24-Apr-19

Unit-5
Data Analysis

Pankaj Chauhan on Business Research Methods 1

Data Analysis

Pankaj Chauhan on Business Research Methods 15o1

Tabular representation
Frequency Table:
Construction of frequency distribution

• Following are the ratings provided by a sample of 20 guests:

Below Average Average Poor Above Average Above Average

Above Average Excellent Above Average Average Below Average

Average Above Average Below Average Above Average Average

Above Average Poor Above Average Average Above Average

Pankaj Chauhan on Business Research Methods 16

1
 24-Apr-19

Frequency Table:
Categories Frequency
Poor 2
Below Average 3
Average 5
Obtained on
Above Average 9
NOMINAL or
Excellent 1 ORDINAL Scale
Total 20

Frequency Table is the grouping of qualitative data

into mutually exclusive classes showing the number
of observation in each class
Pankaj Chauhan on Business Research Methods 17

Frequency Table is the grouping of qualitative data into mutually

exclusive classes showing the number of observation in each class
The number of observation in each
Frequency Table class is called CLASS FREQUENCY
Categories Frequency Relative Frequency Percent Frequency
Poor 2 .10 10
Below Average 3 .15 15
Average 5 .25 1/20 = .05 25
Above Average 9 .45 45
Excellent 1 .05 .10(100) = 10 5
Total 20 1.00 100

The relative frequency of a class is the fraction or The percent frequency of a

proportion of the total number of data items class is the relative
belonging to the class frequency multiplied by18100.
Pankaj Chauhan on Business Research Methods

Graphical representation
BAR CHART
Size of different
• BAR CHART: classes can be
4 Compared
– A graph in which
Class Frequencies

• the classes are reported on 3

the horizontal axis and
• the class frequencies on 2
the vertical axis.
– The class frequencies are 1
proportional to the heights
of the bars
Team-A Team-B Team-C

Class frequencies of Qualitative Variables are represented by BAR CHART

Pankaj Chauhan on Business Research Methods 20

2
 24-Apr-19

Graphical representation
HISTOGRAM
• HISTOGRAM:
– A graph in which Auto Parts Price
Frequenc 18

Class Frequencies
y 16
• the classes with no gap 14
between them are 50 Up to 59 2
12
10
reported on the horizontal
60 Up to 69 13 8
axis and 6
70 Up to 79 16
• the class frequencies on 4
2
the vertical axis. 80 Up to 89 7
0

– The class frequencies are 90 Up to 99 7 50 -59 60 -69 70 - 79 80 - 89 90 - 99 100 -109

proportional to the 100 Up to 109 5

heights of the columns

Class frequencies of Quantitative Variables are represented by HISTOGRAM
Pankaj Chauhan on Business Research Methods 21

Graphical representation
PIE CHART
• PIE CHART Account Amo Angle
unt
– A chart that (in
• shows the proportion or Rs.)
percentage of each class Food 3000 1500
out of the total number of (A)
frequencies in a circle Rent 800 400
(B)
segments is pie chart
Education 1200 600
– The size of each pie is a (C)
record of the percentage Savings 1500 750
of a class. (D)
Miscellaneo 700 350
us
Total 7200 3600

Pankaj Chauhan on Business Research Methods 22

Using the values of the pie chart, find the %

Consumption of the each brand
For P
=16.6
16.6 For Q
33.3 = 33.3
25
For R
8.3 90 x 100/360 = 25
16.6 For S
30 x 100/360 = 8.3

Pankaj Chauhan on Business Research Methods 23

3
 24-Apr-19

Testing Hypothesis

Concept of hypothesis, Null and Alternative Hypothesis

T-test, Z-test
Cross Tabulation: Chi-square test
ANOVA (One Way ANOVA and Two Way ANOVA)

Pankaj Chauhan on Business Research Methods 24

What is a Hypothesis?
“The unproved statement suggesting an assumption
about parameter related to a target population with an
objective to evaluate the claim or speculation. ”

