0% found this document useful (0 votes)
24 views11 pages

1 - Intro To Statistics

Statistics are used to organize and summarize information from research studies. A population is the entire group being studied, while a sample is a subset of individuals from the population. Variables are characteristics that can differ between individuals, such as age or test scores, and measurements of variables from each person in a sample are called data. Descriptive statistics summarize and simplify data, while inferential statistics are used to draw conclusions about populations based on samples.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
24 views11 pages

1 - Intro To Statistics

Statistics are used to organize and summarize information from research studies. A population is the entire group being studied, while a sample is a subset of individuals from the population. Variables are characteristics that can differ between individuals, such as age or test scores, and measurements of variables from each person in a sample are called data. Descriptive statistics summarize and simplify data, while inferential statistics are used to draw conclusions about populations based on samples.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 11

8/22/2022

Definition
of Statistics
• Statistics consist of facts and
figures.
• Statistics are usually
informative and time-saving
because they condense large
quantities of information
into a few simple figures.
• Research in the behavioral
sciences involves gathering
INTRODUCTION TO STATISTICS CHAPTER 1 information.

1 2

Two General Populations and


Purposes Samples
• Statistics are used to organize and • Research in the behavioral sciences typically
summarize the information so that begins with a general question about a
the researcher can see what specific group (or groups) of individuals.
happened in the study and can
communicate the results to • A population is the set of all the individuals of
others. interest in a particular study
• Statistics help the researcher to • Populations can obviously vary in size from
answer the questions that extremely large to very small, depending on
initiated the research by how the investigator identifies the population
determining exactly what general to be studied.
conclusions are justified based on
the specific results that were
obtained

3 4

Populations and Samples • The researcher should


always specify the Populations
population being studied. In
addition, the population
need not consist of people
and Samples
• Because populations tend to
be very large, it usually is • When a researcher
impossible for a researcher finishes examining the
to examine every individual
in the population of interest
sample, the goal is to
generalize the results back
• A sample is a set of to the entire population.
individuals selected from a
population, usually intended
to represent the population
in a research study.

5 6

1
8/22/2022

Variables and Data Variables and Data

• Typically, researchers are interested in specific • For example, Bakhshi, Kanuparthy, and Gilbert
characteristics of the individuals in the (2014) wanted to determine if the weather is
population (or in the sample), or they are related to online ratings of restaurants.
interested in outside factors that may influence • Variables can be characteristics that differ from
behavior of the individuals one individual to another
• Variables can be environmental conditions that
• A variable is a characteristic or condition that change
changes or has different values for different • To demonstrate changes in variables, it is
individuals. necessary to make measurements of the
variables being examined.

7 8

Parameters and Statistics


Variables and Data
• A characteristic that describes a
population—for example, the
average score for the population—
is called a parameter.
• The measurement obtained for each individual is
called a datum, or more commonly, a score or
• A characteristic that describes a
raw score. The complete set of scores is called sample is called a statistic
the data set or simply the data. • Every population parameter has a
• Research typically involves measuring each corresponding sample statistic,
individual to obtain a score, therefore every and most research studies involve
sample (or population) of individuals produces a using statistics from samples as
corresponding sample (or population) of scores. the basis for answering questions
about population parameters.

9 10

Sampling Error
Descriptive and • Descriptive statistics are statistical procedures
used to summarize, organize, and simplify data
Inferential • Table • One problem with using samples,
however, is that a sample provides
• Graph only limited information about the
• Computing for average population
• There usually is some discrepancy
between a sample statistic and the
• Inferential statistics consist of techniques that corresponding population
parameter. This discrepancy is called
allow us to study samples and then make sampling error, and it creates the
generalizations about the populations from fundamental problem inferential
which they were selected. statistics must always address.

