Anda di halaman 1dari 16

STATISTICAL

TREATMENT
Statistical treatment is used to properly test
the hypothesis, answer the research questions,
and present the results of the study in a clear
and understandalbe manner. In quantitative
research which deals with more numerical data,
as in most surveys and experiments, it is logical
to use statistical treatment.
Statistics is a body of knowledge and
techniques used in collecting, organizing,
presenting and interpreting data. It is a
prerequisite in any research that the researcher
has sufficient knowledge of various statistical
treatment.
Two branches of Statistics:
1. Descriptive statistics – it involves
tabulating, depicting and describing
the collected data. The data are
summarized to reveal overall data
patterns and make them
manageable.
2. Inferential statistics – it involves
making generalizations about the
population through a sample drawn
from it. It also includes hypothesis
testing and sampling.
LEVELS OF MEASUREMENT OF VARIABLES
•Nominal data – these are attributes that only name
variables. These data are considered at the simplest level.
Example:
Numbers on the uniform of basketball teams; naming the
data for statistical purposes like “Male -1” and “Female –
2”
•Ordinal data – these are attributes of variables that can
be placed as one is higher than two. They can be used for
ranking purposes. They are mostly used in Likert scaling.
Examples: 1 – Very Good 1 – Very Satisfied
2 – Good 2 - Satisfied
3 – Fair 3 - Unsatisfied
4 – Poor 4 – Very Unsatisfied
3. Interval data – these are
attributes of variables where the
distance from one another to the
other has a meaning.
Examples: scores of test, grades
4. Ratio data – these are attributes
of variables that has a natural
zero.
Examples: weight, height, age,
number of customers who
complained for the month
DESCRIPTIVE STATISTICS
1. Frequency distribution – it is the
record of the number of individual or
cases located in each category on the
scale of measurement.
2. Proportion – it is the total frequency
dividied by the number of cases in each
category. It can be derived from the
frequency distribution.
3. Percentage – it is the propotion
expressed in percentage.
4. Measure of central tendencies – it
indicates where the center of the
distribution tends to be located. It
referes to the typical or average score in
a distribution.
a. Mode – it refers to the most frequently
occuring score in a distribution.
b. Median – it is
the middlemost value in a distribution
below or above which is exactly 50% of
cases that are found
c. Mean – it is equal to the sum of all
scores divided by the number of cases.
5. Variability or dispersion – it refers to the
extent and manner in which the scores in a
distribution differ from each other.
a. Range – it is the difference between the
highest value and the lowest value in the
given distribution.
b. Average deviation – it is the measure of
variation that takes into consideratoin the
deviations of the individual scores from the
mean.
c. Variance – it is the swuare of the standard
deviation.
d. Standard deviation – it is the square root
of the quotient of the total squared deviation
of the mean and the total number of cases,
INFERENTIAL STATISTICS
1. Paramedic tests – these tests require a normal
distribution.
a. T-test – the test is used to compare two means; the
means of two independent samples
b. Z-test - it is used to compare two means; the sample
mean and the perceived population mean.
c. F - test – also known as the analysis of variance (ANOVA),
it is used when comparing the means of two or more
independent groups.
d. Pearson product-moment coefficient of correlation –
it is an index of relationship between two variables.
e. Simple linear regression analysis – it is used when
there is a significant relationship between x and y
variables. It is used in predicting the value of y, given the
value of x.
f. Multiple regression analysis – it is used in predictions.
The dependent variable can be predicted given several
independent variables.
2. Non-paramedic tests – it does not
require the normal distribution of scores. It
can be used when the data are nominal or
ordinal.
a. Chi-square test – this is a test of
difference between the observed and
the expected frequencies.
b.Spearman’s Rank Order Correlation
coefficient – this measures the
strength and direction of association
between two ranked variable.
SAMPLE STATEMENTS OF THE PROBLEM
WITH A CORRESPONDING STATISTICAL
TOOL
1. What is the demographic profile of the elementary
pupils in terms of:
a. age b. civil statis c. religion
Statistical tool: Percentage
Justification: Data are nominal and are used to show the
distribution of the parts of a whole.
2. What is the level of effectiveness of information,
education, and communication in the awareness of
students considering the following variables:
a. academic institutions b. media c. economic status
Statistical tool: Weighted mean
Justification: The researcher is looking into the average
of some elements with different weights on the results
than other elements in the set.
3. What is the significant relationship between
religious beliefs and the effectiveness of
information, education, and communication on
natural family planning?
Statistical tool: Chi-square test
Justification: The two categorical variables, religious
beliefs (nominal data) and effectiveness of
information, education and communication (interval
data), are being compared to assess relationships.
4. What is the level of performance of the engineering
students in their licensure examination?
Statistical tool: Average weighted mean
Justification: The researcher is looking into the
average of some elements with different weights on
the result than other elements in the set.
5. How varied are the scores of the senior high
school students in their final examinations?
Statistical tool: Measures of variability
Justification: This shows how varied the
distribution of continuous variables is, which in this
case os the scores in the final examinations.
6. How significantly different is the performance of
private institutions compared to that of
government institutions?
Statistical tool: T-test for two independent
variables
Justification: Because two groups are being
compared
7. What is the significant relationship between the pre-
test and post test scores of accounting students in
their qualifying examinations?
Statistical tool: Pearson product-moment
coefficient of correlation
Justification:There are two continuous variables in
which data are interval. In this case, the variables pre-
test scores and the post-test scores are related.
8. How does the number of hours spent for reviewing
significantly relate to the licensure performance?
Statistical tool: Spearman rank order correlation
coefficient
Justification: One variable is compared to the other
variable in which frequencies or means are ranked.
This is used in ordinal data.
9. What is the level of practicum performance of
students as compared to their academic
performance in major subjects?
Statistical tool: Simple regression
Justification: There are two continuous
categorical variables in which one is causing the
changes to the other: This is used to predict the
changes to the dependent variable.
10. What is the significant difference in the weights
of newly bread animals in the four different
cages?
Statistical tool: F-test (one-way ANOVA)
Justification: The mean scores of two or more
groups are being compared. In this case, the
various weights of newly-bred animals in four
cages are compared.
11. How significantly diffeeerent are the three
instructional methods of teaching
Research to four groups of students?
Statistical tool: Two-factor ANOVA
Justification: Three mean scores of three
variables for four groups are compared.
12. What is the significant difference between
the evaluation of the supervisor and the
students?
Statistical tool: Pearson product-moment
coefficient correlation
Justification: Two continuous categorical
variables having interval data are being
compared.

Anda mungkin juga menyukai