Skip to content

令和6年度 ITパスポート試験 問14

This question's explanation and your answers so far.

問14
頻出度★★★

ある商品の販売量と気温の関係が一次式で近似できるとき, 予測した気温から商品の販売量を推定する手法として, 適切なものはどれか。

出典 令和6年度 ITパスポート試験 問14
解説

問 14

  • ア

    正解 The correct answer is ア, regression analysis. Regression analysis is a statistical method that expresses the relationship between two or more variables with a regression equation and uses that equation to predict the value of one variable from another. In this question, the relationship between sales volume and temperature can be approximated by a linear equation y = ax + b (the coefficients a and b are found by the least squares method), so you can estimate the sales volume y simply by substituting the predicted temperature x into the equation. The conditions of being approximated by a linear equation and estimating from a predicted value are exactly the typical use of regression analysis (especially simple regression), so ア is appropriate.

  • Incorrectイ

    Linear programming is an optimization method that maximizes or minimizes an objective function such as profit under multiple constraints (linear inequalities). Although it shares the term linear equation, its purpose is to find an optimal allocation or combination, not to predict sales volume from temperature, so it is wrong.

  • Incorrectウ

    The Delphi method is a qualitative forecasting method that repeatedly surveys multiple experts and feeds back their opinions so that their views converge. It has nothing to do with estimation based on a linear approximation of numerical data, so it is wrong.

  • Incorrectエ

    Pareto analysis is a method (ABC analysis, the 80/20 rule) that arranges items in descending order of amount or count and uses the cumulative ratio to find the elements that should be managed with priority. Its purpose is to narrow down the important items, not to predict values, so it is wrong.

ここがポイント
  • Regression analysis expresses the relationship between variables with a regression equation (such as a linear equation) and predicts the value of the dependent variable from the value of the explanatory variable; the coefficients are found by the least squares method.
  • When keywords like approximated by a linear equation or estimating from a predicted value appear, choose regression analysis. Linear programming is for optimization, the Delphi method is qualitative forecasting, and Pareto analysis extracts priority items; none of them estimate using a prediction equation.
用語

Your answers