Introduction to Statistics
Introduction to Statistics
Welcome to the introduction chapter to statistics.
Purpose: To simplify the calculations and demystify statistics.
Instructor will stop video but expects students to engage by listening to the voice-over.
Students are encouraged to pause slides, take notes, and perform calculations.
Basic Mathematical Operations
Basic math operations required for statistics:
Addition
Subtraction
Multiplication
Squaring
Square roots
Notes:
While numbers may increase in size or include decimals, the operations remain the same.
Working familiarity with these operations is essential for success in statistics.
Understanding Psychology
Core Definition: Psychology primarily studies behavior rather than just mind, thought, or feelings.
Rationale for Studying Behavior:
Behavior is observable and measurable.
Thoughts and memories are indirectly studied through associated behaviors.
Introduction to Statistics
Definition of Statistics:
Statistics refers to both:
A process to organize, summarize, interpret, and communicate data.
A set of calculations for deriving measures of behavior.
Importance of Statistics:
Facilitates understanding of large datasets and communicates findings effectively.
Allows researchers to answer specific research questions.
Concepts of Population and Sample
Population:
Entire collection of individuals or items being studied.
Sample:
Small, representative subset of the population selected, ideally through random methods.
Rationale for Using Samples:
Population data may be too large or unavailable for manageable analysis.
Conclusions about the population are often drawn from sample analysis.
Understanding Variables
Variable:
A characteristic or attribute that can take on different values.
Types of variables:
Independent Variable (IV):
The variable that is manipulated or tested.
Dependent Variable (DV):
The outcome variable that is measured.
Distinction aid:
Remember IV manipulates and DV measures; the DV depends on the IV.
Understanding Data
Data:
A collection of measurements and observations; the scores used to understand group characteristics.
Data can be collected from either a population or a sample, with a tendency towards samples in practice.
Parameters and Statistics
Parameters:
Measures summarizing characteristics of a population.
Statistics:
Measures summarizing characteristics of a sample.
Connections:
Remember: Parameters relate to populations (P to P), and statistics relate to samples (S to S).
Types of Statistics
Descriptive Statistics:
Help describe, organize, summarize, and simplify scores, e.g., mean, median, mode, correlations.
Data visualization: Tables and graphs.
Inferential Statistics:
Allow for inferences about populations based on sample data.
Evaluate cause-effect relationships derived from the IV's impact on the DV.
Sampling Error
Sampling Error:
Variability or differences observed when comparing sample results to population values.
Cases discussed:
The mean SAT score example and sample results disparity.
Understanding Relationship between Measures
Examines relationships like attendance and final grades.
Observational data show correlation but not causation; attendance may relate to grades without implying causation.
Correlation:
Measures the degree of association between two variables but does not indicate direct cause-effect relationships.
Non-experimental research.
Experimental Studies
Definition of True Experimental Study:
Involves manipulating the independent variable (IV) and measuring its effect on the dependent measure (DV).
Groups defined:
Experimental Group:
Exposed to the manipulated IV.
Control Group:
Receives nothing or a placebo level of treatment.
Example:
A diet treatment study examining weight loss percentage with a control and experimental group.
Importance of Manipulation in Research
Manipulation:
Altering the values of the IV to observe its effect on the DV.
Outlining the significance of control aspects during manipulation to avoid confounding factors in the outcome.
Control Techniques
Random Assignment:
Participants randomly assigned to different experimental groups to avoid systematic bias.
Matching:
Ensures groups are similar in specific attributes (like age).
Holding Constant:
Controlling for attributes that might confound results by studying only participants within limited parameters (e.g., same age).
Control Groups and Conditions
Methodologies in study design:
Between Groups Design:
Observes differences between groups exposed to different IV conditions.
Control Condition:
Measures the same group before and after exposure to the IV to see changes.
Non-Experimental Designs
Types of Non-Experimental Designs:
Correlational Designs:
Examine relationships without manipulation of IV.
Quasi-Experimental Designs:
Closely resemble experimental studies but lack random assignment (e.g., age differences).
Frequency Data and Chi-Square Tests
Introduces frequency data analysis via count methodologies, leading to chi-square testing towards the semester's end.
Constructs and Operational Definitions
Constructs:
Measurement of abstract aspects of behavior indirectly, e.g., intelligence, emotion.
Operational Definitions:
Step-by-step descriptions of how constructs will be measured and quantified in research.
Statistical Notation
Use of letters and symbols:
Scores denoted with uppercase letters (X, Y).
Number of scores represented by letters (N for population, n for sample).
Summation:
Indicated by the uppercase Greek letter sigma (Σ), showing the addition of scores.
Order of Operations
PEMDAS:
Parentheses
Exponents
Multiplication/Division (left to right)
Addition/Subtraction (left to right)
Importance of summation noted, typically before addition/subtraction.
Properties of Variables
Discrete Variables:
Countable, whole numbers without fractional parts.
Continuous Variables:
Can take on an infinite number of values within a range.
Dichotomous Variables:
Only two values exist; classified as discrete.
Qualitative vs. Quantitative Variables:
Qualitative: Changes in type or kind, no numeric value.
Quantitative: Changes in numeric value or amount.
Scales of Measurement
Nominal:
Least precise, categorizes by name without numeric value.
Ordinal:
Ranks items without establishing equal increments between ranks.
Interval:
Numeric scales with equal intervals but lacking a true zero.
Ratio:
Numeric scales with equal increments and an absolute zero value, permitting meaningful comparisons.
Real vs. Apparent Limits
Apparent Limit:
The measured value as shown on a device (e.g., a ruler).
Real Limit:
The true range of the measured value accounting for the precision of measurement (e.g., half a unit above and below).
Conclusion
Encouragement to pause, review materials, and engage with exercises.
Reminder of availability for questions in subsequent classes as students progress into practical assignments using MindTap.
End of the session with gratitude expressed for attention and participation.