PYC3704 – PSYCHOLOGICAL RESEARCH

TOPIC 1 – QUANTITATIVE METHODS IN RESEARCH PSYCHOLOGY

Quantitative Research in Psychology:

 Psychology is a discipline that endeavours to collect information and develop theories about
human behaviour and mental processes
 All scientific knowledge begins with description of the phenomena being studied, based on
careful observation
o Knowledge based on observation of physical events is referred to as empirical
knowledge
o The next step in the scientific process is to go beyond the level of description by
attempting to develop explanations for the things we observe: we want to know not
only what the facts are, but also why they appear to be as they are
 In other words, we want to develop theories, which explain why things are as
they appear to be when we observe them
 Quantitative methods refer to situations where information (referred to as data) is available
as numbers, which are the consequences of measurements of some kind
o Statistics refer to the study of probabilities, which becomes relevant when we deal
with data that are imperfect or incomplete, data that contain measurement error
o An inference – a conclusion that follows from existing information, by generalising
from the specific information to the general type of phenomenon, where the
conclusion isn’t absolutely certain

Constructs as the Building Blocks of Theories:

Constructs:
 Psychologists try to develop explanations for human experiences and behaviour
o To do this, they often have to make use of abstract concepts that serve as
explanations for the behaviour they observe

Theories:
 Psychologists are interested to find out which constructs are important and how they work
together in a pattern, or what their interrelationships are
 Constructs are the building blocks of theory
 In science, a theory is a framework for facts
 Constructs and their interrelations are used in this way to develop theoretical explanations
of why people behave in certain ways in certain contexts, or why mental phenomena
appear to be as they are

How Constructs are Made Visible Through Measurement:

Measurement:
 Anything that can be differentiated in terms of type or amount can be measured
 Quantification becomes relevant when we ask not only what the construct is that is in force
in the situation, but also to what extent it appears – that is, how much of it exists, or to what
intensity it exists
 In psychological research, quantification depends on our ability to operationalise the
particular construct
o This refers to that fact that we have to devise a systematic procedure or operation to
make the construct visible, in such a way that we can measure it
  Measurement refers to a process whereby numbers are allocated to something according
to a rule
 The link between observing a construct and measuring it is so close that when we talk
about ‘observation’ in quantitative research, we often imply the process of measurement
o The taking of a measurement is regarded as an act of observation
 Because of this link between measurement and construct, the procedure of
operationalisation can also be said to provide an operational definition of a construct, as it
can be seen as a practical demonstration of what the construct is
 The subdiscipline that deals with psychological measurement is psychometrics
o This discipline is concerned with issues such as the validity of measurements and
their reliability
 Something one should always be aware of when considering measurements is the level of
measurement
 We distinguish between 2 kinds of measurement
o Measurements where the quantity or intensity of some construct is considered which
we refer to as a quantity or measurement of intensity
o We use measurements that indicate category membership

Variables:
 A construct that has been measured in some way produces a variable
 A variable refers to a number that can take on any one of a range of possible values
 They can be discrete or continuous
 Variables can be contrasted with constants, which are numbers that can only take on a
single size
 To the visible variable reflects the intensity of the underlying (invisible) construct, in terms of
how it was measured
o We say that the variable is manifest (it is visible in the sense that we can observe it)
and the construct is latent (it is invisible in the sense that we need some way to
make it appear)
 When researchers refer to the interaction of specific variables, you have to keep in mind
that when they refer to how variables interact, they are really interested in the interaction of
the underlying constructs
 One important distinction that we often need to make when we study the interaction among
variables, is the distinction between the dependent and the independent variable
o When a researcher focuses on the interaction of only 2 variables at a time, the
dependent variable is usually the 1 that the researcher is interested in, the variable
that is the focus of the research
o The independent variable is something that the researcher manipulates, to see how
this affects the dependent variable
o When there are only 2 variables involved, we often indicate the dependent variable
with a y and the independent variable with an x
 Something else to keep in mind, even when we consider 2 variables only, is the possible
effect of hidden variables
o Hidden variables are effects on the dependent variable that may be unaware of, or
that we choose to ignore
o Very often the events or behaviour that we observed are the consequence of many
interacting factors, and we have to analyse the situation carefully to try and identify
as many things as possible that may interfere with our ability to find a clear
relationship between a dependent variable and some specific independent variable
 Techniques of statistical inference can show you that a difference exists, but it cannot tell
you why it exists

