BASIC CONCEPTS OF STATISTICS CLASSIFICATION OF DATA

STATISTICS- is defined as a branch of mathematics/ 1. Qualitative data VS. Quantitative data

science which deals with the collection, organization, 2. Raw data VS. Array data
presentation, analysis and interpretation of numerical
data for the purpose of assisting in making a more Qualitative data- measures of “types” and may
effective decision. be represented by names or symbols.
- describes individuals or objects by their
*STATISTICS is everywhere.
categories or groups.
Ex: NSO/PSA - answer the question “what type”

MAJOR DIVISIONS OF STATISTICS Ex: GENDER (male or female) NATIONALITY

(Filipino, American, Swedish, Chinese, Korean
1.) DESCRIPTIVE STATISTICS- is the field of statistics and many more.) STUDENT TYPE (freshmen,
that focuses on quantitatively description of sophomore, junior and senior)
collection data.
*Central tendencies- mean, median and mode. Quantitative data- measure of “values” or
Variation, skewness and kurtosis “counts” and expressed in numbers
Ex: The market researcher of a manufacturing - Operations such as addition and averaging
company constructs a graph showing the make sense
fluctuations in sales for a major product line - Answers the questions “how many” and
during the last 3 years. “how much”
2.) INFERENTIAL STATISTICS- used to make
Ex: WEIGHT (kilograms) GRADES (70, 89, 91, 99)
conclusions of the probability that a difference
AGES (16yrs old, 19yrs old)
between samples is either reliable or by chance.
*E-test/ Z-test
Ex: The manager of a department store records
Raw data- a data can be considered raw if it is in
the number of buying customers daily for seven
its original form.
consecutive weeks and then estimates the
Array data- if the data is already arranged in its
average number of buying customers for the
certain pattern such as in ascending or
following weeks. (COMPARING RELIABLE DATAS)
descending order, then it is no longer in its
original form but rather in it arrayed form.

TWO SIGNIFICANT TERMINOLOGIES

1.) Parameter- is the field of statistics that focuses CLASSIFICATIONS OF VARIABLES

on quantitatively description of the collection of
Variables- is an observable characteristics or attribute
data. (AS A WHOLE)
associated with the population or sample being studied
2.) Statistics- is a concluded data from a proportion
which makes one different from each other.
of a population. (ONLY A PORTION)
1. According to functional relationship
 Independent variable- called the
5 BASIC STEPS IN CONDUCTING STATISTICAL INQUIRY predictor variable
 Dependent variable- called the criterion
1. Defining the problem.
variable
2. Collecting and organizing relevant information.
2. According to continuity of values
3. Presenting the data.
 Continuous variable- can be expressed
4. Analyzing the data.
in decimals
5. Interpreting the results.
 Discrete/ Discontinuous variable-
cannot be expressed in decimals
LEVEL OF MEASUREMENT person and collected through the same
process.
1. Nominal scale- data that consist of names,
3. REGISTRATION METHOD- it is executed through
labels or categories only
the collection of data from the concerned
- The data cannot be arranged in an ordering
offices.
scheme
- Examples of concerned offices can be city
- Numbers or symbols are used to classify an
municipality or psa, government offices
object or person to identify the group they
4. OBSERVATION METHOD- this method is purely
belong
based on personal remarks of the observer.
2. Ordinal scale- data contain the properties of
- Psychiatrists- observation on patients for
nominal level.
study or research.
- The data can be arranged in ordering
5. EXPERIMENTAL METHOD- it is the method that
scheme or ranks.
defines the cause-and-effect relationships of a
- The difference between the values of the
certain parameter or event under a controlled
data cannot be determined. The interval is
condition.
meaningless.
- Science: chemist, biologist…
3. Interval scale- data contains the properties of
ordinal level.
- Data values can be ranked.
SAMPLE SIZE FORMULA
- The difference between the values of the
data is of known sizes. Population- is the complete set of individuals or subject.
- The interval between the values has
meaning. Sample- is just representative of the whole.
4. Ratio scale- data contain the properties of N
interval level n= 2
1+ Ne
- The “zero” indicates the absence of the
characteristics under consideration. Where:
- The ratio of data values has meaning.
n = sample size
N= population
TOPIC 2
e= margin of error

