Density Curves and Normal Distributions Study Notes

This section discusses the concepts of density curves and normal distributions in statistics, focusing on how they model quantitative data.

Exercise 39: Travel Time
- Prompt: Describe the distribution from the dotplot showing how long it usually takes students to travel to school.
Exercise 40: Left-Handedness
- Prompt: Create a graph for the responses showing how many students are right-handed (R), left-handed (L), or ambidextrous (A).
- Follow-up: Estimate the percentage of left-handed students in Canadian high school based on data from the Census At School survey.

Understand and use density curves to model the distribution of quantitative data.
Identify the relative locations of mean and median in a density curve.
Apply the empirical rule to estimate proportions and percentiles in a normal distribution.
Utilize tables or technology to find proportions in a normal distribution.
Determine if a distribution is approximately normal through visual and numerical evidence.

The recommended procedure for examining quantitative data includes:
1. Always plot your data: Create a graph such as a dotplot, stemplot, or histogram.
2. Investigate the overall pattern: Look for the shape, center, and variability, as well as outliers.
3. Calculate numerical summaries to describe the center and variability.
Density curves may be employed as a simplified model in cases where there's a regular distribution pattern.

Definition of a Density Curve: A smooth curve that models the distribution of a quantitative variable.
- Characteristics:
  - Always lies on or above the horizontal axis.
  - The total area under the curve equals 1.
Example: Selena's travel time to work modeled with a density curve to estimate the proportion of days she arrives in less than 4 minutes; approximated area is calculated based on the area under the curve.
An area of 66.7% indicates that Selena will arrive in less than 4 minutes on approximately 66.7% of days.

Area Calculation: For example, if the base is 2 and height is 1/3:
- Area = Base × Height = 2 × 1/3 = 2/3 = 0.667 = 66.7%.
For the example, 669 out of 1000 days mean a proportion of 66.9%.

Shapes of Density Curves: Can be roughly symmetric, skewed right, or skewed left.
Mean: The balance point of the curve.
Median: The point dividing the area under the curve in half.

Mean of a Density Curve: The point where the curve balances if made of solid material (μ).
Median of a Density Curve: The equal-areas point dividing the area into two equal parts.
In symmetric curves, mean = median. In skewed curves, mean is typically pulled in the direction of the skew (right or left).

Definition of Normal Distribution: A special density curve that is symmetric, single-peaked, and bell-shaped.
- Parameters:
  - Mean (μ): The center.
  - Standard Deviation (σ): Indicates variability (width) of the distribution.
Example: ITBS vocabulary scores among seventh graders in Gary, Indiana, which can be described as approximately normal.
Empirical rule applies (68-95-99.7 rule):
1. 68% within 1 standard deviation.
2. 95% within 2 standard deviations.
3. 99.7% within 3 standard deviations.

Using the empirical rule to assess the rarity of a particular z-score or observation.
Example: Observing scores below a certain z-score indicates how unusual those scores are in context of the normal distribution of student scores.

Standardizing Values: Use the formula $z = \frac{(x - \mu)}{\sigma}$ for converting to a standard normal distribution (mean = 0, standard deviation = 1).
- Areas left for each z-score can be found through a z-table or technology.
Methods: Can calculate using the standard normal distribution (z-score) or directly from the original normal distribution parameters.
Example: Using the proportion of vocabulary scores below the sixth-grade level, the calculations show a certain percentage based on a standardized z-score and corresponding area derived from the Z-table or a calculator.

Density curves provide useful models for analyzing quantitative data distributions. Normal distributions reflect many real-world datasets closely and are critical in statistical inferences. Understanding their properties assists in statistics and probability analysis.