Standard Deviation as a Ruler and the Normal Model: Study Notes

Standard Deviation as a Ruler and the Normal Model

Introduction

The standard deviation is a fundamental measure of spread in statistics, and the normal model is a key theoretical distribution for quantitative data. These concepts allow statisticians to compare values, standardize data, and make probabilistic inferences about populations.

Standardization and Z-Scores

What is Standardization?

• Standardization is the process of converting data to a common scale, typically by expressing values in terms of their distance from the mean, measured in standard deviations.

• This allows for comparison across different units or distributions.

Calculating Z-Scores

• A z-score measures how many standard deviations a data point is from the mean.

• Formula for z-score: $z = \frac{y - \bar{y}}{s}$ where $y$ is the data value, $\bar{y}$ is the mean, and $s$ is the standard deviation.

• Z-scores allow for comparison of values from different distributions or units.

Benefits of Standardizing

• Enables comparison of values from different data sets or variables.

• Removes units, making data dimensionless and easier to interpret.

• Standardized values have been rescaled to the standard deviation unit.

Effects of Shifting and Scaling Data

Shifting Data

• Adding or subtracting a constant to all data points shifts the mean but does not affect the spread (standard deviation).

• Example: Subtracting recommended weight from actual weight shifts the histogram but does not change its shape.

Scaling Data

• Multiplying or dividing all data points by a constant changes both the mean and the spread.

• All measures of spread (variance, standard deviation, range) are multiplied by the same constant.

• Example: Converting weights from kilograms to pounds by multiplying by 2.2.

The Normal Model

Density Curves and the Normal Distribution

• A density curve is a smooth curve that models the frequency distribution of a quantitative variable.

• The Normal Model (or Normal Distribution) is symmetric, bell-shaped, and unimodal.

• Defined by two parameters: mean ($\mu$) and standard deviation ($\sigma$).

• Notation: $\mathcal{N}(\mu, \sigma)$

Properties of the Normal Model

• Symmetric about the mean.

• Mean, median, and mode are all equal.

• Spread determined by standard deviation ($\sigma$): larger $\sigma$ = wider curve.

• Empirical Rule (68-95-99.7 Rule):

  • 68% of data within 1 standard deviation of the mean

  • 95% within 2 standard deviations

  • 99.7% within 3 standard deviations

Checking for Normality

• Histograms: Look for symmetry and bell shape.

• Normal Probability Plots: Data points should fall close to a straight line if the data are normally distributed.

• Skewed or multimodal data are not well modeled by the normal distribution.

Working with Normal Models

Sketching a Normal Curve

• Draw a symmetric, bell-shaped curve centered at the mean.

• Mark points at $\mu$, $\mu \pm \sigma$, $\mu \pm 2\sigma$, etc.

• Indicate inflection points where the curve changes from curving downward to upward.

Normal Probability Plots

• Used to assess normality of data.

• If points deviate systematically from a straight line, data may be skewed or not normal.

• Right skew: points bend up and to the left; left skew: points bend down and to the right.

Percentiles and the Standard Normal Table

Finding Percentiles

• Convert data values to z-scores using $z = \frac{y - \bar{y}}{s}$.

• Use the standard normal table to find the area (percentile) below a given z-score.

• To find the percentile above a z-score, subtract the table value from 1.

Standard Normal Table

The standard normal table provides the cumulative area under the normal curve to the left of a given z-score. This area represents the percentile rank of the value.

z	Area to Left
0.0	0.5000
1.0	0.8413
2.0	0.9772
-1.0	0.1587
-2.0	0.0228

Summary: Key Points

• Standard deviation is a measure of spread and is used as a ruler for comparing data values.

• Z-scores standardize data, allowing for comparison across different distributions.

• The Normal Model is a theoretical distribution used to model symmetric, unimodal data.

• Percentiles and probabilities can be found using z-scores and the standard normal table.

Example Application

• Suppose a student scores 85 on a test with mean 75 and standard deviation 5. The z-score is: $z = \frac{85 - 75}{5} = 2$ From the standard normal table, the area to the left of z = 2 is 0.9772, so the student is at the 97.72 percentile.

Additional info: These notes expand on the original slides and handwritten content, providing full definitions, formulas, and context for the standard deviation as a ruler and the normal model, as covered in a college statistics course.