- Home
- /
- Statistics
- /
- Mistakes
- /
- Probability & Chance
Common Mistakes in Probability & Chance
52 common pitfalls across 13 concepts, including 13 recurring stuck points
These are the pitfalls students hit across all 13 probability & chance concepts, from Basic Probability, Theoretical Probability and Experimental Probability onward. Each entry names the concept it comes from, so you can tell a slip from a genuine gap and go straight to the explanation.
Students often know a procedure related to basic probability but skip the recognition step: Is the question about one event in one draw, roll or spin, and how likely it is from 0 to 1? That leads to a calculation or graph that looks reasonable but answers a different question.
Thinking 0.5 means it WILL happen half the time (short-run variation)
Gambler's fallacy (thinking past outcomes affect future independent events)
Forgetting that all probabilities for a sample space must sum to 1
Students often know a procedure related to theoretical probability but skip the recognition step: Can you work out the chance from the fair design of the die, coin, deck or spinner alone, before anything is tried? That leads to a calculation or graph that looks reasonable but answers a different question.
Assuming all outcomes are equally likely
Forgetting theoretical experimental results
Not listing all outcomes
Students often know a procedure related to experimental probability but skip the recognition step: Is the chance estimated from results someone actually recorded, counting how often the event happened out of all the tries? That leads to a calculation or graph that looks reasonable but answers a different question.
Too few trials for reliable estimates
Expecting exact match with theoretical
Not recording all trials
Students often know a procedure related to sample space but skip the recognition step: Is the task to list or count every possible outcome, rather than to find the chance of one of them? That leads to a calculation or graph that looks reasonable but answers a different question.
Missing outcomes
Counting HT and TH as the same
Not accounting for order when it matters
Students often know a procedure related to tree diagram but skip the recognition step: Does the chance process happen in steps, with every result of one step leading on to the possible results of the next? That leads to a calculation or graph that looks reasonable but answers a different question.
Forgetting branches and missing valid outcomes
Adding branch probabilities when the path requires multiplication
Treating different stages as if they happen at the same time
Students often know a procedure related to compound events but skip the recognition step: Is the event made of two simpler events, so you must decide whether both have to happen or either one is enough? That leads to a calculation or graph that looks reasonable but answers a different question.
Adding when should multiply
Forgetting to subtract overlap for 'or'
Assuming events are independent when they're not
Students often know a procedure related to conditional probability but skip the recognition step: Are you told that some condition is already true, so only the cases meeting it count as the new total? That leads to a calculation or graph that looks reasonable but answers a different question.
Keeping the original total instead of the conditional total
Confusing with - These are usually different because they divide by different totals. With 12 sport, 8 music, and 5 both: , but . Always ask which event is the “given” one — that event is your denominator.
Treating conditional probability as the same as independence
Students often assume events are independent just because the story describes two different actions. Recognition is harder than the formula.
Assuming independence just because two events sound unrelated — always check whether the first event's outcome actually changes the second event's probability before applying .
Using the multiplication rule when events are actually dependent — for dependent events you must use instead.
Confusing mutually exclusive with independent — mutually exclusive events CAN'T both happen so , while independent events have , which is nonzero.
Students often know a procedure related to addition rule but skip the recognition step: Is a success either of two events, so outcomes belonging to both must be counted only once? That leads to a calculation or graph that looks reasonable but answers a different question.
Adding probabilities without subtracting overlap
Using the addition rule for “and” problems
Assuming the overlap is zero without checking the context
Students often know a procedure related to multiplication rule but skip the recognition step: Must both events happen, with the second event's chance taken after the first one has already occurred? That leads to a calculation or graph that looks reasonable but answers a different question.
Multiplying original probabilities when the second event is conditional
Using the multiplication rule for “or” problems
Ignoring whether the process uses replacement or not
Students often know a procedure related to statistical simulation but skip the recognition step: Is the exact chance too messy to count, so you would model the process with random numbers and repeat it many times? That leads to a calculation or graph that looks reasonable but answers a different question.
Too few simulations for accuracy
Not properly randomizing
Forgetting simulation is approximate
Students often know a procedure related to law of large numbers but skip the recognition step: Is the question about how an average or a proportion behaves as the number of independent trials grows very large? That leads to a calculation or graph that looks reasonable but answers a different question.
Gambler's fallacy (thinking short-run must 'balance')
Applying to single events
Expecting exact convergence
Students often know a procedure related to expected value but skip the recognition step: Does each possible outcome carry a value, such as points or dollars, so you need the probability-weighted average per try? That leads to a calculation or graph that looks reasonable but answers a different question.
Confusing EV with most likely outcome
Ignoring EV for emotional decisions
Not accounting for all outcomes