Professional Documents
Culture Documents
Hrishabh-Research Methodology File
Hrishabh-Research Methodology File
ON
“RESEARCH METHODOLOGY”
SUBMITTED IN PARTIAL FULFILLMENT FOR THE
AWARD OF THE DEGREE OF
BACHELOR OF COMMERCE (H)
2019-2022
UNDER THE GUIDANCE OF
MS. NUPUR ARORA
FACULTY, VIPS
SUBMITTED BY:
Name: HRISHABH SRIVASTAVA
Enrolment No. 12517788819
B.COM (H)
HYPOTHESIS TESTING
T-test one sample test using Dummy (One Tailed)
t-Test Two-Sample Assuming Equal Variances
t-Test Paired Two Sample for Means
Two sample - Independent sample t test
Two sample - Paired Sample t test
Objectives of Research:
The objective of research is to find answers to the questions by applying scientific
procedures. In other words, the main aim of research is to find out the truth which is hidden
and has not yet been discovered. Although every research study has its own specific
objectives, the research objectives may be broadly grouped as follows:
1. To gain familiarity with new insights into a phenomenon (i.e., formulative research
studies);
2. To accurately portray the characteristics of a particular individual, group, or a situation
(i.e., descriptive research studies);
3. To analyze the frequency with which something occurs (i.e., diagnostic research studies);
and
4. To examine the hypothesis of a causal relationship between two variables (i.e., hypothesis-
testing research studies).
COUNT A - The COUNTA function counts cells containing any type of information,
including error values and empty text ("")
SUM - The SUM function adds values. You can add individual values, cell references or
ranges or a mix of all three
COUNT IF - COUNTIF is an Excel function to count cells in a range that meet a single
condition. COUNTIF can be used to count cells that contain dates, numbers, and text.
OTHER TOOLS
TRANSPOSE TABLE –
The TRANSPOSE function returns a vertical range of cells as a horizontal range, or vice
versa. The TRANSPOSE function must be entered as an array formula in a range that has the
same number of rows and columns, respectively, as the source range has columns and rows.
1. Numbers:
Right Alignment:
DATA VALIDATION:
The data validation feature helps you control what can be entered in your worksheet. For
example, you can: create a drop down list of items in a cell. Restrict entries, such as a date
range or whole numbers only.
Number:
2. Input Message:
8. Histogram-Pareto
Age DUMMY
42 0
76 0
56
56
67
65
65
89
76
45
45
65
78
55
52
Decision Rule:
If t Stat is greater than t Critical, reject Null Hypothesis.
If t Stat is less than t Critical, accept Null Hypothesis.
Jan May
45 56
54 57
44 45
56 67
34 44
45 34
34 34
67 76
45 56
54 45
67 76
56 87
56 66
56 65
76 45
76 76
Hypothesis Testing:
Null Hypothesis: Result in January is better than or equal to result in May
H 0: µJan ≥ µMay or µJan - µMay ≥ 0
Jan May
df 30
t Stat -0.77851
0.22118
P(T<=t) one-tail 4
1.69726
t Critical one-tail 1
Decision Rule:
If t Stat is greater than t Critical, reject Null Hypothesis.
If t Stat is less than t Critical, accept Null Hypothesis.
Inference:
Since t Stat= -0.77851 is less than t Critical=1.697261, accept Null Hypothesis.
Since P=0.221184 is greater than α=0.05, accept Null hypothesis.
Conclusion:
Therefore, the results of students for statistical software in January is better than or equal to
result in May.
Data:
1 50.46 42.9
2 47.08 50.1
3 57.51 41.67
Hypothesis Testing:
Null Hypothesis: The mean time to exhaustion is less than or equal to chocolate milk.
H 0: µcm ≤ µcd OR µcm - µcd ≤ 0
Alternate Hypothesis: The mean time to exhaustion is greater after chocolate milk.
H 1: µcm > µcd OR µcm - µcd > 0
Chocolate Carbohydrate
Milk Replacement Drink
Mean 41.79333333 33.44777778
Variance 164.53125 160.9338194
Observations 9 9
Pearson Correlation 0.508406248
Hypothesized Mean
Difference 0
df 8
t Stat 1.979280834
P(T<=t) one-tail 0.0415706
t Critical one-tail 1.859548038
Decision Rule:
If t Stat is greater than t Critical, reject Null Hypothesis.
If t Stat is less than t Critical, accept Null Hypothesis.
Group A Group B
76 95
87 97
98 87
45 89
66 87
78 45
76 76
88 56
78 76
87 87
54 45
65 76
76 45
89 88
65 76
78 66
54 78
87 56
45 77
Hypothesis Testing:
H 0: ua -ub=0
H 1: UA-UB ≠ 0
Decision Rule:
If t Stat is greater than t Critical, reject Null Hypothesis.
If t Stat is less than t Critical, accept Null Hypothesis.
Data:
Before After
162 168
170 136
184 147
164 159
172 143
176 161
159 143
170 145
Hypothesis Testing:
Null Hypothesis: The mean weight after the diet is more than or equal to the mean weight
before the diet.
H 0: µa ≥ µb OR µa - µb ≥ 0
Alternate Hypothesis: The mean weight after the diet is less than the mean weight before the
diet.
H 1: µa < µb OR µa - µb < 0
Variable 1 Variable 2
Mean 169.625 150.25
121.928571
Variance 65.125 4
Observations 8 8
-
0.17674777
Pearson Correlation 2
Hypothesized Mean Difference 0
df 7
3.70687337
t Stat 3
0.00379299
P(T<=t) one-tail 4
1.89457860
t Critical one-tail 5
Decision Rule:
If t Stat is greater than t Critical, reject Null Hypothesis.