Pankaj Chauhan on Business Research Methods 25

Hypothesis Testing Procedure

Pankaj Chauhan on Business Research Methods 26

4
 24-Apr-19

Null Hypothesis

 The hypothesis that sample results do not show any

significant difference from the population parameter
with respect to the variable under study is termed
as NULL Hypothesis
 Designated as Ho
 Always contains “=” or “≤” or “” sign

Pankaj Chauhan on Business Research Methods 27

Null Hypothesis
Example
 Researcher is interested in knowing the proportion of consumer who
purchased a brand before and after advertisement. State the Null
hypothesis in this case.
 Ho = There is no difference in the proportion of consumer who purchased a
brand before & after advertisement
 Ho = p1 = p2
 This statement is same as saying the proportion of consumer before &
after the advertisement is same

Pankaj Chauhan on Business Research Methods 28

ALTERNATIVE HYPOTHESIS
• The conclusion which is accepted as an option because the
null hypothesis is not accepted is termed as ALTERNATIVE
HYPOTHESIS
• Designated as H1
• If we want to see whether the mean age of class is 21 years
• Ho= The mean age of the class is not different from 21
years
Ho : μ = 21
• H1 =The mean age of the class is different from 21 years
H1 : μ ǂ 21
NON-DIRECTIONAL H1:TWO TAILED TEST DIRECTIONAL H1 : ONE TAILED TEST
H1 :μ ǂ21 H1 :μ >21 OR H1 :μ <21
Pankaj Chauhan on Business Research Methods 29

5
 24-Apr-19

TYPE-I and TYPE-II ERROR

Actual Situation

Decision H0 True H0 False

Do Not
Reject No Type II
H0 error Error
Reject Type I No
H0 Error Error

Pankaj Chauhan on Business Research Methods 30

Level of Significance

•The probability of making Type I error is termed as the level of

significance.
•it is denoted by α (Greek letter alpha).
•Confidence level=(1-α)

Pankaj Chauhan on Business Research Methods 31

What is Critical Value?

 The value which is the dividing point between area of

rejection & the area of acceptance is called CRITICAL
VALUE
 Directional hypothesis has one critical value. Non-
directional hypothesis have two critical values

Pankaj Chauhan on Business Research Methods 32o1

6
 24-Apr-19

Types of Hypothesis Tests: Parametric & Non- Parametric test

Points of
Parametric Non-Parametric
Difference
Assumed Distribution Bell Shaped (Normal) Distribution free

Type of data scaled Ratio & Interval scaled Nominal & ordinal scaled

Usual central Measure Mean Median

Z-test, t-test, one-way Chi-square test, Mann-

Test options
ANOVA Whitney Test, Wilcoxon Test

Pankaj Chauhan on Business Research Methods 33o1

Pankaj Chauhan on Business Research Methods 34

Testing For a Population Mean: t-Test and Z -test

Pankaj Chauhan on Business Research Methods 35

7
 24-Apr-19

Criteria to decide t-Test or Z-Test

Standard Deviation
Unknown Known
(σ)

Number of Sample ONE ONE

Sample Size Less than 30 More than 30

TEST t-test Z-test

Formula
Pankaj Chauhan on Business Research Methods 36

Testing For a Population Mean

• The average breaking strength of steel rods is specified to be 18.5
thousand Kg. For this a sample of 14 rods was tested. The mean and
standard deviation obtained were 17.85 and 1.955 respectively. Test the
claim with 95% confidence.
Null Hypothesis
There is no significant deviation in the breaking strength of the rods:
H0 : μ = 18.5
H1 : μ ǂ 18.5 (Two tailed test)
Given:
n=14,mean=17.85, standard deviation=1.955 (use in place of population
standard deviation) Statistical test: t- test
The level of significance(α)=5%
Pankaj Chauhan on Business Research Methods 37

α = 5 % or 5/100 or 0.05 | It is a case of two tail test so divide ‘α’ into two parts
α/2= 0.025
Degree of freedom = (n-1)
=(14-1) or =13
Critical Value: at α/2=0.025 and df =13 the critical value is 2.16
Calculation of t-statistic
=(17.85-18.8)/(1.955/sqrt 14)
= -0.65/0.522
= -1.24
Conclusion:
Null Hypothesis is not rejected as calculated value is lesser than
critical value.
There is no significant deviation in the breaking strength of the rods:

Pankaj Chauhan on Business Research Methods 38

8
 24-Apr-19

Testing For a Population Mean

Suppose the regional planning council of a particular community in which a
speciality chain is considering locating its new store released a report that the
average family income of the community's citizens is $24000. Since income level is
an important aspect in the decision of locating a store, researcher has been
assigned to verify the council's claim. The researcher takes a sample of 200
residents, with the results that the sample mean is equal to $17000 with a
standard deviation of $5000. Comment on council's claim.
 Null Hypothesis
 The mean income of sample is the same as the income level of
the total population as reported by council
H0 : μ = $24000
H1 : μ ǂ $24000(Two tailed test)
 Let the level of significance(α) = 5%
Pankaj Chauhan on Business Research Methods 39

Population Average income is $24000. Sample Size = 200 , Sample Mean = $17000
and Standard deviation of $5000. Statistical test: z- test

 Standard error
 Standard deviation of sample divided by square root of (n-1)
 Decision Rule:
 Since it is a two tailed test we take half of ‘α’ (5%). α/2=0.025, which is
the part of each tail.
 To find appropriate value from table subtract 0.025 from 0.5
 (0.5 – 0.025=0.475) Now see this value in the Z-table & add the Decimal
value with respective Z-value. It will be 1.9+.06= ±1.96
 The decision rule will be to reject the H0 and not reject the alternate if
computed value of Z- does not fall within the region of -1.96 and +1.96
 Now calculate the Z-Value
 Std. Error will be $5000/sqrt(200-1) = $ 354.61
 Z= ($17000 - $24000)/$354.61
 =-19.74 Pankaj Chauhan on Business Research Methods 40

 Statistical Conclusion:
 Since the calculated value of Z is larger than ±1.96 so
null hypothesis would be rejected.
 It means the sample mean lies more than 1.96 standard
deviation from the true population mean.

Pankaj Chauhan on Business Research Methods 41

9
 24-Apr-19

One sample z-test for Proportions

A survey claims that 9 out of 10 doctors recommend aspirin for their patients with
headaches. To test this claim, a random sample of 100 doctors is obtained. Of these
100 doctors, 82 indicate that they recommend aspirin. Is this claim accurate? Use
alpha = 0.05 1. Define HO and H1
Define HO and H1 2. State Alpha
3. State Decision Rule
4. Calculate Test Statistic
5. State Conclusion
State Alpha: Use alpha = 0.05 as given in question
State Decision Rule
Using an alpha of 0.05 with a two-tailed test, the distribution
look like this:
we have 0.025 in each tail. A critical value of 1.96 is obtained using Z-table.
Thus, decision rule for this two-tailed test is: If Z is less than -1.96, or greater than
1.96, reject the null hypothesis.
Pankaj Chauhan on Business Research Methods 42

Calculate Test Statistic

The sample proportion

Po The Population proportion

State Conclusion
Reject the null hypothesis. The claim that 9 out of 10 doctors recommend aspirin
for their patients is not accurate.

Pankaj Chauhan on Business Research Methods 43

Chi-Square Test

Pankaj Chauhan on Business Research Methods 44o1

10
 24-Apr-19

Chi-Square Test
• The chi-square is one of the widely used Non
parametric test
• Makes no assumption about distribution of population
• Use data at the nominal scale
• Chi-square describe the magnitude of discrepancy
between actually observed frequency and expected
frequency.

