See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/309893046

Biostatistics Series Module 6: Correlation and Linear Regression

Article  in  Indian Journal of Dermatology · November 2016

DOI: 10.4103/0019-5154.193662

CITATIONS READS
49 7,446

2 authors:

Avijit Hazra Nithya J Gogtay

Institute of Post-Graduate Medical Education and Research and Seth Sukhlal Karnan… KEM Hospital
180 PUBLICATIONS   2,514 CITATIONS    265 PUBLICATIONS   3,180 CITATIONS   

SEE PROFILE SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Biostatistics series in Indian Journal of Dermatology View project

Controlled release mebeverine in diarrhoea predominant irritable bowel syndrome View project

All content following this page was uploaded by Avijit Hazra on 21 November 2016.

The user has requested enhancement of the downloaded file.

 IJD® MODULE ON BIOSTATISTICS AND RESEARCH METHODOLOGY FOR THE DERMATOLOGIST
MODULE EDITOR: SAUMYA PANDA

Biostatistics Series Module 6: Correlation and Linear Regression

Avijit Hazra, Nithya Gogtay1

Abstract From the Department of

Correlation and linear regression are the most commonly used techniques for quantifying the Pharmacology, Institute of
association between two numeric variables. Correlation quantifies the strength of the linear Postgraduate Medical Education
and Research, Kolkata,
relationship between paired variables, expressing this as a correlation coefficient. If both
West Bengal, 1Department of
variables x and y are normally distributed, we calculate Pearson’s correlation coefficient (r). Clinical Pharmacology, Seth GS
If normality assumption is not met for one or both variables in a correlation analysis, a Medical College and KEM Hospital,
rank correlation coefficient, such as Spearman’s rho (ρ) may be calculated. A hypothesis Mumbai, Maharashtra, India
test of correlation tests whether the linear relationship between the two variables holds in
the underlying population, in which case it returns a P < 0.05. A 95% confidence interval
of the correlation coefficient can also be calculated for an idea of the correlation in the Address for correspondence:
Dr. Avijit Hazra,
population. The value r2 denotes the proportion of the variability of the dependent variable
Department of Pharmacology,
y that can be attributed to its linear relation with the independent variable x and is called Institute of Postgraduate Medical
the coefficient of determination. Linear regression is a technique that attempts to link Education and Research,
two correlated variables x and y in the form of a mathematical equation (y = a + bx), such 244B Acharya J. C. Bose Road,
that given the value of one variable the other may be predicted. In general, the method Kolkata ‑ 700 020,
of least squares is applied to obtain the equation of the regression line. Correlation and West Bengal, India.
linear regression analysis are based on certain assumptions pertaining to the data sets. If E‑mail: blowfans@yahoo.co.in
these assumptions are not met, misleading conclusions may be drawn. The first assumption
is that of linear relationship between the two variables. A scatter plot is essential before
embarking on any correlation‑regression analysis to show that this is indeed the case. Outliers
or clustering within data sets can distort the correlation coefficient value. Finally, it is vital
to remember that though strong correlation can be a pointer toward causation, the two are
not synonymous.

Key Words: Bland–Altman plot, correlation, correlation coefficient, intraclass correlation

coefficient, method of least squares, Pearson’s r, point biserial correlation coefficient,
Spearman’s rho, regression

Introduction The Scatter Plot

The word correlation is used in day‑to‑day life to denote
some form of association. In statistics, correlation
analysis quantifies the strength of the association
between two numerical variables. If the association is
“strong” then an attempt may be made mathematically
to develop a predictive relationship between the two
variables so that given the value of one, the value of
the other may be predicted from it and vice versa.
Defining this mathematical relationship as an equation
is the essence of regression analysis. Correlation and
regression analysis are therefore like two sides of the
same coin.
Access this article online
Quick Response Code:
Website: www.e‑ijd.org
When exploring the relationship between two numerical
variables, the first and essential step is to graphically
depict the relationship on a scatter plot or scatter
diagram or scattergram. This is simply a bivariate plot
of one variable against the other. Before plotting, one
or both variables may be logarithmically transformed to
obtain a more normal distribution.
On a scatter diagram, it is customary to plot the
independent variable on the X‑axis and the dependent
This is an open access article distributed under the terms of the Creative
Commons Attribution‑NonCommercial‑ShareAlike 3.0 License, which allows
others to remix, tweak, and build upon the work non‑commercially, as long as
the author is credited and the new creations are licensed under the identical
terms.
For reprints contact: reprints@medknow.com

How to cite this article: Hazra A, Gogtay N. Biostatistics series module 6:

DOI: 10.4103/0019-5154.193662 Correlation and linear regression. Indian J Dermatol 2016;61:593-601.
Received: October, 2016. Accepted: October, 2016.

