Statistics -​ Not numbers but rather characteristics or

-​ Both an art and science that deals with the properties of a population of a population or
collection, organization, presentation, sample which makes the members similar to
analysis (extracting important info from the each other
data), and interpretation (be able to explain -​ There should be diversity and, preferrably, no
why scores are good/bad then offer findings constant
and recommendations after) of data; science Variable
because we use it in making decisions -​ Any characteristics or info measurable or
observable on every element of the
Purpose of statistics population or sample
-​ Provide info -​ Subdivided into 2 general categories
-​ Provide comparisons Qualitative (Categorical)
-​ Help discern relationships -​ Answers wh questions
-​ Aid in decision-making -​ Indicate what kind of a given characteristic
-​ Justify claims or assertions an individual, object, or even possesses
-​ Estimate unknown quantities Quantitative (Numerical)
-​ Predict future outcomes -​ Indicate how much a given characteristic an
individual, object, or event possesses
Branches of statistics -​ Discrete
Descriptive -​ Values are obtained through the
-​ Consists of methods concerned with the process of counting
collection, organization, summarization, and -​ Whole number
presentation of a set of data -​ Continuous
Inferential -​ Values are obtained through the
-​ Comprised of those methods concerned with process of measuring
making predictions or inferences about an -​ Using simple tools
entire population based on info provided by -​ Can be whole or decimal numbers
the sample Dependent
-​ Variable that is affected by another variable
Population Independent
-​ totality of all the elements or entities from -​ Affects the dependent variable
which you want to obtain an information
Sample Frameworks
-​ Small portion of the population; subset of the -​ Dependent variable lagi sa right and
population independent sa left
-​ If randomly selected, more or less the same Moderating (indirect)
result as the population compared to when Mediating (effect of IV can give + / - effect on the
chosen using a preferential method DV)

Census and survey Scales of measurement of variable

-​ Referring to different data sets Nominal
Census -​ Variables whose values are simply labels or
-​ Process of collecting information from the names or categories without any explicit or
population implicit ordering of the labels
-​ PSA -​ Lowest level of measurement known as
Survey categorical scale
-​ The process of collecting information from Ordinal
the sample -​ Variables whose values are simply labels or
Parameter names or categories with an implied ordering
-​ A summary or numerical measure used to in these labels
describe a population -​ Ranking can be done on the data
Statistic -​ Distance between two labels can not be
-​ A summary or numerical measure used to determined
describe a sample; from sample data Interval
Constant
 -​ Variables whose values can be ordered and 4.​ Identity the class intervals (CI)
distance between any two labels are of -​ If inclusive kasama yung lowest or
known size highest
-​ Always numeric and have no true zero point 5.​ Identify the frequency in each CI or
Ratio tallying
-​ Variable whose values have all the properties
of the interval scale and the ratio of two Class size/width
values is meaningful -​ Difference between the upper or lower class
-​ Has true zero point limits of consecutive classes
-​ Highest level of measurement -​ All classes should have the same class width
_____________________ -​ Lower class limit (least value that can belong
to a class) and Higher class limit (greatest
Data presentation value)
-​ Numerical quantities focus
Textual Class boundaries
-​ Data are presented in paragraph form -​ Numbers that separates classes without
-​ Enumeration or important characteristics, forming gaps between them; like intervals
giving emphasis on significant figures and pero walang gaps so may overlapping na
identifying the important features of the data -​ Dapat laging a little more kesa a little less
-​ If hindi naman super laki yung data pwede -​ Use histogram
naman i-text nalang
-​ Arrange i array form (smallest to largest/least Class mark/midpoint
to most) -​ Middle value of each data class
-​ To find the class midpoint, average the upper
and lower class limits

Relative frequency
-​ Obtained by dividing the frequency of the
given class by the total number of
observations

