INQUIRIES, INVESTIGATION AND MEASURES OF CENTRAL TENDENCY

IMMERSION 1. Mean – Average

Inquiries through solving of problems and probing. 2. Median – Middlemost data
It involves questioning and interrogation. 3. Mode – Most Frequency data

Investigation is done carefully and by thoroughly

inspecting details in organized manner and assessing MEASURES OF VARIABILITY
facts which are uncovered in process. 1. Range – Measurement of dispersion
Immersion means that the researchers immerse 2. Variance – A measurement of how far each
themselves in the culture they are studying. number in a data set is from the mean
(average).

CHAPTER 4: PRESENTING, ANALYSIS, and

INTERPRETATION OF DATA

• Presenting of Data
• Analysis
• Interpretation
• Discussion
3. Standard Deviation – A statistic that
STATISTICS measures the dispersion of a dataset relative
to its mean and is calculated as the square
➢ Statistics is the discipline that concerns with root of the variance.
the collection, organization, analysis,
interpretation and presentation of data.

Variable
Qualitative Quantitative
(categorical attribute) (numerical data)

Discrete
(countable data)
Continuous HYPOTHESIS
(measurable data)
1. A Hypothesis is an approximate explanation
that relates to the sets of facts that can be
tested by certain further investigation.
LEVELS OF MEASURABLE
1. Nominal – Aims to identify of label a class of 1. Null – there is no significant relationship.
variable. Ho: 1 = 2
2. Ordinal – Express ranks to denote position in 2. Alternative – there is a significant
the ordering. relationship.
3. Interval – Equal interval or distances Ho: 1  2
between any two-starting point at an Ho: 1  2
arbitrary zero. Ho: 1  2
4. Ratio – has an absolute zero point.
PARAMETER VS. STATISTICS

Parameter Statistics
1. Mean  
2. Variance 2 S2
3. Standard Deviation  s

• Parameter – a measure that describes a

population.
• Population – totality of the subject.
• Sample – representative part of the
population.
GRAPHS
NORMAL DISTRIBUTION
− A graph is a pictorial representation of data
is an organized manner. Graphs are usually
formed from various data points, which
represent the relationship between two or
more things.

• Pie Graph
− A pie chart is a type of graph that represents
the data in the circular graph. The slices of
pie show the relative size of the data, and it
is a type of pictorial representation of data.

ACCURACY PRECISION
Measures of Central Measures of Variability
Tendency
Mean () Range
Median () Variance (s2)
Mode () Standard Deviation (s)

• Line Graph
− Line graphs illustrate how related data
SKEWNESS changed over a specific period of table.
− Measure of asymmetry of a distribution.

1. Right Skewed
2. Zero Skewed
3. Left Skewed
• Bar Graph • Area Graph
− Bar graphs offer a simple way to compare − Area graphs show a change is one or more
numerical value of any kind, including quantities over a certain period of time. They
inventories, group sizes and financial often help when displaying trends and
predictions. patterns.

• Pictograph • Scatter Plot

− A pictograph uses pictures or symbols to − Scatter plots use dots to depict the
display data instead of bars. Each picture relationship between two different variables.
represents a certain number of items. The process involver plotting one variable
along the horizontal axis and the variable
along the vertical axis.

• Histogram
− A histogram is another type of bar graph that
illustrate that illustrates the distribution of
numeric data across categoric. People often STATISTICAL TEST
use histogram to illustrate statistics. • z – test
− In a z-test, we assume the sample is
normally distributed. A z-score is
calculated with population parameters
such as population mean and population
standard deviation. We use this test to
validate a hypothesis that states the
sample belongs to the same population.
This is used for hypothesis testing for
larger sample sizes.
• t – test • Chi – Square test
− We use a t-test to compare the mean of − A chi-square test is a statistical test used
two given samples. Like a z-test, a t-test to compared observed results with
also assumes a normal distribution of the expected results. We use the chi-square
sample. When we don’t know the test to compare categorical variables.
population parameters (mean and The purposes of this test of significance
standard deviation), we use t-test. This is to determine the different observed and
also used for hypothesis testing for small expected frequencies of certain
sample sizes. observations.

FORMULA:
(3) Three Version of a t – test
1. Independent Sample t – test
− Compares means for two (2) Two types of Chi-square test
groups. 1. Goodness of fit test
Ex. Group A vs. Group B − Determines if a sample matches
the populations.
2. Paired Sample t – test
− Compres means from the 2. Chi-square fit test for two
same group at different times. independent variables
Ex. Pre-test vs. Post-test − Used to compare two compare
two variables in a contingency
3. One Sample t – test table to check if the data fits.
− Tests the means of a single
group against known mean.
Ex. Section A vs. Grade 10 • ANOVA
− ANOVA, which stands for Analysis of
Variance, is statistical test used to
z - test vs. t - test z - test t - test analyze the difference between the
means of more than two groups. We use
• One Sample ANOVA to compare three or more
samples with a single test.

• Dependent/ (2) Two major types of ANOVA

Paired Sample 1. One – way ANOVA
(2 Results)
− Used to compare the difference
between three or more samples/
groups of a single independent
• Independent variable.
Sample
(2 Groups) Section (A) Section (B) Section (C)
90 85 85
95 92 95
92 90 100
 2. MANOVA: Multivariate determine its correlation coefficient
Analysis of Variance using Person Product Momentum
Coefficient.
− Allows us to test the effect of one
− Use to correlate rational data and
or more independent variables
interval data.
on two or more dependent
− When the data set is ordinal, we use the
variables.
spearman rho.
Section Section Section
(A) (B) (C) ▪ Pearson – r
Male − The Pearson Correlation Coefficient
Female (r) is the most common way of
measuring a linear correlation. It is a
number between -1 and 1 that
measures the strength and direction
CORRELATION of the relationship between two
− It is the degree of linear relationships variables. This involves determining if
between two variables. variables have a degree of the
relationship.

Positive Correlation ▪ Spearman – rho

• Indicates that large − A Spearman Correlation coefficient is
value of one variable also referred to as Spearman rank
tend to accompany correlation of Spearman’s rho. It is
large value of the other
typically denoted either with the
variable.
Greek letter rho (p), or rs. Like all
correlation coefficients, spearman’s
Zero Correlation rho measures the strength of
• Indicates no consistent association between two variables.
relationship.
▪ Kendall – tau
− Kendall’s tau is a non-parametric
measure of relationships between
columns of ranked data. This is a
Negative Correlation statistics tool used to measure the
• Indicates that small ordinal association between two
values of one variable measured quantities and determine
tend to accompany
the strength of dependence of the
large values of the other
given variables. The tau correlation
variables.
coefficient returns a value of 0 to 1,
where:
− 0 is no relationship;
• Pearson Product Momentum Coefficient − 1 is a perfect relationship.
− One way of getting a quantitative
measure for the strength and direction of
association between two variables is to
▪ Turkey’s Test
− The Turkey’s honesty significance
difference test (Turkey’s HSD) used to
test differences among sample
means for significance. The Turkey’s
HSD tests all pair wise differences
while controlling the probability of
making one or more type I errors.

▪ Mann Whitney U Test

▪ Wilcoxon Rank Sums Test