11 12

2
8/22/2022

Sampling Error Sampling Error

• Candidate Baby M leads the poll • Further demonstration of


with 51% of the vote (sa true lang?). sampling error:
Candidate Leni has 42% approval
(sayang talaga), and the remaining • Class is separated into
7% are undecided. This poll was two groups (by a drawing
taken from a sample of registered
voters and has a margin of error of
a line from front to back
plus or minus 4 percentage points. through the middle of
• The “margin of error” is the the room)
sampling error. In this case, the • Imagine you have
reported percentages were obtained computed for the
from a sample and are being
generalized to the whole population average age for each
of potential voters. group.

13 14

Sampling Error

• However, the difference you obtain does not


necessarily mean that there is a systematic
difference between the two groups
• Instead, the difference is probably the result of Statistics in
random factors such as chance. the Context
• Inferential statistics tell us whether the differences of Research
between samples (e.g., a difference in age, height,
or GPA) are the result of random factors (sampling
error) or the result of some meaningful relationship
in the population / difference between the groups.

15 16

Observations and Measurements

• Science is empirical.
OBSERVATIONS AND • Variables can be observed / measured directly
MEASUREMENTS • Constructs are internal attributes or characteristics that cannot be
directly observed but are useful for describing and explaining behavior
• An operational definition identifies a measurement procedure (a set of
operations) for measuring an external behavior and uses the resulting
measurements as a definition and a measurement of a hypothetical
construct

17 18

3
8/22/2022

• The variables in a study can be • A discrete variable consists of


characterized by the type of values
that can be assigned to them.
separate, indivisible categories. No
Discrete and • The type of values influences the
Discrete and values can exist between two
neighboring categories
Continuous statistical procedures that can be Continuous • Commonly restricted to whole, countable
used to summarize or make
Variables inferences about those values. Variables numbers (i.e., integers)
• May also consist of observations that
differ qualitatively.

19 20

Discrete and Continuous • When measuring a


Variables continuous variable, it
should be very rare to
obtain identical
• For a continuous variable, there are an measurements for two
Discrete and infinite number of possible values that different individuals.
Continuous fall between any two observed values. • When measuring a
continuous variable,
A continuous variable is divisible into
Variables an infinite number of fractional parts
researchers must first
identify a series of
measurement
categories on the scale
of measurement.

21 22

Scales of
Measurements
• Finally, remember that the terms • It should be obvious by now
Discrete and continuous and discrete apply to the that data collection requires
that we make measurements
Continuous variables that are being measured and of our observations.
Measurement involves
not to the scores that are obtained
Variables from the measurement.
assigning individuals or
events to categories
• The categories used to
measure a variable make up a
scale of measurement, and
the relationships between
the categories determine
different types of scales

23 24

4
8/22/2022

• The categories that make up an ordinal scale not only have different
names (as in a nominal scale) but also are organized in a fixed order
corresponding to differences of magnitude.

• The word nominal means “having to do with • With measurements from an ordinal scale, you can determine whether
names.” Measurement on a nominal scale two individuals are different, and you can determine the direction of
involves classifying individuals into categories difference
that have different names but are not
The Nominal quantitative or numerically related to each The Ordinal
Scale other.
Scale
• Although the categories on a nominal scale are
not quantitative values, they are occasionally
represented by numbers
• It also is fairly common to use numerical values
as a code for nominal categories when data are
entered into computer programs for analysis.

25 26

The Ordinal The Ordinal


Scale Scale
• The categories that make up an • However, ordinal
ordinal scale not only have measurements do not allow
different names (as in a nominal you to determine the size of
scale) but also are organized in a
the difference between two
fixed order corresponding to
differences of magnitude. individuals.
• With measurements from an • In addition, ordinal scales are
ordinal scale, you can determine often used to measure
whether two individuals are variables for which it is difficult
different, and you can determine to assign numerical scores
the direction of difference

27 28

• The factor that differentiates


The Interval and an interval scale from a ratio
scale is the nature of the
Ratio Scales zero point.
• A ratio scale is anchored by a
zero point that is not
• Both an interval scale and a ratio scale arbitrary but rather is a
consist of a series of ordered categories meaningful value
(like an ordinal scale) with the additional representing none (a
requirement that the categories form a complete absence) of the
series of intervals that are all exactly the variable being measured.
same size
• The existence of an absolute,
• The fact that the differences between non-arbitrary zero point
adjacent values are all the same size makes means that we can measure
it possible to determine both the size and the absolute amount of the
the direction of the difference between two variable; that is, we can
measurements
The Interval and Ratio Scales measure the distance from 0

