Example: Median-Median Regression

Functions > Data Analysis > Curve Fitting > Example: Median-Median Regression

Use the medfit function to calculate the median-median straight line fit for a data set.

1. Define a data set.

The last point is an outlier:

2. Call the medfit function to find the coefficients of the median-median straight line fit. Use these coefficients to define the median-median line.

3. Call the line function to find the coefficients of the least-squares linear fit. Use these coefficients to define the line of best fit.

4. Plot the data points and the two lines defined above.

<region id="ID0EA64S" top="480" left="48" width="312" height="312" xmlns="http://schemas.mathsoft.com/worksheet50">
  <plot origin-positioning="true">
    <xyPlot>
      <title class="- topic/title " wwtype:type="Paragraph" xmlns:wwtype="urn:WebWorks-Type-Schema" />
      <legend />
      <traces>
        <trace>
          <traceStyle color="#FF00008B" symbol="x" line-weight="1" line-style="None">lines</traceStyle>
        </trace>
        <trace num-of-points="500">
          <traceStyle color="#FF000000" symbol="none" line-weight="1" line-style="Solid">lines</traceStyle>
        </trace>
        <trace num-of-points="500">
          <traceStyle color="#FFFF0000" symbol="none" line-weight="1" line-style="Solid">lines</traceStyle>
        </trace>
      </traces>
      <axes>
        <xAxis legend-position="PlotBoundaryBottom" rank="1">
          <axisLine position="origin" positionticmark="6" />
          <axisGrid>
            <gridFrequency>11</gridFrequency>
            <gridLabels display="true" />
            <gridLines />
            <tickMarks display="true" />
          </axisGrid>
          <axisLabel />
          <markers />
          <numberFormat />
          <plotEquations>
            <plotEquation>
              <math>
                <id xmlns="http://schemas.mathsoft.com/math50">X</id>
              </math>
              <math>
                <placeholder xmlns="http://schemas.mathsoft.com/math50" />
              </math>
            </plotEquation>
            <plotEquation>
              <math>
                <id xmlns="http://schemas.mathsoft.com/math50">x</id>
              </math>
              <math>
                <placeholder xmlns="http://schemas.mathsoft.com/math50" />
              </math>
            </plotEquation>
          </plotEquations>
          <xyDomain scale-type="linear" auto-scale="true">
            <startValue>
              <real xmlns="http://schemas.mathsoft.com/math50">-10</real>
            </startValue>
            <endValue>
              <real xmlns="http://schemas.mathsoft.com/math50">10</real>
            </endValue>
          </xyDomain>
        </xAxis>
        <yAxis legend-position="PlotBoundaryLeft" rank="1">
          <axisLine position="origin" positionticmark="5" />
          <axisGrid>
            <gridFrequency>11</gridFrequency>
            <gridLabels display="true" />
            <gridLines />
            <tickMarks display="true" />
          </axisGrid>
          <axisLabel />
          <markers />
          <numberFormat />
          <plotEquations>
            <plotEquation>
              <math>
                <id xmlns="http://schemas.mathsoft.com/math50">Y</id>
              </math>
              <math>
                <placeholder xmlns="http://schemas.mathsoft.com/math50" />
              </math>
            </plotEquation>
            <plotEquation>
              <math>
                <apply xmlns="http://schemas.mathsoft.com/math50">
                  <id>med</id>
                  <id>x</id>
                </apply>
              </math>
              <math>
                <placeholder xmlns="http://schemas.mathsoft.com/math50" />
              </math>
            </plotEquation>
            <plotEquation>
              <math>
                <apply xmlns="http://schemas.mathsoft.com/math50">
                  <id>lsq</id>
                  <id>x</id>
                </apply>
              </math>
              <math>
                <placeholder xmlns="http://schemas.mathsoft.com/math50" />
              </math>
            </plotEquation>
          </plotEquations>
          <xyDomain scale-type="linear" auto-scale="true">
            <startValue>
              <real xmlns="http://schemas.mathsoft.com/math50">-120</real>
            </startValue>
            <endValue>
              <real xmlns="http://schemas.mathsoft.com/math50">80</real>
            </endValue>
          </xyDomain>
        </yAxis>
      </axes>
    </xyPlot>
  </plot>
</region>

The linear fit is much more affected by the outlier than is the median-median fit.