STATISTICS DEFINITION typically through hypothesis testing,

estimation, and confidence intervals.

• Statistics is the branch of mathematics which deals - For example, the retailer predicts the
with the collection, organization, and analysis and sales for the upcoming holiday season
interpretation of quantitative data to come up with a based on the past 12 months' average
generalization that aides in intelligent decision sales and seasonal trends.
making.
•Estimation

•Hypothesis Testing
EXAMPLES:
DESCRIPTIVE STATISTICS: Measure of Central
• Analyzing sales trends to forecast future revenue. Tendency

• Evaluating customer satisfaction using survey data. • A measure of central tendency is a single value
that attempts to describe a set of data by identifying
• Monitoring inventory levels to optimize stock the central position of data. within that set
management.
• a.k.a. measures of central location, MOCT are
• Assessing the effectiveness of marketing classed as summary statistics.
campaigns using conversion rates.
• It involves the use of mean, median, and mode.

MEAN
IMPORTANCE OF STATISTICS
• The mean considers every value in the dataset,
• It provides data-driven insights that help making it highly sensitive to all data.
businesses make well-informed decisions.
• Extreme values can significantly impact the mean,
• It helps in understanding market trends, customer pulling it higher or lower.
preferences, and competitive positioning.
• For a given dataset, the mean is always unique.
• Businesses use statistical models to identify and
mitigate potential risks. • When the dataset is evenly distributed without
outliers, the mean is the most accurate
• Statistics measure and evaluate the performance of representation of central tendency.
business strategies and processes.
MEDIAN
• It ensures efficient allocation of resources by
analyzing data on production, sales, and operations. • The median is robust and resistant to extreme
values, making it a better measure for skewed
TYPES OF STATISTICS distributions.
1. DESCRIPTIVE STATISTICS • The data must be arranged in ascending or
- involve methods for summarizing, descending order to find the median.
organizing, and presenting data in a
meaningful way, such as using • For an odd number of values, the median is the
measures of central tendency, middle value.
dispersion, and graphical
representations. • For an even number of values, it is the average of
- For example, a retailer calculates the the two middle values.
average sales of their top-selling
product over the last 12 months. • It provides a central value even when the dataset is
Inferential Statistics not symmetrically distributed.

•Collect Data e.g. Survey

•Present Data e.g. Tables and MODE

Graphs
• The mode identifies the most frequently occurring
•Characterize Data e.g. Mean value in the dataset.

• It is resistant to outliers.

2. INFERENTIAL STATISTICS • A dataset can have more than one mode if multiple
- involve methods for drawing values occur with the same highest frequency.
conclusions or making predictions about
a population based on sample data,
• The mode is especially useful for non-numerical VARIANCE
data, such as identifying the most common category
in a survey. • The average squared deviation of each data point
from the mean.
• If no value repeats, the dataset has no mode.
• Considers all data points.
Measure of Central Tendency (Grouped Data)
• Units are squared, making it less interpretable.
• Grouped data refers to data that has been
organized into classes or intervals for easier analysis STANDARD DEVIATION
and interpretation. Instead of listing every individual
• The square root of the variance; measures the
data point, the data values are grouped into ranges
average deviation from the mean.
(intervals), and the number of observations
(frequency) in each range is recorded. This method is • Same units as the data; widely used.
commonly used when dealing with large datasets to
summarize and simplify the data. • Sensitive to outliers.

N Choosing the Right Measure

x=
∑ fx 2
−cf
~
x=Lcb +( )i • Use range or IQR for quick insights into variability.
n f • Use variance and standard deviation for detailed

^x =Lcb + ( ∆1
∆ 1+∆ 2
i ) and mathematically robust analysis.

• Consider MAD or IQR for datasets with outliers.

DESCRIPTIVE STATISTICS: Measure of Formula:

Dispersion
UNGROUPED
• The measures of dispersion describe the degree of
spread of scores in a distribution. R = highest value – lowest value IQR = Q3 – Q1

• It determines how close or far are the score of the k (N +1) 2 ∑ (x−x)2
students from the average, usually the mean, Qk =rank s=
performance of the set of observations. 4 n−1
RANGE

• The difference between the highest and lowest

values in the dataset.
s=
√ ∑ ( x−x)2
n−1
GROUPED (SAMPLE)
• Simple to calculate.

R=U CB −LCB s2= ∑

2
• Sensitive to outliers; does not provide information f (x−x )
about the distribution of data. n−1

INTERQUARTILE RANGE
s=
√ ∑ f ( x−x)2
n−1
GROUPED (POPULATION)
• The range of the middle 50% of the data,
calculated as the difference between the third R=U CB −LCB
∑ ∑
√
quartile (Q3) and the first quartile (Q1). • Robust to
outliers. 2 f (x−x )2 f ( x−x )2
s= s=
• Ignores the tails of the distribution.
N N