Collecting Information by Sampling Data:

Data:
 Refers to the collected information
 All the variables for all the cases in the research
 Often displayed in the form of a spreadsheet – with rows each representing a case, and the
variables arranged in columns

Descriptive Statistics vs Inferential Statistics:

 Descriptive statistics
o Set of quantities used to summarise aspects of numerical data
o Means, range, variance, and standard deviation
o These summary quantities are sometimes referred to as parameters
 Inferential statistics
o Refers to the use of statistical techniques to make generalisation about the
relationships among (2 or more) variables
 Statistical techniques or tests that make a number of assumptions about the nature and
distributions of the descriptive statistics that can be calculated are referred to as parametric
statistics
 There are statistical techniques that don’t involve descriptive statistics as such (referred to
as non-parametric methods)
o These techniques make use of other characteristics of the data than the summaries
provided by the descriptive statistics

Populations and Samples:

 Population – the entire collection of cases that you are interested in when you make your
measurements for a particular construct
o Depends on which people/objects/events you are interested in studying
 Note – if you define your cases in a certain way, some of the variables could become
constants
 Because populations can be very large, and we rarely have access to them, we would draw
a sample of observations from the population and use that sample to infer certain things
about the population’s characteristics
 Most appropriate sample – usually a simple random sample
o Where each individual has the same chance of being included
 Page 12-13

Measurement Error:
 One of the consequences of using samples to represent populations is that this always
leads to a certain degree of measurement error, no matter how rigorous our sampling
procedure is
 The measurement of a psychological construct is only more or less accurate
o Kind of a hidden variable, which we always presume to exist in social scientific
research
 This is referred to as the error component or the error term
o This is one of the major reasons for using statistical probability theory in a data
analysis: we assume that any variable we measure contains a ‘true’ element and an
‘error’ component
o We assume that the mean of the error component is zero
 We can do this because it is reasonable to assume that positive deviations
and negative deviations from the perfect score will cancel each other out
 Page 15

The Research Hypothesis:

 Informally described as an educated guess
  Normally start with a research question
o This could be an implication of a theory
 We reformulate the research question in terms of a conjecture or supposition, which has the
goal of helping the researcher select what he/she has to observe in order to answer the
research question
o This is the research hypothesis – expresses the problem in terms of very specific
relationships among constructs that we expect to find
 It is important that this possible relationship should be clear and unambiguous
 An hypothesis that is stated clearly and specifies exactly what is to be observed and what
should be true if it is valid, is often called an operational hypothesis
o The way the research hypothesis is expressed in the form of the relationships among
the variables produced when the constructs are measured
 If it isn’t possible to relate the research question to possible constructs, it may be that there
is something wrong with the question
 It is important that research hypotheses should be testable in principle
 The fact that a question isn’t a scientific question doesn’t imply that it isn’t important; it just
means that no amount of empirical research will decide it

TOPIC 2 – PROBABILITY

Introduction to the Study of Probability:

Defining Probability:
 Probability can be studied in 3 ways
o Can be approached in an a priori or classical manner in which the focus is purely on
reasoning and mathematical deduction
o It can also be studied in an empirical or frequentist manner, where probability is
analysed in terms of the relative frequency of an event’s occurrence by actual
observations and conducting experiments
o 3rd alternative is to think of probability in a purely subjective manner, as a degree of
belief in something happening
 Classical approach:
o Origin in games of chance
o Used to help us estimate the likelihood of something happening based on reasoning
alone
o Works by analysing something happening in terms of all the possible outcomes
associated with that something
 The ‘something happening’ is called an event
o Page 29-30
 The relative frequency approach:
o Page 30-31

Some Basic Terminology Related to the Theory of Probabilities:

 Sample space – all the possible outcomes of a statistical experiment
 General principle that can be used as a guideline when interpreting probability as a relative
frequency (law of large numbers)
o If an experiment is done repeatedly, and if the outcomes are independent of one
another, the observed proportion of favourable occurrences of an event will
eventually approach its theoretical probability
o The probability value should be seen as a theoretical limit on which the relative
occurrence of an event (outcome) can be expected to converge over time in the long
run
  Some incorrect thinking about probability stems from a misunderstanding of the law of large
numbers
o Gambler’s fallacy – based on the assumption that if a certain event hasn’t occurred
in a number of trials, its probability of occurring in the next trail increases