Additional information
Less than CF (<cummlative frequency)
-​ Total no. of observations within a class
whose values do not exceed the upper limit
of the class
Greater than CF
-​ Total no. of observations within a class
Tabular
whose values are not less than the lower limit
-​ Sometimes we could hardly grasp info from a
of the class
textual presentation thus data are presented
Cumulative frequency of a data class
using tables
-​ The number of data elements in that class
and all previous classes
Frequency distribution table
__________________________________________
-​ Tubular summary of data showing the
_
frequency or number of items in each several
non-overlapping classes
Numerical descriptive measure
-​ Use bar graph
-​ Values to describe data
1.​ Determine the range (R)
-​ Point intersection of ogives (central
-​ Range - difference between the
tendency)
highest and lowest value
2.​ Decide on the number of classes (K)
Measures of central tendency
-​ K - no. of non-overlapping intervals
-​ Describes the center of a given data set;
3.​ Compute for the class size (C)
single value about which the observation
-​ C - quotient of steps 1 and 2
tends to cluster
Mean -​ Variability is descriptive statistics that
-​ Average describe how similar a set of scores are to
1.​ It always exist each other
2.​ It is unique -​ Types of variability
3.​ It is sensitive; it takes into account all the 1.​ range
element; sensitive = good quality -​ Diff. between max and min
values; not that reliable
Median 2.​ Variance
-​ Observation -​ Mean squared differences of
1.​ It always exist the observation from their
2.​ It is unique mean (deviation score)
3.​ Not sensitive; not very reliable measurement 3.​ standard deviation
-​ Only the positive square root
Mode of the variance
-​ Appear more often compared to other 4.​ Coefficient of variation
1.​ May not exist -​ Ration of the SD to its mean
2.​ May not be unique; can be multiple expressed in percentage
3.​ No computation needed -​ Expressed in percent; higher =
more dispersed, lower = less
●​ For nominal variables, mode is the only dispersed
measure that can be used
●​ For ordinal variables, the mode and the Skewness
median may be used; median provides more -​ Measure if it is normal or not; related to
info (taking into account the ranking of normality of data; measure of symmetry in
categories) the distribution of scores
●​ For interval-ratio variables, the mode, -​ If data is normal, it should be approx. normal
median, and mean may all be calculated; distributed; skewness = 0 pag hindi pa nag
mean provides the most info about the one above its approx normal; all measures of
distribution, but the median is preferred if the central tendency are in one place
distribution is skewed -​ Mean > median = positively skewed (sk > 0);
mean < median = negatively skewed (sk < 0)
Measures of position -​ Positively skewed (skewed to the right); left is
-​ Descriptive statistics that discriminate (being almost normal (more low scores) and right
categorized) one score from another score side is not (less high scores)
within the same data set; fighting for a -​ Negatively skewed right is almost normal
position (more high scores) and left is not (less low
-​ Quantile scores)
-​ Dividing the data set into several
parts equally
-​ Types of quantiles
1.​ Quartile (4)
2.​ Decile (10)
3.​ Percentile (100)

Interpolation Kurtosis
-​ Looking for a number between two identified -​ Measuring the peakedness
numbers

Measure of Variability (measures of dispersion)

-​ Far from each other = very disperse
-​ More similar scores = lower dispersion, less
similar scores = higher dispersion
-​ Measure the closeness and layo
 -​ Perfectly normal curve (mesokurtic)
-​ Medyo flat (platykurtic)
-​ Normal curve but high peak (leptokurtic) =
data is compressed the gitna so frequency
increases
-​ 3 = mesokurtic
-​ k < 3 = platy
-​ k > 3 = lepto
__________________________________________
Pearson product moment coefficient of correlation
Pearson (r)
-​ An index of relationship between two
variables
-​ x = independent variable, y = dependent
-​ The value of r ranges from -1, 0, +1
-​ If r = 1 or -1 = perfect correlation
-​ If r = 0, x and y are independent of
each other
-​ Ex. test scores

If the trend of the line graph is going upward, the

value of r is positive. This indicates that as the value
x increases, the value of y also increases, x and y
being positively correlated -​ Pag nasa middle moderate correlation
-​ If malapit sa zero pwedeng + or - , medyo
weak correlation
-​ If malapit sa + or -1, medyo strong correlation

