SFP - Statistical Analysis in Psychology Lesson

Learning Targets:

  • Apply basic descriptive statistical concepts, including interpreting, constructing graphs, and calculating simple descriptive statistics.
  • Distinguish the purpose of descriptive and inferential statistics. 

AP psychology course and exam description, effective fall 2020. (n.d.). https://apcentral.collegeboard.org/media/pdf/ap-psychology-course-and-exam-description.pdf

Statistical Analysis in Psychology

Statistics allow researchers to organize and evaluate the data they have been collecting, back up a hypothesis, and can also be used to distort the truth! They provide a common language to organize, summarize, and make inferences about gathered data.

Descriptive Statistics

Descriptive statistics are a way of listing or summarizing data. It can help us to recognize patterns that describe how often a behavior takes place. Categories are set up and occurrences of each are tallied to describe the frequency of a behavior. The data can be organized in several ways.

Central Tendency

Central tendency is a way of measuring a set of data that utilizes a single number to present information about the center of a frequency distribution (A frequency distribution is a summary of how often scores occur within a sample.) Measures of central tendency include mean, median, and mode.

  • The mean is the sum of a set of scores divided by the total number of scores.
  • The median is the score that divides a frequency distribution in half with half of the numbers above and half of the numbers below the median.
  • The mode is the most frequently occurring score in a distribution.

Image of a Normal Bell CurveNormal Distribution

In statistics, you may hear the term normal distribution or bell curve. The normal distribution is often the goal in research and what the researcher strives to achieve. In a normal distribution the mean, median, and mode are all the same and fall at the highest peak of the curve of a bell-shaped polygon. Standardized tests produce a normal distribution and can be explained in more detail by examining variability (A variability is a single number that presents information about the spread of scores in a distribution.).

Measures of Variability

Range describes the distance from the highest to the lowest scores on a data set. It can be achieved by subtracting the smallest number from the highest number. For example, say we are looking for the range of scores in a psychology class. The highest-scoring student has an average of 96 and the lowest-scoring student has an average of 51, the range for the class is 45.

Standard deviation is another measure of variance that describes the distance of scores around the mean. It measures how spread out a set of scores is. With low standard deviation data points are close to the mean. In high standard deviation data points are spread out over a broad range. In a normal distribution, approximately 68% of the scores are within one standard deviation (SD); 95% of the scores are within 2 SD, and 99.7% of the scores are within 3 SD from the mean as illustrated in the image.

Inferential Statistics

Inferential statistics seek to identify if your hypothesis can be supported and whether the findings of your study can be applied to the population at large. Are they generalizable? Researchers are looking for at least 95% assurance that their hypothesis can be supported. This can be illustrated with a P value of .05 or less and provides the borderline for statistical significance (Statistical significance is a statistical statement of how likely it is that an obtained result occurred by chance.).

[CC BY 4.0] UNLESS OTHERWISE NOTED | IMAGES: LICENSED AND USED ACCORDING TO TERMS OF SUBSCRIPTION