STATISTICS

(RESEARCH-BASED)
ZENAIDA ULPINDO-GARAMBAS
MARCH 3, 2018
 STATISTICAL HYPOTHESIS
• A STATISTICAL HYPOTHESIS IS A CLAIM OR ASSERTION
MADE ON THE DISTRIBUTION OF A POPULATION OR
CONCERNING THE VALUES OF ONE OR MORE POPULATION
PARAMETERS.
• THE STATISTICAL HYPOTHESIS MAY EITHER BE ACCEPTED
(TRUE) OR REJECTED (FALSE).
• HYPOTHESIS TESTING IS A STATISTICAL PROCEDURE
USING SAMPLE DATA TO ASSESS OR DETERMINE WHICH
HYPOTHESIS IS MORE ACCEPTABLE AS TRUE OR WHICH
HYPOTHESIS IS MORE LIKELY TO BE TRUE; IT IS AN
EVALUATION OF A PARAMETER VALUE.
 EXAMPLES OF HYPOTHESES THAT CAN
BE TESTED:
• 1. THE MEAN MONTHLY SALARY OF TEACHERS IS
PHP26,000.00
• 2. UNEMPLOYMENT RATE IN THE RURAL AREAS IS MORE
THAN 35%.
• 3. THE NEW TYPE OF TIRE MANUFACTURED BY WEA
COMPANY HAS A SHORTER SKID DISTANCE.
• 4. THERE IS A SIGNIFICANT DIFFERENCE BETWEEN THE
MEAN DIASTOLIC BLOOD PRESSURES OF VEGETARIANS
AND NON-VEGETARIANS.
 Null • Statement being tested
• Claim that there is no difference in
hypothesis, the population parameter and the
hypothesized value
Ho

Alternative • Converse of the null hypothesis;

provides an alternative to the
hypothesis, null hypothesis
Ha • The research hypothesis
THERE IS NO SIGNIFICANT DIFFERENCE IN THE LISTENING
COMPREHENSION LEVEL OF THE STUDENTS ALONG THE
MICRO-SKILLS ACCORDING TO: A) GENDER, AND B)
YEAR LEVEL
THERE IS NO SIGNIFICANT RELATIONSHIP BETWEEN
UNSATURATED OIL VISCOSITY AND OPERATING
CONDITION.
THERE ARE NO SIGNIFICANT DIFFERENCES IN THE
PHOTOCATALYTIC EFFICIENCY OF AG3PO4 AMONG
DIFFERENT NUMBERS OF RECYCLES USED.
THERE IS NO SIGNIFICANT RELATIONSHIP
BETWEEN THE LEVEL OF KNOWLEDGE AND LEVEL
OF SKILLS OF THE TEACHERS IN XYZ SCHOOL
GENDER IS INDEPENDENT OF THE LEVEL OF
ACADEMIC PERFORMANCE OF THE STUDENTS.
THERE ARE NO SIGNIFICANT DIFFERENCES IN THE
EXTENT OF USE OF TECHNOLOGY WHEN THE
RESPONDENTS ARE GROUPED ACCORDING TO
EDUCATIONAL ATTAINMENT.
THERE IS A SIGNIFICANT DIFFERENCE IN THE LISTENING
COMPREHENSION LEVEL OF THE STUDENTS ALONG THE
MICRO-SKILLS ACCORDING TO: A) GENDER, AND B) YEAR
LEVEL
THERE IS A SIGNIFICANT RELATIONSHIP BETWEEN
UNSATURATED OIL VISCOSITY AND OPERATING CONDITION.
THERE ARE SIGNIFICANT DIFFERENCES IN THE
PHOTOCATALYTIC EFFICIENCY OF AG3PO4 AMONG
DIFFERENT NUMBERS OF RECYCLES USED.
THERE IS A SIGNIFICANT RELATIONSHIP BETWEEN
THE LEVEL OF KNOWLEDGE AND LEVEL OF SKILLS
OF THE TEACHERS IN XYZ SCHOOL
GENDER IS ASSOCIATED WITH THE LEVEL OF
ACADEMIC PERFORMANCE OF THE STUDENTS.
THERE ARE SIGNIFICANT DIFFERENCES IN THE
EXTENT OF USE OF TECHNOLOGY WHEN THE
RESPONDENTS ARE GROUPED ACCORDING TO
EDUCATIONAL ATTAINMENT.
 • area under the curve that contains
all values of the statistic that allow
Critical region rejection of the null hypothesis (also
called the rejection region)
• Critical point; associated with the
Critical critical region
• it is the point of division between
value, C.V. the rejection region and the non-
rejection region
• corresponds to the area in the rejection
region.
Level of • When a test statistic falls in this area, the
result is referred to as statistically
significance, α significant at the given level of
significance, α ).
 Test • derived or computed from a
sample data set that is used
statistic to determine the relative
position of the mean

