Probability and Statistics Basic Class 12 Questions for AGNIVEER NAVY

Probability: Definitions and Basic Rules

Probability measures how likely an event is to happen, ranging from 0 (impossible) to 1 (certain). Think of it as a fraction: favorable outcomes divided by total possible outcomes. In Agniveer exams, you'll see problems involving dice, cards, coins, and real-world naval/military scenarios. The key is identifying the sample space correctly and counting without repetition. Mutually exclusive events cannot happen together (like getting heads AND tails in one flip). Independent events don't affect each other's probability.

• Probability P(A) = (Number of favorable outcomes) / (Total possible outcomes)
• P(A) + P(not A) = 1 always
• For mutually exclusive events: P(A or B) = P(A) + P(B)
• For independent events: P(A and B) = P(A) × P(B)
• Conditional probability P(A|B) = P(A and B) / P(B) — probability of A given B already happened
• Sample space must be exhaustive and mutually exclusive

Bayes' Theorem and Conditional Probability

Bayes' theorem is the workhorse of conditional probability problems. It lets you reverse conditional probabilities—if you know P(B|A), you can find P(A|B). In Agniveer exams, this appears in real-world scenarios: 'A radar detects enemy ships with 95% accuracy. If it signals, what's the probability an enemy is actually there?' This requires Bayes' theorem. The key is setting up the problem carefully: identify what you know and what you're asked to find.

• Bayes' theorem: P(A|B) = [P(B|A) × P(A)] / P(B)
• P(B) = P(B|A) × P(A) + P(B|not A) × P(not A) — law of total probability
• Use a tree diagram or table to organize given probabilities
• Watch for 'prior' (initial belief) vs 'posterior' (updated belief) language
• Common trap: confusing P(A|B) with P(B|A)

Statistics: Mean, Variance, Standard Deviation

Statistics summarize data. Mean is the average. Variance measures spread—how far data points scatter from the mean. Standard deviation is the square root of variance, in the same units as the data. In Agniveer exams, you'll calculate these from frequency tables or raw data, often under time pressure. Grouped data (ranges) requires midpoints. The formulas look intimidating but are mechanical once you organize your work.

• Mean (average) = sum of all values / count of values
• Variance = average of squared deviations from mean = E(X²) - [E(X)]²
• Standard deviation = square root of variance; measures spread in original units
• For grouped data, use class midpoints and frequencies
• Coefficient of variation = (SD / Mean) × 100; compares spread relative to mean

Normal Distribution and Z-Scores

The normal distribution is bell-shaped and symmetric. Most real-world data (heights, test scores, measurement errors) follow this pattern. Z-score standardizes data: it tells you how many standard deviations a value is from the mean. In Agniveer exams, you'll use z-score tables to find probabilities. The key insight: any normal distribution can be converted to a standard normal (mean 0, SD 1) using z-scores, then you look up the probability in a table.

• Normal distribution is symmetric around the mean; 68% of data within 1 SD, 95% within 2 SD, 99.7% within 3 SD
• Z-score = (value - mean) / standard deviation; tells you position relative to mean
• Standard normal distribution has mean 0 and SD 1
• Use z-score tables to find cumulative probability P(Z ≤ z)
• For P(a < X < b), convert both a and b to z-scores, then subtract probabilities

• Confusing P(A|B) with P(B|A). These are NOT the same. Always identify which event is the condition (denominator).
• Forgetting to divide by total outcomes when sample space is not obvious. Example: 'At least one head in 3 coin flips' has 7 favorable outcomes out of 8, not 3 out of 6.
• Using population variance formula (divide by n) instead of sample variance (divide by n-1) when data is a sample. Agniveer papers usually specify; read carefully.
• Misreading grouped data tables. Always use class midpoints, not boundaries, for calculations.
• Rounding z-scores too early. Keep 2-3 decimal places until final answer to avoid table lookup errors.
• Assuming independence without justification. Example: drawing cards without replacement changes probabilities; they are NOT independent.

• PEMDAS for probability: Prior × Evidence / Denominator = Adjusted Strength (Bayes' mnemonic: numerator is P(B|A)×P(A), denominator is P(B)).
• 68-95-99.7 rule: Within 1-2-3 standard deviations, you capture 68%-95%-99.7% of normal data. Visual: one-sigma hug captures most data.
• Variance is 'average squared distance'; SD is 'typical distance' — SD is more intuitive for interpretation.
• Z-score = 'how many SDs away?' — positive z means above mean, negative means below. Z = 0 is the mean itself.

• Agniveer Navy papers typically include 1 Bayes' theorem problem (real-world scenario like radar/detection) and 1-2 statistics problems (mean/variance from tables). These are time-sensitive; practice speed.
• Conditional probability questions often hide the condition in the problem statement. Underline 'given that' or 'if' clauses before solving.
• Normal distribution questions almost always require a z-score table. Memorize the table or know how to interpolate. The exam provides a table, but reading it quickly saves 1-2 minutes per question.
• Grouped data problems are common in statistics section. Set up a frequency table with columns for class, midpoint, frequency, f×x, and f×x² to avoid errors.
• Watch for 'at least' and 'at most' language in probability. 'At least 1' usually means 1 - P(none). This is faster than counting all cases.