EDUCATIONAL STATISTICS REVIEWER
BASIC CONCEPTS
LEVELS / SCALES OF MEASUREMENT
*NON – PARAMETRIC STATISTICS
NOMINAL * A set of data is said to be nominal if the values / observations belonging to it can be assigned a
code in the form of a number where the numbers are simply labels.
* You can count but not order or measure nominal data.
* For example, in a data set males could be coded as 1, females as 2; marital status of an
individual could be coded as X if married, Y if single; Athletes wearing nos. at their back.
ORDINAL *A set of data is said to be ordinal if the values / observations belonging to it can be ranked (put in
order) or have a rating scale attached. You can count and order, but not measure, ordinal data.
*The categories for an ordinal set of data have a natural order, for example, suppose a group of
people were asked to taste varieties of biscuit and classify each biscuit on a rating scale of 1 to 5,
representing strongly dislike, dislike, neutral, like, strongly like. A rating of 5 indicates more
enjoyment than a rating of 4, for example, so such data are ordinal.
*PARAMETRIC STATISTICS
INTERVAL *This scale has equal interval, that is the distances between points and equal starting at an
arbitrary zero. Arbitrary means not fixed / not absolute.
*this can show how much is the difference.
* For example, the time interval between the starts of years 1981 and 1982 is the same as that
between 1983 and 1984, namely 365 days. The zero point, year 1 AD, is arbitrary; time did not
begin then. Other examples of interval scales include the heights of tides, and the measurement of
longitude.
RATIO *It has all characteristics of the interval scale but zero is absolute.
*Ratio scales are the ultimate nirvana when it comes to measurement scales because they tell us
about the order, they tell us the exact value between units, AND they also have an absolute zero–
which allows for a wide range of both descriptive and inferential statistics to be applied.
Summary
In summary, nominal variables are used to “name,” or label a series of values. Ordinal scales provide good
information about the order of choices, such as in a customer satisfaction survey. Interval scales give us the order of values
+ the ability to quantify the difference between each one . Finally, Ratio scales give us the ultimate–order, interval values,
plus the ability to calculate ratios since a “true zero” can be defined.
summary of data types and scale measures
MEASURE OF -Average performance of a certain UNGROUPED DATA GROUPED DATA
CENTRAL TENDENCY group
MEAN -the most commonly used. Mean = ΣX/n Mean = Σfx/n
-reliable, dependable, stable
MEDIAN -divides the distribution into equal Arrange the data from highest
half. to lowest. Mdn = ll + (50% of N) –cf (i)
No. of cases is odd ex. 9 f
(middle)
No. of cases is even ex. 8
****average of the 2 middle
scores
MODE -the most frequently used score. Most frequent data Mo = 3Mdn – 2Mean
-UNRELIABLE, UNSTABLE
MEASURE OF UNGROUPED DATA GROUPED DATA
VARIABILITY
STANDARD DEVIATION *the counterpart of MEAN.
QUARTILE DEVIATION *the counterpart part of median.
RANGE -the difference of the most extreme
scores. *Note: If N is more than 50, no
*highest score – lowest score + 1 need to subtract 1.
STATISTICAL DEFINITION / FUNCTION SCALEOF MEASUREMENT SAMPLE HYPOTHESIS /
TREATEMENT RESEARCH PROBLEM
MEASURE OF
RELATIONSHIPS /
CORRELATION
1. Pearson r Used to determine if there is a What is the relationship between
relationship between two Interval / ratio height and arm span?
variables. A simple correlation (scores)
measures the relationship between Is there a correlation between
two variables. The variables have self-concept and academic
equal status and are not achievement?
considered independent variables
or dependent variables. A dietetics student wanted to look
at the relationship between
calcium intake and knowledge
about calcium in sports science
students.
Is there a relationship between
calcium intake and knowledge
about calcium
in sports science students?
2. Spearman-rank order Draw conclusion even without
correlation taking into accounts some ORDINAL *Survey of 25 students with items
assumptions. (rank /order) measuring age, current GPA, and
Even the no. of cases is low, we expectations for a communication
could still draw conclusions, course. Expectation is measured
by a 7-point agreement question: I
expect to do well for this course.