© 2016 Indian Journal of Dermatology | Published by Wolters Kluwer - Medknow 593

 Hazra and Gogtay: Correlation and regression
variable on the Y‑axis. However, “independent” and
“dependent” distinction can be puzzling at times. For
instance, if we are exploring the relationship between
age and stature in children, it is reasonable to assume
that age is the “independent” variable on which the
height depends. So customarily, we will plot age on
the X‑axis and height on the Y‑axis. However, if we are
exploring the relationship between serum potassium
and venous plasma glucose levels, which variable do
we treat as the “dependent” variable? In such cases, it
usually does not matter which variable is attributed to
a particular axis of the scatter diagram. If our intention
is to draw inferences about one variable (the outcome
or response variable) from the other (the predictor or
explanatory variable), the observations from which the
inferences are to be made are usually placed on the
horizontal axis.
Once plotted, the closer the points lie to a straight
line; the stronger is the linear relationship between two
variables. Examine the two scatter plots presented in
Figure 1. In Figure 1a, the individual dots representing
the paired xy values are obviously, closely approximating
a straight line and the value of y increases as the value
of x increases. This type of relationship is referred to as
direct linear relationship. In Figure 1b, the dots are also
approximating a straight line, though not so closely, as
in Figure 1a. Moreover, the value of y is declining as
that of x is increasing. This type of relationship is an
inverse or reciprocal linear relationship.
Now inspect the scatter plot shown in Figure 2. In this
instance, there also is a strong relation between the dose
of the drug and the response – the response is low to
begin with, rises steadily in the subsequent portion of
the dose range, but then tends to decline with further
increase in dose. It is clear that although the relationship
is strong it cannot be approximated by a single straight
line but can be described by an appropriate curved line.
The association, in this case, is curvilinear rather than
linear. We are going to discuss correlation and regression
assuming linear relationship between the variables in
question. Although many biological phenomena will show
nonlinear relationships, the mathematics of these are
more complex and beyond the scope of this module.
a b
Figure 1: Scatter diagram depicting direct and inverse linear relationships
Indian Journal of Dermatology 2016; 61(6)
The Correlation Coefficient
To quantify the strength of the relationship between
two variables shown to have a linear relationship on the
scatter plot, we calculate the correlation coefficient. The
coefficient takes values only between −1 and +1, with
the numerical magnitude depicting the strength of the
relationship, and the sign indicating its direction. Thus,
the sign accompanying a correlation coefficient is not
a +or −sign in the arithmetic sense. Rather the plus sign
denotes a direct relationship, whereas minus denotes an
inverse relationship.
If both variables x and y are normally distributed,
we calculate Pearson’s product moment correlation
coefficient r or Pearson’s correlation coefficient r, or
simply r (after Karl Pearson). It is calculated as the
covariance of the two variables divided by the product of
their standard deviations (SDs), and the term “product
moment” in the name derives from the mathematical
nature of the relationship.
A value of r close to +1 indicates a strong direct linear
relationship (i.e., one variable increases with the other;
as in Figure 3a). A value close to −1 indicates a strong
inverse linear relationship (i.e., one variable decreases
as the other increases; Figure 3b). A value close to
0 indicates a random scatter of the values [Figure 3c];
alternatively, there could be a nonlinear relationship
between the variables [Figure 3d]. The scatter plot
is indispensable in checking the assumption of a
linear relationship and it is meaningless to calculate a
correlation coefficient without such a relation between
the two variables. In between the state of “no correlation
at all” (r = 0) and “perfect correlation” (r = 1), interim
values of the correlation coefficient are interpreted
by convention. Thus, values >0.7 may be regarded as
“strong” correlation, values between 0.50 and 0.70 may
be interpreted as “good” correlation, between 0.3 and
0.5 may be treated as “fair” or “moderate” correlation,
and any value <0.30 would be poor correlation.
However, we must remember that the interpretation of
Figure 2: Scatter diagram depicting a curvilinear relationship
594
 Hazra and Gogtay: Correlation and regression
a b
c d
Figure 3: Scatter diagram depicting relationship patterns between two variables
a correlation coefficient depends on the context and
purposes. A correlation of 0.85 may be very low if one is
verifying a physical law using high‑quality instruments
or trying to derive the standard curve for a quantitative
assay but may be regarded as very high in the clinical
context.
Note that the correlation coefficient has no units and
is, therefore, a dimensionless statistic. The position of
x and y can be interchanged on a scatter plot without
affecting the value of r.
If one or both variables in a correlation analysis is/are
not normally distributed a rank correlation coefficient
that depends on the rank order of the values rather
than the actual observed values can be calculated.
Examples include Spearman’s rho (ρ) (after Charles
Edward Spearman) and Kendall’s tau (τ) (after Maurice
George Kendall) statistics. In essence Spearman’s rank
