do now: on your do now sheet in the tuesday box: what is a common diagram psychologists use to...

DO NOW: On your DO NOW sheet in the Tuesday

box: What is a common diagram psychologists

use to describe data? Why can this graph be misleading?

Central Tendency, Variation, and Generalization

AP PsychologyMs. Desgrosellier

10.6.2009

Objectives: SWBAT describe three measures of central

tendency, and tell which is most affected by extreme scores.

SWBAT describe two measures of variation.

SWBAT identify three principles for making generalizations from samples.

Measures of Central Tendency Mode: the most frequently occurring score

or scores Organize data in order, by grouping the

same number together Example: Find the mode: 5, 3, 4, 5, 7, 5, 1,

9, 5

Measures of Central Tendency Mean: the most commonly reported

measure, also known as the arithmetic average

Total up the scores and divide by the total number of scores

Example: Find the mean: 5, 2, 9, 6, 3, 5

Measures of Central Tendency Median: the midpoint, or the 50th percentile The middle score; half the points are above it and

half are below it Arrange the scores from highest to lowest and the

median number is the one in the middle If you have an even number of data points, you

should find the mean of the two middle scores Example: find the median: 8, 3, 5, 7, 1, 3, 6

Skewed Data

Skewed Data The mean is greatly affected by extreme

scores Remember: always note which measure of

central tendency is reported. Then, if it is a mean, consider whether or not a few atypical scores could be distorting it.

Measures of Variation Variation of data: how similar or diverse the

scores are. Averages from data with low variability are more

reliable than averages based on scores with high variability

E.g. Soccer player who scores 2-4 goals a game. We would by more confident saying he would score 3 goals a game than if his goal count varied from 0 – 10

Measures of Variation Range: the gap between the lowest and

highest scores Only provides a rough estimate of variation

because a couple of extreme scores will create a deceptively large range

Measures of Variation Find the range of this data set: Chris took 7 math tests in one quarter. What is

the range of his test scores? 89, 73, 84, 91, 87, 77, 94

Ordering the test scores from least to greatest, we get: 73, 77, 84, 87, 89, 91, 94

highest - lowest = 94 - 73 = 21 Answer: The range of these test scores is 21

points.

Measures of Variation Standard deviation: a computed measure

of how much scores vary around the mean score

A better gauge of how scores are spread out because it uses information from each score

Measures of Variation

Making Inferences Data are “noisy” Average scores could vary because of

random fluctuation or chance in the sample How can we infer that an observed

difference accurately estimates the true difference?

Three Principles: 1. Representative samples are better than

biased samples Remember to keep in mind what population a

study has sampled All men or all women? One education or

income level? All young or all older? Etc.

Three Principles: 2. Less-variable observations are more

reliable than those that are more variable An average is more reliable when it

comes from scores with low variability Why? Extreme scores greatly affect the

average!

Three Principles: 3. More cases are better than fewer

Averages based on many cases are more reliable (less variable) than averages based on only a few cases.

E.g. If you visit two colleges and find two professors at one school are better than two at the other, you could say that the first university is clearly better. However, you only met two of the hundred faculty members.

Three Principles: Remember: don’t be overly impressed by

a few stories. Generalizability based on a few unrepresentative cases is unreliable.