limited. Alternatively, a dichotomized version of the score
may be constructed and analyzed using logistic regression. For instance, the Barthel index could be split
at 0.9. A value above 0.9 implies that the patients are able to perform most of their daily activities, and
hence the dichotomized Barthel index has a simple interpretation. However, such an approach has two
disadvantages; first the choice of the threshold is usually ad hoc and second reducing the score to a binary
variable may reduce the efficiency of the comparison. Ordinal regression (McCullagh, 1980) is an alter-

Downloaded from by guest on February 7, 2011

native method to analyze bounded outcome scores although this ignores the numeric character of the data.
In this paper, we explore the use of the logistic transformation first suggested by Johnson (1949) to
model the distribution of bounded outcome scores on (0, 1). However, many outcome scores are defined
on a closed interval. In this case, we assume here that a latent variable with range (0, 1) gives rise to an
observed score on [0, 1]. Bounded outcomes on [0, 1] can be discrete or of a mixed continuous–discrete
type. Here, we will concentrate on the first type and consider two cases: (1) a proportion where the true
probabilities have a logit-normal (LN) distribution on (0, 1) and (2) a discrete score ranging from 0 to
1 interpreted as the grouped version of a continuous latent variable on (0, 1). We call the first case the
“binomial-logit-normal (BLN) approach” and the second case the “coarsening (CO) approach.” A typical
example of a continuous–discrete score on [0, 1] would be the visual analog scale, which takes values
continuously on (0, 1) but can also give the extreme values 0 or 1 with a non-zero probability.
In Section 2, we indicate the usefulness of the logistic transformation for comparative clinical re-
search with bounded outcomes on (0, 1). We then present methods for analyzing bounded outcomes on
[0, 1] and focus on the comparison of two treatments. We consider the cases of equal and unequal vari-
ances on the transformed scale. The competitor to the CO approach is the classical ordinal probit (OP)
regression. We will show that OP regression is very similar to the CO approach for equal variances, but
with unequal variances it may give a severely biased estimate of the treatment effect. Section 4 describes a
simulation study evaluating the performance of our approaches for various distributions on [0, 1] in com-
parison with the two-sample Wilcoxon test and OP regression. Details of the simulation study are given in
supplementary material available at Biostatistics online ( In
Section 5, we illustrate our method first on “pdays,” the primary endpoint of the THAMES study, a recent
compliance-enhancing intervention study performed in Belgium. Further, we re-analyzed the primary
endpoint (Barthel index) of the European Cooperative Acute Stroke Study I study, an early placebo-
controlled randomized clinical trial evaluating the effect of a thrombolytic drug on patients with an acute
ischemic stroke. In Section 6, we look at distributions other than the LN, discuss some other approaches,
and look at the goodness-of-fit of the LN distribution. Finally, in Section 7, we summarize our results and
make some suggestions for further research in this area.


Johnson (1949) suggested the logistic transformation Z = α + β log U b−U , where α, β, a, b ∈ R and
U is a score on the interval (a, b). The aim of Johnson was to achieve standard normality. In the case of
proportions, a = 0 and b = 1. Here we take α = 0 and β = 1 and assume that the logistic transformation
achieves a normal density N (µ, σ 2 ). In general, when Z has density
 f (z) ≡ f (z; θ ), then U has density
g(u) ≡ g(u; θ ) = f (logit(u)) u(1−u)
, where logit(u) = log 1−uu
. When Z ∼ N (µ, σ 2 ), then U has a
LN distribution, denoted as LN(µ, σ 2 ) and θ T = (µ, σ 2 ).

Downloaded from by guest on February 7, 2011

Fig. 1. Different LN distributions.

