Chapter 1 Psych Stat
Chapter 1 Psych Stat
Chapter 1 Psych Stat
Page 1 of 7
o How many are you talking about in total?
o To find this out, you need to be clear about n=126 respondents
who does and doesn’t fit into your group. Using the other formula:
o For example, if you want to know about dog Z2( N )
owners, you’ll include everyone who has at n= 2 2
some point owned at least one dog. Z + 4 N (e )
2. MARGIN OF ERROR (CONFIDENCE INTERVAL) ( 1.96 )2 (185)
o Errors are inevitable – the question is how n= 2 2
much error you’ll allow. (1.96) + 4 (185)(0.5)
o The margin of error (confidence interval) is n=125 respondents
expressed in terms of mean numbers.
o You can set how much difference you’ll allow Note: The larger the size of the sample, the more
between the mean number of your sample and certain we can be sure that the sample size will be
the mean number of your population. good estimate of the population. The larger the size
o If you’ve ever seen a political poll on the news, of the sample, the closer its characteristics would
you’ve seen a confidence interval and how it’s be from the characteristics of the entire population.
expressed. It will look something like this:
“68% of voters said yes to Proposition Z, with
a margin of error of ± 5%.” TYPES OF DATA
o DATA – the information we gather about the sample
3. CONFIDENCE LEVEL or the population.
o This is a separate step to the similarly-named
confidence interval in step 2.
Nominal
o It deals with how confident you want to be that Qualitative or
Types of Data
the actual mean falls within your margin of Categorical
error. Ordinal
o The most common confidence intervals are
90% confident, 95% confident, and 99% Discrete
confident. Quantitative
Continuous
The sample size can be obtained by the following
formula:
SLOVIN’S FORMULA
QUALITATIVE OR CATEGORICAL VARIABLE – a
N variable that cannot assume a numerical value but can
n= 2
1+ Ne be classified into two or more nonnumeric categories
2|Page
3|Page
TYPES OF VARIABLES 1. NOMINAL VARIABLE.
o VARIABLE – a measurable characteristic that o When measuring using a nominal
varies. It may change from group to group, person scale, one name or categorizes
to person, or even within one person over time responses.
. 1. REAL NOMINAL
1. DEPENDENT VARIABLES o those classified based
o show the effect of manipulating or on a naturally occurring
introducing the independent attribute.
variables. 2. ARTIFICIAL NOMINAL
o For example, if the independent o those classified based
variable is the use or non-use of a on a “man-made”
new language teaching procedure, attribute following
then the dependent variable might be certain rules.
students' scores on a test of the
content taught using that procedure. 2. ORDINAL VARIABLE.
o In other words, the variation in the o It is grouped according to the rank or
dependent variable depends on the order of the categories.
variation in the independent variable. o Unlike nominal scales, ordinal scales
allow comparisons of the degree to
2. INDEPENDENT VARIABLES which two subjects possess the
o are those that the researcher has dependent variable.
control over.
o This "control" may involve 3. INTERVAL VARIABLE.
manipulating existing variables (e.g., o Interval scales are numerical scales
modifying existing methods of in which intervals have the same
instruction) or introducing new interpretation throughout.
variables (e.g., adopting a totally new o interval scale has no true zero point
method for some sections of a class)
in the research setting. 4. RATIO VARIABLE.
o Whatever the case may be, the o The ratio scale of measurement is the
researcher expects that the most informative scale.
independent variable(s) will have o It is an interval scale with the additional
some effect on (or relationship with) property that its zero position indicates the
the dependent variables. absence of the quantity being measured.
SAMPLING
Nominal Ordinal SAMPLING
Variable Variable o is a process used in statistical analysis in
which a predetermined number of
observations are taken from a larger
Interval
Real Nominal Variable population.
1. PROBABILITY SAMPLING
o every member of
Artificial Ratio Variable a population has a known and
Nominal equal chance of being selected.
