Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 2

FM 16 NOTES

CHAPTER 1: Introduction to Statistics PARAMETER vs STATISTIC TYPES OF VARIABLES

BASICS OF STATISTICS • Parameter – a number that describes a • Qualitative variable – are non-measurable
characteristic of the population. Symbol, µ characteristics that cannot assume a numerical
Definition: Science of collection, presentation, analysis, (Greek letter mu) value but can be classified into two or more
and reasonable interpretation of data. • Statistic – a number that describes a categories.
characteristic of a sample. Symbol x (read “x • Quantitative variable – are those quantities
Statistics presents a rigorous scientific method for bar”) that can be counted (discrete) or measured
gaining insight into data. For example, suppose we (continuous) with the use of some measuring
measure the weight of 100 patients in a study. With so devices.
many measurements, simply looking at the data fails to • Discrete variables (such as class size) consist of
provide an informative account. However, statistics can indivisible categories, and
give an instant overall picture of data based on graphical • Continuous variables (such as time or weight)
presentation or numerical summarization irrespective to are infinitely divisible into whatever units a
the number of data points. Besides data summarization, researcher may choose. For example, time can
another important task of statistics is to make inference be measured to the nearest minute, second,
and predict relations of variables. half-second, etc.

POPULATION LEVELS OF MEASUREMENT

• The entire group of individuals is called the • Nominal - Categorical variables with no
population. inherent order or ranking sequence such as
• For example, a researcher may be interested in DESCRIPTIVE AND INFERENTIAL STATISTICS names or classes (e.g., gender). Value may be a
the relation between class size (variable 1) and numerical, but without numerical value (e.g., I,
academic performance (variable 2) for the • Descriptive Statistics – involves the use of II, III). The only operation that can be applied to
population of third-grade children. numerical indices to describe either a Nominal variables is enumeration.
population or sample. • Ordinal - Variables with an inherent rank or
SAMPLE • Inferential Statistics – involves taking order, e.g. mild, moderate, severe. Can be
measurements on a sample and then, from the compared for equality, or greater or less, but
• Usually, populations are so large that a observations, inferring something about a not how much greater or less
researcher cannot examine the entire group. population. .
Therefore, a sample is selected to represent the • Interval - Values of the variable are ordered as
population in a research study. The goal is to VARIABLES in Ordinal, and additionally, differences
use the results obtained from the sample to between values are meaningful, however, the
help answer questions about the population. A • A variable is a characteristic or condition that scale is not absolutely anchored. Calendar dates
sample is a subset or a part of a given can change or take on different values. and temperatures on the Fahrenheit scale are
population, its size is smaller than the size of the • Most research begins with a general question examples. Addition and subtraction, but not
population. about the relationship between two variables multiplication and division are meaningful
for a specific group of individuals. operations.
• Ratio - Variables with all properties of Interval
plus an absolute, non-arbitrary zero point, e.g.
age, weight, temperature (Kelvin). Addition, member of the population has an equal chance, of people you have access to “snowballs” as you
subtraction, multiplication, and division are all or probability, of being selected. get in contact with more people.
meaningful operations. 2. Systematic sampling - Individuals are selected
at regular intervals from the sampling frame.
The intervals are chosen to ensure an adequate
INDEPENDENT AND DEPENDENT VARIABLES sample size.

• Independent variables are variables that are 3. Stratified sampling - Stratified sampling
manipulated or are changed by researchers and involves dividing the population into
whose effects are measured and compared. subpopulations that may differ in important
• Dependent variables refer to that type of ways. It allows you draw more precise
variable that measures the affect of the conclusions by ensuring that every subgroup is
independent variable(s) on the test units. properly represented in the sample.
Dependent variables are the types of variables
that are completely dependent on the 4. Cluster sampling - Cluster sampling also
independent variable(s). involves dividing the population into subgroups,
but each subgroup should have similar
• Sampling frame - The sampling frame is the characteristics to the whole sample. Instead of
actual list of individuals that the sample will be sampling individuals from each subgroup, you
drawn from. Ideally, it should include the entire randomly select entire subgroups.
target population (and nobody who is not part
of that population). NON-PROBABILITY SAMPLING METHODS

• Sample size - The number of individuals in your 1. Convenience sampling - A convenience sample
sample depends on the size of the population, simply includes the individuals who happen to
and on how precisely you want the results to be most accessible to the researcher.
represent the population as a whole. 2. Voluntary response sampling - Similar to a
convenience sample, a voluntary response
SAMPLING sample is mainly based on ease of access.
3. Quota Sampling – quota samples are usually
When investigation of the entire population is difficult utilized by market researchers and pollsters.
due to material constraints like time, money, and effort, Drawn by specifying the characteristics desired
a sample is obtained. in the subjects to be interviewed.
4. Purposive sampling - This type of sampling, also
Random Sampling – is a technique in which every known as judgement sampling, involves the
member of the population has an equal chance of being researcher using their expertise to select a
selected in the sample. sample that is most useful to the purposes of
the research.
RANDOM SAMPLING TECHNIQUES 5. Snowball sampling - If the population is hard to
access, snowball sampling can be used to recruit
1. Simple random sampling - In this case each participants via other participants. The number
individual is chosen entirely by chance and each

You might also like