The LN distribution can take very different shapes depending on the choice of µ and σ 2 , as is shown
in Figure 1. Note that when µ changes sign this corresponds to mirroring the distribution around u = 0.5.
Hence, the logistic transformation is very well suited to model a variety of distributions on (0, 1). A
similar property holds for the Beta family, but Aitchison and Begg (1976) indicate that the LN distribution
is richer and can approximate any Beta density.
It is clear that when the bounded outcome scores have a LN distribution, the analysis could be done
on the Z -scale using classical statistical analyses assuming a Gaussian distribution. For instance, suppose
we wish to compare the effects of control and new treatments based on a bounded score with distributions
LN(µ, σ12 ) and LN(µ + , σ22 ), respectively. When σ12 = σ22 = σ 2 , a simple unpaired t-test can be
calculated on the final Z -values and a 95% confidence interval can be obtained for  (>0) on the Z -
scale. The interpretation of  is more difficult because it represents a location shift on the transformed
scale. Since the logistic transformation is strictly monotone,  = log νν21 /(1−ν 2)
/(1−ν1 ) , where ν1 and ν2 are the
medians for the control and new treatment, respectively, on the original scale. Figure 2 gives an example
of how the location-shift alternative on the Z -scale is translated into an alternative hypothesis on the
observed U -scale, when σ12 = σ22 . The parameter  can also be interpreted in relation to the Wilcoxon–
Mann–Whitney test (Lehmann and D’Abrera, 1998). Assume that Z 1 and Z 2 are independent random
variables on the transformed  scale
 corresponding to the control and new treatments, respectively, then
P(Z 2 > Z 1 ) = P =   √ , which is also equal to P(U2 > U1 ) for the corresponding original U
σ 2
values. Brunner and Munzel (2000) called P the “relative effect” of the treatment,  which is therefore
seen to be determined by the ratio /σ . In general, the relative effect is equal to F1 dF2 , where F j is the
cumulative distribution function of Z j or here equivalently of U j ( j = 1, 2). Hence, loosely speaking, P
determines the proportion of individuals better off with the new treatment than with the control treatment.
A 95% CI for P can be obtained using the Delta method when estimates for , σ , and their covariance
matrix are available. If instead transformation to a logistic distribution is envisaged, then /σ can be
directly interpreted as a log-odds ratio of cumulative distribution functions, see Section 6.
When σ1 = σ2 , one could use the Welch test (Welch, 1951) on the transformed Z -scale. This test is
also called the unpaired t-test for unequal variances. However, it is well known that ignoring the inequality
of the variances, i.e. applying in this case the classical unpaired t-test, has no great impact on the type I
error as long as n 1 ≈ n 2 (see, e.g. 
 1960;Murphy, 1967). Further, in this case the relative effect is
equal to P(Z 2 > Z 1 ) = P =  / σ12 + σ22 , which can be estimated in a similar manner as above.
The logistic transform for bounded outcome scores 75

Downloaded from by guest on February 7, 2011

Fig. 2. Correspondence of the location-shift alternative hypothesis on the transformed Z -scale to the corresponding
alternative hypothesis on the observed U -scale.

The logistic transformation is useful for power and sample size calculations in a clinical trial with
a bounded outcome score U as primary endpoint because the classical location-shift alternative is most
often not appropriate. While power and sample size calculations are more difficult, they can be realized
by first specifying the relative effect together with σ .
Finally, the logistic transformation is also useful in statistical modeling of bounded outcome scores on
(0, 1). Indeed, the logistic regression model
log = xT β + σ Z , (2.1)
with Z ∼ N (0, 1), has been used in various applications (Kieschnick and McCullough, 2003). This
approach is especially useful in clinical trial applications when baseline covariate adjustment is envisaged.
Finally, Expression (2.1) can easily be extended to allow σ to depend on covariates, as for example in
Pourahmadi (1999).


In this section, we primarily focus on bounded outcomes on [0, 1] which we denote by Yi to distinguish
them from Ui ∈ (0, 1). Two different types of outcomes are considered here. First, the bounded outcome
scores Yi are observed proportions equal to ri /Ni (i = 1, . . . , n), whereby ri is the ith count out of Ni
units. In this case, Ui represents the true proportion measured with error by Yi . For instance, in compliance
research, Yi = ri /Ni , whereby ri is the number of days out of Ni on which the ith patient has correctly
taken the drug. Second, Yi is a coarsened version of Ui on (0, 1). Typical examples can be found in
Quality of Life research (e.g. the Barthel index) where Yi denote sums of individual items each measuring
an aspect of the subject’s true quality of life Ui . Such a score can be standardized to lie between 0 and 1
while taking a finite number of values.

3.1 Modeling proportions on [0, 1]

When the bounded outcome score is a proportion derived from a series of conditionally (conditional
on the subject) independent Bernoulli experiments, then an obvious choice is to work with a binomial

distribution. Namely, in the BLN approach, we assume that

ri ∼ Bin(Ui , Ni ) (i = 1, . . . , n) (3.1)

with Ui ∼ LN(µ, σ 2 ) and say that ri has a BLN distribution. For each value of Ui , one observes Ni
binary outcomes Wi j ( j = 1, . . . , Ni ) summing up to ri . For the compliance example, the rec-
orded adherence is the observed proportion of days that the patients take their medication correctly
(with respect to dosage and timing) in a period of Ni days. In this case, the Ui could be interpreted
as the (true but unobserved) latent adherence of the ith patient to the drug. Observe that this model is
actually a classical measurement error model (Carroll and others, 1995), specifying the distribution
f (Y |U ).
Model (3.1) can be extended by replacing µ by xiT β to give a “generalized linear mixed-effects model,”

Downloaded from by guest on February 7, 2011

whereby conditional on Ui the Wi j are assumed to be independent. As indicated above, a further exten-
sion allows σ to depend on covariates. Fitting such a model can be done with, e.g. the SAS procedure
NLMIXED or the function “lmer()” in package “lme4” in R Development Core Team (2005).