correlation coefficient rho, which is the more frequently
used nonparametric correlation, is simply Pearson’s
product moment correlation coefficient calculated for
the rank values of x and y rather than their actual
values. It is also appropriate to use ρ rather than r
when at least one variable is measured on an ordinal
scale or when the sample size is small (say n  ≤10); ρ
is also less sensitive to deviations from linear relation
than r.
Although less often used, Kendall’s tau is another
nonparametric correlation offered by many statistical
packages. Some statisticians recommend that it should
be used, rather than Spearman’s coefficient, when the
data set is small with the possibility of a large number
of tied ranks. This means that if we rank all of the
scores and many scores have the same rank, Kendall’s
tau should be used. It is also considered to be a more
accurate gauge of the correlation in the underlying
population.
595
Hypothesis Test of Correlation and Confidence
Interval for Correlation Coefficient
When we calculate the correlation coefficient for sample
data, we quantify the strength of the linear relationship
between two variables measured in the sample.
A high correlation coefficient value indicates a strong
correlation for the sample. However, what about the
relationship in the population as a whole from which
the sample has been drawn? A significance test, based
on the t distribution, addresses this question. It allows
us to test whether the association might have occurred
merely by chance or whether it is a true association.
This significance test is applied with the null hypothesis
that the population correlation coefficient equals 0. For
any given value of r and taking the sample size into
consideration, P values can be obtained from most
statistical packages. As usual, P < 0.05 indicates that
there is sufficient evidence to suggest that the true
(population) correlation coefficient is not 0 and that the
linear relationship between the two variables observed
in the sample also holds for the underlying population.
However, although the hypothesis test indicates whether
there is a linear relationship, it gives no indication
of the strength of that association. This additional
information can be obtained from the 95% confidence
interval (CI) for the population correlation coefficient.
Calculation of this CI requires r to be transformed to
give a normal distribution by making use of Fisher’s
z transformation. The width of the CI depends on the
sample size, and it is possible to calculate the sample
size required for a given level of accuracy.
Coefficient of Determination
When exploring linear relationship between numerical
variables, a part of the variation in one of the variables
can be thought of as being due to its relationship with
the other variable with the rest due to undetermined
(often random) causes. A coefficient of determination
can be calculated to denote the proportion of the
variability of y that can be attributed to its linear
relation with x. This is taken simply as r multiplied by
itself that is r2. It is also denoted as R2.
For any given value of r, the r2 will denote a value
that is closer to 0 and will be devoid of a sign. Thus, if
r is +0.7 or −0.7, r2 will be 0.49. We can interpret this
0.49 figures as that 49% of the variability in y is due to
variation of x. Values of r2 close to 1 imply that most of
the variability in y is explained by its linear relationship
with x. The value (1 −r2) has sometimes been referred to
as the coefficient of alienation.
In statistical modeling, the r2 statistics gives information
about the goodness of fit of a model. In regression, it
Indian Journal of Dermatology 2016; 61(6)
 Hazra and Gogtay: Correlation and regression
denotes how well the regression line approximates the
real data points. An r2 of 1 indicates that the regression
line perfectly fits the data. Note that values of r2 outside
the range 0–1 can occur where it is used to measure the
agreement between observed and modeled values, and
the modeled values are not obtained by linear regression.
Point Biserial and Biserial Correlation
The point biserial correlation is a special case of the
product‑moment correlation, in which one variable is
continuous, and the other variable is binary. The point
biserial correlation coefficient measures the association
between a binary variable x, taking values 0 or 1, and
a continuous numerical variable y. It is assumed that
for each value of x, the distribution of y is normal,
with different means but same variance. It is often
abbreviated as rPB.
The binary variable frequently has categories such as yes
or no, present or absent, success or failure, etc.
If the variable x is not naturally dichotomous but
is artificially dichotomized, we calculate the biserial
correlation coefficient rB instead of the point‑biserial
correlation coefficient.
Although not often used, an example where we
may apply the point biserial correlation coefficient
would be in cancer studies. How strong is the
association between administering the anticancer drug
(active drug vs. placebo) and the length of survival
after treatment? The value would be interpreted in the
same way as Pearson’s r. Thus, the value would range
from −1 to +1, where −1 indicates a perfect inverse
association, +1 indicates a perfect direct association, and
0 indicates no association at all. Take another example.
Suppose we want to calculate the correlation between
intelligence quotient and the score on a certain test, but
all the test scores are not available with us although we
know whether each subject passed or failed. We could
then use the biserial correlation.
The Phi Coefficient
The phi coefficient (also called the mean square