If t Stat is less than t Critical, accept Null Hypothesis.
H 1: µd>µb or µd-µb>0
Direct Broker
Mean 6.6312 3.7232
Known Variance 37.488 43.339
Observations 50 50
Hypothesized Mean Difference 0
z 2.28718437
P(Z<=z) one-tail 0.011092532
z Critical one-tail 1.644853627
Decision Rule:
If z Stat is greater than z Critical, reject Null Hypothesis.
If z Stat is less than z Critical, accept Null Hypothesis.
If sig level (p value, alpha) > 0.05, Accept Null Hypothesis.
If sig level (p value, alpha) < 0.05, reject Null Hypothesis.
Inference:
Since z stat = 2.28 is greater than z critical = 1.644, reject null hypothesis
Since p = 0.011 is less than a=0.05, reject null hypothesis
Conclusion:
Therefore the Net Annual returns on mutual funds is greater when investors purchase then directly
from bank rather than purchasing from brokers.
Hypothesis Testing:
H 0: Mean marks of all subjects are equal
μe =μs=μh
H 1: Mean marks of at least one group is different
ANOVA
Source of
Variation SS df MS F P-value F crit
1085.8 15.1962 7.16E- 3.44335
Between Groups 4 2 542.92 3 05 7
Within Groups 786 22 35.72727273
1871.8
Total 4 24
Decision Rule:
Hypothesis Testing:
Row wise
H0: no significant difference in mean marks of students
H1: Mean marks of at least one of the students is different
Column wise
H0: no significant difference in marks of subjects
H1: Mean marks of at least one of the subjects is different
Varianc
SUMMARY Count Sum Average e
48.6666 322.333
a 3 146 7 3
b 3 147 49 61
53.3333 20.3333
c 3 160 3 3
d 3 159 53 121
52.3333 114.333
e 3 157 3 3
economics 5 240 48 28
science 5 309 61.8 34.2
history 5 220 44 54.5
ANOVA
Source of Variation SS df MS F P-value F crit
Rows 60.933 4 15.2333 0.30026 0.86988 3.83785
1338.9
Total 3 14
Decision Rule:
f stat > f critical, reject Ho
If p value < 0.05 , reject H0
Inference:
Row Wise
Since f Stat=0.300 is less than f Critical=3.83, accept Null Hypothesis.
Since P=0.86 is greater than α=0.05, accept Null hypothesis.
Column Wise
Since f Stat=8.59 is greater than f Critical=4.45, reject Null Hypothesis.
Since P= 0.01 is less than α=0.05, reject Null hypothesis.
Conclusion:
Therefore,
The mean marks of the students in subjects- Economics, Science and History are equal
column wise but different row wise.
Hypothesis Testing:
H0: No significant difference between the mean marks of school A and School B ( Row wise)
H0: no significant difference between the mean marks of economics, medicine and history
H0: no significant difference between school A and School B subject-wise (interactions)
Total 12255.2 29
Decision Rule:
f stat > f critical, reject H0
If p value < 0.05 , reject H0
Inference:
Since F = 8.6 is greater than F crit = 4.2, reject H0
Since p value = 0.007 is less than a=0.05, reject H0
Conclusion:
Therefore marks of students differ with respect with school, subject wise and school wise in conjunction
with the subjects
Class1 Class2
65 76
76 54
65 67
76 65
56 76
45 66
Hypothesis Testing:
H 0: Variance group 1 = Variance group 2
Class1 Class2
Observations 6 6
df 5 5
F 2.131709742
Decision Rule:
If f is greater than f Critical, reject Null Hypothesis.
If f is equal to f critical , accept null hypothesis
Inference:
Since F > F Critical one-tail, we reject the null hypothesis
Conclusion:
Therefore, variance of Class 1 is greater than variance of class 2 in mathematics
Hypothesis Testing:
H 0: There is no association between brand preference and age group
Decision Rule:
If calculated value > Critical one-tail, we reject the null hypothesis
Inference:
Since calculated value is less than critical point, accept null hypothesis
Conclusion:
INTRODUCTION TO R
1. How to Install R Studios:
To Install R
2. Click the "download R" link in the middle of the page under "Getting Started."
3. Select a CRAN location (a mirror site) and click the corresponding link.
4. Click on the "Download R for (Mac) OS X" link at the top of the page.
6. Save the .pkg file, double-click it to open, and follow the installation
instructions.
To Install RStudio
3. Click on the version recommended for your system, or the latest Mac version,
save the .dmg file on your computer, double-click it to open, and then drag and drop it to
your applications folder.
2. Four panels in R
RStudio has four main panes each in a quadrant of your screen: Source
Editor, Console, Workspace Browser (and History), and Plots (and Files, Packages, Help).
These can also be adjusted under the ‘Preferences’ menu. Note that there might be subtle
differences between RStudio installations on different operating systems
TOP RIGHT:
Environment and history window. The environment window contains objects (data, values,
functions) R has currently stored in its memory. The history window shows all commands
that were executed in the Console.
BOTTOM RIGHT:
Files, plots, packages, help, and viewer pane. Here you can open files, view plots, install and
load packages, read man pages, and view markdown and other documents in the viewer tab.
4. Correlation:
Correlation is a statistical technique that can show whether and how strongly pairs of
variables are related.
5. Independent Samples:
Data Set
Score shift
3.1 Part time
3.4 Part time
4.6 Part time
2.8 Part time
Attach the file and run the test by using t.test() command.
6.Paired Sample
Data Set
Subject Before After
1 135 127
2 142 145
3 137 131
Class1 Class2
65 76
76 54