Psy 2116

Basics of Inferential Statistics

Conceptual Overview
- Utilizes behaviors of samples to predict population behaviors.
- Predictions hinge on calculated probabilities, estimating likelihood of accuracy.
- Influences on likelihood include research design and statistical methods used.

Independent Variables (IV):
- Those that are manipulated in an experiment.
Dependent Variables (DV):
- Measured factors that depend on the IV.
Extraneous Variables:
- Variables that should be controlled to avoid affecting the DV.
Scales of Measurement:
- Nominal: categorical, no order (e.g., gender).
- Ordinal: categorical, with an order (e.g., rankings).
- Interval: numerical, with no true zero (e.g., temperature).
- Ratio: numerical, with a true zero (e.g., weight).

Example 1: LH vs. RH Texting Speed
- IV: Handedness (left-handed vs. right-handed).
- DV: Time taken to send a message.
- Levels of IV: 2 (LH and RH).
Example 2: Panic Attack Treatment Methods
- IV: Type of therapy (individual, online video, online chat).
- DV: Number of panic attacks.
- Levels of IV: 3 (different therapy types).
Example 3: Learning Speed of Rats vs. Mice
- IV: Type of animal (rat or mouse).
- DV: Time taken to complete a maze.
- Levels of IV: 2 (rats and mice).
Example 4: Drinks Consumed Based on Extraversion
- IV: Extraversion levels (high, moderate, low).
- DV: Number of drinks consumed.
- Levels of IV: 3 (high, moderate, low).

Types of Statistics:
- Descriptive Statistics: An overview including center (mean, median), spread (range, variance), and frequency.
Figures:
- Common visual representations include histograms, bar graphs, and line graphs highlighting shape, spread, and error bars.

Concept:
- A summary showing the frequency of each value (or range of values) of a variable.
Example Data:
- Range bins (e.g., 35-39, 40-44) are used to show how often scores fall into each range.

Histogram:
- A graphical representation of frequency distribution.
Frequency Polygon:
- Connects points on a graph representing frequencies for easier visualization.
Critical Concept:
- Higher points along the curve indicate more likely scores.

Critical Concept:
- Statistics try to determine if variability in behavior is due to experimental manipulation or individual differences (random error).
- Questions if differences in groups are results of the manipulation or random variability among individuals.

Average Deviations:
- Differences from the mean showing individual score deviations.
- Mathematical summary where total deviations sum to zero doesn’t provide useful information, leading instead to squared deviations for analysis.

Variance:
- Average squared deviation from the mean provides a non-zero sum, accounting for variability.
Standard Deviation:
- The positive square root of variance indicating how much scores differ from the mean on average.

Use definitional formulae for clarity but note inefficiencies.
Computational Formulas:
- Provide efficient calculations yielding the same outcomes as definitional methods.

Area Under the Normal Curve:
- The area represents the percentage of data represented, with 100% of data under the curve.
Symmetrical Standard Normal Distribution:
- Unimodal and bell-shaped, with critical areas between standard deviations (e.g., u=0, probabilities of .34, .14, etc.).
Z-scores:
- Sign indicates position relative to mean (positive above mean, negative below).
- Utilizes standard deviations for direct comparison across varying scales.

Example comparing scores on two different exams, considering averages and standard deviations to show relative performance.
Questions exploring which score reflects better performance contextualized in distribution differences.

Read chapters and solve recommended questions to reinforce materials learned in the lectures. Review notes and post questions for clarification.