***Q: Is there a relationship
between students’ age and their
expectations regarding how well
they will do in a course?
***Q: Is there a relationship
between students’ existing GPA
and their expectations regarding
how well they will do in a course?
3. Chi-Square test of *used to determine if there is a 100 high school students were
Independence correlation or relationship between NOMINAL asked about their drink
two variables of nominal type. (codes) preferences.
Among the 50 male students 20
preferred frozen drinks, 15
preferred Cold drinks& 15
preferred regular drinks.
Among the 50 female students, 30
preferred frozen drinks, 10
preferred cold drinks and 10
preferred regular drinks.
Is sex related to drink preference?
STATISTICAL DEFINITION / FUNCTION SCALEOF MEASUREMENT SAMPLE HYPOTHESIS /
TREATEMENT RESEARCH PROBLEM
HYPOTHESIS
TESTING / test of
difference
1. Z-TEST of dependent *used to determine if there is a NOMINAL *50 teachers were asked about
proportion significant difference between their opinion on the issue of
pairs of observation from a single political dynasty. 20 are in favour
group. (comparing two sets of and 30 are against.
responses).
*50 teachers were asked to attend
a symposium on political dynasty.
Advantages and Disadvantages
were presented, afterwards the
same questions were asked about
political dynasty.
Out of 20 teachers who are in
favour before, 4 remained in
favour and 16 went against. Out of
30 who are against 22 remained
‘AGAINST’ and 5 switch to ‘in 4
favour’.
*Is there a significant difference
between the proportion of teacher
who are in favour of political
dynasty before and after the
symposium.
2. Z-TEST of independent *used to determine if there is a NOMINAL *50 Graduate and 50
proportion significant difference between two undergraduate students were
independent or two different asked their opinion about political
groups on situations that call for dynasty. Out of 50 Graduate
two types of responses. students, 20 are in favour and 30
are against & out of 50
undergraduate students, 25 are in
favour & 25 are against.
*Is there a significant difference
between graduate or
undergraduate students who are
in favour about political dynasty?
*used to determine if there is a INTERVAL *Is there a significant difference
3. t-test of dependent significant difference between two RATIO between the pre test and post test
means sets or two group of correlated (SCORES) scores in Statistics of the
scores. Experimental group?
*pre test and post test of one
group.
*Used to determine if there is a INTERVAL *Is there a significant difference
4. t-test of independent significant difference between two RATIO between the Experimental Group
means independent groups in terms of (SCORES) & Control Group in terms of
means. achievement in statistics?
*used to determine if there is a INDEPENDENT VARIABLE
5. ONE-WAY ANOVA significant difference between two NOMINAL (pupils)
(Analysis of variance) or more group in terms of means. *****(One Independent Methods of teaching
Variable) ***1. Instructional TV
INTERVAL / RATIO ***2. Distance Learning Approach,
*****(One Dependent Variable) ***3. Discovery Approach)
DEPENDENT VARIABLE
***Achievement in Math
Do the three groups of pupils differ
significantly in terms of
achievement in Math?
* The two-way analysis of variance INTERVAL / RATIO INDEPENDENT VARIABLE
6. TWO-WAY ANOVA is an extension to the one-way *****(One Dependent Variable) (pupils)
analysis of variance. There are NOMINAL 1. Methods of teaching
two independent variables (hence *****(Two Independent ***Instructional TV
the name two-way). Variable) ***Distance Learning Approach,
***Discovery Approach)
2. Medium of Instruction
***English
***Filipino
DEPENDENT VARIABLE
***Achievement in Math
7. Chi-square test of *We compare the observed ORDINAL 100 Graduate students were
goodness of fit (actual) distribution and the asked about their attitude towards
expected (pre-determined) politics, their responses are as
distribution. OBSERVED follows:
*Used to determine if there is a EXPECTED
significant difference between the 25 – strongly Agree
observed and expected 20
distribution. 30 – Agree *Is there a significant difference
20 between the observed and the
5 – Neutral expected difference in terms of
20 responses?
15 – Disagree
20
25 – Strongly disagree
20