Why do we use r?
-​ To analyze if a relationship exists between
two variables
-​ Coefficient of determination
-​ Equal to the square of r and multiplied
by 100%
-​ Explain or answer how much the
independent variable influences the
dependent variables or how much y
depends on x
If the trend of the line graph is going downward, the -​ Degree of relationship between x and
value of r is negative. This indicates that as the value y which cannot be seen in other
x increases, the value of y decreases, x and y being statistical tests of relationship
negatively correlated -​ More powerful test of relationship
compared with other nonparametric
tests

When do we use r, the pearson product moment

coefficient of correlation?
-​ Determine the index relationship between IV
and DV
-​ The value of r ranges from +1 through zero
-1. There is a perfect positive correlation of r
= +1, likewise there is a negative perfect
correlation if the value of r = -1. However, if r
= 0 then there is no correlation between the
two variables x and y
-​ Positive correlation, as x increases y also
If the trend of the line cannot be established either increases or vice versa
upward or downward, then r = 0, indicating that there -​ negative correlation, as x decreases y
is no correlation between x and y variables increases or vice versa
 When to use?
-​ When there is a relationship between x and y
variables
-​ Data should be normally distributed using the
level of measurement, which is expressed in
an interval or ratio data
Why use?
-​ Interest in predicting the value of y, the
dependent variable; used for forecasting and
prediction

__________________________________________

F test
-​ A parametric test used to compare the
means of two or more groups of independent
__________________________________________ samples
-​ Analysis of variance (ANOVA)
Simple regression analysis -​ Kinds of analysis of variance:
Regression model (equation) -​ One-way: only 1 variables
-​ predict the value of y given the value of x -​ Two-way: 2 variables (column and
row); used to know if there are
 significant differences between and
among columns and rows

Why use?
-​ To find if there is a significant difference
between and among the means of the two or
more independent groups
When to use?
-​ If there is normal distribution and when the
level of measurement is expressed in interval
or ratio data (like t-test and z-test)
-​ Data should be numeric to know if they are
the same or different

Formula:

-​ TSS = the total sum of squares minus CF, the

correction factor
-​ BSS = the between sum of squares minus
the CF
-​ WSS = within sum of squares or it is the
difference between the TSS minus BSS
-​ GT = grand total
-​ N = total number of observations

B+W=T
W=T-B
-​ Compare three groups
F-test two-way ANOVA with interaction effect
-​ If there is interaction between variables
-​ If its two-way there can be more than 2 hypo
; hypothesis is 3 (one for each problem)
-​ The presence of 1 can affect the other
-​ Only used to know if they are the same or not
the same
Multiple regression
-​ Several independent variables
-​ Used to predict the dependent variable y
given the independent variable x
-​ Aside from prediction, we can also see
relationship between the dependent variable
and the different independent variables
 -​ Selects every kth member of the
population with the starting point
determined at random
Non probability
-​ Each member does not have equal chance
1.​ Used when there isnt an exhaustive
population list available (no list)
2.​ Not random
3.​ Can be effective when trying to generate
ideas and getting feedback; not considered
for the whole population parang feedback
lang from the sample
4.​ More convenient and less costly
Sampling techniques -​ Convenience sampling
Population -​ Uses subject that are readily available
-​ Set of which includes all measurements of or includes only people who are easy
interest to the researcher to reach
-​ Collection of responses measurements or -​ Purposive sampling
counts that are of interest -​ Researcher looks for predefined
Sample groups that will serve as samples
-​ A subset of the population
Sample size (n)
Why do we do sampling -​ Number of respondents
-​ Impossible to study the whole population -​ Most statisticians agree that the minimum
-​ Manageability of data sample size to get any kind of meaningful is
-​ Economic reasons 100 but if less than 100 lang yung population,
-​ Time and effort try to get all of them.
-​ A good maximum sample size is usually 10%
Types of sampling as long as it does not exceed 1000
Probability samping
-​ Everybody in the population is given equal
chance of being includes
1.​ You have a complete sampling frame
2.​ You can select a random sample from the
population -​ The more samples, the better; the opinion of
3.​ You can generalize your results from a 1000 people is always better than 100
random sample
4.​ Can be more expensive and time consuming Determining sample size
(theres a process) 1.​ Using a census for small population
-​ Simple random sampling (everyone is surveyed)
-​ All members of the population have a 2.​ Using sample size which is 10% of N
chance of being included in the 3.​ Using published tables
sample 4.​ Using formulas to determine sample size:
-​ Fish bowl method slovin’s formula
-​ Stratified sampling
-​ Used when the population can be
subdivided into several smaller
groups or strata and then SRS is
applied to get samples from each
stratum
-​ Cluster sampling
-​ Employs the use of cluster (groups)
instead of individuals that are
randomly chosen; usually for big data
-​ Systematic sampling
 -​ Critical point = divides the rejection and
acceptance (this is the decision rule)
-​ Value is taken from a statistical table;
Tabular value (z or t-table)
4. Test statistics; do the computation
5. Make a decision
6. Write a conclusion