contingency coefficient) is a measure of association for
two binary variables. It is denoted as ϕ or rϕ.
Also introduced by Karl Pearson, this statistic is similar
to the Pearson’s correlation coefficient in its derivation.
In fact, a Pearson’s correlation coefficient estimated
for two binary variables will return the phi coefficient.
The interpretation of the phi coefficient requires
caution. It has a maximum value that is determined
by the distribution of the two variables. If both have a
50/50 split, values of phi will range from −1 to +1.
Application of the phi coefficient is particularly seen
in educational and psychological research, in which
Indian Journal of Dermatology 2016; 61(6)
the use of dichotomous variables is frequent. Suppose
we are interested in exploring whether in a group of
students opting for university courses, there is gender
preference for physical sciences or life sciences. Here,
we have two binary variables – gender (male or female)
and discipline (physical science or life science). We
can arrange the data as a 2 × 2 contingency table and
calculate the phi coefficient.
Simple Linear Regression
If two variables are highly correlated, it is then feasible
to predict the value of one (the dependent variable)
from the value of the other (the independent variable)
using regression techniques. In simple linear regression,
the value of one variable (x) is used to predict the
value of the other variable (y) by means of a simple
mathematical function, the linear regression equation,
which quantifies the straight‑line relationship between
the two variables. This straight line, or regression line,
is actually the “line of best fit” for the data points on
the scatter plot showing the relationship between the
variables in question.
The regression line has the general formula:
y = a + bx.
Where “a” and “b” are two constants denoting the
intercept of the line on the Y‑axis (y‑intercept) and the
gradient (slope) of the line, respectively. The other name
for b is the “regression coefficient.”
Physically, “b” represents the change in y, for every 1
unit change in x; while “a” represents the value that
y would take, if x is 0. Once the values of a and b
have been established, the expected value of y can be
predicted for any given value of x, and vice versa. Thus, a
model for predicting y from x is established. There may be
situations, in which a straight line passing through the
origin will be appropriate for the data, and in these cases,
the equation of the regression line simplifies to y = bx.
But how do we fit a straight line to a scattered set of
points which seem to be in linear relationship? If the
points are not all on a single straight line, we can, by
eye estimation, draw multiple lines that seem to fit the
series of data points on the scatter diagram. But which
is the line of best fit? This problem had mathematicians
stumped literally for centuries. The solution was in the
form of the method of least squares, which was first
published by the French mathematician Adrien‑Marie
Legendre in 1805 but used earlier by Carl Friedrich Gauss
in Germany in 1795 to calculate the orbit of celestial
bodies. Gauss developed the idea further and today is
known as the father of regression.
Look at Figure 4. When we have a scattered series of
dot which are lying approximately but not exactly
on a straight line, we can, by eye estimation, draw a
596
 Hazra and Gogtay: Correlation and regression
number of lines that seem to fit the series. But which
is the line of best fit? The method of least squares, in
essence, selects the line that would provide the least
sum of squares for the vertical residuals or offsets. In
Figure 4, it is line B as is shown in the lower panel. For
a particular value of x, the vertical distance between the
observed and fitted value of y is known as the residual
or offset. Since some of the residuals are above and
some below the line of best fit, we require a +or −sign
to mathematically denote the residuals. Squaring removes
the effect of the −sign. The method of least squares finds
the values of “a” and “b” that minimizes the sum of the
squares of all the residuals. The method of least squares
is not the only technique, but is regarded as the simplest
technique for linear regression, that is for the task of
finding the straight line of best fit for a series of points
depicting a linear relationship on a scatter diagram.
You may wonder why the statistical procedure of fitting a
line is called “regression” which in common usage means
“going backward.” Interestingly, the term was used
neither by Legendre or Gauss but is attributed to the
English scientist Francis Galton who had a keen interest
in heredity. In Victorian England, Galton measured the
heights of 202 fathers and their first born adult sons and
plotted them on a graph of median height versus height
group. The scatter for fathers and sons approximated to
two lines that intersected at a point representing the
average height of the adult English population. Studying
this plot, Galton made the very interesting observation
that tall fathers tend to have tall sons but they are not
as tall as their fathers, and short fathers tend to have
short sons but they are not as short as their fathers;
and in the course of just two or three generations the
height of individuals tended to go back or “regress” to
the mean population height. He published a famous
paper titled “Regression towards mediocrity in hereditary
stature.” This phenomenon of regression to the mean
can be observed in many biological variables. The term
Figure 4: The principle of the method of least squares for linear regression. The sum
of the squared “Residuals” is the least for the line of best fit