• If…then statement on the null

Decision hypothesis: Reject if computed
value is greater than the
rule critical value; otherwise fail to
reject
• Non-directional • Directional
• The critical • The critical
region is region is
located in both located in one
tails tail
 EXAMPLE

• TWO-TAILED TEST • ONE-TAILED TEST

• THE MEAN LEVELS OF • THE MEAN LEVEL OF

COMPETENCE OF COMPETENCE OF
EDUCATIONAL LEADERS IN EDUCATIONAL LEADERS IN
THE URBAN AND IN THE THE URBAN AREAS IS
RURAL AREAS DIFFER HIGHER THAN THOSE IN
SIGNIFICANTLY. THE RURAL AREAS.
IN CHOOSING A PARTICULAR SIGNIFICANCE TEST, THE
FOLLOWING QUESTIONS SHOULD BE CONSIDERED:

1. IS THE LEVEL OF MEASUREMENT NOMINAL,

ORDINAL, INTERVAL OR RATIO?
2. DOES THE TEST INVOLVE ONE SAMPLE, TWO
SAMPLES, OR K (MORE THAN TWO) SAMPLES?
3. IF TWO SAMPLES OR K SAMPLES ARE INVOLVED,
ARE THE INDIVIDUAL CASES INDEPENDENT OR
DEPENDENT (RELATED)?
4. WHAT IS THE SAMPLE SIZE (OR NUMBER OF
RESPONDENTS)?
 LEVELS OF MEASUREMENT
• NOMINAL (QUALITATIVE) – DATA VALUE IS A DISTINCT
CATEGORY WHICH SERVES AS A LABEL.
EX: SEX (MALE , FEMALE); REGION; OPINION (IN FAVOR,
NOT IN FAVOR OR YES, NO); TYPE OF AGRICULTURAL
PRACTICES (ORGANIC, NON-ORGANIC);
• ORDINAL (QUALITATIVE) – VALUES ARE CATEGORIES WHICH
CAN BE RANKED OR ORDERED TO SOME CRITERION, BUT
DISTANCE BETWEEN TWO CATEGORIES CAN NOT BE
QUANTIFIED; DATA WHICH COULD BE RANKED BUT
DIFFERENCE COULD NOT BE QUANTIFIED.
EX: NUTRITIONAL STATUS (UNDERWEIGHT, NORMAL
WEIGHT, OVERWEIGHT); SEVERE, MODERATE, MILD; SUPERIOR,
GOOD, AVERAGE, POOR
 LEVELS OF MEASUREMENT
• INTERVAL AND RATIO SCALES (QUANTITATIVE) – VALUES
ARE REAL NUMBERS SUCH AS WEIGHT, HEIGHT, AMOUNT
OF DAILY FOOD INTAKE.
• EXAMPLES FOR INTERVAL SCALE: LEVEL OF HAPPINESS
WITH A SCALE OF 1 TO 10; DEGREE OF SERIOUSNESS OF
PROBLEMS ENCOUNTERED WITH A SCALE FROM 1 TO 5;
IQ AND FOR RATIO SCALE: MILES PER HOUR, TONS PER
DAY; NUMBER OF STUDENTS VISITING THE INTERNET
LIBRARY PER WEEK
NUMBER OF SAMPLES/GROUPS
• ONE SAMPLE
• TWO SAMPLES
• K-SAMPLES (MORE THAN TWO)