29 30

5
8/22/2022

The Interval Statistics and Scales of


and Ratio Scales Measurements
• To recap, with a ratio scale,
we can measure the direction • For our purposes, scales of measurement are important because
and the size of the difference they help determine the statistics that are used to evaluate the
data.
between two measurements
and we can describe the
difference in terms of a ratio • For most statistical applications, the distinction between an
interval scale and a ratio scale is not important because both
scales produce numerical values that permit us to compute
differences between scores, add scores, and calculate mean
scores. On the other hand, measurements from nominal or ordinal
scales are typically not numerical values, do not measure distance,
and are not compatible with many basic arithmetic operations

31 32

Data Structure 1. One Group with One or


More Separate Variables Measured for
Each Individual: Descriptive Research • Some research studies are
conducted simply to describe

Three Data Structures, individual variables as they


exist naturally.

Research Methods, and • Descriptive research or the


descriptive research strategy
involves measuring one or
Statistics more separate variables for
each individual with the intent
of simply describing the
individual variables.

33 34

Descriptive Statistics Relationships between Variables

• When the results from a descriptive • Most research, however, is intended to


research study consist of numerical scores, examine relationships between two or
they are typically described by the statistical more variables.
techniques measures of central tendency
and variability • To establish the existence of a
relationship, researchers must make
• Non-numerical scores are typically
observations— that is, measurements
described by computing the proportion or of the two variables.
percentage in each category

35 36

6
8/22/2022

Data Structure 2. One Group with Two Variables Measured


Statistics for the Correlational Method
for Each Individual: The Correlational Method
• One method for examining the • When the data from a correlational
relationship between variables study consist of numerical scores,
is to observe the two variables the relationship between the two
variables is usually measured and
as they exist naturally for a set described using a statistic called a
of individuals. correlation.
• In the scatter plot, each
individual is represented by a • Occasionally, the measurement
point so that the horizontal process used for a correlational
position corresponds to the study simply classifies individuals
into categories that do not
student’s Facebook time and the correspond to numerical values
vertical position corresponds to
the student’s academic
performance score.

37 38

Limitations of the Correlational Data Structure 3. Comparing Two (or More) Groups of
Method Scores: Experimental and Nonexperimental Methods
• The second method for examining
• The results from a correlational study can the relationship between two
variables compares two or more
demonstrate the existence of a relationship groups of scores. In this situation,
between two variables, but they do not the relationship between variables
is examined by using one of the
provide an explanation for the relationship. variables to define the groups, and
then measuring the second variable
to obtain scores for each group
• In particular, a correlational study cannot
demonstrate a cause-and-effect relationship. • For example, Polman, de Castro, and
van Aken (2008) randomly divided a
sample of 10-year-old boys into two
groups.

39 40

Statistics for Comparing


Two (or More) Groups of
• We examine descriptive statistics that
summarize and describe the scores in each Scores
group and we use inferential statistics to
determine whether the differences between the
Statistics for Comparing groups can be generalized to the entire • If the measurement process
population.
simply classifies individuals
Two (or More) Groups of into non-numerical categories,
Scores • When the measurement procedure produces
numerical scores, the statistical evaluation
the statistical evaluation
typically involves computing the average score usually consists of computing
for each group and then comparing the proportions for each group
averages.
and then comparing
proportions

41 42

7
8/22/2022

Experimental and The Experimental Method


Nonexperimental
Methods

43 44

The Experimental Method The Experimental


Method
• Manipulation - the researcher manipulates
one variable by changing its value from one • To be able to say that the difference in
level to another. A second variable is observed aggressive behavior is caused by the
(measured) to determine whether the amount of violence in the game, the
manipulation causes changes to occur.
researcher must rule out any other possible
explanation for the difference
• Control - the researcher must exercise control
over the research situation to ensure that
other, extraneous variables do not influence • That is, any other variables that might
the relationship being examined. Control affect aggressive behavior must be
usually involves matching different groups as
closely as possible on those variables that we controlled.
don’t want to manipulate.