597
regression subsequently somehow got attached to the
procedure of line fitting itself.
Note that in our discussion above; we have discussed
the predictive relationship between two numerical
variables. This is simple linear regression. If the value
of y requires more than one numerical variable for a
reasonable prediction, we are encountering the situation
called multiple linear regression. We will be discussing
the basics of this in a future module.
Pitfalls in Correlation and Regression
Analysis
Correlation and linear regression analysis are based on
certain assumptions pertaining to the data sets. If these
assumptions are not met, conclusions drawn can be
misleading. Both assume that the relationship between
the two variables is linear. The observations have to be
independent – they are not independent if there is more
than one pair of observations (that is repeat measurements)
from one individual. For correlation, both variables should
be random variables although for regression, only the
response variable y needs to be random.
Inspecting a scatter plot is of utmost importance before
estimation of the correlation coefficient for many
reasons:
• A nonlinear relationship may exist between two
variables that would be inadequately described,
or possibly even undetected, by the correlation
coefficient. For instance, the correlation coefficient
if calculated for the set of data points in Figure 2,
would be almost zero, but we will be grossly wrong
if we conclude that there is no association between
the variables. The zero coefficient only tells us that
there is no linear (straight‑line) association between
the variables, when in reality there is a clear
curvilinear (curved‑line) association between them
• An outlier may create a false correlation. Inspect
the scatter plot in Figure 5a. The r value of 0.923
a b
c
Figure 5: Examples of misleading correlations
Indian Journal of Dermatology 2016; 61(6)
 Hazra and Gogtay: Correlation and regression
suggests a strong correlation. However, a closer look
makes it obvious that the series of dots is actually
quite scattered, and the apparent correlation is being
created by the outlier point. This kind of outlier is
called univariate outlier. If we consider the x value of
this point, it is way beyond the range of rest of the
x values; similarly, the y value of the point is much
beyond the range of y values for the rest of the
dots. An univariate outlier is easy to spot by simply
sorting the values or constructing boxplots
• Conversely, an outlier can also spoil a correlation.
The scatter plot in Figure 5b suggests only moderate
correlation at r value of 0.583, but closer inspection
reveals that a single bivariate outlier reduces what is
otherwise an almost perfect association between the
variables. Note that the deviant case is not an outlier
in the usual univariate sense. Individually, its x value
and y value are unexceptional. What is exceptional is
the combination of values on the two variables that
it exhibits, making it an outlier, and this would be
evident only on a scatter plot
• Clustering within datasets may also inflate a
correlation. Look at Figure 5c. Two clusters are
evident, and individually they do not appear to
show strong correlation. However, combining the two
suggests a decent correlation. This combination may
be undesirable in real life. Clustering within datasets
may be a pointer that the sampling has not really
been random.
When using a regression equation for prediction, errors
in prediction may not be just random but may also
be due to inadequacies in the model. In particular,
extrapolating beyond the range of observed data can be
risky and is best avoided. Consider the simple regression
equation:
Weight = a + b × height.
Suppose we give a height value of 0. The corresponding
weight value, strangely, is not 0 but equals a. What
is the matter here? Is the equation derived through
regression faulty? The fact is that the equation is not
at fault, but we are trying to extrapolate its use beyond
the range of values used in deriving the equation
through least squares regression. This is a common
pitfall. Equations derived from one sample should not
be automatically applied to another sample. Equations
derived from adults, for instance, should not be applied
to children.
Correlation is Not Causation
One of the common errors in interpreting the correlation
coefficient is failure to consider that there may be
a third variable related to both of the variables being
investigated, which is responsible for the apparent
correlation. Therefore, it is wrong to infer that there is
Indian Journal of Dermatology 2016; 61(6)
cause and effect relationship between two variables that
are correlated, even if the correlation is strong. In other
words, correlation does not imply causation.
As a now widely stated example, numerous
epidemiological studies showed that women taking
combined hormone replacement therapy (HRT) also
had a lower‑than‑average incidence of coronary heart
disease (CHD). The correlation was strong leading
researchers to propose that HRT was protective against
CHD. However, subsequent randomized controlled
trials showed that HRT causes a small but statistically
significant increase in the risk of CHD. Reanalysis of
the data from the epidemiological studies showed that
women undertaking HRT were more likely to be from
higher socioeconomic groups, with better‑than‑average
diet and exercise regimens. The use of HRT and
decreased the incidence of CHD were coincident effects
of a common cause (i.e., the benefits associated with a
higher socioeconomic status), rather than a direct cause
and effect, as had been supposed.