A Few Useful Facts About Probabilities:

 The probability value tells us at a glance how frequent or infrequent the event is, and what
the likelihood is of obtaining a favourable outcome associated with it
 Probabilities can be expressed as %s, fractions, or as decimals
 A probability value represents a proportion
 In the rest of the module, we often refer to the probability of an event as its p-value
 When decimal notation is used to describe probabilities, they fall in a range between 0 and
1, with values closer to 1 indicating a greater likelihood than values close to 0
 Because probabilities fall in a range from 0.0 to 1.0 when expressed decimally, a probability
can never be higher than 1 or lower than 0
 You will typically encounter reference to probabilities in expressions such as “p> 0.05”
 The probability of an event not happening is (1 – p(E))
 The sum of the probabilities of all simple events in S (sample space) equals 1

Rules for Combining Probabilities:

 2 events are said to be independent if the occurrence of 1 has no effect on the probability of
the other occurring
 2 events are said to be mutually exclusive if the occurrence of one precludes the
occurrence of the other
 The additive rule:
o P(A or B) = p(A) + p(B)
o Used when 2 or more events are mutually exclusive
o Used to determine the sum of 2 or more probabilities
 The multiplicative rule:
o States that p(A and B) = p(A) x p(B)
o Where A and B are both independent event
o Used to determine the product of 2 or more probabilities and is indicated by the word
‘and’
o In some cases a particular probability is conditional on something else happening –
conditional probabilities are written as p(B|A), where | indicates that a condition
applies
 p(A and B) = p(A) x p(B|A)
 we can then derive the following formula
 p(B|A) = p(A and B)/p(A)
o Bayes’ rule – page 37

Discrete Probability Distributions and the Binomial Distribution:

A Probability Model for Discrete Events: The Even Distribution

 A model can be a table with values, a computer programme, a set of equations, or a
formula
 The important property of such a model is that it can take particular values as input and
then generate an output
o The model is just a method or mechanism for calculating an answer
o Page 39

A Probability Distribution for Multiple Flips of a Coin:

 Page 39-41
The Binomial Distribution:
 Introduced as a probability model for the con testing experiment
 Page 41
 The binomial distribution applies in all cases where a random variable has the following
properties:
o The random variable is for a sample that consists of a fixed number of experimental
trials
 Probabilities can be computed for trials of various lengths, but the length of
the trials must be kept constant for the determination of each probability in the
distribution
o The random variable has only 2 mutually exclusive and collectively exhaustive
events, typically labelled as ‘success’ and ‘failure’
 These terms apply to any outcome that has a binary character
o The probability of an event being classified as a success, p, and the probability of an
event being classified as a failure, 1 – p, are both constant in all the experimental
trials
 This simply means that the probabilities cannot change during the trials
 You cannot start a probability with one value and then later change it
o The event (success or failure) of any single experimental trial is independent of the
event of any other trial
 Using the binomial distribution avoids having to determine the probabilities using a list of all
possible outcomes and applying the multiplication rule
 Page 42-46
 Can be symmetrical or skewed

Continuous Probabilities and the Normal Curve:

Cumulative Probabilities:
 Page 46-49

The Normal Curve:

 Page 49-54

The Z Transformation:
 The standard normal curve presents a standardised distribution of probability values, which
is very useful in hypothesis testing
 Any variable (x) that comes from a normal distribution can be transformed to its
representation on a standard normal distribution, provided that we know the mean and the
standard deviation of the variable scores
 Formula on page 55
 A z-score is the original measurement transformed into a point on a standard normal
distribution
o Therefore, all the characteristics of the standard normal distribution apply
 Page 55-56

Sampling Distributions and the Central Limit Theorem:

TOPIC 3 – GENERAL PRINCIPLES OF STATISTICAL HYPOTHESIS TESTING

TOPIC 4 – STATISTICAL HYPOTHESIS TESTING: TESTING MEANS FOR A SINGLE SAMPLE

 TOPIC 5 – STATISTICAL HYPOTHESIS TESTING: COMPARING 2 SAMPLES

TOPIC 6 – TESTING HYPOTHESES ABOUT A RELAITONSHIP BETWEEN 2 VARIABLES