3.2 Modeling discrete bounded outcome scores on [0, 1]

When Yi is a discrete random variable on [0, 1] (e.g. the Barthel index), but not a proportion, then it is
natural to assume that Yi is a grouped version of Ui . As a specific example, Yi could have been realized
from a CO mechanism such that Yi = k/m when (k − 0.5)/m  Ui < (k + 0.5)/m, where k = 0, . . . , m.
At the boundaries, Yi = 0 when 0 < Ui < 0.5/m and Yi = 1 when (m − 0.5)/m < Ui < 1. The above
grid of boundary values is equal for all subjects and is denoted below as

a0 ≡ 0 < a1 = 0.5/m < · · · < am = (m − 0.5)/m < a(m+1) ≡ 1.

However, our approach also allows a grid varying with the subjects.
The framework of coarsened data has been formalized by Heitjan and Rubin (1991) and Heitjan
(1993). In their terminology, we consider here only deterministic CO. More formally, we assume that
as(i)  Ui < as(i)+1 when Yi is recorded. For the likelihood this implies the following expression:

L(θθ ; y) = g(u i ; θ )du, (3.2)
i=1 as(i)

where g(·) is the probability density function of the LN distribution. This leads to the likelihood
(u) (l) 

z s(i) − xiT β z s(i) − xiT β
L(θθ ; y) ≡ L(β
β , σ ; y) =  − , (3.3)
σ σ

(l) (u)
where z s(i) = logit(as(i) ), z s(i) = logit(as(i)+1 ), and (·) is the distribution function of the standard
normal distribution. At the boundaries, i.e. a0 = 0 and a(m+1) = 1, the values of z s(i) become −∞ and
∞, respectively. When σ depends on covariates, the above expression needs to be adapted. For instance,
in the two-group comparison Expression (3.3) splits up in two parts, one with σ1 (first treatment) and
the other with σ2 (second treatment). For obvious reasons, we have called this the “CO approach” either
assuming equal variances or allowing unequal variances.
The maximum likelihood estimates for this model can easily be obtained using standard numerical
optimization procedures such as the Broyden, Fletcher, Goldfarb, and Shanno (BFGS) algorithm (Lange,
The logistic transform for bounded outcome scores 77

3.3 Ordinal regression modeling versus CO approach

An interesting feature of the CO model is its resemblance to ordinal regression models. Bounded outcomes
Yi could also be regarded as ordinal response variables taking values in {0, 1, . . . , m}, where i = 1, . . . , n.
The OP regression model (McCullagh, 1980) specifies that the following equation should hold:

P(Yi  j) = (θ j − xiT γ ) (i = 1, . . . , n; j = 0, . . . , m), (3.4)

where −∞ < θ0  θ1  · · ·  θ(m−1) < ∞ are unknown ordered cut points that need to be estimated
from the data.
Suppose that, after standardization to the [0, 1] interval, Yi satisfies the CO model of Section 3.2 and
σ does not depend on covariates. Then (3.2) and (3.3) imply that

Downloaded from by guest on February 7, 2011

z ( j+1) − xiT β
P(Yi  a j ) =  (i = 1, . . . , n; j = 0, . . . , m), (3.5)

with z j = logit(a j ). Consequently, with θ j ≡ z j /σ and γ ≡ β /σ , the CO model equates to a classical

OP regression model. However, in the CO model the cut points are known up to a translation and scale
factor, whereas in the OP regression model they need to be estimated under constraints. Since maximum
likelihood estimators are consistent, θ̂ j ≈ z j /σ̂ for large n so that in this case the two approaches will
give similar parameter estimates, up to a proportionality factor. One might expect the CO approach to be
more efficient, since only two parameters need to be estimated, rather than m + 1 cut points. We give some
numerical results in Section 4.
When σ depends on covariates, e.g. when σ1 = σ2 for the two treatment groups, the CO model as
specified by Expression (3.3) will give biased parameter estimates and thus also a biased estimate of
the treatment effect. The same is also true for OP regression. In fact, for a binary Yi the true treatment
effect is equal to β1 /σ2 , where β1 is the regression coefficient of the binary treatment indicator (0 for
control and 1 otherwise). On the other hand, the estimate from the OP regression model will converge to
(z 1 /σ1 −z 2 /σ2 )+β1 /σ2 , where z 1 = logit(a1 ) when no covariate adjustment is involved. When covariates
are involved their regression coefficients will also be distorted. In Section 3.2, we have seen that we can
adapt the CO approach quite easily to allow for unequal variances. The OP regression model can also be
extended to accommodate this more general case, as has been done by Johnson and Albert (1999). Their
generalization is quite similar to the CO model with a variance depending on covariates, but cannot be
fitted using standard software.
When the cut points differ between individuals, as in Heitjan and Rubin (1991) and Heitjan (1993),
Expression (3.3) can also be extended easily. The corresponding generalization of the OP regression model
again leads to the approach of Johnson and Albert (1999).
Finally, when the bounded outcome score is a proportion, we have suggested to fit the data using the
BLN model. Clearly, in this case the OP regression model is not equivalent to our approach because it
does not take into account the variability with which the proportions ri /Ni are determined.

