Common mistakes

• Assuming independence in every multiple-test screen

  Inspect the product step rather than treating 1 − (1 − alpha)^m as universal.

  Common mistakes

• Halving every two-sided p-value

  Check the statistic sign and the planned alternative before using a tail shortcut.

  Common mistakes

• Treating a p-value as the probability of the null

  Repair the reversal from a model-conditional tail area to a hypothesis probability.

  Common mistakes

• Basis points, percentage points and decimal yield changes

  Avoid a hundredfold error when entering yield changes in formulas.

  Common mistakes

• Why a cash-cycle reduction does not specify cash released

  Use each changed component’s own flow base instead of multiplying all days by COGS.

  Common mistakes

• Mixing average and ending assets in DuPont analysis

  Check that the asset amount cancels between turnover and the equity multiplier.

  Common mistakes

• Why dividing an effective annual rate by twelve changes the model

  Use the annual growth factor to obtain an equivalent monthly rate.

  Common mistakes

• Material nonpublic information during an engagement meeting

  Identify the information-handling issue before making a trading recommendation.

  Common mistakes

• A rising goodwill percentage does not identify its cause

  Separate changes in the numerator from changes in the asset denominator.

  Common mistakes

• Recognising a solution versus solving independently

  Check what you can produce before viewing the worked answer.

  Common mistakes

• Why P(A given B) differs from P(B given A)

  Recover the joint probability, then divide by the probability of the new condition.

  Common mistakes

• Variance in percentage units and decimal-return units

  Account for the squared scale factor when converting variance.

  Common mistakes

• Centering a sampling distribution at the observed mean

  Distinguish the fixed population parameter from an estimate in one realized sample.

  Common mistakes

• Defining simple random sampling only by equal chances

  Check the allowed subsets before choosing a variance formula.

  Common mistakes

• Treating thirty observations as a normality guarantee

  Read the theorem conditions and actual approximation quality.

  Common mistakes