METHODS IN COLLECTION OF DATA

SAMPLING TECHNIQUES
1. DIRECT METHOD- it is frequently called the
1. Probability Sampling- “simple random
interview method
sampling”
- This is executed through a direct and
- Each member of the population has equal
personal interaction of the researcher with
chance of being selected as part of the
the person from whom the data will be
sample.
collected. (Personal or telephone interview)
- Ex: fishbowl, raffle draw, Lotto draw
- Advantage: questions can be repeated,
2. Restricted Random Sampling- this is often times
rephrased or being modified for better
used when the population is too big.
understanding.
Systematic sampling- the selection of
2. INDIRECT METHOD- performed through the use
sample is done every kth element of the
of either online questionnaire or paper form
population.
questionnaire.
- The kth element in the population is
- The researcher distributes the questionnaire
attained using the given formula below.
either by mail or hand carry to the intended
 th N percentage distribution. It is a table
k = population ¿ ¿ sample ¿ ¿ ¿¿
n presenting the frequency and percentage
Stratified sampling- the population is sharing of nominal data.
divided into strata (groups) based on their Presents data in columns or rows
homogeneity or commonalities. Graphical Presentation- there are many
- Steps in doing sampling are as follows: types of graphs such as line, graph,
 Define the distribution of the pictograph, pie, chart etc.
population in each stratum. Its shows the important relationship
 Find the percentage of each clearly
stratum from population.
 Multiply the percentage of each 1. Line graph- it shows associations
stratum by the sample size. between two or more sets of
3. Cluster Sampling- it is frequently used on quantities. In this technique, the
geographical basis when the population from values are plotted using dots which
which sample is to be chosen includes are called “markers” to be connected
heterogenous groups. together by line segments.
4. Non-Random Sampling- not all of the -shows pattern of changes in a given
population has to be equal opportunity to be time
chosen. The selection is influenced by the goal 2. Bar graph- it is a graphical method in
of the researcher. which each value in the data is
Purposive sampling- the samples are represented by rectangular bars. The
picked based on purpose or definite length of the bars shows the measure
criteria of a certain value while its width has a
Ex: The effects of being sporty in the fixed size.
academic performance 3. Pictograph- this is a graphical
Quota sampling- in this technique a technique that expresses the meaning
certain limit is pre-established to find who through its pictorial similarity to
among the population can be part of the physical object. Each object used in
sample. pictograph stands for corresponding
Ex: The determination of the students who measure. Effective for attracting
can qualify in a university. attention.
Convenience sampling- the sample is 4. Pie chart- this is the type of graphical
chosen based on the accessibility of the presentation in which a circle (or
researcher in the convenience sampling. sometimes a cylinder) is divided into
Ex: The performance of universities in the several parts with each parts typifying
Philippines. the categories of the data.

METHODS IN PRESENTATION OF DATA

Textual Presentation- this is the technique

in the paragraph form. In this technique, it
does not necessary mean that the
presentation contains of words only but
figures can also be utilized as part of the
presentation. “Paragraph method”
Tabular Presentation- this is another way
of presenting data. In this technique, the
data are summarized using tables. A table
usually used is on the frequency and
 STEPS IN HYPOTHESIS TESTING

1. Formulate the null and alternative hypotheses.

2. Choose a level of significance to be used.
3. Decide the test statistics to be used and the
ztabular or ttabular.
4. Compute for the value of test statistics.
TOPIC 3 5. Make a decision.
HYPOTHESIS TESTING - If the computed value of the test statistics is
greater than the critical or tabular value,
HYPOTHESIS- wild guest; a supposition or proposed reject Ho and accept Ha.
explanation made on the basis of limited evidence as a - If the computed value of the test statistics is
starting point for further investigation. less than or equal the critical or tabular
2 TYPES OF HYPOTHESES value, reject Ha and accept Ho.
6. State the conclusion.
1. NULL HYPOTHESIS- is the claim about a
population characteristic that is initially
assumed to be true. Z-TEST – if the sample size is greater than or equal 30
- You have an overview on the results sample units, the z-test is the most appropriate test
- Simply denoted by Ho statistics.
2. ALTERNATIVE HYPOTHESIS- is the claim that
contradicts the null hypothesis. ONE SAMPLE MEAN
- Denotes by Ha
( x−µ ) √ n
Zcomputed=
2 WAYS TO CONTRADICT NULL HYPOTHESIS σ
1. ONE-TAILED TEST- basically opposing the null
hypothesis with one directional claim
2. TWO TAILED TEST- is opposing using a two-
directional claim.

TERMINOLOGIES IN HYPOTHESIS TESTING

1. TEST STATISTICS- is the quantity calculated from

the sample data that is used a decisive
parameter in forming the final conclusions.
- Z-test, T-test, ANNOVA/ F-test Where:
2. SIGNIFICANCE LEVEL- is the degree of certainty
required in order to reject the null hypothesis in x = sample mean
favor of the alternative hypothesis.
µ= population mean
3. CRITICAL VALUE- is the value for a hypothesis
test that is threshold to which the value of the n= number of samples
statistics in a sample is being compared to
σ = population’s standard deviation
determine whether or not the null hypothesis is
rejected. TWO SAMPLE MEAN
4. CRITICAL REGION- also called region of
rejection; the set of values of the test statistics
x1 −x2

√
2 2
for which the null hypothesis is rejected. Zcomputed= s1 s 2
+
n1 n2
x 1= 1st sample mean

x 2= 2nd sample mean

n1 = number of samples of the first group sample

n2 = number of samples of the second group sample

s1= 1st sample’s standard deviation

s2= 2nd sample’s standard deviation