In this section, we describe a simulation study that we have performed to evaluate our proposals in Sections
3.1 and 3.2 for analyzing bounded outcome scores on [0, 1] in the two-group situation and under the
location-shift alternative on the transformed scale. For more details, we refer to supplementary material
available at Biostatistics online (

4.1 Set up of the simulation study

We have divided the simulation study according to the type of the bounded outcome score on [0, 1]. For
a proportion, we have compared the Wilcoxon test and the BLN approach, and in some cases also the OP
regression model, despite it being not strictly appropriate for proportions. For coarsened data, we have
compared the Wilcoxon test, the OP regression model, and the CO approach. A variety of scenarios were
considered, all involving two-group comparisons.
One of the main purposes of the simulation study is to show that including covariates can greatly
increase the power in detecting a treatment effect when dealing with bounded outcome scores. Therefore,
we considered cases with and without covariates. Further, we included a variety of distributions on [0, 1].
Three different treatment effects were evaluated, which could be classified as low, moderate, and large.
Finally, we also varied the study size, but in all cases specified n 1 = n 2 .

Downloaded from by guest on February 7, 2011

For a proportion, we compared the probability of the type I error and the power of the three approaches.
For coarsened data, we additionally determined the estimated treatment effect, except of course for the
Wilcoxon test.
For coarsened data on [0, 1], we considered both the case of equal variances (σ1 = σ2 ) and unequal
variances (σ1 = σ2 ), specifically σ1 = 2σ2 and σ2 = 2σ1 . Consequently, we included two versions of the
CO approach: (a) assuming equal variances (CO1 approach) and (b) allowing for unequal variances (CO2
approach). While OP regression is a popular approach in this setting, the possibility of unequal variances
is often neglected. Therefore, we have included the additional case of unequal variances for coarsened
data to highlight the impact of ignoring inequality of variances. On the other hand, for proportions the
BLN approach is actually the only appropriate method, and can also be easily extended to the case of
unequal variances. Thus, in this case extensive empirical comparison with OP regression is unnecessary.
To determine the performance of the different approaches, we used the following software—(a)
Wilcoxon test: the R-function wilcox.test(), (b) OP regression: R-function polr() from package MASS,
(c) BLN approach: generalized mixed-effects model (SAS proc NLMIXED and R-function lmer() from
package lme4), and (d): CO approach: R-function grouped() from package grouped written by the authors
(available from CRAN

4.2 Simulation results and discussion

Proportions on [0, 1]. When no covariates are involved, the performance of the Wilcoxon test is nearly
identical to that of the BLN model. The Pr(type I error) is close to 0.05 for all cases even for a sample size
of n 1 = n 2 = 20. Further, we observed the expected positive association of the power with the sample
size and the effect size /σ . However, the power also seems to depend on the shape of the distribution.
In particular, we observed that the U -shaped distribution yields in general a higher power, followed by
the unimodal and the J -shaped distributions. An explanation of this phenomenon lies in the fact that the
latent score Ui (true probability of success) is not known but only the observed proportion yi . When all
true proportions are relatively close to 0 or 1, the observed proportions will be relatively close to each
other. A proof of this is seen in the power of the Wilcoxon test which shows a similar behavior.
When a significant baseline covariate is included, the Wilcoxon test had a much lower power than the
covariate adjusted parametric models, and mainly as the effect of the covariate and σ increases. Finally,
the BLN and OP models behaved similarly with a slight inferiority for the latter.

Coarsened data on [0, 1]. First we summarize the results when there are no covariates. When σ1 = σ2 ,
the type I error was well preserved for all approaches. Further, overall the power of the CO2-approach
was less than for the other approaches, which is natural because the other approaches are developed under
the assumption of equal variances. In all cases, the treatment effect was estimated without bias. When
σ1 = σ2 , the type I error was well preserved for the CO2-approach, but was sometimes severely increased
The logistic transform for bounded outcome scores 79

for the other approaches. For the CO1- and the OP regression models, the reason is that the treatment
effect is sometimes estimated with a large bias. The anti-conservative character of the Wilcoxon test is
explained by its relationship with ordinal logistic regression (McCullagh, 1980). The power of the CO2-
approach was sometimes much less than for the other approaches, but this can be explained by their anti-
conservative character. Indeed, the power of the other approaches was even higher than the corresponding
power obtained from the Welch test, i.e. when no CO is involved.
When covariates are available, the first and obvious conclusion is that the power can be greatly im-
proved depending on the relationship of the covariates with the response. Apart from that, the conclusions
are similar to those reported.

