Module 1.

Introduction to Psychological Statistics  Laboratory Experiments: Done in a

controlled environment.
Psychology and Philosophy ▪︎Psychology
 Field Experiments: Done in real-life
comes from Philosophy and shares deep connections
with it. settings.
▪︎Philosophy asks big questions about human life and ▪︎Correlational Studies: Looks at relationships
guides ideas to explain the human experience. between variables.
▪︎Psychology, while inspired by philosophy, uses ▪︎Surveys: Collects data through questionnaires or
evidence and systematic methods to study human interviews.
behavior and mental processes scientifically.
 Qualitative Research: Focuses on personal
Psychology as a Science experiences and meanings.
▪︎Psychology is the scientific study of behavior and
mental processes. ▪︎Case Studies: In-depth analysis of one person,
▪︎It uses the scientific method to explore thoughts, group, or event.
feelings, and actions. ▪︎Interviews: One-on-one discussions to gather
▪︎As a science, it relies on theory, research, and details.
practice ▪︎Focus Groups: Small group discussions led by
a researcher. Narrative Analysis: Studies stories to
find meaning. ▪︎Discourse Analysis: Examines
What Makes Psychology a Science? how language reflects power and culture.
1. Empirical Evidence: Uses measurable and
observable data through experiments and observation. The Role of Theories in Research
2. Objectivity: Reduces bias and personal opinions in
research. ▪︎Theory: A well-supported explanation tested through
3. Systematic Methods: Follows organized steps to research.
ensure consistent results. ▪︎Facts: Unchanging, objective observations.
4. Falsifiability: Theories and ideas can be tested and ▪︎Theories explain facts and are tested through
proven wrong. hypotheses.
5. Peer Review: Experts evaluate research to ensure it
is valid and reliable. Why Are Theories Important?

Positivism: The Basis of Scientific ▪︎They guide research and help focus investigations.
▪︎They allow researchers to create testable ideas
Psychology
(hypotheses).
▪︎Positivism is a belief that only observable, ▪︎They help interpret research findings.
measurable things are real.
▪︎It uses experiments, numbers, and statistical Why Test Hypotheses?
analysis to study reality.
▪︎A hypothesis is an educated guess or tentative
In Psychology: explanation based on a theory.

▪︎Psychologists often use positivist methods like ▪︎It is tested using real-world data to confirm or refute
experiments and statistics to understand human it.
behavior.  Hypothesis Testing:
▪︎A statistical process to check if a hypothesis is likely
true.
Types of Research in Psychology
▪︎Involves gathering and analyzing data.
 Quantitative Research: Focuses on numbers
 Importance of hypothesis Importance
and patterns.
testing:
 Experiments: Control variables to observe
their effects. ▪︎Reveals patterns and relationships.
▪︎Helps draw conclusions about a larger group from a ▪︎Quantifying Behavior: Statistics allows
sample. psychologists to quantify complex human behaviors,
▪︎Ensures research is rigorous and objective. emotions, and cognitive processes. ▪︎Reducing Bias:
By using statistical methods, researchers can minimize
Why is Math Important in Psychology? subjective biases and ensure objectivity in their findings.

▪︎Psychology uses numbers to measure behavior, 2. Understanding Data Patterns:

describe patterns, and make decisions. ▪︎Identifying Trends: Statistical analysis helps identify
▪︎Math helps test theories and analyze research patterns and trends within large datasets.
findings. ▪︎Making Predictions: By analyzing historical data,
psychologists can make informed predictions about
Functions of Statistics in Psychological future behaviors or outcomes.
Research
 Description: 3. Testing Hypotheses:
▪︎Organizes data using mean, median, mode, and ▪︎Hypothesis Testing: Statistical tests allow
measures like variance. researchers to test hypotheses and draw conclusions
 Inference: about the validity of their theories. ▪︎Determining
▪︎Draws conclusions about a population based on a Significance: Statistical significance tests help
small sample using tools like t-tests and confidence determine whether observed differences or
intervals. relationships are likely due to chance or a real effect.
 Prediction: Enter
▪︎Predicts future trends based on past data using
statistical tools like regression analysis.
Enter 4. Drawing Inferences:
▪︎Generalizing Results: Statistics enables
Generalization in Research researchers to generalize their findings from a sample
to a larger population.
▪︎Psychology, especially positivist research, ▪︎Making Claims: By using statistical analysis,
aims to explain human experiences in general psychologists can make strong, evidence-based claims
terms. about human behavior.
▪︎However, other approaches like
5. Evaluating Interventions:
constructivism (qualitative research) focus on
▪︎Measuring Effectiveness: Statistical methods are
personal and unique experiences instead of
used to evaluate the effectiveness of psychological
generalizing.
interventions, such as therapies and treatments.
▪︎Identifying Best Practices: By analyzing data,
Module 2. Statistics and Research Process
researchers can identify the most effective approaches
to address psychological issues.
What is Statistics?
 Statistics is the science of collecting, analyzing, 6. Informing Policy and Practice:
interpreting, presenting, and organizing data. It's a ▪︎Evidence-Based Practice: Statistical analysis
tool that helps us make sense of information and provides the evidence needed to inform evidence-
draw meaningful conclusions. based practices in psychology and related fields.
▪︎Policy Development: Data-driven insights from
Why do we need Statistics in Psychology? statistical analysis can guide the development of
 Statistics is the backbone of psychological effective policies and regulations.
research (in Positivist perspective). It provides
the tools to analyze data, draw meaningful Applying Descriptive and Inferential
conclusions, and make informed decisions. Statistics
Here's why statistics is indispensable in  Descriptive Statistics
Psychology:
o Summarizes and describes data without
1. Objectivity and Precision: making conclusions about a larger
population.
 Measures of central tendency (mean, median,  We measure them and generate quantified
mode) scores.
 Measures of dispersion (range, variance, standard  Scores may vary from simple to complex.
deviation)  These types of score is called Levels of
 Standardized scores (Percentiles, z-scores, Sten measurement
scores etc). o A system of classifying variables based on the
 Data visualization (Pie chart, bar graph, histogram mathematical properties of the numbers used
etc.) to represent them.
o Choosing the appropriate statistical analysis
 Inferential Statistics depends on the level of measurement. ○
Misunderstanding levels can lead to incorrect
o Draws conclusions about a population conclusions.
based on a sample.
What are the levels of measurement?
Key Methods:  Nominal -. Categorical/Discrete
 Hypothesis Testing:
 Ordinal -. Categorical/Discrete
 Test sample data to accept or reject a hypothesis.
 Interval - Continuous/Scale
 Confidence Intervals:
▪︎Estimate population parameters with a confidence  Ratio - Continuous/Scale
range. o Again, the types of scores may vary in terms of
their degree of sophistication or refinement.
Examples: T-tests, ANOVA, Correlation, Regression
Analysis. Nominal Level of Measurement
 Definition:
o Categorical data with no inherent order.
What are the types of information we are
o Numbers are used as labels, not values.
dealing with?  Examples:
o Gender (Male, Female, Other)
● Variables – any characteristics that differ or vary from o Marital Status (Single, Married, Divorced)
one individual to another. ○ This are usually the interest o Eye Color (Blue, Brown, Green
of Behavioral Science research. o
● Constant – any characteristics that does not vary. It is Ordinal Level of Measurement
given or a fact of life. o Definition:
o Example, only females are capable of o Categorical data with a specific order.
giving birth so no need to ask for the o Differences between categories are not
mother’s sex because it is already equal.
understood as constant o Examples:
o Educational Attainment (High School,
● Psychological Constructs Bachelor's, Master's, PhD)
o These are hypothetical variables that can o Likert Scale Ratings (Strongly Disagree,
be measured using some Disagree, Neutral, Agree, Strongly Agree)
measures/scales/ questionnaires. o Socioeconomic Status (Low, Middle, High
o These are theoretically grounded variables.
 Examples may include: Interval Level of Measurement
 Well-being (Ryff, 1989) o Definition:
 Locus of hope (Bernardo, 2010) o Numerical data with equal intervals between
 Big Five Personality Factors (McCrae and Costa, values.
1996) o No true zero point.
 Basic Psychological Need Satisfaction (Deci and o Examples:
Ryan, 2000) o IQ Scores
o Most Psychological variables (Psychological
How do we quantify these Psychological constructs
constructs?
Ratio Level of Measurement
o Definition:
 o Numerical data with equal intervals and a true  Table Title: Contains the title of what the table is
zero point. about.
o Examples:  Category: The characteristic or attribute being
o Number of children organized.
o Income  Frequency: The number of times a particular value
or category occurs.
Important note to remember  Percentage: A number or ratio expressed as a
fraction of 100. It is often denoted using the percent
 Recap of the Four Levels of Measurement: sign (%).
o Nominal: Categorical, no order
o Ordinal: Categorical, with order Some rules in dealing with Ordinal data for
o Interval: Numerical, equal intervals, no true Simple Frequency Distribution:
zero
o Ratio: Numerical, equal intervals, true zero  Retain the logical sequence of the categories.
 Importance of correct Identification of data  Disrupting the sequence can reduced legibility
o For appropriate statistical analysis of the tabular presentation.
o Generate valid conclusions
o Remember this basic skill in identifying the
appropriate level of measurement since this
Grouped Frequency Distribution
will be our basic “ABC” in Statistics.  A grouped frequency distribution is used when
the data is continuous (INTERVAL AND RATIO)
Module 3. Frequency Distribution and Graphical Presentation and there are many different values. It groups
the data into intervals, or classes, and then
Frequency Distribution: A Visual Summary counts the number of values that fall into each
interval.
of Data
Determine class interval
 A frequency distribution is a statistical technique
used to summarize and organize data by showing
 A category in a group distribution containing
the number of times each value or category occurs
more than one score values.
in a dataset. It's a powerful tool for understanding
 Range: The difference between the highest and
the distribution and patterns within data.
the lowest scores in a distribution.
Types of Frequency Distributions: Range = highest score – lowest score –