SOME PARAMETRIC
TESTS
TYPES OF STATISTICAL HYPOTHESIS TEST:
1. PARAMETRIC TESTS – ARE TESTS THAT MAKE USE OF
PARAMETERS (FACTORS) SUCH AS POPULATION MEAN
OR STANDARD DEVIATION. THE DATA ARE DERIVED
FROM INTERVAL AND RATIO MEASUREMENTS.
2. NON - PARAMETRIC TESTS – ARE USED TO TEST
HYPOTHESIS WITH NOMINAL-SCALED AND
ORDINAL-SCALED DATA. OBSERVATIONS NEED NOT
TO BE DRAWN FROM NORMALLY DISTRIBUTED
POPULATION.
 DIFFERENCE BETWEEN TWO POPULATION
MEANS USING THE
T-TEST
• THE POPULATIONS ARE APPROXIMATELY
NORMAL
• THE DATA ARE AT LEAST INTERVAL-SCALED
 DIFFERENCE BETWEEN TWO POPULATION
MEANS USING THE
T-TEST
• FOR TWO SAMPLES
INDEPENDENT SAMPLES
DEPENDENT SAMPLES
(MATCHED PAIRS, PAIRED OR
CORRELATED SAMPLES)
• WHEN YOU CONDUCT A HYPOTHESIS TEST
USING TWO RANDOM SAMPLES, YOU MUST
CHOOSE THE TYPE OF TEST BASED ON WHETHER
THE SAMPLES ARE DEPENDENT OR INDEPENDENT.
THEREFORE, IT IS IMPORTANT TO KNOW
WHETHER YOUR SAMPLES ARE DEPENDENT OR
INDEPENDENT.
• DATA ARE INDEPENDENT WHEN THE DATA FOR
DIFFERENT SUBJECTS DO NOT DEPEND ON EACH
OTHER. WHEN WE SAY A VARIABLE IS INDEPENDENT
WE MEAN THAT IT DOES NOT DEPEND ON ANOTHER
VARIABLE FOR THE SAME SUBJECT.
• INDEPENDENT SAMPLES ARE MEASUREMENTS MADE
ON TWO DIFFERENT SETS OF ITEMS.
• IF THE VALUES IN ONE SAMPLE REVEAL NO
INFORMATION ABOUT THOSE OF THE OTHER SAMPLE,
THEN THE SAMPLES ARE INDEPENDENT.
• DEPENDENT SAMPLES ARE PAIRED MEASUREMENTS
FOR ONE SET OF ITEMS
• IF THE VALUES IN ONE SAMPLE AFFECT THE VALUES IN
THE OTHER SAMPLE, THEN THE SAMPLES ARE
DEPENDENT.
• ONE EXAMPLE IS WHEN WE MEASURE THE SAME
PERSON (OR OTHER SUBJECT) MORE THAN ONCE. IF I
GIVE A GROUP OF STUDENTS A MIDTERM AND A
FINAL GRADE, THE FINAL GRADE IS LIKELY TO DEPEND
ON THE MIDTERM GRADE, NOT JUST BECAUSE OF A
GENERAL RELATIONSHIP BETWEEN THE TWO GRADES,
BUT BECAUSE IT IS THE SAME PERSON.
EXAMPLE OF COLLECTING DEPENDENT
SAMPLES AND INDEPENDENT SAMPLES
• CONSIDER A DRUG COMPANY THAT WANTS TO TEST THE
EFFECTIVENESS OF A NEW DRUG IN REDUCING BLOOD
PRESSURE. THEY COULD COLLECT DATA IN TWO WAYS:

OR ANOTHER PROCEDURE . . . . .
• GIVE ONE GROUP OF PEOPLE AN ACTIVE DRUG AND
GIVE A DIFFERENT GROUP OF PEOPLE AN INACTIVE
PLACEBO, THEN COMPARE THE BLOOD PRESSURES
BETWEEN THE GROUPS. THESE TWO SAMPLES WOULD
LIKELY BE INDEPENDENT BECAUSE THE MEASUREMENTS
ARE FROM DIFFERENT PEOPLE. KNOWING SOMETHING
ABOUT THE DISTRIBUTION OF VALUES IN THE FIRST
SAMPLE DOESN'T INFORM YOU ABOUT THE
DISTRIBUTION OF VALUES IN THE SECOND.
ANALYSIS OF VARIANCE (ANOVA)
• THE ANOVA IS USED TO TEST HYPOTHESES
ABOUT MEANS RATHER THAN FOR VARIANCES
• FOR MORE THAN TWO SAMPLES
• POPULATIONS APPROXIMATELY NORMAL
• CAN BE USED TO DETERMINE IF THERE IS A
SIGNIFICANT DIFFERENCE AMONG THE MEANS
OF THE GROUPS
• ONE-WAY ANOVA (COMPLETELY
RANDOMIZED DESIGN)
• TWO-WAY ANOVA (TWO-FACTOR ANOVA)
• EXAMPLE: IT WAS KNOWN THAT A TOXIC MATERIAL WAS
DUMPED IN A RIVER LEADING INTO A LARGE SALT WATER
COMMERCIAL FISHING AREA. CIVIL ENGINEERS STUDIED
THE WAY THE WATER CARRIED THE TOXIC MATERIAL BY
MEASURING THE AMOUNT OF THE MATERIAL (IN PARTS PER
MILLION, PPM) FOUND IN OYSTERS HARVESTED AT THREE
DIFFERENT LOCATIONS, RANGING FROM THE ESTUARY
OUT INTO THE BAY WHERE THE MAJORITY OF
COMMERCIAL FISHING WAS CARRIED OUT. THE RESULTING
DATA ARE AS FOLLOWS:
DATA
Site 1 Site 2 Site 3
29 13 25
28 15 24
21 18 23
15 20 26
26 15 15
20 10 17
20 25 24
26 20
18
• TEST WHETHER THERE IS A SIGNIFICANT
DIFFERENCE IN THE AVERAGE PARTS PER
MILLION OF TOXIC MATERIAL FOUND IN
OYSTERS HARVESTED AT THE THREE SITES
USING THE 5% LEVEL OF SIGNIFICANCE.
PEARSON PRODUCT-MOMENT
CORRELATION COEFFICIENT, R
• MEASURE OF THE LINEAR CORRELATION
BETWEEN TWO VARIABLES X AND Y, GIVING A
VALUE BETWEEN +1 AND −1 INCLUSIVE, WHERE
1 IS TOTAL POSITIVE CORRELATION, 0 IS NO
CORRELATION, AND −1 IS TOTAL NEGATIVE
CORRELATION
• USES INTERVAL OR RATIO DATA
THE STRENGTH OR DEGREE OF THE RELATIONSHIP
IS BASED ON THE FOLLOWING RANGES OF THE
CORRELATION COEFFICIENT:
• RANGES OF R DEGREE/STRENGTH OF
RELATIONSHIP

±1.00 PERFECT RELATIONSHIP

• ± 0.90 TO ± 0.99 VERY STRONG/VERY HIGH
• ± 0.70 TO ± 0.89 STRONG/HIGH
• ± 0.40 TO ± 0.69 MODERATE/SUBSTANTIAL
• ± 0.20 TO ± 0.39 WEAK/SMALL
• ± 0.01 TO ± 0.19 ALMOST NEGLIGIBLE TO SLIGHT
• 0 NO CORRELATION
 •USING TECHNOLOGY IN
TREATING STATISTICAL DATA
• (MICROSOFT EXCEL)
CORRELATION
'Ice cream Sales' for a particular firm and 'Average
Monthly Temperature'.
Sales
Month Ave temp (°C) (Php ‘000)
January 24 365
February 24 285
March 27 405
April 28 470
May 32 550
June 35 620
July 36 670
August 37 695
September 34 620
October 31 515
November 27 405
December 25 400
 STATISTICAL DATA ANALYSIS TOOLS
IN THE MICROSOFT EXCEL
INSTALLING OR LOADING THE ANALYSIS TOOLPAK
1. ON THE MICROSOFT EXCEL WORKBOOK, CLICK THE OFFICE BUTTON
AT THE TOP LEFT PART OF THE SCREEN.
2. CLICK EXCEL OPTIONS.
3. CLICK ADD-INS. THEN, CLICK ANALYSIS TOOLPAK.
CHOOSE
EXCEL ADD-INS BESIDE MANAGE AND THEN CLICK GO…
4. CHOOSE ANALYSIS TOOLPAK AND CLICK OK.
5. THE DATA ANALYSIS TAB IS INCLUDED
UNDER DATA TAB.
 IF THE ANALYSIS TOOLPAK ADD-IN
PROGRAM IS ALREADY LOADED, WE CAN NOW
USE THE DATA ANALYSIS COMMAND.
COMPUTING THE
WEIGHTED MEAN
 INDICATORS
A. Academic Competence