Discussion. We expected the BLN approach, and especially the CO approach, to be more powerful than
OP regression since the latter requires more parameters to be estimated. However, the simulation results

Downloaded from by guest on February 7, 2011

showed only small differences. We attribute this to the low correlation of all estimated cut points (except
for θ0 ) with the estimated regression parameters in the OP regression model.
When the variances are unequal in the treatment groups, our simulations indicated that the Wilcoxon
test, the CO1 approach, and classical OP regression yield seriously distorted type I errors. The two latter
approaches also produced severely biased treatment effects, even with n 1 = n 2 . In Wetherill (1960), the-
oretical calculations revealed that the type I error and the power of the Wilcoxon test are fairly insensitive
to unequal variances provided n 1 = n 2 . However, we observed that when the data are coarsened the per-
formance of the Wilcoxon test is severely affected even when the sample sizes are equal, probably due
to the large number of ties. The sensitivity of the CO1 approach and classical OP regression is explained
by the fact that for non-linear models misspecification of the (co)variance structure has an impact on the
correct estimation of the mean parameters (see, e.g. Butler and Louis, 1992).

5.1 A compliance-enhancing intervention study: THAMES study
Recently, an open-label, multicenter compliance-enhancing intervention (THAMES) study was completed
in Belgium to measure the effect of a program of pharmaceutical care, designed to enhance adherence to
atorvastatin treatment. Four well-defined districts were identified, two in Flanders (northern Belgium)
and two in Wallonia (southern Belgium). In both Flanders and Wallonia, all pharmacists in one of the
districts were to apply measures to improve compliance and enhance persistence, whereas in the second
district no such measures were taken. There were 187 patients in the intervention group and 182 patients
in the control group. All pharmacists were equipped with the Medication Electronic Monitoring System
(MEMS) system, an electronically monitored pharmaceutical package designed to compile the dosing
histories of ambulatory patients taking oral medications (Urquhart, 1997). The total study duration was
12 months. The number of visits to the pharmacy ranged from 5 to 13. At each visit, the patient’s dosing
history was checked by means of the electronic monitoring system. The period between the first and
second visit was considered to be the baseline period. More details on the setup of this intervention study
can be found in Vrijens and others (2006).
The primary efficacy parameter of the THAMES study was adherence to prescribed therapy in the
post-baseline period, whereby adherence was defined for each patient as the proportion of days during
which the MEMS record showed that the patient had opened the pill container correctly. This variable
was also estimated at baseline (baseline adherence). Finally, for the calculation of the “post-baseline
adherence” the post-baseline period was arbitrarily cut off at day 300.

Baseline covariates. The THAMES study could not be randomized due to practical difficulties. There-
fore, we need to compare the baseline covariates of the intervention and control groups. In Table 1, we

Table 1. THAMES study: comparison of baseline covariates for difference in the two groups. For
categorical variables frequencies (percentages) and for continuous variables the mean are reported

Variable Levels Intervention Control p-value

Total number — 187 182 —
Adherence — 0.93 0.90 0.011
Gender Males 102(55%) 85(45%) 0.161
Age — 62 60 0.231
Weight — 77 78 0.735
Work Unemployed 46(25%) 64(35%) 0.029
Cardiovascular risk — 12.74 10.52 0.013
Family history No 145(78%) 142(78%) 0.911

Downloaded from by guest on February 7, 2011

compared gender, age, weight, work status (unemployed versus employed), a cardiovascular risk score
(Vrijens and others, 2006), family history of CHD, and the pdays at baseline with the appropriate statisti-
cal techniques. The adherence at baseline is of particular interest and the Wilcoxon test gives a significant
result ( p = 0.011). The reasons for this significant difference at the start are not clear, but it requires that
the imbalance at the start needs to be taken into account. We were aware of the potential dangers of correct-
ing for baseline covariates in the presence of imbalance at baseline (Wainer and Brown, 2004). However,
for illustrative purposes we still performed an analysis of covariance type of analysis in Section 5.2.