45 46

The Experimental Method The Experimental Method


• Participant Variables – these
are characteristics such as
age, gender, motivation, and
• Environmental Variables - these are personality that vary from
characteristics of the environment such as one individual to another.
lighting, time of day, and weather
conditions. • Whenever an experiment
compares different groups of
participants (one group in
• Whenever a research study allows more treatment A and a different
than one explanation for
the results, the study is said to be
group in treatment B), the
confounded because it is impossible to concern is that there may be
reach an unambiguous conclusion. consistent differences
between groups for one or
more participant variables

47 48

8
8/22/2022

Basic Techniques to Control other Variables The Experimental Method

• The researcher could use random assignment, which means that each
participant has an equal chance of being assigned to each of the • In the experimental method, one variable is manipulated while
treatment conditions. another variable is observed and measured. To establish a cause-and-
• A second technique for controlling variables is to use matching to effect relationship between the two variables, an experiment attempts
ensure groups are equivalent in terms of participant variables and to control all other variables to prevent them from influencing the
environmental variables results.
• Finally, the researcher can control variables by holding them constant

49 50

Terminology in the Terminology in the


Experimental Method Experimental Method

• The variable that is manipulated by the experimenter is called the


independent variable. It can be identified as the treatment conditions to • Note that in an experiment only one variable is actually measured. You
which participants are assigned. should realize that this is different from a correlational study, in which all
variables are measured and the data consist of at least two separate
• The variable that is observed and measured to obtain scores within each scores for each individual.
condition is the dependent variable

51 52

Control Conditions in an Experiment


Control • Often an experiment will
Conditions in include a condition in which • Individuals in a control condition do not receive the experimental
the participants do not treatment. Instead, they either receive no treatment or they receive a
an Experiment receive any experimental neutral, placebo treatment. The purpose of a control condition is to
treatment. The scores from provide a baseline for comparison with the experimental condition.
these individuals are then
compared with scores from
participants who do receive • Individuals in the experimental condition do receive the
the treatment. experimental treatment.

53 54

9
8/22/2022

Nonexperimental Methods: Nonexperimental


Nonequivalent Groups Methods:
and Pre-Post Studies Nonequivalent • Because this type of
Groups research compares
• An example of a nonequivalent preexisting groups, the
groups study comparing third-
and Pre-Post researcher cannot control
grade students from suburban Studies the assignment of
communities to those from rural participants to groups and
communities. Notice that this study cannot ensure equivalent
involves comparing two groups of groups.
scores (like an experiment).

55 56

Nonexperimental Methods: • In each case, one variable is


Nonequivalent Groups used to create groups, and a
and Pre-Post Studies Terminology in second variable is measured
to obtain scores within each
Nonexperimental group.
• An example of a pre-post study Research
comparing depression scores • In a nonexperimental study,
before therapy and after the “independent variable”
therapy. A pre-post study uses that is used to create the
the passage of time different groups of scores is
(before/after) to create the often called the quasi-
independent variable.
groups of scores

57 58

Summary Notation

Summation Notation
• Many of the computations required in statistics involve adding a set of
scores. Because this procedure is used so frequently, a special notation is
used to refer to the sum of a set of scores. The Greek letter sigma, or Σ,
is used to stand for summation

59 60

10
8/22/2022

Order of Mathematical Operations

1. Any calculation contained within


parentheses is done first.
2. Squaring (or raising to other
exponents) is done second.
3. Multiplying and/or dividing is
done third. A series of multiplication
and/or division operations should be
done in order from left to right.
4. Summation using the Σ notation is
done next.
5. Finally, any other addition and/or
subtraction is done

61

11

You might also like