Answer 1:

Introduction

The dimension scale of each column in a dataset is critical for comprehending the
nature of the facts and selecting the most suitable statistical evaluttation
techniques. We can ascertain the level of size and the type of information each
column represents by identifying the measurement scale. In this evaluation, we
can investigate the size scales of the columns blanketed inside the dataset, which
includes respondent code, gender, age categories, city, Instagram rating, and
score. We can determine whether or not the records in every column fall under
nominal, ordinal, c language or ratio measures by analyzing the characteristics of
each column's data.

Concept and Application

Respondent’s code: Nominal Scale

Measurement Scale: Nominal

Justification: The "Respondents code" column represents a unique identifier

assigned to each participant. It functions as an identifier or identification code for
respondents but has no inherent order or numerical cost. The classifications are
distinct and particular, permitting individual participants to be identified,
however, stopping any significant contrast or calculation.

Gender: Nominal Scale

Measurement Scale: Nominal

Justification: The "Gender" column indicates the respondents' gender. This

variable has outstanding categories: "Male" and "female." Gender is a nominal
scale variable representing qualitative facts without a numeric price. The classes
provide facts about the gender identity of every respondent and are mutually
specific.

Groups of Age: Ordinal Scale

The scale of measurement: ordinal

Justification: The "Age groups" column classifies respondents into various age
classes. The age classes detailed are "19 to 22 years," "23 to 26 years," and "more
than 26 years." "19 to 22 years" follows earlier than "23 to 26 years," and
"greateer than 26 years" represents the oldest age variety. Nonetheless, the gaps
between age categories need to be extra constant. Therefore, the "Age agencies"
column is assessed on an ordinal scale, representing a classification or order
without genuine numerical values.

Municipality: Nominal Scale

Measurement Scale: Nominal

Justification: The "metropolis" column consists of every respondent's town of

habitation. It presents qualitative data in a precise format, with respondents
assigned to cities including "Ahmedabad," "Mumbai," and "Delhi." The city
names are identifiers or classifications with no inherent order or numeric value.
Each town represents a unique class; the data can't be compared or measured
quantitatively.

Instagram Rating: Ordinal Scale

Measurement Scale: Ordinal

Justification: The "score for Instagram" column suggests how without difficulty,
respondents use Instagram. Consists of "very plenty upset," "dissatisfieed," "
neutral," and "secure”. Without outstanding numerical values, those categories
constitute varying tiers of pride. "Very lots upset" represents the bottom stage of
pleasure, accompanied by "disillusioned," "neutral," and "secure" because the
most stage of satisfaction. Therefore, the "rating for Instagram" column is
measured on an ordinal scale, bearing in thoughts a relative class of delight
degrees; however, now not a unique measurement of delight magnitude.

REELS Rating: Ordinal Scale

Measurement Scale: Ordinal

Justification: The "rating for REELS" column displays respondents' pleasure

with the Instagram REELS feature. There are four categories: "very heaps
disillusioned," "disillusioned," "impartial," and "comfy." similar to Instagram's
score system, these categories denote numerous stages of gratification besides
assigning pearticular numerical values. "very plenty upset" represents the lowest
stage of pride, observed through using "dissatisfied," "neutral," and
"comfortable" because the maximum degree of pleasure. Consequently, the
"rating for REELS" column is measured on an ordinal scale, considering a
relative assessment of pride tiers. However, now not a unique size of satisfaction
value.
These size scale assignments clarify the nature of the data and the size leveel for
each column, thereby facilitating the evaluation and interpretation of the records.
Further, figuring out the measurement scales will resource in nicely handling and
studying the facts. It will assist us in selecting the proper visualization techniques,
statistical analyses, and modeling processes that correspond to the nature of the
variables. The Instagram and REELS ratings are measured on an ordinal scale,
indicating various degrees of satisfaction witheeout specific numerical values.
With expertise in size scales, we will rent suitable statistical techniques and
interpret the records accurately.e
e
Conclusion

Ultimately, it's vital to comprehend the measurement scales of the columns in a

dataset for aeccurate facts analysis and interpretation. We've recognized nominal
and ordinal measurement scales for every column within the dataset as part of
this evaluation. The respondent code and town columns are measured on a minor
scale, representing distinct categories or identifiers without a numerical fee. Also
measured on a nominal scale, the gewnder column categorizes respondents into
male and female sorts. The age groups column is calculated on an ordinal scale,
representing categories of age tiers without steady intervals.