1. I am able to manage the academic course load

2. I find the lessons taught interesting
3. I do the assigned activities and homework
4. I do my best to understand the course material taught
5. I try to supplement the lessons learned by researching/reading
other references
B. Time Management
1. I can balance my time for house work, study, and leisure.
2. I find time to study regularly
3. I avoid “cramming” for quizzes/examinations
4. I find time for spiritual nourishment (daily prayer and Sunday
services)
5. I arrive in school a few minutes before my class starts (or just on
time).
A. Academic Competence R1 R2 R3 R4 R5 R6 R7 R8 R9 R10 R11 R12 R13 R14 R15 WM

1. I am able to manage the

academic course load 5 4 5 3 4 4 3 5 5 4 4 3 4 4 5

2. I can easily understand

course material taught 4 3 3 4 5 5 5 3 3 3 4 4 4 3 3
3. I find the lessons taught
interesting 4 4 4 4 4 5 5 2 2 4 3 3 4 3 3

4. I do the assigned activities

and homework 4 4 3 3 3 3 3 3 3 4 2 2 3 3 3

5. I do my best to understand
the course material taught 3 3 3 2 4 4 4 4 3 3 3 3 3 4 4
6. I try to supplement the
lessons learned by
researching/reading other
references 4 4 4 3 3 3 3 3 3 4 4 4 3 3 3
 Some-
Almost Always Rarely Almost
Often (4) times WM DE
(5) (2) Never (1)
(3)

12 15 6 2 0 4.06 O
7 8 7 8 5
15 9 7 3 1
6 12 10 5 2

5 5 10 8 7

5 5 12 10 3
5 6 8 10 6
3 5 10 4 13

7 12 10 5 1

3 4 9 9 10
 STEPS IN USING MICROSOFT
EXCEL FOR T-TEST
• ENCODE THE DATA IN EXCEL WORKSHEET.
• IN THE DATA ANALYSIS MENU, CHOOSE T-TEST:
TWO-SAMPLE ASSUMING EQUAL VARIANCES.
CLICK OK.
• EXAMPLE
• A GROUP OF HIGH SCHOOL STUDENTS WAS
EXPOSED TO TWO DIFFERENT TEACHING
METHODS AND THE STUDENTS’ RATINGS IN THE
TESTS WERE OBTAINED AS FOLLOWS:

• METHOD A: 77, 85, 92, 87, 88, 84, 92

• METHOD B: 75, 93, 83, 90, 78
• FILL IN THE NECESSARY DETAILS. FOR VARIABLE 1
RANGE, HIGHLIGHT THE VALUES OF METHOD A
INCLUDING THE LABEL “METHOD A”
• CLICK THE CIRCLE BESIDE THE OUTPUT RANGE, THEN,
CLICK THE BOX BESIDE IT. THEN, CLICK ON ANY EMPTY
CELL ON THE WORKSHEET WHERE YOU WANT THE
OUTPUT TO BE DISPLAYED. THEN, CLICK OK.
• LIKEWISE, FOR VARIABLE 2 RANGE, HIGHLIGHT THE VALUES
OF METHOD B, INCLUDING THE LABEL “METHOD B”. THEN
TYPE 0 FOR THE HYPOTHESIZED MEAN DIFFERENCE.
• CHECK THE BOX BESIDE LABELS BECAUSE WE INCLUDED THE
LABELS OF OUR VARIABLE RANGES.
• INTERPRETATION: BASED ON THE RESULTS, THE T STAT
EQUALS 0.7129 AND THE TCRIT TWO-TAIL IS 2.228.
SINCE TC < TCRIT, WE FAIL TO REJECT THE NULL
HYPOTHESIS. THERE IS NO DIFFERENCE IN THE
STUDENTS’ MEAN RATINGS WITH RESPECT TO THE
TWO METHODS. ALSO, THE P-VALUE (TWO-TAIL) IS
0.492; SINCE P > , WE ACCEPT THE NULL
HYPOTHESIS.
 PAIRED T-TEST
Examination results under each learning procedure
Pair Programmed materials Lecture
1 75 80
2 89 84
3 60 52
4 75 77
5 68 80
6 90 85
7 79 85
8 72 71
9 83 91
10 78 80
t-Test: Paired Two Sample for Means
Lectur
Programmed e
Mean 76.9 78.5
115.38
Variance 84.1 88889
Observations 10 10
Pearson Correlation 0.805897
Hypothesized Mean
Difference 0
Df 9
t Stat -0.79298
P(T<=t) one-tail 0.224094
t Critical one-tail 2.821438
P(T<=t) two-tail 0.448187
t Critical two-tail 3.249836
• FOUR EXPERIMENTAL GROUPS OF
STUDENTS WERE SUBJECTED TO
DIFFERENT TEACHING TECHNIQUES AND
TESTED AT THE END OF A SPECIFIED
PERIOD OF TIME. THE NUMBER OF
STUDENTS VARIED BECAUSE OF DROP-
OUTS. THE FOLLOWING ACHIEVEMENT
SCORES WERE OBTAINED:
DATA
Group 1 Group 2 Group 3 Group 4
78 82 95 79
73 79 80 72
69 69 89 69
65 91 82 81
88 68 85
75 71
83
• DO THE DATA PRESENT SUFFICIENT
EVIDENCE TO INDICATE A DIFFERENCE
IN THE MEAN ACHIEVEMENT FOR THE
FOUR TEACHING TECHNIQUES?
• USE  = .05
Age Number of ATM transactions

