Textbook Notes (280,000)
CA (170,000)
SFU (6,000)
PSYC (1,000)
Chapter 2

PSYC 210 Chapter Notes - Chapter 2: Random Number Table, Exclusive Or, Dependent And Independent Variables

Course Code
PSYC 210
Russell Day

This preview shows page 1. to view the full 5 pages of the document.
Chapter 2
Basic Concepts
In statistics everything we do begins with the measurement of whatever it is we
want to study
Measurement = the assignment of numbers to objects
Example  we use paw-lick latency as a measure of pain sensitivity, we are
measuring sensitivity by assigning a number (a time) to an object (a mouse) to
assess the sensitivity of that mouse
Black depression inventory is the most popular measure of depression
Depending on what we are measuring and how we measure it, the number we
obtain may have different properties and those different properties of numbers
often are discussed under the specific topic of scales of measurements
2.1 scales of measurement
Scales of measurement = characteristics of relations among numbers assigned to
Realize that statistics as a subject is a set of facts put together with a variety of
interpretations and opinions
S. S. Stevens defined 4 types of scales: nominal, ordinal, interval and ratio
Nominal scales
Nominal scales = numbers used to only distinguish among objects
Not really a scale at all, because it doesn’t scale items along any dimension but
rather label items
Frequently these numbers have no meaning whatsoever other than as convenient
labels that distinguish the players or their positions from one another
Gender is a nominal scale (1 = male and 2 = female)
Could also use letters or pictures of animals
Nominal scales generally are used for the purpose of classification  categorical
Quantitative data are measured on the other 3 types of scales
Ordinal scales
The simplest true scale is an ordinal scale = numbers used only to place objects
in order
Example  the class standings of people graduating from high school OR Homles
and Rahe’s scale of life stress
These 2 examples of ordinal scales differ in the numbers that are assigned. In the
first case we assigned the ranks 1,2,3 … whereas in the 2nd case the scores
represented the number of changes rather than ranks
No information is given about the differences between points on the scales
Interval scales
You're Reading a Preview

Unlock to view full version

Only page 1 are available for preview. Some parts have been intentionally blurred.

Interval scales = scale on which equal intervals between objects represent an
equal difference – differences are meaningful
Example  Fahrenheit scale of temperature in which a 10-point difference has the
same meaning anywhere along the scale
You can find the meaning anywhere along the scale
However we still don’t have the ability to speak meaningfully about ratios  no
true 0 point
Example  the measurement of pain sensitivity is a good example of something
that is probably measured on an interval scale
Ratio scales
Ratio scales = a scale with a true 0 point  ratios are meaningful
A 0 must be a true 0 point and not an arbitrary one such as 0°F or 0°C
A true 0 point is the point that corresponds to the absence of the thing being
Example  common physical ones of length, volume, time, etc.
Important fact: it is the underlying variable being measured not the numbers
themselves that define the scale
Because there is usually no unanimous agreement concerning the scale of
measurement employed it is up to you to make the best decision about the nature
of the data
The role of measurement scales
There is a difference in opinion as to the importance assigned to scales of
Argument for the example of room temperature  wherein the scale (interval or
ordinal) depended on whether we were interested in measuring some physical
attribute of temperature or its effects on people
In other words we have an interval scale of the physical units but no more than an
ordinal scale for comfort
Because statistical tests use numbers without considering the objects or events we
can carry out standard mathematical operations regardless of the nature of the
underlying scale
The problem comes when its time to interpret the results of some form of
statistical manipulation  ask if there are meaningful statistical relationships
Now dealing with a methodological issue
Statistical tests can be applies only to the numbers we obtain and the validity of
the statements about the objects or events depends on our knowledge of the
object or event not to the scale of measurement
Do our best to ensure that our measures bear as close relationships as possible to
what we want to measure, but our results are ultimately only the numbers we
obtain and our faith in the relationship between those numbers and the underlying
objects or events
You're Reading a Preview

Unlock to view full version