Efficacy comparison. Initially, we checked for a treatment effect without correcting for any baseline
covariates. Both the Wilcoxon test and the BLN model gave a significant intervention effect with p <
0.001. Figure 3 shows histograms for the two treatment groups with superimposed kernel estimates and
fitted LN distributions. The LN distributions provide a good fit to the observed data. Since  ˆ = 1.054,
and σ̂ = 1.848, the estimated effect size /σ̂ is equal to 0.57 with 95% CI = (0.36, 0.79), supporting the
intervention effect. The same conclusion can be drawn from P̂ = 0.66 with 95% CI (0.60, 0.71).
We then re-analyzed the data taking into account baseline covariates, including the logit of baseline
adherence. Table 2 shows the results for the BLN model. The effect of intervention and baseline adherence
are both highly significant ( p < 0.001). The estimated value of  decreased from 1.054 to 0.818 after
taking into account the imbalance at baseline. Further, the estimated value of σ decreased from 1.848 to
1.433 because the inclusion of covariates decreased the residual variability. As a result, the intervention
effect remained at / ˆ σ̂ = 0.57 with 95% CI (0.35, 0.79) and P̂ = 0.66 with 95% CI (0.60, 0.72). An
additional analysis, allowing for unequal variances for the latent adherence score, resulted in practically
identical parameter estimates and almost equal variances.
Thus, we can conclude that the intervention significantly improves the adherence of the patients de-
spite the fact that the two groups differed in adherence already at baseline. Finally, we did not fit an OP
regression model, for reasons stated above.

5.2 A stroke trial: ECASS-1 study

The ECASS-1 stroke study is a double-blind randomized parallel study designed to compare the effect
of alteplase (a thrombolytic drug) and placebo in patients with an acute ischemic stroke. In total, 545
patients were randomly allocated to the alteplase arm (268 patients) and to the control arm (277 patients).
The primary outcome is patient status at 3 months assessed by the Barthel index standardized such that
the values lie in [0, 1]. The score could be considered as a reflection of a latent scale which measures the
ability to cope with a handicap resulting from, say, a cerebrovascular stroke. In this way, it is plausible that
The logistic transform for bounded outcome scores 81

Downloaded from by guest on February 7, 2011

Fig. 3. THAMES study: proportion of correct dosing days.

Table 2. THAMES study: parameter estimates, standard errors, and p-values for the BLN model for the
compliance data

Variable Estimate Standard error p-value

Intercept 0.545 0.249 0.029
Baseline 0.648 0.051 <0.001
Intervention 0.818 0.161 <0.001
Gender −0.171 0.199 0.391
Age 0.009 0.011 0.403
Weight 0.005 0.006 0.429
Work −0.240 0.233 0.302
Cardiovascular risk −0.021 0.012 0.064
History −0.444 0.191 0.021
σ 1.433 0.062

the latent score for most if not all patients is less than 1. This is medically supported since an observed
score of 1 does not necessarily imply complete neurologic recovery of the patient. Also, patients who
survived a stroke with an observed score of zero may have a true latent score close to, rather than equal to,
zero, whereas non-survivors can be considered as having a true score of zero. One way to treat “death” in
the analysis is to regard it as a separate class and hence to distinguish it from the zero values of survivors.

Table 3. ECASS-1 study: parameter estimates, standard errors, and p-values for the CO2-approach
model for the Barthel index

Variable Estimate Standard error p-value

Intercept 2.099 0.311 <0.001
Treatment 0.992 0.486 0.042
Gender −0.121 0.450 0.79
Age −0.126 0.020 <0.001
σ1 4.045 0.267
σ2 5.577 0.444

However, in a clinical trial context this approach does not give a clear picture of the overall effect of

Downloaded from by guest on February 7, 2011

the treatment. For this reason, we prefer to analyze the Barthel index using the approach outlined in
Section 3.2.
In accordance with Lesaffre and others (1993), we first performed a Wilcoxon test. This gives a non-
significant treatment effect ( p = 0.104). Observe that this analysis addresses the more practical question
of how beneficial the thrombolytic treatment is overall, combining ability with mortality.
To apply the CO model, we assumed for the Barthel index the CO mechanism outlined in Section
3.2, with m = 20. Without baseline covariates the CO model assuming equal variances gives  ˆ = 0.51
and σ̂ = 4.96 yielding a small, non-significant effect size, namely 0.10 (95% CI = (−0.08, 0.28)). The
estimated relative effect is also close to 0.50, i.e. P̂ = 0.53 with 95% CI of (0.48, 0.58). However, there
is strong evidence that the two variances are unequal. A likelihood ratio test comparing the CO1 with the
CO2 model is highly significant ( p = 0.0015). The two variances are estimated as σ̂1 = 4.26 (control)
and σ̂2 = 5.91 (alteplase). The treatment effect now becomes  ˆ = 0.99, with 95% CI = (−0.01, 2.00),
p = 0.053. We again observe that histograms for the two treatment groups (figure not shown) are well
fitted by LN distributions now assuming unequal variances.
In a second step the baseline covariates gender and age are introduced into the model. Again, there is
evidence for unequal variances. The p-value for the likelihood ratio test is now 0.0017. Table 3 presents
the results of the CO2 approach. The two standard deviations are now estimated as σ̂1 = 4.04 (control)
and σ̂2 = 5.58 (alteplase). However, while the estimate of  remained at 0.99, including the covariates
resulted in a significant treatment effect ( p = 0.042). We do not wish to overemphasize the significant
result of the treatment effect. There does seem to be some effect of alteplase on average, but treating acute
stroke patients with alteplase may also give more variable outcomes, either very bad (completely disabled
or died) or very good (completely independent of others). The estimated relative effect now becomes
P̂ = 0.57 with 95% CI of (0.53, 0.61).
Finally, we also performed an OP regression. Nineteen cut points needed to be estimated. With the
same covariates, the estimated treatment effect is equal to 0.13 with 95% CI of (−0.05, 0.32) and p-value
equal to 0.16. Hence, the results of the OP regression model and the CO1 approach are quite close, but
they differ considerably from the CO2 approach.