Answer 2

Introduction
Stratified random sampling guarantees a consultant and impartial sample by
partitioning a population into outstanding companies or strata. Through
employing this technique, ressearchers can gain valuable insights into specific
subgroups of interest while preserving the traits of the general population. In this
context, we can create a stratified random pattern of 20 businesses, with company
reputation as the stratification variable for Leh and Ladakh.
This sampling approach aims to research the characteristics, performance, and
other relevant factsors of Leh and Ladakh-based groups while ensuring a
numerous representation across organization statuses. Via utilizing stratified
random sampling, we can correctly cope with the opportunity of bias from
choosing groups randomly without regard to their situation. This methods will
enhance the validity and generalizability of the study's findings, resulting in extra
solid and reliable conclusions. Interior each Stratum, we can look at revenue
growth, profitability, employment tiers, innovation, and marketplace percentage.
This analysis can help discover styles, traits, and disparities and tell enterprise-
unique policies and techniques.

Concept and Application

In data and research, proportionate stratified sampling guarantees that a sample

correctly represents the population. It involves partitioning the populace into
homogeneous corporatsions called strata and selecting a proportional number of
representatives from every Stratum primarily based on its relative size in the
masses. This approach is practical when a populace carries distinct subgroups
with distinct characteristics.
Using the organization fame because of the stratification variable, we can pick
out a pattern of 20 agencies from the companies-2021 dataset for Leh and Ladakh
with the usage of stratified random sampling. The categories of enterprise
reputation are "lively," "Strike Off," and "Othqers."

Using the provided data, the following are the procedures to execute a
proportional stratified sample:

Step 1: Data gathering

Download the companies-2021 dataset for Leh and Ladakh, which includes
information approximately regdistered organizations inside the region. The
variables consist of corporate identification number, corporation call,
organization status, company class, and company category.

Step 2: Specify the Stratum

Identify the pertinent stratification variable, the organization's reputation, in this
example. Create three strata dbased totally on the types of company status:
"lively," "Strike Off," and "Others." each Stratum represents a unique subset of
the entire population.

Step 3: Determine Stratum Sizes

Remember the number of companies in the dataset that belong to each repute
class to determine the significance of every Stratum. In this example, tally the
range of businesses specified as "active,"g "Strike Off," and "Others."

Step 4: Calculate Proportional Allocation

Determine the proportional allocation for each Stratum by dividing each
Stratum's size by the population's overall length. Multiplying the resulting
proportions with the preferred sample size yields the sample length objectives for
every Stratum.
e
Select Representative Samples from Each Stratum
And select a random number of samples from each Stratum based totally on the
pattern sizes decided in the previous section. Ensure the selection manner is
objective and representative o3f every Stratum corporation.

Analyze and validate the sample in Step 6.

Analyze the records of the selected groups to benefit the perception of their
characteristics, performance, and other applicable factors as soon as samples were
drawn from every Stratum. Perform statistical analyses or different vital studies
techniques to derive significant cofnclusions.
Using the company reputation because of the stratification variable, you may
assemble a proportional stratified pattern of 20 companies from the corporations-
2021 dataset for Leh aned Ladakh by following these steps. This sampling
technique ensures that the version correctly reflects the population and perwmits
meaningful evaluation and studies inside every stratum and across the entire
population.
Using stratified random sampling primarily based on company reputation to pick
out a sample of twenty businesses from Leh and Ladakh affords several blessings.
It opens up avenues for insightful dialogue and evalwuation. By stratifying the
population primarily based on agency status, we will look at the traits, standard
performance, and different factors specific to every stratum and seize the broad
range of the place's commercial enterprise landscape.
One of the primary advantages of stratified random sampling is that it ensures
that each organization's reputation elegance is represewnted within the final
pattern. This representation allows for comparisons among several employer
classes, which include minor companies, medium-sized corporations, and large
businesses. It presents an entire comprehension of the region's business company
surroundings by allowing us to investigate the unique, disturbing conditions,
possibilities, and trends inner each stratum.
In addition, stratification mitigates any capacity biags resulting from an easy
random pattern. Barring stratification, it's far viable to oversample or
undersample certain employer statuses, which can result in faulty results and
conclusions.

Conclusion

In conclusion, stratified random sampling primarily based on company fame

gives a scientific and green method for choosing a sample of twenty corporations
from the Leh and Ladakh areas. We ensure that each stratum is adequateely
regpresented within the last selection by dividing the population into distinct
strata based on enterprise reputation. This system allows us to investigate
companies with various statuses' characteristics, overall performance, and other
pertinent aspects, imparting complete knowledge of the nearby business
landscape.
Using stratified random sampling; we can triumph over capability biases and
beautify our sample's precision and representativeness. Twenety companies will
permit us to behavior in-intensity analyses, draw meaningful conclusions, and
make well-knowledgeable choices based on the results.

Answer 3 (A)

Introduction

The paired t-test was performed to research the relationship between "college"
and "standaloneInst," representing an impartial organization. On a sample of 13
observations, the evaluation turned into performed. The implied scoere for the
"university" variable was decided to be 36, with a popular error of 11.76642 and
a well-known deviation of 42.42444. The "standaloneInst" variable had an
average rating of 12, 76923, a standard error of 3.299483, and a standard
deviation of 11, 89645.