Correlation may simply be due to chance. For
example, one could compute r between the abdominal
circumference of subjects and their shoe sizes,
intelligence, or income. Irrespective of the value of r,
these associations would make no sense.
For any two correlated variables, A and B, the following
relationships are possible:
• A causes B or vice versa (direct causation)
• A causes C which causes B or the other way
round (indirect causation)
• A causes B and B causes A  (bidirectional or cyclic
causation)
• A and B are consequences of a common cause but do
not cause each other
• There is no causal connection between A and B; the
correlation is just coincidence.
Thus, causality ascertainment requires consideration of
several other factors, including temporal relationship,
dose‑effect relationship, effect of dechallenge and
rechallenge, and biological plausibility. Of course, a strong
correlation may be an initial pointer that a cause‑effect
relationship exists, but per se it is not sufficient to infer
causality. There must also be no reasonable alternative
explanation that challenges causality. Establishing
causality is one of the most daunting challenges in both
public health and drug research. Carefully controlled
studies are needed to address this question.
Assessing Agreement
In the past correlation has been used to assess
this degree of agreement between sets of paired
measurements. However, correlation quantifies the
relationship between numerical variables and has
limitations if used for assessing comparability between
598
 Hazra and Gogtay: Correlation and regression
methods. Two sets of measurements would be perfectly
correlated if the scatter diagram shows that they all lie
on a single straight line, but they are not likely to be
in perfect agreement unless this line passes through
the origin. It is very likely that two tests designed
to measure the same variable would return figures
that would be strongly correlated, but that does not
automatically mean that the repeat measurements are
also in strong agreement. Data which seem to be in
poor agreement can produce quite high correlations. In
addition, a change in scale of measurement does not
affect the correlation, but it can affect the agreement.
Bland–Altman Plot
Bland and Altman devised a simple but informative
graphical method of comparing repeat measurements.
When repeat measurements have been taken on a series
of subjects or samples, the difference between pairs of
measurements (Y‑axis) is plotted against the arithmetic
mean of the corresponding measurements (X‑axis).
The resulting scatter diagram such as figure is the
Bland–Altman plot (after John Martin Bland and
Douglas G. Altman, who first proposed it in 1983 and
then popularized it through a Lancet paper in 1986)
an example of which is given in Figure 6. The repeat
measurements could represent results of two different
assay methods or scores from the same subjects by two
different raters.
Computer software that draws a Bland–Altman plot
can usually add a ‘bias’ line parallel to the X‑axis.
This represents the difference between the means
of the two sets of measurements. Lines denoting
95% limits of agreement (mean difference ± 1.96 SD of
the difference) can be added on either side of the bias
line. Alternatively, lines denoting 95% confidence limits
of mean of differences can be drawn surrounding the
bias line.
Bland–Altman plots are generally interpreted informally.
Three things may be looked at:
Figure 6: Example of a Bland–Altman plot used to compare two test methods. The
bias line with the limits of agreement is provided
599
• How big is the average discrepancy between the
methods, which is indicated by the position of
the bias line. This discrepancy may be too large to
accept clinically. However, if the differences within
mean ± 1.96 SD are not clinically important, the two
methods may be used interchangeably
• Whether the scatter around the bias line is too much,
with a number of points falling outside the 95%
agreement limit lines
• Whether the difference between the methods tends
to get larger or smaller as the values increase. If it
does, as is indicated in Figure 7, it indicates the
existence of a proportional bias which means that
the methods do not agree equally through the range
of measurements.
The Bland–Altman plot may also be used to assess
the repeatability of a method by comparing repeated
measurements on a series of subjects or samples by
that single method. A coefficient of repeatability can
be calculated as 1.96 times the SD of the differences
between the paired measurements. Since the same
method is used for the repeated measurements, it is
expected that the mean difference should be zero. This
can be checked from the plot.
Intraclass Correlation Coefficient
Although originally introduced in genetics to judge
sibling correlations, the intraclass correlation coefficient
(ICC) statistic is now most often used to assess the
consistency, or conformity, of measurements made by
multiple observers measuring the same parameter or two
or more raters scoring the same set of subjects.
The methods of ICC calculation have evolved over time.
The earliest work on intraclass correlations focused on
paired measurements, and the first ICC statistics to be
proposed was modifications of the Pearson’s correlation
coefficient (which can be regarded interclass correlation)
calculations. Beginning with Ronald Fisher, the intraclass
Figure 7: Example of a Bland–Altman plot showing proportional bias. In this case,
the difference between the methods first tends to narrow down and then increase as
the value of measurements increase
Indian Journal of Dermatology 2016; 61(6)
 Hazra and Gogtay: Correlation and regression