< 30 11 9 5 13 8 4 2 4 11 10

31- 50 10 8 12 7 7 5 13 9 8 11

>50 7 5 4 6 2 10 4 6 1 3
•ONE EXAMPLE OF A NON-
PARAMETRIC TEST:
CHI-SQUARE TEST
•CHI-SQUARED TEST
•CHI-SQUARE –  2

•FORMULA:
O  E 
•  =
2
2
 E
 CHI-SQUARE
• CHI-SQUARE IS USED AS A TEST OF SIGNIFICANCE
WHEN WE HAVE FREQUENCY DATA OR WHEN THE DATA
ARE IN TERMS OF PERCENTAGES OR PROPORTIONS AND
THAT CAN BE REDUCED TO FREQUENCIES. MANY OF THE
APPLICATIONS OF CHI-SQUARE ARE WITH DISCRETE DATA;
HOWEVER, ANY CONTINUOUS DATA MAY BE REDUCED TO
CATEGORIES AND THE DATA SO TABULATED IN TERMS OF
FREQUENCIES SO THAT CHI-SQUARE MAY BE APPLIED. THE
TABLE USED FOR CLASSIFYING DATA INTO SEVERAL
MUTUALLY EXCLUSIVE CATEGORIES AND THE CELL ENTRIES
ARE FREQUENCIES IS CALLED A CONTINGENCY TABLE.
• THE FOLLOWING ASSUMPTIONS UNDERLIE THE USE OF CHI-
SQUARE:
THE DATA MUST BE INDEPENDENT, THAT IS, NO RESPONSE IS
RELATED TO ANY OTHER RESPONSE; ONLY ONE MEASUREMENT
IS TAKEN FOR EACH SUBJECT. A FREQUENCY MAY BE PLACED IN
ONE AND ONLY ONE CATEGORY.
THE SAMPLE SIZE MUST BE LARGE ENOUGH. WHEN THE NUMBER
OF ROWS OR THE NUMBER OF COLUMNS IS MORE THAN 2,
THAT IS, DEGREES OF FREEDOM DF > 1, THE CHI-SQUARE TEST
MAY BE USED IF FEWER THAN 20% OF THE CELLS HAVE
EXPECTED FREQUENCIES THAT ARE LESS THAN 5 AND IF NO CELL
HAS AN EXPECTED FREQUENCY THAT IS LESS THAN 1. FOR
EXPECTED FREQUENCIES LESS THAN 5, THE FISHER-IRWIN EXACT
TEST SHOULD BE USED. IT IS SUGGESTED, HOWEVER, THAT THE
INVESTIGATOR
CHI-SQUARE TEST FOR INDEPENDENCE
• TO DETERMINE IF THERE IS AN ASSOCIATION BETWEEN
TWO VARIABLES UNDER SOME CLASSIFICATION OR
CATEGORIES; OR IF ONE VARIABLE IS INDEPENDENT OF
THE OTHER
• EXAMPLE
Willingness to use Leadership Roles
computerized Transform-
system Autocratic Participative ational Total
Yes 150 170 30 350
No 30 30 90 150
Total 180 200 120 500
• WE WISH TO TEST THE INDEPENDENCE OF
SECTOR TYPE AND OPINION OF
RANDOMLY SELECTED RESIDENTS ON THE
IMPLEMENTATION OF K TO 12. TEST USING
A SIGNIFICANCE LEVEL OF 0.05.
 Attitude of the residents
Sector type In favor Opposed No
opinion
Gov’t
23 18 3
employees
Parents 17 25 10
Private
18 27 9
sector
College
25 30 5
students
Business
15 20 15
sector
• REFERENCES:
• STATISTICS (RESEARCH-BASED)
BY: ZENAIDA GARAMBAS
• BASIC PROBABILITY AND STATISTICS
BY: ZENAIDA GARAMBAS