Pankaj Chauhan on Business Research Methods 45

Basic formula for Chi-Square Test

In Chi-square we compare the observed frequency of some observation
With an expected frequency

The comparison of observed and expected frequencies is used to

calculate the value of the chi-square statistic

The symbol for chi-square and the formula is:

Where, ‘O’ is the observed frequency, and ‘E’ is the expected frequency

Pankaj Chauhan on Business Research Methods

One-Variable Chi-Square (goodness-of-fit test)

“with equal expected frequencies”

Admin-IT of a company going to purchase a computer for office

use. The available brands are Apple Computers, IBM
Computers, or some other brand of computer. Admin-IT wants to
know if there is a significant difference among the frequencies
with which these three brands of computers are purchased so the
data for 100 consumers was collected from the computer stores
and is listed in the table on next slide.. .
Pankaj Chauhan on Business Research Methods

11
 24-Apr-19

Computer Purchase Frequency

IBM 47

Apple 36

Other 17

Pankaj Chauhan on Business Research

Methods

One-Variable Chi-Square (goodness-of-fit test)

“with equal expected frequencies”
Null hypothesis:
• there is no significant difference between the observed and the
expected frequencies.
Alternate hypothesis
• there is significant difference between the observed and expected
frequencies.
Set the alpha level.
• alpha level at .05
To find the critical value for Chi-square the degree of freedom has to be
calculated.
The degree of freedom: It is the number of constraints or assumptions
For one Sample: Degree
Pankaj Chauhan of freedom
on Business Research (df)= (n-1)
Methods

One-Variable Chi-Square (goodness-of-fit test)

“with equal expected frequencies”
Frequency with which consumers select computer brands
Computer Observed Frequency Expected Frequency (O-E)2/E
IBM 47 33.333 5.604
Apple 36 33.333 0.213
Other 17 33.333 8.003
Total (chi-square) 13.820

Since calculated value (13.820) is greater than 5.991, we reject the null hypothesis:
there is no significant differences between the observed and expected frequencies.
Pankaj Chauhan on Business Research Methods

12
 24-Apr-19

One-Variable Chi-Square (goodness-of-fit test)

“with predetermined expected frequencies”

Re-Statement of Previous Question:

In a national study, consumers who buy computers for their office
usage, bought IBM computers 50% of the time, Apple computers 25%
of the time, and other computers 25% of the time. Out of 100
consumers who were surveyed, 36 bought Apple Computers, 47
bought IBM computers, and 17 bought some other brand of computer.
Admin-IT wants to know if these frequencies of computer buying
behavior is similar to or different than the national study data.

Pankaj Chauhan on Business Research Methods

One-Variable Chi-Square (goodness-of-fit test)

“with predetermined expected frequencies”
Null hypothesis:
• there is no significant difference between the observed and the
expected frequencies.
Alternate hypothesis
• there is significant difference between the observed and expected
frequencies.
The alpha level.
• alpha level at .05
To find the critical value for Chi-square the degree of freedom has to be
calculated.
The degree of freedom: It is the number of constraints or assumptions
In case of one Sample: Degree
Pankaj Chauhan on Business of freedom (df)= (n-1)
Research
Methods

One-Variable Chi-Square (goodness-of-fit test)

“with predetermined expected frequencies”
• Calculate the critical value with respect to the degrees of freedom & alpha
level
• df = n – 1 = (3 -1) = 2
• For df =2 & Alpha =.05,
• The critical value is 5.991

The decision rule for rejecting the null hypothesis.

Reject H0 if Chi-Square >= 5.991
Pankaj Chauhan on Business Research Methods 53o1

13
 24-Apr-19

One-Variable Chi-Square (goodness-of-fit test)

“with predetermined expected frequencies”
The data for 100 students is recorded in the table on the next slide (the
observed frequencies). In this case the expected frequencies are those
from the national study. To get the expected frequency we take the
percentages from the national study times the total number of subjects
in the current study.

Expected frequency for IBM = 100 X 50% = 50

Expected frequency for Apple = 100 X 25% = 25
Expected frequency for Other = 100 X 25% = 25

Pankaj Chauhan on Business Research

Methods

One-Variable Chi-Square (goodness-of-fit test)

“with predetermined expected frequencies”

Since calculated value 7.58 is greater than 5.991, we reject the null hypothesis:
there is no significant differences between the observed and expected frequencies.
Pankaj Chauhan on Business Research Methods

Chi square test: for two variables

Test of Independence
we wants to know if there is a significant difference in the frequencies
with which males come from small, medium, or large cities and
females comes. The two variables we are considering here are
hometown size (small, medium, or large) and gender (male or female).
Another way of putting our research question is:
Is gender independent of size of hometown?