In this section, we will consider only the case of equal variances. When the logistic transformation yields
a logistic distribution on the z-scale, then the effect size /σ can be interpreted as a log-odds ratio for the
cumulative distributions on the z-scale, i.e.
 F0 (z)/(1 − F0 (z))
= log , (6.1)
σ F (z)/(1 − F (z))
The logistic transform for bounded outcome scores 83

where F0 (z) and F (z) are the cumulative logistic distributions under H0 and Ha , respectively. Thus,
a generalization of the proportional odds model to continuous data is obtained. Further, a more robust
approach would be to use the logistic t-distribution instead of the LN (Lange and others, 1989). Of course,
for scores on (0, 1) a part of the attractiveness of the approach is lost because we would need to replace
classical techniques, like the t-test, by more sophisticated ones.
Another extension to the LN distribution is obtained by changing the logistic transformation. Aitchi-
son and Lauder (1985) suggested a Box-Cox transformation. For the analysis of clinical trial data, we
suspect that this extra flexibility has little to offer. Trigonometric functions like arctan (suitably scaled to
[0, 1]) provide another class of transformations to normality. Dexter and Chestnut (1995) experimented
with the arc sine square root transformation for the analysis of VAS pain data. This is an interesting
transformation since it attains its boundary values. Finally, one referee pointed out that OP regression
allows the possibility that an arbitrary transformation of the underlying distribution is normally dis-

Downloaded from by guest on February 7, 2011

A rather different approach has been suggested in Quality of Life Research (Grootendorst, 2000). In
this approach a classical distribution, such as the normal distribution, is assumed to be censored at the
boundaries 0 and 1 on the original scale.

The logistic transform is one of the most used transformations in statistics. Hence, we do not claim orig-
inality when proposing the BLN and CO approaches. However, we argue that the strategy to analyze
bounded outcome scores as laid down in this paper has some advantages over other well-established
approaches, like OP and logistic regression. First, our strategy makes the distinction between the two
types of bounded outcome scores. Second, we believe that explicitly drawing the relationship with a
latent normal variable on the transformed scale will help practitioners in planning a clinical trial even
when they decide to use an ordinal regression model for the analysis. Third, our approach is quite flex-
ible. The extension to unequal variances could be quite important in practice. Other extensions, like
allowing for a varying grid of cut points, are also easy to do. Finally, we have developed an ap-
proach to perform sample size calculation based on the CO approach, see Tsonaka and others (2005).
Given that the power of the OP regression model is close to that of the CO approach in the case of
equal variances, we believe that this approach is also useful for sample size calculations for ordinal re-
With respect to further research, we believe that models for repeated bounded outcome scores either
using a multivariate approach as suggested by Aitchison and Shen (1980) or incorporating random effects
could be useful. In this context, it would also be useful to draw the connection with random-effects OP
regression. Further, it is of interest to develop an approach which can handle a bounded outcome score as
a covariate in a regression model. Recently, Liang and others (2005) have published a related paper that
deals with a bounded covariate. Finally, we intend to explore various procedures to analyze VAS data,
again allowing the variance to depend on covariates.

The authors acknowledge support from the Interuniversity Attraction Poles Program P5/24—Belgian
State—Federal Office for Scientific, Technical, and Cultural Affairs. The authors also thank Pfizer
Belgium for the permission to use the data of the THAMES study and Boehringer Ingelheim for the
permission to use the ECASS-1 data. Finally, the authors also acknowledge the comments of a referee,
the associate editor, and the editor which improved the readability of the paper considerably. Conflict of
Interest: None declared.

