C-PBC2: PSYCHOLOGICAL STATISTICS

Chapter 1: Introduction to Psychological Statistics

What are statistics? TYPES OF VARIABLES

 Statistics include numerical facts and figures. For
instance: A. Independent variable – It is a variable that
 Men are at least 10 times more likely than stands alone and isn't changed by the other
women to commit murder. variables you are trying to measure.
 One in every 8 South Africans is HIV
positive. B. Dependent variable – the behavior or mental
 By the year 2020, there will be 15 people process that is being measured; changes as a
aged 65 and over for every new baby born. result of exposure to IV.

Why do we study statistics? The independent variable is the cause, and

 Without statistics, we would be unable to the dependent variable is the effect.
interpret the massive amounts of information
contained in data. Example:
 Statistics provides tools that you need in order 1. If students study for a quiz before going to
to react intelligently to information you hear or sleep, rather than in the morning, then they
read. will get higher scores on the quiz.
o What is the independent variable?
Statistics o What is the dependent variable?
 refers to a range of techniques and procedures
for analyzing, interpreting, displaying, and 2. A psychologist injects several lab animals
making decisions based on data. with male hormones and compares their
 It is the language of science and data. subsequent aggressive behavior to control
 Two main statistical methods are used in data animals.
analysis: o What is the independent variable?
 Descriptive statistics – describes data; they o What is the dependent variable?
do not involve generalizing beyond the data
at hand. 3. Can blueberries slow down aging? A study
 Inferential statistics – allows you to make indicates that antioxidants found in
predictions (“inferences”) from that data blueberries may slow down the process of
aging. In this study, 19-month-old rats
TERMS TO REMEMBER: (equivalent to 60-year-old humans) were
fed either their standard diet or a diet
 Data – refers to the information that has been supplemented by either blueberry,
collected from an experiment, a survey, an strawberry, or spinach powder. After eight
historical record, etc.; represent the measured weeks, the rats were given memory and
value of variables motor skills tests. Although all
 Data – plural supplemented rats showed improvement,
 Datum – singular those supplemented with blueberry powder
showed the most notable improvement.
 Variable – simply a characteristic or feature of o What is the independent variable?
the thing we are interested in understanding. o What is the dependent variable?
In psychology, we are interested in people, so we
might get a group of people together and
measure their levels of stress (one variable),
anxiety (a second variable), and their physical
health (a third variable).
 QUALITATIVE AND QUANTITATIVE VARIABLES C. Interval scales – applies to data that can be
arranged in order. Also, differences between
A. Qualitative variables data values are meaningful, but they do not
 are those that express a qualitative attribute (ex. have a true zero point.
eye color).
 The values of a qualitative variable do not imply D. Ratio scale – numerical data that has equal
a numerical ordering. distances between adjacent values and a
 sometimes referred to as categorical variables. meaningful zero

B. Quantitative variables WHOM TO COLLECT THE DATA?

 are those variables that are measured in terms
of numbers (ex. height) Population:
 a set which includes all measurements of
DISCRETE AND CONTINUOUS VARIABLES interest to the researcher;
 the collection of all people who have some
A. Discrete variables – value is obtained by characteristic in common
counting  the entire group that you want to draw
Example: number of children in a household – conclusions about
three children or six children, but not 4.53
children. Sample:
 A subset of the population
B. Continuous variables – value is obtained by  the specific group that you will collect data from
measuring
Example: time to respond to a question – WHEN TO COLLECT DATA FROM:
1.64237123922121 seconds
Population
HOW TO COLLECT DATA?  when your research question requires
 when you have access to data from every
 Different types are measured differently. member of the population
 Time taken to respond to a stimulus –  when whole population is small, accessible and
stopwatch cooperative
 Attitude towards a political candidate –
rating scale (“very favorable,” “somewhat Sample
favorable,” etc.)  when your population is large, geographically
 Favorite color – ask the color-word (“red”) dispersed, or difficult to contact
 Memory – number of items correctly
recalled Does it use SAMPLE or POPULATION?