Concept and application

The calculation suggests distinction among the variables becomes 23, 23077,
with a well-known error of 8,553117 and a standard deviation of 30, 8387. The
difference's 95% confidence interval ranged from 4.595127 to 41.866431.
Consistent with that information, the "college" variable had, in common, a higher
rating than the "standaloneInst" variable. With 12 degrees of freedom, a t-price
of 2.71361 was obtained to check the hypotheses. In line with the null hypothesis
(Ho), the mean distinction between the two variables is 0. The alternative
thoughts (Ha) covered the opportunities where the implied difference is extra than
0, much less than 0, or identical to 0.
The p-values for the opportunity hypotheses were calculated as follows: for Ha:
suggest (diff) 0, p = 0.9906; for Ha: imply (diff)! = 0, p = 0.0187; and for Ha:
suggest (diff) > 0, p = 0.0094.

In step with these findings, there may be inadequate evidence to help resource the
opportunity speculation of a mean difference beneath 0. But there may be enough
evidence to reject the null hypothesis and conclude that the two variables range
extensively. The suggested difference was significantly more than 0, indicating
that the "university" variable had a tremendous effect compared to the
"standaloneInst" variable.

The paired t-test revealed a statistically significant difference between the

"college" and "standaloneInst" variables. This analysis gives critical insights into
the relationship between these variables and supports the idea that the
"university" variable has a greater significant effect or influence than the
"standaloneIdnst" variable.

t-Test: Paired Two Sample for Means

Variable 1 Variable 2
Mean 36 12.76923077
Variance 1799.833333 141.525641
Observations 13 13
Pearson Correlation 0.981109974
Hypothesized Mean Difference 5
df 12
t Stat 2.131476539
P(T<=t) one-tail 0.027205773
t Critical one-tail 1.782287556
P(T<=t) two-tail 0.054411545
t Critical two-tail 2.17881283

The paired t-check on the variables "university" and "standaloneInst" revealed a

statistically significant distinction. It turned out as soon as determined that the
implied rating for the "college" variable became considerably more potent than
the implied rating for the "standaloneInst" variable. This suggests that the
"college" variable has a fantastic effect, implying a more significant impact or
influence than the "standaloneInst" variable.

Conclusion

Its miles indispensable to amend the examination's boundaries, the confined

pattern length, and the specific context of the examined variables. Destiny
research must consider growing tshe sample length and incorporating a wider
variety of variables to understand better the connection between diverse
educational establishments and their consequences.

Answer 3 (b)

Introduction

The presented results of the evaluation of variance (ANOVA) reveal the sources
of variation and the corresponding statistical values for the provided facts.
ANOVA is a statistical look used to decide whether or not the manner of 3 or
greater companies or variables differ significantly.

Concept and Application

Tshe table lists the sources of variation, sum of squares (SS), degrees of freedom
(df), mean squares (MS), F-value, p-value, and the F-value at which significance
is lost.

Concept and Application

ANOVA
Source of
Variation SS df MS F P-value F crib
Between
Groups 24.9411765 16 1.55882353 65535 #NUM! #NUM!
Within Groups 0 0 65535

Total 24.9411765 16
The "among corporations" row represents the version among the compared
groups. In this instance, 16 classes are being analyzed. The among-group sum of
squares (SS) is 24.94117647, and the degree of freedom (DF) are 16. MS is
decided by dividing the sum of squares using the degrees of freedom, yielding
1.558823529.

The pronounced F-value is 65535, the ratio between the institution and within-
group vasriability. F-values greater than one indicate that variation among groups
exceeds version within groups.

However, the p-value and critical F-value are pronounced as "#NUM!” which
suggests a calculation error or trouble. This makes it difficult to interpret, based
on the available information, the statistical significance of the variations among
groups.

Variation within Groups: The "inside organizations" row represents the

positioned model inner every institution. On this situation, the sum of squares and
the ranges of freedom are mesntioned as 0, indicating that there can be no model
among companies. This may be the result of insufficient information or
calculation mistakes.

Total variation: The "overall" row represents the entire variation inside the
records and between and within classes. The overall sum of squares is 24,
94117647, with 16 degrees of freedom.

The big F-value among organizations indicates that there may be variations
between the organizations being compared, as indicated by way of the ANOVA
results. The inability to draw definitive conclusions regarding the statistical
significance of those differences needs to be improved by the absence of a p-price
and critical F-price. Examining the calculations or obtarining additional records
is usually recommended to interpret the ANOVA results correctly.

Conclusion
Evaluating the among-institution variability to the inside-institution variability
yields the F-price. A high F-price indicates that there are significant disparities
among businesses. In this instatnce, the reported F-price, 65535, is relatively
high.