A ITCHISON , J. AND B EGG , C. (1976). Statistical diagnosis when cases are not classified with certainty. Biometrika
63, 1–12.
A ITCHISON , J. AND L AUDER , I. J. (1985). Kernel density estimation for compositional data. Applied Statistics 34,
A ITCHISON , J. AND S HEN , S. (1980). Logistic-normal distributions: some properties and uses. Biometrika 67,
B RUNNER , E. AND M UNZEL , U. (2000). The non-parametric Behrens–Fisher problem: asymptotic theory and small-
sample approximation. Biometrical Journal 42, 17–25.
B UTLER , B. AND L OUIS , T. (1992). Random effects models with non-parametric priors. Statistics in Medicine 11,

Downloaded from by guest on February 7, 2011

C ARROLL , R., RUPPERT, D. AND S TEFANSKI , L. (1995). Nonlinear Measurement Error Models. Monographs on
Statistics and Applied Probability, Volume 63. New York: Chapman and Hall.
D EXTER , F. AND C HESTNUT, D. (1995). Analysis of statistical tests to compare visual analog scale measurements
among groups. Anesthesiology 82, 896–902.
G ROOTENDORST, P. (2000). Censoring in statistical models of health status: what happens when one can do better
than ’1’. Quality of Life Research 9, 911–4.
H EITJAN , D. (1993). Ignorability and coarse data: some biomedical examples. Biometrics 49, 1099–109.
H EITJAN , D. AND RUBIN , D. (1991). Ignorability and coarse data. Annals of Statistics 19, 2244–53.
J OHNSON , N. (1949). Systems of frequency curves generated by methods of translation. Biometrika 36, 149–76.
J OHNSON , S. AND A LBERT, J. (1999). Ordinal Data Modelling. New York: Springer. pp 161–3.
K IESCHNICK , R. AND M C C ULLOUGH , B. (2003). Regression analysis of variates observed on (0,1): percentages,
proportions and fractions. Statistical Modelling 3, 193–213.
L ANGE , K. (2004). Optimization. New York: Springer.
L ANGE , K., L ITTLE , R. AND TAYLOR , J. (1989). Robust statistical modeling using the t distribution. Journal of the
American Statistical Association 84, 881–96.
L EHMANN , E. L. AND D’A BRERA , H. J. M. (1998). Nonparametrics: Statistical Methods Based on Ranks. Upper
Saddle River, NJ: Prentice Hall.
L ESAFFRE , E., S CHEYS , I., F R ÖHLICH , J. AND B LUHMKI , E. (1993). Calculation of power and sample size with
bounded outcome scores. Statistics in Medicine 12, 1063–78.
L IANG , L., S HAO , J. AND PALTA , M. (2005). A longitudinal measurement error model with a semi-continuous
covariate. Biometrics 61, 824–30.
M AHONEY, F. AND BARTHEL , D. (1965). Functional evaluation: the Barthel index. Maryland State Medical Journal
14, 56–61.
M C C ULLAGH , P. (1980). Regression models for ordinal data. Journal of the Royal Statistical Society, Series B 42,
M URPHY, B. (1967). Some two-sample tests when the variances are unequal: a simulation study. Biometrika 54,
P OURAHMADI , M. (1999). Joint mean-covariance models with applications to longitudinal data: unconstrained
parametrisation. Biometrika 86, 677–90.
R D EVELOPMENT C ORE T EAM (2005). R: A Language and Environment for Statistical Computing. Vienna, Austria:
R Foundation for Statistical Computing.
The logistic transform for bounded outcome scores 85

T SONAKA , R., R IZOPOULOS , D. AND L ESAFFRE , E. (2005). Power and sample size calculations for discrete
bounded outcome scores (submitted).
U RQUHART, J. (1997). The electronic medication event monitor: lessons for pharmacotherapy. Clinical Pharmacoki-
netics 32, 345–56.
V RIJENS , B., B ELMANS , A., M ATTHYS , K., K LERK , E. D. AND L ESAFFRE , E. (2006). Effect of intervention
through a pharmaceutical care program on patient adherence with prescribed once-daily atorvastatin. Pharma-
coepidemiology and Drug Safety, 15, 115–121.
WAINER , H. AND B ROWN , L. (2004). Two statistical paradoxes in the interpretation of group differences: illustrated
with medical school admission and licensing data. American Statistician 58, 117–23.
W ELCH , B. (1951). On the comparison of several mean values. Biometrika 38, 330–6.

Downloaded from by guest on February 7, 2011

W ETHERILL , G. (1960). The Wilcoxon test and non-null hypotheses. Journal of the Royal Statistical Society 22,

[Received September 30, 2004; first revision June 8, 2005; second revision January 17, 2006;
third revision February 17, 2006; fourth revision March 16, 2006 ]