Pankaj Chauhan on Business Research Methods 56

14
 24-Apr-19

Chi square test: for two variables

Test of Independence
Frequency with which males & females come from small, medium, & large cities

Null hypothesis
Small Medium Large Totals

Alternative hypothesis
Female 10 14 6 30
Male 4 1 1 6
The alpha level = 5% or .05 Totals 14 15 7 36

In case of two variable : The degrees of freedom df = (C - 1)(R - 1) df = (2)(1) = 2

‘C’ is the number of columns or levels of the first variable and ‘R’ is the number
of rows or levels of the second variable.
The critical value : At 2 df and 5%α, the critical value is 5.991
The decision rule: Reject H0 if Chi-square cal.value >= 5.991.
Pankaj Chauhan on Business Research Methods

Chi square test: for two variables

Test of Independence

• In the table we have the observed

frequencies. Now we must calculate Small Medium Large Totals
the expected frequency for each of
the six cells. Female 10 14 6 30
• Expected Frequency for a Cell = Male 4 1 1 6
(Column Total X Row Total)/Grand Total Totals 14 15 7 36

Pankaj Chauhan on Business Research Methods 58

Chi square test: for two variables

Test of Independence
We can put these expected frequencies in our table and also include the values
We can put these expected frequencies in our table and also include the values
for (O - E)2/E. The sum of all these will be the value of chi-square.
for (O - E)2/E. The sum of all these will of course be the value of chi-square.
Small Medium Large Total

(O-
Observed Expected (O-E)2/E Observed Expected (O-E)2/E Observed Expected
E)2/E

Femal
10 11.667 0.238 14 12.500 0.180 6 5.833 0.005 30
e
Male 4 2.333 1.191 1 2.500 0.900 1 1.167 0.024 6
14 14 15 15 7 7
Total 36

Since the calculated value 2.538 is not greater than 5.991, we fail to reject the null hypothesis

Pankaj Chauhan on Business Research Methods 59

15
 24-Apr-19

One-Way ANOVA
The one-way analysis of variance is used to test the
claim that three or more population means are
equal.

One way ANOVA contain one IV with two or more

treatment levels. The one-way is because each value
is related to one variable only.

It is also known as completely randomized design.

Conditions or Assumptions
• The data are randomly sampled
• The variances of each sample are assumed equal
• The residualsPankaj
are normally
Chauhan on distributed
Business Research Methods 60

One-Way ANOVA
• A classroom is divided into three rows: front, middle, and
back. The instructor noticed that the far away the students
were from him, the more likely they were to less engage in
class. He wanted to see if the students far away did worse
on the exams. A random sample of the students in each row
was obtained. The score for those students on the second
exam was recorded
– Front: 82, 83, 97, 93, 55, 67, 53
– Middle: 83, 78, 68, 61, 77, 54, 69, 51, 63
– Back: 38, 59, 55, 66, 45, 52, 52, 61

Pankaj Chauhan on Business Research Methods 61

The summary statistics for the grades of each row are shown in the table below
Row Front Middle Back
Sample size 7 9 8
Mean 75.71 67.11 53.50
St. Dev 17.63 10.95 8.96
Variance 310.90 119.86 80.29
The null hypothesis is that the population means are all equal
μ1 = μ2= μ3
The alternative hypothesis is that at least one of the means is different

