Topic :
Statistical Inference Terminology
(Types of error, Tails of Test, Confidence
Interval)
By:
Swati Mahajan
Tushar Gaikwad
Atharva Yenurkar
Agenda
- Introduction to Statistical Inference
- Types of Errors
- Tails of Test
- Confidence Intervals
- Applications and Examples
Introduction to Statistical Inference
● Statistical inference is the process of drawing conclusions
about a population's characteristics based on a sample of
data taken from that population.
● It involves using mathematical techniques to make
predictions or decisions about the population.
Key Concepts
● Population:
○ Definition: The entire set of individuals or items of interest in a statistical
study.
○ Characteristics: Includes all possible observations relevant to the study.
○ Example: All citizens of a country when studying national health statistics.
● Sample:
○ Definition: A subset of the population selected for analysis.
○ Characteristics: Represents the population and is used to make inferences
about the entire group.
○ Example: A group of 1,000 citizens surveyed about their health, selected
from the national population.
● Population Parameter:
○ Definition: A numerical value that describes a characteristic of a population.
○ Characteristics: Fixed and usually unknown, representing the entire
population.
○ Example: Population mean, population proportion, population standard
deviation.
● Sample Statistic:
○ Definition: A numerical value calculated from sample data that describes a
characteristic of a sample.
○ Characteristics: Variable and known, representing a subset of the
population.
○ Example: Sample mean, sample proportion, sample standard deviation.
Hypothesis Testing
● Definition: Hypothesis testing is a statistical method used to make inferences about a
population based on sample data.
● Purpose: To assess the strength of evidence against a null hypothesis and make
decisions about population parameters or effects.
Key Components
● Null Hypothesis (H0):
○ Definition: The default assumption that there is no significant difference or effect.
○ Characteristics: Typically represents the status quo or no change scenario.
○ Example: H0: The mean exam score of students is 75
● Alternative Hypothesis (H1 or Ha):
○ Definition: The hypothesis that there is a significant difference or effect.
○ Characteristics: Challenges or opposes the null hypothesis.
○ Example: Ha: The mean exam score of students is not equal to 75.
Types of Errors
In statistical inference ,the primary types of error are Type I and Type II
Error
• Type I Error:
○ Definition: Occurs when the null hypothesis is true, but it is incorrectly rejected.
○ Characteristics: Represents the situation where we conclude that there is a significant
effect or difference when there isn't one.
○ Example: Let's say a drug company is testing a new medication and wishes to
determine if it's effective in treating a certain condition. The null hypothesis (H0)
would be that the medication has no effect, and the alternative hypothesis (H1)
would be that the medication is effective. A Type I error would occur if, based on
the sample data, the drug company incorrectly concludes that the medication is
effective (rejects the null hypothesis) when, in reality, it has no effect
● Type II Error:
○ Definition: Occurs when the null hypothesis is false, but it is incorrectly
retained or not rejected
○ Characteristics: Represents the situation where we fail to detect an effect or
difference that actually exists
○ Example: : Using the same example as above, a Type II error would occur if,
based on the sample data, the drug company fails to conclude that the
medication is effective (fails to reject the null hypothesis) when, in reality, it
does have a positive effect.
Tails of Test
● One-Tailed Test:
○ Definition: Test in which the critical region lies in one tail of the sampling
distribution.
○ Purpose: Mainly used when the researcher is specifically interested in testing a hypothesis in one
direction (either greater than or less than).
○ Example: Testing if a new drug increases blood pressure (only interested in
whether it increases, not decreases).
● Two-Tailed Test:
○ Definition: Test in which the critical region lies in both tails of the
sampling distribution.
○ Purpose: This type of test is used when the researcher wants to test whether there is a
significant effect in either direction.
○ Example: Testing if a new drug has any effect on blood pressure
(interested in both increase and decrease).
Confidence Intervals
● Confidence Intervals:
○ Definition: Range of values around a point estimate that likely
contains the true population parameter.
○ Characteristics: Estimation range, confidence level, point estimate,
standard error.
○ Example: Calculating a 95% confidence interval for the mean
time spent daily on social media by teenagers in a city.
Conclusion:
● Statistical inference involves understanding and
interpreting key concepts such as types of error, tails of
tests, and confidence intervals.
● roper application of these concepts is crucial for drawing
valid conclusions from data and making informed
decisions.