PSYC331 – Statistics for Psychologists
PSYC331 - Statistics for Psychologists (First Semester 2024/2025)
Course Instructors
Instructor: John E. K. Dotse, PhD
Office Location: Main Building, Psychology
Office Hours: Wednesdays, 10.30 am – 12.30 pm
Email: jekdotse@ug.edu.gh
Course Structure
Lecture 1: Introduction to Statistics
Instructions
Mode of teaching: Face-to-face.
All students should procure calculators.
Teaching assistants will be available for tutorial assistance.
Attend all lectures, as the course is technical and involves self-practice in computations.
Assessment and Grading
Assessment Format: Both online and paper-based.
Tests:
Test 1: Interim Assessment (online, MCQ) - Weight: 25%
Test 2: Interim Assessment (online, MCQ) - Weight: 25%
Test 3: Final Exam (paper-based) - Weight: 50%
Dates and times for tests, as well as any changes, will be communicated via the SAKAI platform and during lectures.
Reading List
Opoku, J. Y. (2007). Tutorials in Inferential Social Statistics. (2nd Ed.). Accra: Ghana Universities Press. Pages 3 – 22.
Inferential Statistics Observations
A solid grounding in statistics is essential for research in the social sciences.
Characteristics:
Technical yet manageable.
Statistics are not mathematics; focused on data analyses with basic calculations.
Crucial for data analytics in research projects.
Example Computation
Computational formula for Independent t-test.
Course Outline
Descriptive statistics.
Inferential statistics.
Properties/levels of measurement scales.
Summation notations.
Computation of mean and standard deviation.
What is Statistics?
Definition: A branch of mathematics concentrating on the organization, analysis, and interpretation of numerical groups (Aron, Coups, & Aron, 2014).
Branches of Statistical Methods:
Descriptive Statistics: Used to summarize and describe quantitative data.
Inferential Statistics: Techniques to draw conclusions about a population based on sample data.
Descriptive Statistics
Overview
Summarize and describe quantitative data, providing an overall picture of samples.
Examples of Summarized Measures: Mean, mode, median, variance, and standard deviation.
Measures of Central Tendency
Definition: Indicate the typical score in a sample.
Types:
Mean: Sum of all scores divided by the number of observations.
Median: The middle score when ordered from lowest to highest.
Mode: The most frequently occurring score.
Quartiles: Data division into four equal parts.
Measures of Dispersion/Variation
Purpose: Indicate how variable scores are in distribution.
Types:
Range: Difference between the highest and lowest scores.
Variance: Average squared deviation of scores from the mean.
Standard Deviation: Square root of the variance; it reflects variability of scores around the mean.
Implications of Descriptive Statistics
Allow for educated guesses about population trends based on summarized data.
Cannot definitively indicate exact circumstances within the population.
Inferential Statistics
Overview
Techniques for estimating population attributes based on sample data.
Assumption: Well-selected samples represent the population.
Key Concepts
Sample Statistic: Estimate computed from a sample.
Population Parameter: Estimate derived from entire population, typically denoted by Greek letters (e.g., $\mu$ for mean).
Sample Statistics: Denoted by Latin letters (e.g., $\bar{x}$ for sample mean, $s$ for sample standard deviation).
Generalization from Sample to Population
Inferences can be made about population parameters using sample statistics.
Conceptual Visuals
Illustration showing multiple samples taken from a population (e.g., faces).
Variables
Definition: Characteristics capable of taking various values.
Types:
Continuous Variables: Numeric with infinite values (e.g., time).
Discrete Variables: Numeric with countable values (e.g., number of students).
Categorical Variables: Group data into finite categories (e.g., gender).
Measurement Scales
Properties
Measurement Scale Properties:
Identity: Numbers assigned for identification, not for mathematical operations (e.g., 1 = male, 2 = female).
Magnitude: Ordered relationship among values; can compare instances (higher, lower).
Equal Intervals: Uniform distance between points on a scale (e.g., temperature).
Absolute Zero Point: Indicates absence of an attribute being measured (e.g., 0 siblings).
Types of Measurement Scales
Ratio Scale: Highest level; all four properties present (e.g., height, weight).
Interval Scale: Lacks absolute zero; measures on a continuum (e.g., temperature in Celsius).
Ordinal Scale: Orders distinct categories without magnitude (e.g., satisfaction level).
Nominal Scale: Classifies into distinct categories without order (e.g., gender).
Exercises on Measurement Scales
Example Situations
GRE Scores - Continuous interval scale.
Children classified by reading level - Ordinal scale.
PTSD symptom survey - Nominal scale.
Student hall preferences - Nominal scale.
Statistical Testing
Types of Tests by Measurement Scale
Scale -> Tests:
Ratio: Parametric tests (e.g., t-test, F-test).
Interval: Non-parametric tests (e.g., Mann-Whitney U).
Ordinal: Non-parametric tests (e.g., Wilcoxon).
Nominal: Non-parametric tests (e.g., Chi-Square).
Summation Notations
Definitions
Summation Symbol (Σ): Used to indicate sum of a set of values.
Sum of a Set: Example with numbers: $2, 3, 5, 7, 11$ with $ ext{x}_i$ notation.
Exercises
Sum of Squares (ΣX²): Squaring individual numbers and summing.
Square of the Sum (ΣX)²: Adding values and squaring resultant sum.
Product Sums (ΣXY): Determining sum of products of two variables.
Variability Measures
Mean Calculation
Calculate the mean: Sum divided by the number of observations:
\text{Mean} = \frac{\text{Sum of observations}}{N}
Standard Deviation and Variance Calculations
Standard Deviation: Measure of dispersion from mean. Use variance to compute:
Variance formula for population and sample calculations:
\sigma^2 = \frac{\Sigma(X - \mu)^2}{N}
s^2 = \frac{\Sigma(X - \bar{x})^2}{n - 1}
Calculate variability for individual scores: Squaring differences from mean, summing results
Example Calculations
Compute standard deviation from score set (e.g., 2, 4, 6, 8, 10, 12) using defined formulae.
Conclusion
Mastery of descriptive and inferential statistics is critical for effective data analysis in psychological research. Individual performance on assessments will demonstrate understanding of these fundamental statistical concepts.