NORMAL DISTRIBUTION, STANDARD ERROR, Z-TEST, T-TEST & HYPOTHESIS TESTING
(SIMPLIFIED NOTES)
1. NORMAL DISTRIBUTION
A normal distribution is a bell■shaped curve that shows how data values are spread. Most values
lie close to the mean, and fewer values lie at the extreme ends. Many natural and human
measurements follow this pattern.
2. STANDARD NORMAL DISTRIBUTION (Z-DISTRIBUTION)
When a normal distribution is converted into standard form, the mean becomes 0 and SD becomes
1. This conversion is done using:
Z = (X – µ) / σ
This allows all different normal datasets to be compared on a common scale.
3. Z-SCORES
A Z-score tells how many standard deviations a value is away from its mean. It helps us understand
how unusual or common a value is.
4. SAMPLING DISTRIBUTION & STANDARD ERROR
If we take repeated samples from the same population, the means of these samples form a
sampling distribution. The spread of these sample means is called Standard Error (SE):
SE = σ / √n
It tells how much a sample mean is expected to differ from the true population mean.
5. HYPOTHESIS TESTING
It is a method to check whether a sample provides enough evidence to support or reject an
assumption about a population.
- Null hypothesis (H0): The assumption we start with (e.g., mean is equal to some value).
- Alternative hypothesis (H1): The claim we want to check.
We compare probability of observing our sample result if H0 is true. If the probability is too low, we
reject H0.
6. Z-TEST
Used when:
- Sample size is large (n ≥ 30), OR
- Population SD (σ) is known.
Test statistic:
Z = (X■ – µ0) / (σ / √n)
The calculated Z is compared with Z-table values to decide acceptance or rejection of H0.
7. T-TEST
Used when:
- Sample size is small (n < 30), AND
- Population SD is unknown.
Test statistic:
t = (X■ – µ0) / (s / √n)
Here “s” is sample SD. t-values depend on Degrees of Freedom (df = n – 1). t-distribution is wider
because small samples have more uncertainty.
8. DEGREE OF FREEDOM
DF means the number of values that are free to vary. For a single sample mean, df = n – 1. It
adjusts the shape of the t-distribution depending on sample size.
9. CONNECTION BETWEEN PROBABILITY & TESTING
Z-test and t-test are based on probability distributions. Probability tables tell us the cutoff values
beyond which results are considered unlikely. If the test statistic falls beyond these cutoffs, the
result is significant and H0 is rejected.
10. SUMMARY IN SIMPLE WORDS
- Normal distribution explains natural variation.
- Z-distribution standardizes any normal data.
- Standard Error explains variation in sample means.
- Hypothesis testing uses probability to judge claims.
- Z-test is for large samples or known σ.
- t-test is for small samples with unknown σ.
- Degrees of freedom adjust the t-distribution.
- Decisions are made by comparing calculated statistics to probability-based critical values.
These concepts together form the core of inferential statistics.