1. Question: formulate questions that
explore whether or not a relationship exists in a real-world context. The question
needs to be clearly stated and based on collectable data. Not all questions can be
answered!

"Data as they are" questions can be answered:

If the U.S. Presidential elections were held today, what percent of Americans would
vote for Al Gore as president?

"What-if questions under replicable circumstances" can be answered:

Among all American school children age 6 to 12, would giving Vitamin C prevent colds?
(You can imagine testing this out on more and more children.)

Data from nonreplicable events, in general, can NOT be answered!

"How many U.S. troops be in Bosnia if the American Revoluation had failed?"

- data acquisition (survey, observation, self-report, examination of official
records)

- design of evaluation (pretest, post-test only)^{ 1}

- data collection schedule (fixed intervals between pre and posttest, at the
beginning and end of participation, after each session,...)^{ 2}

3. Displaying Data: select, use, and defend appropriate
methods of displaying data

display data by hand or by computer in a variety of ways, including circle graphs

4. Conclusions: present analyses and conclusions based on
displayed data. Conclusions are clearly stated and answer the question based on
available data.

read and interpret graphs that are provided

determine and use the most appropriate measure of central tendency in a given context
(mode, median, mean)

describe the variability of given data using range or box-and-whisker plots (range,
extremes, gaps, clusters, and quartiles)

analyse sets of data by comparing different measures of central tendency (mode, median,
mean)

How much household garbage is produced in our homes? In the average home in
Canada?

Design a questionnaire to investigate this problem. Justify your questions. Explain how
you will carry out this survey. Could you collect data via computer networking? How can
you use a computer to record, organize, and display your data? How can you display your
data to have the most impact?

appropriate language - surveys need to be delivered in the appropriate
language and reports need to be written in the same language. One must also use
language that will not offend persons providing the data. Some suggestions:

USE: disabled people / people with disabilities / people
with impairments
DO NOT USE: the disabled / the handicapped / invalid (means not valid)

USE: blind people / people who are blind / people with a visual impairment
DO NOT USE: the blind

USE: deaf people / people who are deaf / hearing impairment / hard of hearing
DO NOT USE: the deaf

USE: a person who is unable to speak, having a speech impairment / deaf without speech /
profoundly deaf.
DO NOT USE: dumb / mute

USE: person with a speech impairment
DO NOT USE: speech problem / can't talk properly

USE: wheelchair user
DO NOT USE: wheelchair-bound / confined to a wheelchair

USE: a person who has epilepsy
DO NOT USE: an epileptic

USE: a person with spina bifida
DO NOT USE: spina bifida case

Some groups and individuals may express a preference.

Researcher qualifications - - competence, perspective and character of
researcher

Vulnerable populations - - dissimilarity with researcher may expose individuals to risk
because of researcher’s lack of knowledge. Good approach to have members of the group
help design the study.

Conflict of interest - - choice of data collection instrument or intervention has
financial implications for the researcher.

Neglecting important topics - - -generalizing findings too far, ignoring ethnic
differences, ignoring areas where research on the topic is relevant and needed.

Subjects have a right to privacy and confidentiality. They should be told
who has access to the data. Every effort should be made to prohibit unauthorized access to
the data; a good rule - minimize the number of individuals who know the identity of the
participants. In general, research data do not have privileged status. Confidentiality
should be maintained in publications/presentations (do not use the names of individuals,
locations, etc.). There are some situations when the participants may want to be
identified. Ways to enhance confidentiality: ask for anonymous information, use third
parties to select sample and collect data, use a detachable identifier, have subjects make
up a code when matched data is required, dispose of sensitive data after study is
completed.

cultural sensitivity - considerations include race
(white, black, Asian, Native American, Eskimo, Pacific Islander....), ethnicity
(Hispanic, Italian, Mexican, Cuban, Puerto Rican, Central/South American, ...), language
(English, French, Chinese, Italilan, ...), and religion (Buddhism, Islam,
Judaism, Sikhism, Alternative Spirituality, Christianity, Canadian First Nations:
Religions ...)

consistency - surveys may be administered in many countries. Care
must be taken to ensure the survey is the same in each case. Different versions of
the survey will make data analysis much more difficult.

statistics - systematic collection and
arrangement of large numbers of observations and quantities of numerical observations, and
with ways of drawing useful conclusions from such data

population - eligible people for a data collection
investigation

sample - part of a population selected so as to give
information about the population as a whole

Biased Samples

Unbiased Samples

convenience sampling - quick and easy way
to obtain data, but not everyone in the population has an equal chance of being selected

systematic sampling - every nth member of the
population is sampled

self selective sampling - population
provides information by volunteering their opinions

simple random sampling - the sample is chosen randomly
from the population

cluster sampling - a particular segment of
the population is sampled

stratified random sampling - the population is divided
into groups (strata)

frequency - the number of times an event occurs

frequency table - a table showing a set of values of a variable and
the number of times each value occurs

The Independent variable is always assigned to the X-AXIS.

What is the independent variable? The independent
variable does not relying on an other variable. The values of the independent
variable can be chosen freely.

There are
three types of relationships between variables:

linear

non-linear (curved-line or other pattern)

no relationship at all

axis - a line drawn through the center of a figure

scale - a sequence of marks, usually along a line, used
in making measurements

proportional - one variable is proportional to another if
the ration of corresponding values remains constant

interpolation - to estimate a value by following a
pattern and staying within the values already known

extrapolation - to estimate a value by following a
pattern and going beyond the values already known

discreet variable - have measurements that are distinct,
periodic, and unconnected between data points (e.g. the distance an athlete throws a
discus)

continuous variable - measurements are uninterrupted and connected
between data points (e.g. growth of a plant)

scatter plot - a graph that relates data from two
different sets

line of best fit (trend line) - A line on a scatter plot
which can be drawn near the points to more clearly show the trend between two sets of data

trend - relationship between two sets of data. The trend
will show a positive correlation, a negative correlation, or no correlation.

positive correlation -both sets of data increase together

negative correlation -one set of data decreases as the
other set of data increases

no correlation - the two data sets are not related.

weak correlation - when the data is not clustered along
an obvious line

strong correlation - when the data is clustered along an
obvious line ( can be positive or negative)

lower extreme - minimum data value

upper extreme - maximum data value

range - upper extreme minus lower extreme

cluster - a particular segment of the population

gaps - spaces in the data set without a segment of the
population

outlier - a point separted from the main body of the data

central tendency - point within the range about
which the rest of the data is considered balanced.
The three common measures of central tendency
are mean, median and mode.

lower quartile - separates the first 25% of the distribution from the
remaining 75%.

upper quartile - separates the first 75% of the distribution from the
remaining 25%.