 Simple Frequency Distribution:  Interval width (i)

o Used for small datasets with few distinct i = _____Range________
values/categories. Number of class intervals
o Used for NOMINAL and ORDINAL data
(Categorical variables). Example: i = 175-150
o Each value is listed separately, along with its 5
corresponding frequency. i = 25/ 5
 Grouped Frequency Distribution: i=5
o Used for large datasets with many distinct In every class interval/group there are 5 scores
values/scores.
o Used for INTERVAL and RATIO data Determine the Class Limits
(Continuous variables).
o Data is divided into intervals or classes, and  The point midway between adjacent class
the frequency of values falling within each intervals that serves to close the gap between
interval is counted. them.

Key Components of a Simple Frequency  Formula:

Distribution Class limits = Upper limit of one class + lower limit of the next class
2

Determine the Midpoint

 across the categories of one or more additional
 The middle-most score value in a class interval. variables
 Serves as the spokesperson for all score
values in class interval. Pie chart
 Single number can represent the entire class
interval.  A circular graphs whose slices add up to 100%.
 Formula:  One of the simplest method.
m = lowest score value + highest score value  Nominal-level variable.
2  Showing differences in frequencies or
percentages among categories.
Get the frequency, Relative frequency, and
percentage Bar Graph

 Frequency – the number of cases or count that  Plotting frequency distribution of nominal or
fell within the class interval. ordinal data.
o Just tally the scores/responses that fell for  It can accommodate any number of categories.
every class interval  The height of the bar represents the frequency
 Relative frequency – the ratio of the number of in each category.
times the scores occurs in the set relative to  The bars for each category in a bar graph do
the total outcomes. not touch each other.
o Equation is: Rel f = f/N  Distribution of Discrete variables.
 Percentage – a number or ratio expressed as
a fraction of 100. Histogram
o Equation is:
Percentage= Rel f X 100 or f/N x 10  This is used to represent frequency
distributions composed of interval or ratio.
Get the Frequency Cumulative Distribution  Resembles the bar graph, but with the
histogram, a bar is drawn for each class
 Cumulative frequencies (cf) : Total number of interval.
cases having any given score or a score that is  To display continuous measures.
lower.  There is continuity along the scale
 Adding the frequency of a category to the total
frequency for all categories below it. Shape of a Frequency Distribution
Get the Percentage Cumulative ● Kurtosis (u): peakedness of the distribution. ●
Distribution Skewness (e): asymmetrical distribution.
 Scores pile up in one direction creating a tail.
 Cumulative percentage (c%): the percentage of  The position of the tail indicates where the
cases having any score or a score that is lower. relatively few extreme scores are located and
 Formula: determines the direction of skewness.
c% = (100) cf
N Module 4. Descriptive Statistics: MEASURES OF
o cf = cumulative frequency in any category CENTRAL TENDENCY AND VARIABILITY
o N = total number of cases in the distribution
What are the measures of central tendency?
- Can also be obtained by summing the percent
distribution.  Descriptive statistics that describe the
representative or typical score in a distribution
Cross tabulation  A single value that is usually at the center of a
distribution
 Also called as cross-tabs  Three main types: mode, median, mean
 A table that presents the distribution  Choice depends on the level of measurement
(frequencies and percent) of one variable of a variable.
Mode (Mo)  Symmetrical distribution = Mo, Mdn, M the
 Most frequently occurring category or value of same and at the center of a distribution
a variable  Asymmetrical = Mean heavily influenced by
 Distributions are usually unimodal, i.e. have outliers; alternative is Mdn Which level of
one (1) mode measurement is appropriate for a variable
 Multiple modes can exist, e.g. bimodal  Choice of central tendency depends on level of
distribution accuracy needed
 For nominal-level variables  For skewed distributions, median is more
balanced than mean
What is the mode?  In large distributions, or for inferential statistics
or advanced statistical analyses, mean is
 80 students said that asking a classmate for preferred
help in understanding their statistics lessons  Mean is usually reported in published studies
does not make them anxious Which measure of central tendency is
 60 students said that asking their teacher for appropriate for a variable
help in understanding their statistics lessons What are the measures of variability
does not make them anxious
 90 students said that asking a classmate for  Descriptive statistics that describe the
help in understanding their statistics lessons spread of scores around the center of a
makes them anxious distribution
 170 students said that asking their teacher for  Aka measures of dispersion
help in understanding their statistics lessons  Measures of central tendency are
makes them anxious incomplete without a description of how
Median (Mdn) varied or consistent they are
 Three main types: Range, variance,
 Middle-most point in a distribution that standard deviation
divides it into two equal parts
 For ordinal- or interval-level variables Range (R)
 Arrange the categories or scores, i.e.
lowest to highest  Difference between highest (H) and lowest
 For an odd number of categories or scores, scores (L) in a distribution
 For an even number of categories or R=H–L
scores.  Simple, crude measure of variability
Rmales = 4 – 1 = 3
Mdn = n+1 Rfemales = 4 – 1 = 3
2
Mdn = 1st middle + 2nd middle case “Doing statistics calculations by hand makes me
2 nervous.”

 What is the median?  The mean statistics anxiety of the six

How would you rank your performance when you take participants is 2.167, which indicates that
quizzes or tests in statistics? statistics calculations do not trigger anxiety
 2 students said “excellent,” 1 student said  The standard deviation of 1.169 indicates that
“good,” 3 students said “passed,” and 3 the anxiety scores differ by an average of 1.17
students said, “poor” “anxiety points” 1
 First, determine if there is an odd or even 3
number of categories or scores 2
2
 Consider the following: 1
4
– Level of measurement of a variable n=6
– Shape of distribution (skewness, kurtosis) s=1.16
– Research goals
Which measure of variability is appropriate for a
variable?

 Range is easy to obtain, but least accurate

– Range can never be greater than the
standard deviation
 Interpretation of variance is tricky because a
variable’s unit of measurement is squared too
 Standard deviation reflects the effect of all
scores of a continuous variable
– Standard deviation is the “average” of
deviations from the mean, aka mean variability
of a distribution
– The larger the standard deviation, the greater
the variability.