There's a natural order to how we do things, driving a car, for instance. You need to start the engine for a car to move. However, the following steps depend on the type of car, e.g. is it automatic or manual? The same can be said about data handling and analysis. Before we can identify what statistical tests can be used, we need to find the distributions of data.
Explore our app and discover over 50 million learning materials for free.
Lerne mit deinen Freunden und bleibe auf dem richtigen Kurs mit deinen persönlichen Lernstatistiken
Jetzt kostenlos anmeldenNie wieder prokastinieren mit unseren Lernerinnerungen.
Jetzt kostenlos anmeldenThere's a natural order to how we do things, driving a car, for instance. You need to start the engine for a car to move. However, the following steps depend on the type of car, e.g. is it automatic or manual? The same can be said about data handling and analysis. Before we can identify what statistical tests can be used, we need to find the distributions of data.
Distribution in psychology is one of the initial steps of analysing data. If you put a car in reverse, your vehicle will move backwards; if in first gear, it will move forward. The type of distribution of data also affects the direction of analysis.
When researchers collect data, the majority of the time, researchers aim to use statistical tests to empirically test if their data findings support or reject the hypotheses they proposed at the start of the study.
However, there are two types of parametric tests:
But how do researchers know when to use which test? One of the answers is distribution. When data has a normal distribution, a parametric test is used, and data with skewed distributions use nonparametric tests.
Ideally, researchers aim to use parametric tests as they are more sensitive and are more likely to find significant findings.
Nonparametric tests are only really used when data is not normally distributed.
Now that we've figured out the uses of distributions in psychology let's understand what the data analysis method means.
The distribution psychology definition is a probability distribution that measures the spread of data. From this, researchers can identify the proportion of data that varies/ differs from the average; most commonly, the mean and standard deviation is reported when measuring distributions.
Distribution graphs have numerous names, such as the bell curve graph or Gaussian distribution graph. Let's take a look at the characteristics of a distribution graph:
Now that we know what distributions mean let's look at the different types and how we can identify them.
In psychology, distributions can mean many things. The types of distribution we are focusing on are based on probability. However, frequency distributions are used to understand data. For instance, how often something is observed.
Imagine a research project investigating 100 people of various ages. The researcher can't understand how common specific ages are by looking at each case. Instead, the data is organised using frequency distribution.
An example of how frequency distributions in psychology may look is shown in the table below.
Age | Frequency |
20 | 20 |
23 | 20 |
24 | 35 |
27 | 7 |
30 | 18 |
If you total the frequency, it adds up to 100, the number of participants in the experiment.
Frequency distributions are related to the probability distribution. From frequency distributions, the researcher can identify outliers and whether the data centres around the averages (central tendency values); these factors contribute to whether data is normally distributed.
Let's look at what a normal distribution graph looks like to interpret what the graph shows.
The graph shows that the highest point of the curve is in the middle of the graph, and both sides of the chart are symmetrical. But what does it mean?
The mean, median and mode are the same, as the distribution is symmetrical half of the scores are above the average, and the other half are below the average. The mean is equal to 0, and the standard deviation to 1.
Standard deviation (SD) is how much something deviates/ differs from the average.
In normal distributions:
These are known as the empirical rules of normal distribution.
A smaller SD means that the data is less varied, so the data is less likely to have outliers affecting the reliability and validity of findings.
Suppose in a psychology test. These were the average results of the class:
Mean | Median | Mode |
25 | 26.5 | 25 |
These findings suggest a normal distribution because the mean, median, and mode are approximately the same. And so, if this were plotted onto a graph, it would probably take the shape of a bell curve.
When the mean, median and mode are approximately the same, then this suggests that the dataset does not have many outliers.
The two types of skewed distribution charts we will cover are positive and negative.
Let's start by understanding negatively skewed charts.
Typically the scores will mostly be larger numbers and fewer smaller figures. And the mean will fall to the left of the median, which will cause the tail to extend to the left. The data is skewed when all of the central tendency values are not equal to 0.
Let's use test scores to understand negative skewness. On average, students are less likely to score under 50% on typical tests. Thus, the average is likely to be higher, which shifts the average to the right. However, they may be a lot of variance in scores, making the median differ from the mean. In essence, this describes negatively skewed data.
On the other hand, positively skewed data is the opposite. The majority of the numbers will be smaller rather than larger. The mean will fall to the median's right, causing the graph's tail to extend to the right. The findings would suggest a lower probability of occurrence of the phenomenon investigated.
Let's take a look at an example of a positively skewed distribution graph average data output:
Mean | Median | Mode |
28 | 23 | 18 |
The mode and median are below the mean.
What about these results?
Mean | Median | Mode |
17 | 26 | 30 |
These suggest a negative skew since most people scored high as the mode and median are higher here.
Do these results indicate anything?
If we look at the examples above, the positively skewed shape indicates that the participants scored lower on average, so perhaps the test was too hard. Similarly, the negatively skewed graph shows higher scores, so maybe the test was too easy. The mode is the highest point that illustrates the distribution.
We can then suggest making the test harder or easier, depending on the distributions above.
There is normal distribution psychology, in addition to positively skewed distribution and negatively skewed distribution.
The distribution psychology definition is a probability distribution that measures the spread of data.
Frequency distribution measures how often a value occurs in a data set. Frequency distributions are usually presented in tables.
A normal distribution in psychology can be achieved by collecting data with few outliers, and the figures centre closely to the measures of central tendency.
Skewed distribution in psychology means that the values are spread quite far from the average, and many outliers are present. There are two types: positively and negatively skewed distributions.
Because it determines later statistical tests that can be used. For example, parametric tests can only be used when a normal distribution is found. In contrast, non-parametric tests are used when positively or negatively skewed distributions are found.
Frequency distributions in psychology are used to measure how often a variable occurs and are usually displayed on a table.
What is a distribution?
Distribution is a probability distribution that measures the spread of data. From this, researchers can identify the proportion of data that varies/ differs from the average; most commonly, the mean and standard deviation is reported when measuring distributions.
Why is it important for data to be normally distributed?
So that researchers can use the most powerful statistical test, parametric tests.
What shape does a normal distribution graph have?
A bell curve shape.
What does it mean if we have a normal distribution?
A normal distribution shows us the data is representative of the population. If we were to measure the population on some quality, for example, IQ, we would get this bell-curved shape of results.
Why is the mode still at the highest point of the curve in a skewed distribution?
The mode is not affected by extreme scores.
What does a positive skew look like?
There is a big cluster of scores on the left, with scores tailing off to the right.
Already have an account? Log in
Open in AppThe first learning app that truly has everything you need to ace your exams in one place
Sign up to highlight and take notes. It’s 100% free.
Save explanations to your personalised space and access them anytime, anywhere!
Sign up with Email Sign up with AppleBy signing up, you agree to the Terms and Conditions and the Privacy Policy of StudySmarter.
Already have an account? Log in
Already have an account? Log in
The first learning app that truly has everything you need to ace your exams in one place
Already have an account? Log in