LEVELS OF MEASUREMENT 1. You want to study political attitudes of

(Dependent variable) undergraduate students in the USA. There are
900,000 undergraduate students in the USA
A. Nominal scales – applies to data that consist of 2. A high school administrator wants to analyze the
names, labels, or categories. There are no final exam scores of graduating seniors to see if
implies criteria by which the data can be there is a trend. There are 145 graduating
ordered from smallest to largest. seniors in their school.
3. You have been hired by the National Election
B. Ordinal scales – applies to data that can be Commission to examine how the American
arranged in order. However, differences people feel about the fairness of the voting
between data values either cannot be procedures in the U.S. Who will you ask?
determined or are meaningless.
SAMPLING BIAS sampling has a greater risk of producing a biased
 occurs when some members of a population are sample than does probability sampling.
systematically more likely to be selected in a
sample than others. TYPES OF SAMPLING
 Examples:
 A substitute teacher wants to know how PROBABILITY SAMPLING (Every member of the
students in the class did on their last test. population has a known chance of being selected)
The teacher asks the 10 students sitting in
the front row to state their latest test score. 1. Simple Random Sampling
He concludes from their report that the  Each individual in the population has an equal
class did extremely well. chance of being selected.
 A PE teacher is interested in how many  Equality means that no individual is more likely
push-ups the average college freshmen at to be chosen than another.
his university can do. Eight volunteers from  A second requirement that is sometimes added
the freshman class step forward. After is that each selection is independent of the
observing their performance, the PE others.
teacher concludes that college freshmen  The process of simple random sampling consists
can do an average of 16 push-ups in a row of the following steps:
without stopping. 1. Clearly define the population
2. List all the members
HOW TO REDUCE BIAS? 3. Use a random process to select
 sample should be RANDOMLY selected and
REPRESENTATIVE of the population 2. Systematic Sampling
 SAMPLING METHODS – the process by which  Systematic sampling begins by listing all the
inference is made to the whole by examining a individuals in the population, then randomly
part picking a starting point on the list.
 The sample is then obtained by moving down
SAMPLING TECHNIQUES the list, selecting every nth name.
 The process of selecting individuals for a study is
called sampling. 3. Stratified Random Sampling
 Sampling methods fall into two basic categories:  Used when a researcher’s goal for a
probability sampling and nonprobability representative sample is to ensure that each of
sampling. the different subgroups is adequately
 In probability sampling, the odds of selecting a represented.
particular individual are known and can be  To obtain this kind of sample, we first identify
calculated. Probability sampling requires the specific subgroups (or strata) to be included
extensive knowledge of the population. It is in the sample.
more complex, more time-consuming and  Then we select equal-sized random samples
usually more costly than non-probability from each of the pre-identified subgroups, using
sampling. the same steps as in simple random sampling.
 In nonprobability sampling, researcher selects  Finally, we combine the subgroup samples into
samples based on the subjective judgment of one overall sample.
the researcher rather than random selection. It
is a less stringent method. This sample selection 4. Proportionate Stratified Random
method takes into consideration the availability  Used when the researchers try to improve the
of participants in the study. It involves selecting correspondence between a sample and a
a convenient and accessible sample using population by deliberately ensuring that the
whatever eligible respondents are available to composition of the sample matches the
the researcher. In general, nonprobability composition of the population.
 As with a stratified sample, we begin by
identifying a set of subgroups or segments in the
population. 4. Snowball Sampling
 Next, we determine what proportion of the  This type of sampling is a nonprobability
population corresponds to each subgroup. method which involves random selection of
 Finally, a sample is obtained such that the subjects.
proportions in the sample exactly match the  This method is most effective when the
proportions in the overall population. members of the population are not easily
accessible
5. Cluster Sampling  Steps:
 Used when the individuals in the population are 1. Identify potential subjects in the
already clustered in pre-existing groups, and a population. Often, only one or two subjects
researcher can randomly select groups instead can be found initially.
of selecting individuals. 2. Ask those subjects to recruit other people
 Used whenever well-defined clusters exist (and then ask those people to recruit.
within the population of interest. Participants should be made aware that
they do not have to provide any other
NON-PROBABILITY SAMPLING (not all members of names).
the population have an equal chance of
participating in the study)

1. Convenience Sampling
 The researchers simply use as participants those
individuals who are easy to get.
 People are selected on the basis of their
availability and willingness to respond.
 Convenience sampling is considered a weak
form of sampling because it does not require
knowledge of the population and does not use a
random process for selection.
 The researcher exercises very little control over
the representativeness of the sample and,
therefore, there is a strong possibility that the
obtained sample is biased.

2. Quota Sampling
 involves deciding on a fixed number of subjects
with particular characteristics.

3. Judgment Sampling
 also called purposive sampling
 this method relies on the judgement of the
researcher when it comes to selecting the units
that are to be studied.
 Usually, the sample being investigated is quite
small, especially when compared with
probability sampling techniques.
 The method uses an intentional selection of
informants based on their ability to elucidate a
specific theme, concept, or phenomenon.