Statistics
module 1.
[Link] data
Definition: Data collected firsthand by the researcher for the specific
purpose of their current study.
Collection methods: Surveys, interviews, experiments, and direct
observation.
Strengths:
High level of control over the collection process, ensuring data
accuracy and relevance.
Tailored to the exact research question, making it highly specific and
detailed.
Up-to-date and fresh, collected in real-time.
Weaknesses:
Can be time-consuming and expensive.
Requires adherence to ethical standards, such as obtaining
informed consent.
Example: A psychologist conducts a new experiment to measure the
effect of a specific type of therapy on a group of patients.
+Secondary data
Definition: Data that has already been collected by someone else for a
different purpose.
Sources: Published academic papers, books, journals, government
reports, and existing databases.
Strengths:
Cost-effective and time-saving.
Allows researchers to investigate historical trends or conduct meta-
analyses across many studies.
Provides a broad range of information for comparative analysis.
Weaknesses:
Researchers have no control over the original data collection
methods, leading to potential limitations in quality or accuracy.
May not perfectly align with the research question or could be
outdated.
Example: A researcher analyzes existing medical records to study the
prevalence of a mental disorder in a specific population, as described in
the
2. Qualitative research
Purpose: To explore ideas, formulate hypotheses, and gain an in-depth
understanding of concepts, opinions, and experiences.
Data type: Non-numerical, such as words, descriptions, and
observations.
Methods: Interviews, focus groups, case studies, and observation.
Analysis: Thematic analysis, content analysis, and identifying patterns
in the data.
Example: Conducting interviews with patients to understand how they
experience a chronic illness.
+Quantitative research
Purpose: To measure and test relationships between variables, test
theories, and generalize findings to a larger population.
Data type: Numerical and statistical data.
Methods: Experiments, structured observations, and surveys with
closed-ended questions.
Analysis: Statistical analysis to identify patterns, relationships, and
differences between groups.
Example: Conducting a survey with 1,000 participants to measure the
correlation between sleep hours and stress levels.
3. Population
The complete set of individuals who share a common characteristic of
interest for a study.
Example: All adolescents in the United States who use social media.
The characteristics of a population are called parameters.
Sample
A smaller, manageable subset of the population selected for a study.
It should ideally be representative of the larger population to allow for
accurate inferences about it.
Example: 500 adolescents from different U.S. states chosen randomly
for a study on social media use.
The characteristics of a sample are called statistics.
Census vs. Sampling in Psychology
Feature Census Sampling
Data Data from every individual in the Data from a select group (the
collection population sample)
Feasibility Often impractical or impossible More practical and cost-effective
due to time, cost, and logistics for large populations
Accuracy Highly accurate since every Less accurate; results are
member is included estimates with a margin of error
Application Best for small, well-defined Widely used in psychological
populations or when extensive research to make generalizable
data is absolutely necessary claims about larger groups
4. Discrete data in psychology
Definition: Data that can only take on specific, separate values,
representing counts or categories.
Examples:
The number of correct answers on a memory test.
The number of times a participant blinks during a task.
Whether a participant was a "control" or "experimental" group.
Characteristics:
Values are whole numbers and cannot be subdivided.
Often visualized using bar graphs.
+Continuous data in psychology
Definition: Data that can take any value within a given range,
representing measurements.
Examples:
A person's score on a personality scale (e.g., a 75.5 on a 100-point
scale).
The time it takes to complete a task (reaction time).
The intensity of an emotion, measured on a continuous scale from
low to high.
Characteristics:
Values can include fractions and decimals.
Typically represented by histograms or line graphs.
Can be infinitely divided into smaller parts.
module 2
5. Bar diagrams
Bar diagrams, or bar charts, display categorical data using rectangular bars
of varying heights or lengths. They are ideal for comparing discrete
categories or for showing a distribution of data points.
Comparing different groups: A psychologist might use a bar chart to
compare the average test scores of students who received different
types of instruction.
Showing frequency: They can illustrate the number of people who fall
into different categories, such as a bar chart showing the frequency of
different mental health diagnoses.
Presenting results of surveys: Bar charts are effective for displaying
survey responses, such as how many people chose "agree," "disagree,"
or "neutral" for a particular question.
+Pie diagrams
Pie diagrams, or pie charts, are circular graphs divided into slices to show the
proportion of each category relative to the whole. The entire circle represents
100% of the data.
Illustrating proportions: A pie chart can effectively show the
percentage breakdown of different psychological disorders within a
specific population.
Breaking down a total: It can be used to visualize the composition of a
"whole," such as how a person spends their time, with each slice
representing a different activity.
Displaying demographic data:Researchers can use pie charts to show
the proportion of participants in a study based on gender, age group, or
ethnicity.
Important consideration: Pie charts are most effective when the total
sum of the parts is a meaningful whole, and the number of categories is
small (ideally between four and seven). Research also shows that bar
charts are often more accurate for comparing the sizes of individual
categories.
+Pictograms
A pictogram, or picture graph, uses images or icons to represent quantities of
data. A key is almost always included to explain what each symbol
represents.
Common uses in psychology:
Engaging a broader audience:Pictograms are visually engaging and
easy to understand, making them useful for communicating basic
research findings to a general audience or in educational materials.
Representing discrete items: They are suitable for showing the
frequency of distinct items, such as using an icon of a person to
represent the number of participants in different therapy groups.
Simplifying complex data: While less precise than bar charts,
pictograms can simplify information for quick visual comparisons.
6. Four types of data classification
Geographical Classification: Arranges data based on location, such as
the production of goods in different countries or states.
Chronological Classification:Organizes data over a specific time
period, such as sales figures from year to year.
Qualitative Classification:Categorizes data based on attributes or
qualities that cannot be measured numerically, like political affiliation or
gender. This can be further broken down into simple (using a single
attribute) and manifold (using multiple attributes).
Quantitative Classification: Groups data that can be expressed
numerically, such as height, age, or income
7. Frequency distribution
Purpose: To summarize and organize raw data to make it easier to
understand patterns and trends.
How it works: It lists each score or category and shows the number of
times (the frequency) each one occurs.
+Discrete vs. Continuous frequency tables
Feature Discrete Frequency Table Continuous Frequency Table
Data Type Discrete data (e.g., number of Continuous data (e.g., height,
siblings, score on a multiple- weight, reaction time)
choice test)
Organization Lists each individual value and its Groups data into class intervals
frequency (e.g., 10–19, 20–29)
Example A table might show how many A table might show how many
(Scores) people got a score of 5, 6, 7, etc. people scored between 80–89,
90–99, etc.
8. Frequency distribution terms
Frequency: The number of times a data value or event occurs.
Class interval: A range of values grouped together in a frequency
distribution.
Class frequency: The number of data points that fall within a specific
class interval.
Relative frequency: The proportion or percentage of data points that
fall within a specific class, calculated as the class frequency divided by
the total number of observations.
Midpoint (or classmark): The central value of a class interval, often
calculated by averaging the upper and lower limits.
+Cumulative frequency table terms
Cumulative frequency: The sum of the frequencies for a given class
and all preceding classes. It represents the total number of data points
up to and including a specific value.
"Less than" cumulative frequency:The sum of frequencies for all
classes from the lowest up to the current class.
"More than" (or "greater than") cumulative frequency: The sum of
frequencies for the current class and all following classes, down to the
lowest.
Percentile: The value below which a given percentage of observations
in a group of observations fall. In a cumulative frequency table, this can
be calculated from the cumulative frequency and the total number of
data points.