Pankaj Chauhan on Business Research

62
Methods

16
 24-Apr-19

x1
Calculate Critical Value Calculation
Mean of x2
df MSB (for numerator)=(k-1)
each sample x3 df MSW (for denominator)=(N-K)
dfMSB=3-1=2
Calculate dfMSW=24-3=21
Mean of X1  X 2  X 3 @5%, Critical value = 3.47
sample mean X 
k
Measure the Variation in ANOVA
MSB=SSB/(k-1) | MSW=SSW/(N-K)
Variation between samples: SSB
2 2 2
n1  x1  X   n 2  x 2  X   n3  x3  X 
      MSB
F  Ratio 
Variation within sample: SSW MSW

 x   
 x1   x2i  x2   x3i  x3  
2 2 2
1i

Total Variance (SST )= SSB + SSW

One-Way ANOVA
Source SS df MS F Critical Value

Between 1902 2 951.0 5.9 3.47

Within 3386 21 161.2

Total 5288 23 229.9

As F-Calculated is greater than critical value so reject the null hypothesis.

The null hypothesis is that the means of the three rows in class were the
same, but we reject that,
so at least one row has a different mean.
Pankaj Chauhan on Business Research
64
Methods

Two-Way ANOVA
Two way ANOVA is also known as completely randomized block design. It
focuses on:
• One independent variable
• A blocking variable
• Block – There is a variable that researcher wants to control to reduce error is called as blocking var
• Complete - Every sampling unit is distributed within total block.
• Randomized - Subjects are randomly assigned within block

Two way ANOVA test two hypothesis:

• For treatment: All population means are same
• For blocks: All block means are same

There will be two F-Ratio and each will be compared with corresponding critical
value

Pankaj Chauhan on Business Research Methods 65

17
 24-Apr-19

Calculation: Two Way ANOVA

SST= SSC+SSR+SSE Grand Mean
Col. Mean To Find Critical Value of ‘F’
No. of Blocks (Row) Mean of row or col. Mean
df- Nu-Treat=(C-1)
c 2

n   xj  X 
df- Nu-Block= (n-1)
SSC=  df-Deno for both=(n-1)(C-1)
j i  
Row Mean Grand Mean
No. of Treatment level (Col.) Mean of row or col. Mean
n 2

SSR= C  xi  X 

i 1  
n c 2

SSE= C 
i 1
  x
j 1
ij  x j  xi  X 
 Grand Mean
MSC=SSC/(C-1) Mean of row or col. Mean
MSR=SSR/(n-1) No. of Row Row Mean
MSE=SSE/(C-1)(n-1) Col. Mean
Single Value
F-Treatment=MSC/MSE
F-Block=MSR/MSE Pankaj Chauhan on Business Research Methods 66

Exercise Row. Mean

BRAND Miami Philadelphia Minneapolis San Antonio Oakland xi
A 3.47 3.40 3.38 3.32 3.50 3.414
B 3.43 3.41 3.42 3.35 3.44 3.410
C 3.44 3.41 3.43 3.36 3.45 3.418
D 3.46 3.45 3.40 3.30 3.45 3.412
E 3.46 3.40 3.39 3.39 3.48 3.424
F 3.44 3.43 3.42 3.39 3.49 3.434
xj 3.450 3.4167 3.4067 3.3517 3.4683 3.4187
Col. Mean
Grand Mean
Mean of row or col. Mean
Pankaj Chauhan on Business Research Methods 67

Summary of Results Two Way ANOVA

Source of Critical
SS df MS F-Ratio
Variance Values

Treatment-C 0.04846 4 0.01213 MSC/MSE=18.95 4.43

Block-R 0.00203 5 0.00041 MSR/MSE=0.64 4.10

Error-E 0.01281 20 0.00064

Total 0.06330 29

Pankaj Chauhan on Business Research Methods 68

18
 24-Apr-19

Writing a Research Report

If research was not “written up,” did
it really occur?

Writing a Research Report

• An article, paper, or report generally takes a structure or
form that seems difficult but is intended to help make
reading it or using it for research quick and efficient.
• A research report has seven components:
1. Abstract or Summary
2. Introduction
3. Review of Literature
4. Methods
5. Results
6. Conclusions and Discussion
7. References
• Note: Qualitative research reports will vary from what is
presented here.