CONTACT NO: 0920 924 9061

•THANK YOU!
 PARAMETRIC NON-PARAMETRIC

• THE POPULATION(S) • THE NORMALITY

FROM WHICH WE ARE ASSUMPTION IS
SAMPLING COULD BE SUSPECT (NOT
REASONABLY WELL ESTABLISHED) OR IT
APPROXIMATED WITH MAY BE IMPOSSIBLE
NORMAL DISTRIBUTIONS TO TAKE A LARGE
OR THAT A LARGE SAMPLE
SAMPLE IS SELECTED
 PARAMETRIC NON-PARAMETRIC

• DATA OR MEASURES • DATA OR MEASURES

THAT WERE COLLECTED OBTAINED CANNOT
WERE "GOOD' BE COMPARED
MEASUREMENTS; ANY MEANINGFULLY (THEY
TWO OBSERVATIONS DO NOT USE THE
CAN BE COMPARED ACTUAL MAGNITUDES
LOGICALLY AND OF THE
MEANINGFULLY OBSERVATIONS)
 PARAMETRIC NON-PARAMETRIC
• DATA OBSERVED ARE
• AN INTERVAL OFTEN NOT OF AN
LEVEL OF INTERVAL LEVEL OF
MEASUREMENT; MANY
MEASUREMENT
NONPARAMETRIC
IS ASSUMED METHODS WORK WITH
ORDINAL DATA
 PARAMETRIC NON-PARAMETRIC
• GENERALLY, THEY TEST FOR
• THEY TEST FOR VALUES THAT CAN BE
PARAMETERS COMPUTED FROM
ESTIMATED FROM THE CHARACTERISTICS OF THE
OBSERVATIONS, SUCH AS
OBSERVATIONS OR
FREQUENCY OR POSITION IN
MEASURES THE ARRAY. IN SOME CASES, IT
COLLECTED (SUCH AS IS ALSO A TEST PROCEDURE
TEST FOR EQUAL FOR CLASSICAL PARAMETERS:
A TEST FOR EQUAL MEDIANS
MEANS OR
IS ALSO A TEST PROCEDURE
VARIANCES) FOR EQUALITY OF MEANS.
PARAMETRIC NON-PARAMETRIC
• MORE • ADVANTAGE: QUITE GENERAL, NOT
DIFFICULT TO APPLY
SENSITIVE
TO THE • DISADVANTAGE: THEY TEND TO WASTE
INFORMATION AND TEND TO RESULT IN
DISTRIBUTIO
ACCEPTANCE OF THE NULL HYPOTHESIS
N OF THE MORE OFTEN THAN THEY SHOULD; THEY
POPULATION ARE SOMETIMES LESS SENSITIVE THAN
THAN OTHER OTHER TESTS; LESS STATISTICALLY
METHODS EFFICIENT THAN PARAMETRIC METHODS
WHEN DISTRIBUTION IS NORMAL,
HOWEVER, THIS EFFICIENCY LOSS IS
OFTEN SLIGHT.
 THE MOST COMMON
NON-PARAMETRIC TESTS
ON TWO SAMPLES
• MANN-WHITNEY (COUNTERPART OF T-
TEST FOR INDEPENDENT SAMPLES)
• WILCOXON RANK SUM TEST
(COUNTERPART OF T-TEST INDEPENDENT
SAMPLES)
• WILCOXON SIGNED RANKS TEST
(COUNTERPART OF T-TEST FOR
DEPENDENT SAMPLES/MATCHED PAIRS)
NON-PARAMETRIC TESTS

FOR K INDEPENDENT

SAMPLES
• KRUSKAL WALLIS H-TEST
(COUNTERPART OF ONE-WAY ANOVA)
• FRIEDMAN TEST (COUNTERPART OF
TWO-WAY ANOVA)
 WORKSHOP

USE OF EXCEL ADD-INS

REAL STATISTICS
ANALYSIS TOOLPAK
STATISTICAL PACKAGE FOR
SOCIAL SCIENCES (SPSS)