2. NON-PROBABILITY SAMPLING
o a sampling technique where the
samples are gathered in a
process that does not give all the
4|Page
individuals in the population characteristics, and you want to
equal chances of being selected. ensure that every characteristic is
proportionally represented in the
SAMPLING TECHNIQUES sample.
o It is used when we might reasonably
Sampling expect the measurement of interest to
Techniques vary between the different subgroups.
o The population is first divided into
subgroups (or strata) who all share a
similar characteristic. From the
Probability Non-probability overall proportions of the population,
Sampling Sampling
you calculate how many people
should be sampled from each
subgroup. Then you use random or
Simple random Convenience systematic sampling to select a
Sampling Sampling sample from each subgroup.
o Example: The company has 800
female employees and 200 male
Voluntary employees. You want to ensure that
Systematic
Response the sample reflects the gender
Sampling
Sampling balance of the company, so you sort
the population into two strata based
on gender. Then you use random
Stratified Purposive sampling on each group, selecting 80
Sampling Sampling women and 20 men, which gives you
a representative sample of 100
people
Clustered Snowball .
Sampling Sampling 4. CLUSTERED SAMPLING
o In a clustered sample, subgroups of
the population are used as the
Quota sampling unit, rather than individuals.
Sampling o The population is divided into
subgroups, known as clusters, and a
selection of these are randomly
(PROBABILITY SAMPLING) selected to be included in the study.
All members of the cluster are then
1. SIMPLE RANDOM SAMPLING included in the study.
o In this case each individual is chosen o Clustering should be taken into
entirely by chance and each member account in the analysis. This method
of the population has an equal is good for dealing with large and
chance, or probability, of being dispersed populations, but there is
selected. more risk of error in the sample, as
o One way of obtaining a random there could be substantial differences
sample is to give each individual in a between clusters. It’s difficult to
population a number, and then use a guarantee that the sampled clusters
table of random numbers to decide are really representative of the whole
which individuals to include. population.
o Example: You want to select a simple o Example: The company has offices in
random sample of 100 employees of 10 cities across the country (all with
Company X. You assign a number to roughly the same number of
every employee in the company employees in similar roles). You don’t
database from 1 to 1000, and use a have the capacity to travel to every
random number generator to select office to collect your data, so you use
100 numbers. random sampling to select 3 offices –
these are your clusters.
2. SYSTEMATIC SAMPLING
o Individuals are selected at regular Below illustrates the main types of probability sample.
intervals from a list of the whole
population. The intervals are chosen
to ensure an adequate sample size.
o For example, every 10th member of
the population is included. This is
often convenient and easy to use,
although it may also lead to bias.
3. STRATIFIED SAMPLING
o This sampling method is appropriate
when the population has mixed
5|Page
o An effective purposive sample must have
clear criteria and rationale for inclusion.
o Example: You want to know more about
the opinions and experiences of disabled
students at your university, so you
purposefully select a number of students
with different support needs in order to
gather a varied range of data on their
experiences with student services.
4. SNOWBALL SAMPLING
o This method is commonly used in social
sciences when investigating hard to reach
groups. Existing subjects are asked to
nominate further subjects known to them,
(NON-PROBABILITY SAMPLING) so the sample increases in size like a
rolling snowball.
1. CONVENIENCE SAMPLING o Example: When carrying out a survey of
o A convenience sample simply includes the risk behaviors amongst intravenous drug
individuals who happen to be most users, participants may be asked to
accessible to the researcher. This is an nominate other users to be interviewed.
easy and inexpensive way to gather initial
data, but there is no way to tell if the 5. QUOTA SAMPLING
sample is representative of the population, o This is a relatively quick and inexpensive
so it can’t produce generalizable results. method to operate since the choice of the
o Example: You are researching opinions number of persons or elements to be
about student support services in your included in a sample is done at the
university, so after each of your classes, researcher’s own convenience or
you ask your fellow students to complete preference and is not predetermined by
a survey on the topic. This is a some carefully operated randomizing
convenient way to gather data, but as you plan.
only surveyed students taking the same
classes as you at the same level, the Below illustrates the main types of non-probability
sample is not representative of all the sample.
students at your university.
3. PURPOSIVE SAMPLING
o This type of sampling involves the
researcher using their judgement to select
a sample that is most useful to the
purposes of the research.
o It is often used in qualitative research,
where the researcher wants to gain
detailed knowledge about a specific
phenomenon rather than make statistical
inferences.
6|Page
How are you doing? Assessment Task
1. A father rates his daughter as a 2 on a 7-
EXERCISE 1. Television station GMA wants to
point scale (from 1 to 7) of crankiness. In
know the proportion of TV owners in NCR region
this example,
who watch the station’s new program at least once
(a) what is the variable?
a week. The station asked a random group of 1,000
TV owners in the NCR if they watch the program at
(b) what is the score?
least once a week.
a. What is the population?
(c) what is the range of values?
7|Page