correlation has been regarded within the framework of
analysis of variance and its calculation is now based on
the true (between subject) variance and variance of the
measurement error (during repeat measurement).
The ICC takes a value between 0 and 1. Complete
inter‑rater agreement is indicated by a value of 1 but
this is seldom achieved. Arbitrarily, the agreement
boundaries proposed are <0.40: Poor; 0.40–0.60: Fair;
0.60–0.74: Good, and >0.75: Strong. Software may report
two coefficients with their respective 95% CIs. ICC for
single measures is an index for the reliability of the
multiple ratings by a single typical rater. ICC for average
measures is an index for the reliability of different
raters averaged together. This ICC is always slightly
higher than the single measures ICC. Software may also
offer different models for ICC calculation. One model
assumes that all subjects were rated by the same raters.
A different model may be used when this precondition
is not true. The model may test for consistency when
systematic differences between raters are irrelevant, or

Box 1: Examples of correlation and agreement analysis from published literature

Harbrecht BG, Rosengart MR, Bukauskas K, Zenati MS, Marsh JW Jr, Geller DA. Assessment of transcutaneous bilirubinometry
in hospitalized adults. J Am Coll Surg 2008;206:1129‑36.
Harbrecht et al. validated transcutaneous techniques to measure serum bilirubin in adults at risk of or diagnosed with hepatic
dysfunction. Eighty consecutive hospitalized adult patients from the general surgery, trauma surgery, and liver resection/
transplantation services of a tertiary care university medical center underwent TcB measurement from the forehead, sternum,
forearm, and deltoid. TcB measurements were repeated each time; serum bilirubin measurements were performed. They
found that TcB measurement from the forehead correlated with serum bilirubin better (r=0.963) than measurements from
the forearm (r=0.792), deltoid (r=0.922), or sternum (r=0.928). However, a Bland–Altman plot demonstrated that forehead
measurements became less accurate as the magnitude of hyperbilirubinemia increased. Therefore, the authors concluded that
in adult patients forehead TcB correlates best with serum bilirubin levels but becomes less reliable at higher values and further
refinements in transcutaneous bilirubinometry technology are needed.
Wöpking S, Scherens A, Haussleiter IS, Richter H, Schüning J, Klauenberg S, Maier C. Significant difference between three observers
in the assessment of intraepidermal nerve fiber density in skin biopsy. BMC Neurol 2009;9:13. doi: 10.1186/1471‑2377‑9‑13.
The determination of IENFD in skin biopsy is a useful method for the evaluation of different types of peripheral neuropathies.
To validate the method, it is necessary to determine interobserver reliability which was the aim of the study. Three observers
determined the IENFD and estimated the staining quality of the basement membrane for 120 skin biopsies (stained with indirect
immunofluorescence technique) from 68 patients. The authors found an unexpected significant difference in IENFD between the
observers and hence considered the results not to be in line with the high intraclass correlation coefficient (0.73) reported before
as index of interobserver reliability. The Bland–Altman plot also showed a divergence growing with rising mean. The authors
opined that difference in IENFD between the observers and the resulting low interobserver reliability is likely caused by different
interpretations of the standard counting rules. The standardization of the method is thus important and at least two observers
should analyze the skin biopsies.
Longo Imedio I, Serra‑Guillén C. Adaptation and validation of the Spanish version of the Actinic Keratosis Quality of Life
