24 Working scientifically

Patterns in data Key facts

In some experiments, you might look to see if there ✓ A correlation is when one variable
is a relationship between two variables. In other changes as the other variable does.
words, if you change one variable, how does it ✓ A correlation does not show that one
affect the other? change causes the other.
✓ A relationship between two variables
is linear if the points form a straight
Correlation
line when plotted on a graph.
When two variables appear to be linked, we say they are
correlated. Plotting a scatter graph of your data is a good way ✓ A relationship is proportional if a
to spot correlations. A correlation between two variables doesn’t straight line goes through the origin.
show that one causes the other. For example, ice cream sales and
swimming accidents are positively correlated, but this is because
ice cream and swimming are both more popular in hot weather and
not because ice cream causes swimming accidents.

No correlation Weak correlation Strong positive Strong negative

The data points are scattered The points look as if they might correlation correlation
around randomly and show no be grouped around a diagonal The points form a diagonal The line formed by these
pattern. There is no correlation line. The large scatter means line, showing that one points shows that one variable
between the variables. this is only a weak relationship. variable increases as decreases as the other increases.
the other one does. This is a negative correlation.

Linear and proportional relationships

Graphs showing correlation can reveal other interesting
patterns in a relationship, depending on their shape.

1
y

x
Linear Proportional Inversely proportional Checking
A correlation where the If the points form a straight In an inversely proportional To check whether a relationship
points form a straight line line through the origin (where relationship, one variable is inversely proportional, plot
is described as linear. x and y both equal zero), the halves when the other doubles. one variable against the inverse
relationship is described as This forms a curved line. of the other (1 divided by the
proportional. This means that value). The graph should be a
if one variable doubles, so straight line through the origin.
does the other.
 Working scientifically 25

Conclusions
The conclusion of an experiment describes
what you found out, interprets the results,
and says whether the experiment agrees with 0.5
the prediction you made.
0.4

Current (A)
0.3
An electricity experiment
Three students carried out an experiment to test 0.2
the prediction that the current flowing through
a bulb is proportional to the voltage across it. 0.1
By using an ammeter to measure current in the
0
circuit and a voltmeter to measure voltage across 0 1 2 3 4
the bulb, they obtained the results shown in the
graph. Their conclusions are shown below.
Voltage (V)

Conclusion 1 Conclusion 2 Conclusion 3

“The current does go up “The current increases as “The graph shows that
when the voltage goes up, so voltage increases, but the the current increases as the
the prediction was correct.” graph is a curve. A proportional voltage increases. At lower
relationship would produce a voltages, the relationship
straight line, so the prediction could be proportional, as
was not correct.” the first few points fall on
a straight line. However, at
higher voltages, there is a
smaller increase in current
An incorrect conclusion
for every increase in voltage.
The description is not detailed, A better conclusion
and the graph does not show a The description has This shows that the resistance
proportional relationship, which more detail and the final is increasing. The prediction
would produce a straight line. conclusion is correct. was partially correct, as the
current does increase with
voltage, but the relationship
is not proportional.”

An excellent conclusion
The description is much
more detailed. The student
has used their knowledge
of the link between current,
resistance, and voltage
to suggest what may be
causing the change in
shape of the graph.
26 Working scientifically

Accuracy and Key facts

precision ✓ Accurate measurements are ones

that are close to the true value
being measured.
When planning and evaluating an experiment, you
✓ Precise measurements are those that
need to think about the accuracy and precision
give the same (or similar) values when
of your measurements. The words accurate and the measurement is repeated.
precise have specific meanings in science.
✓ Errors in measurements can be
random or systematic.
Accurate or precise?
A measurement is considered more accurate if it is closer
than other measurements to the true value being measured.
It is precise if repeating the measurement several times
produces values that are the same or very close to each The center of the target
other. To understand the difference, it helps to think of represents the true
measurements as trying to hit a target. value being measured.

Inaccurate and imprecise Precise but inaccurate Accurate but imprecise Accurate and precise
The measurements are These measurements are These are close to the center These measurements are both
inaccurate, as they are not precise because they are all but not to each other, so they accurate and precise.
near the center of the target, nearly the same value, but are accurate but imprecise.
and imprecise, as they are they are inaccurate because
not close to each other. they aren’t close to the center.

Types of error

Systematic errors Random errors

The accuracy of some instruments Random errors are different
depends on how they’re used. Balances for every reading. For example,
should be set to zero with a container on if you take the temperature
them so you only measure the mass of of water in a beaker, the
the contents. If a balance is not zeroed thermometer might return a
properly, all the measurements will be slightly different reading each
incorrect by the same amount. This is time it dips into a different part
a systematic error and reduces the of the water. This reduces the
accuracy of the measurements. precision of your measurements.
0.5
This should be zero when the
beaker is empty.