Punktanalüüs

Punktanalüüs, commonly referred to as point analysis or item analysis in English, is a statistical method used to evaluate the quality of individual questions within a test or assessment. It helps in understanding how well each question performs in differentiating between individuals with high and low overall scores. The primary goals of punktanalüüs are to identify problematic questions that may be too easy, too difficult, or ambiguous, and to improve the overall reliability and validity of the assessment.

The analysis typically involves examining two key statistics for each question: the difficulty index and the discrimination index. The difficulty index, often represented by 'p', indicates the proportion of test-takers who answered a question correctly. A high 'p' value suggests an easy question, while a low 'p' value indicates a difficult question. The discrimination index measures how well a question differentiates between high-scoring and low-scoring individuals. A question with a high discrimination index means that individuals who scored well on the overall test also tended to answer that specific question correctly, and vice versa.

Based on the results of the punktanalüüs, test creators can make informed decisions about revising or removing poorly performing questions. Questions that are too easy or too difficult might be adjusted to fall within an optimal difficulty range. Questions with low or negative discrimination indices may be flawed and require rephrasing or complete replacement. By systematically analyzing each point, punktanalüüs contributes significantly to the development of more effective and psychometrically sound assessments.