questionnaire. Actas Dermosifiliogr 2016;107:474‑81.
While there are questionnaires for evaluating the effects of skin cancer on patient quality of life, there were no specific
questionnaires available in Spanish for evaluating the quality of life in patients with actinic keratosis. The aim of this study was
to translate and culturally adapt the AKQoL questionnaire into Spanish. The original questionnaire was translated into Spanish
following the guidelines for the cross‑cultural adaptation of self‑report measures. Several measures of general reliability and validity
were used, including Cronbach’s α for internal consistency and a Bland–Altman plot for test‑retest reliability. To test concurrent
validity, the authors used the Spearman’s correlation coefficient to measure the correlation between AKQoL and Skindex‑29
scores. The final version of the translated questionnaire was administered to 621 patients with actinic keratosis. The Cronbach’s α
reliability coefficient was 0.84. The correlation between the score on the Skindex‑29 and on the AKQoL was however modest at rho
of 0.344 (P<0.05). The authors considered the translated version as a satisfactory alternative to be used in Spanish‑speaking actinic
keratosis patients.
Apa H, Gözmen S, Bayram N, Çatkoğlu A, Devrim F, Karaarslan U, et al. Clinical accuracy of tympanic thermometer and noncontact
infrared skin thermometer in pediatric practice: An alternative for axillary digital thermometer. Pediatr Emerg Care 2013;29:992‑7.
The aim of this study was to compare body temperature measurements by infrared tympanic and forehead noncontact thermometers
with the conventional axillary digital thermometer. A total of 1639 temperature readings were performed for every method
on fifty hospitalized children. The average difference between the mean (SD) of axillary and tympanic temperatures was
−0.20°C (0.61°C) (95% CI, −1.41°C–1.00°C). The average difference between the mean (SD) of axillary and forehead temperatures
was −0.38 (0.55°C) (95% CI, −1.47°C–0.70°C). The Bland–Altman plot showed that most of the data points were tightly clustered
around the zero line of the difference between the two temperature readings. The authors concluded that the infrared tympanic
thermometer could be a good option for fever assessment in children. The noncontact infrared thermometer is also useful, but it has
greater bias.
TcB: Transcutaneous bilirubin, IENFD: Intraepidermal nerve fiber density, AKQoL: Actinic keratosis quality of life, CI: Confidence interval,
SD: Standard deviation

Indian Journal of Dermatology 2016; 61(6) 600

 Hazra and Gogtay: Correlation and regression
absolute agreement, when systematic differences are
relevant.
Some published examples of the use of correlation
analysis are provided in the Box 1.
Finally, note that assessing agreement between
categorical variables requires different indices such as
Cohen’s kappa. This will be discussed in a future module.
Financial support and sponsorship
Nil.
Conflicts of interest
There are no conflicts of interest.
601
View publication stats
Further Reading
1. Linear regression and correlation. In: Samuels MA, Witmer JA,
Schaffner AA. Statistics for the life sciences. 4th ed. Boston:
Pearson Education; 2012. p. 493‑549.
2. Correlation. In: Kirk RE. Statistics: An introduction. 5th ed.
Belmont: Thomson Wadsworth; 2008. p. 123‑57.
3. Regression. In: Kirk RE. Statistics: An introduction. 5th ed.
Belmont: Thomson Wadsworth; 2008. p. 159‑81.
4. Correlational techniques. In: Glaser AN. High‑yield
biostatistics. Baltimore: Lippincott Williams and Wilkins; 2001.
p. 50‑7.
5. Bewick V, Cheek L, Ball J. Statistics review 7: Correlation and
regression. Crit Care 2003;7:451‑9.
6. Giavarina D. Understanding Bland Altman analysis. Biochem
Med (Zagreb) 2015;25:141‑51.
Indian Journal of Dermatology 2016; 61(6)