Complete Statistical Inference Definitions
Statistical Inference
Statistical inference is the process of using sample data to draw conclusions about a population. It
helps in estimating population parameters and testing hypotheses. Example: Using marks of 50
students to estimate the average marks of all students.
Population
Population is the complete collection of all individuals or items under study. It includes every
possible observation. Example: All students enrolled in a university.
Sample
A sample is a part of the population selected for analysis. It is used when studying the entire
population is not possible. Example: 50 students selected from a university.
Parameter
A parameter is a numerical value that describes a population characteristic. It is fixed but usually
unknown. Example: Population mean µ.
Statistic
A statistic is a numerical value calculated from sample data. It varies from one sample to another.
Example: Sample mean x■.
Estimator
An estimator is a formula or rule used to estimate a population parameter. It depends on sample
observations. Example: x■ = Σx / n.
Estimate
An estimate is the numerical value obtained after applying an estimator. It provides an approximate
value of the parameter. Example: x■ = 72.
Point Estimation
Point estimation provides a single numerical value for a population parameter. It does not show
uncertainty. Example: µ ≈ 72.
Interval Estimation
Interval estimation provides a range of values for a population parameter. It shows possible
variation in estimation. Example: µ lies between 70 and 74.
Confidence Interval
A confidence interval is a range of values that likely contains the true parameter. It is based on a
confidence level. Example: 95% confidence interval (70, 74).
Confidence Level
Confidence level is the probability that the confidence interval contains the true parameter. It is
usually expressed as a percentage. Example: 95% confidence level.
Standard Error
Standard error is the standard deviation of a sampling distribution. It measures the variability of a
statistic. Example: SE = s / √n.
Sampling Distribution
Sampling distribution is the distribution of a statistic for all possible samples. It is used in estimation
and testing. Example: Distribution of sample means.
Unbiased Estimator
An estimator is unbiased if its expected value equals the true parameter. It does not systematically
overestimate or underestimate. Example: Sample mean for µ.
Biased Estimator
An estimator is biased if its expected value differs from the true parameter. It causes systematic
error. Example: Variance using n instead of n−1.
Consistent Estimator
An estimator is consistent if it approaches the true value as sample size increases. Large samples
improve accuracy. Example: x■ approaches µ as n increases.
Efficient Estimator
An estimator is efficient if it has the smallest variance among unbiased estimators. It provides more
precise estimates. Example: Mean is more efficient than median.
Sufficient Estimator
An estimator is sufficient if it uses all information in the sample. No other statistic gives additional
information. Example: Sample mean in normal distribution.
Mean Square Error
Mean square error measures overall accuracy of an estimator. It combines variance and bias.
Example: MSE = Variance + Bias².
Hypothesis
A hypothesis is a statement about a population parameter. It is tested using sample data. Example:
Average height is 165 cm.
Null Hypothesis
Null hypothesis states there is no effect or no difference. It is tested for rejection. Example: H■: µ =
165.
Alternative Hypothesis
Alternative hypothesis states there is an effect or difference. It contradicts the null hypothesis.
Example: H■: µ ≠ 165.
Level of Significance
Level of significance is the probability of rejecting a true null hypothesis. It is denoted by α.
Example: α = 0.05.
Test Statistic
Test statistic is a value calculated from sample data. It is used to make a decision about H■.
Example: Z or t value.
Critical Value
Critical value separates acceptance and rejection regions. It depends on α. Example: Z = ±1.96.
Critical Region
Critical region is the set of values that leads to rejection of H■. It lies beyond the critical value.
Example: Z > 1.96.
Type I Error
Type I error occurs when a true null hypothesis is rejected. Its probability equals α. Example:
Saying medicine works when it does not.
Type II Error
Type II error occurs when a false null hypothesis is not rejected. Its probability equals β. Example:
Saying medicine does not work when it does.
P-value
P-value is the probability of observing results as extreme as the sample result. It assumes H■ is
true. Example: p < 0.05 → reject H■.
One-tailed Test
A one-tailed test has rejection region on one side only. It tests direction of effect. Example: H■: µ >
50.
Two-tailed Test
A two-tailed test has rejection regions on both sides. It tests difference in both directions. Example:
H■: µ ≠ 50.
Central Limit Theorem
Central limit theorem states that sampling distribution of mean becomes normal for large samples.
It applies regardless of population distribution. Example: n ≥ 30.
Degrees of Freedom
Degrees of freedom is the number of independent observations. It is used in t and chi-square tests.
Example: df = n − 1.