Writing a Research Report

• A research report has seven components:
1. Abstract or Summary
The abstract or summary tells the reader very briefly what the main
points and findings of the paper are.
– This allows the reader to decide whether the paper is useful to them.
– Get into the habit of reading only abstracts while searching for
papers that are relevant to your research.
– Read the body of a paper only when you think it will be useful to
you.

19
 24-Apr-19

Writing a Research Report

• A research report has seven components:
2. Introduction
The introduction tells the reader what the topic of the
paper is in general terms, why the topic is
important, and what to expect in the paper.
– Introductions should funnel from general ideas to the
specific topic of the paper
– Introductions are sometimes folded into literature
reviews

Writing a Research Report

• A research report has seven components:
3. Review of Literature
The literature review tells the reader what other researchers
have discovered about the paper’s topic or tells the reader
about other research that is relevant to the topic.
– A literature review educates readers about what the
community of scholars says about a topic and its surrounding
issues.
– Along the way it states facts and ideas about the social world
and supports those facts and ideas with credit for where they
came from.

Writing a Research Report

• A research report has seven components:
4. Methods
A METHODS SECTION MUST CONTAIN:
– Descriptions of Data
• Mention Research Design
• Target Population
• The Ways Data were Collected:
– Sampling
– Delivery Methods
• Response Rates
• Limitations of Data (Who is omitted, biases)
• Any analyses necessary to bolster claims the data are appropriate
• Sample sizes through various decisions
– Such as:
» eliminating non-Christians from the sample
» using only white respondents

20
 24-Apr-19

Writing a Research Report

• A research report has seven components:
5. Results
The results section includes:
– Professional tables showing descriptive and inferential statistics
– Narrative describing most relevant findings
– The narrative and tables are complementary.
• The narrative discusses ONLY VERY IMPORTANT findings and refers to
where information can be found in the tables as different facts are
discussed.
• The tables contain almost all statistical information so that the author
does not have to write a narrative for every detail in the analysis.

Writing a Research Report

• A research report has seven components:
6. Conclusions and Discussion
This section assesses how one’s research findings relate
to what the community of scholars knew already.
– You should summarize the most salient points of your
research.
– Discuss the general significance of your topic and
findings.

Writing a Research Report

• A research report has seven components:
7. References
The references are just as important as any other part of
your paper. They are the link to the community of
scholars that will permit your reader to assess the
worthiness of the claims you make in your research.
References also make the research process much more
efficient because they make it very easy to look up
sources of facts and ideas.

21
 24-Apr-19

Writing a Research Report

• A research report has seven components:
7. References
Should be hanging indented, alphabetical on author’s last name (by increasing year
within same author) with information in order determined by type of source:

Article
Last Name, first name. Year. “Article title.” Journal Name Volume: 1st Page- Last Page.
Lee, James Daniel. 2005. “Do Girls Change More than Boys? Gender Differences and
Similarities in the Impact of New Relationships on Identities and Behaviors.”
Self and Identity 4:131-47.
Chapter
Last Name, first name. Year. “Chapter Name.” Pages in the book in Book Name, edited
by first name last name. City of Publisher: Publisher.

Book:
Last name, first name. Year. Book Name. City of Publisher: Publisher.

Writing a Research Report

… Plagiarism
• What is it?
– All knowledge in a research work has either been copied
from some place or originally discovered by you.
– Most knowledge out of Literature was copied.
– but this is not what we would typically call “plagiarism.”
– Plagiarism is the "wrongful appropriation" and "stealing
and publication" of another author's
"language, thoughts, ideas, or expressions" and the
representation of them as one's own original work.
Plagiarism is considered academic dishonesty and a
breach of journalistic ethics.

Writing a Research Report

Finally…Avoiding Plagiarism
– To avoid plagiarism:
1. Document every source for information that is not “general
knowledge”—this includes facts and ideas.
2. Cite every time a fact or idea is used unless it is clear that one
citation is referring to a group of facts or ideas.
3. If you quote material, put quotation marks around the quoted
stuff and include a page number within the citation.
4. It is alright to paraphrase material, but you still have to cite from
where the paraphrased material came.
5. When in doubt, cite the source.

22