Null hypothesis
-​ default/established= “it is believed”; thought
to be true unless it is rejected
-​ Currently accepted value for a parameter
-​ Always hoped to be rejected
-​ Always contains “=” sign
-​ Status quo
-​ Hypothesis of equality
Alternative hypothesis
-​ Also called the research hypothesis; involves
the claim to be tested
-​ Used to contradict the null hypothesis
-​ Uses > or < or ≠l to
-​ Generally represents the idea which the
researcher want to prove

Ho and Ha are mathematical opposites

______________________

Hypothesis
-​ A premise or claim that we want to test
-​ Assumption about the population parameter
-​ An educated guess
Hypothesis testing
-​ Process of making an inference or
generalization on population parameters
based on the results of the study on samples
-​ Deciding between what is reality and what is
a coincidence
Statistical hypothesis
-​ A guess or prediction made by the
researcher regarding the possible outcome of
the study Level of significance, alpha and the rejection
region
Steps in hypothesis testing -​ alpha = 0.05, means the probability of being
1. Formulate Ho and Ha right is 95% and the probability of being
2. Set the level of significance, usually it is given in wrong is 5%
the problem; the level of significance is the same as
the margin of error Possible outcomes
-​ Maximum tolerance of error; 95% -​ Reject null hypothesis
3. Formulate the decision rule (when to reject Ho); -​ Fail to reject null hypothesis
find the critical value/P-value
-​ Directional and non-directional (left OR Test statistic
right = 1-tailed test, left and right = 2-tailed -​ Calculated from sample data and used to
test) decide (either reject or fail to reject)
-​ Sample 50 bars
Statistically significant
-​ Where do we draw the line to help us decide * If nasatisfy nasa rejection pero pag hindi nasa
if we should reject or fail to reject the null acceptance
hypothesis?
Testing the hypothesized value of the mean
Level of confidence (C)
-​ How confident are we in our decision?

Level of significance (alpha = 1 - C)

-​ 1-10%; normally 5% so 95% ang confidence
level

Types of hypothesis tests

1. One-tailed (left directional) Examples:
-​ Used if Ha uses “<” symbol

2. One-tailed test (right directional)

-​ Used if Ha uses “>” symbol

__________________________________________

-​ .

3. Two-tailed test (Non-directional) __________________________________________

-​ Used if Ha uses “≠” symbol

-​ and
 __________________________________________
__________________________________________

__________________________________________
__________________________________________
__________________________________________
Testing the difference between two means

__________________________________________ __________________________________________

Decisions made regarding Ho (Reject Ho/Do not

reject Ho)
-​ If we reject Ho, it means it is wrong
-​ If we accept Ho, it doesn’t mean it is correct,
we just don’t have enough evidence to reject
it

Errors in hypothesis testing

__________________________________________
Source SS d MS F-value
s of f
variatio Comput Tabula Interpr
n ed r et.

Betwee 178. 2 89.09 24.82 3.26 S

nC 18

Betwee 14.0 2 7.02 1.95 3.26 NS

nR 5

Interacti 187. 4 46.79 13.03 2.63 S

on 15

Within 129. 3 3.59

20 6

Total 508. 4
58 4

A B C GT

MT1 198 241 197 636

MT2 196 210 224 630

MT3 201 216 199 616

GT 595 667 620 1882