Development of Multiple Linear Regression Model to Predict COD Concentration based on West Tarum Canal Surface Water Quality Data

Abstract

<strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US">Abstract. </span></strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA; mso-bidi-font-weight: bold;" lang="EN-US">COD level indicates the organic matter pollution in water. A predictive analysis, such as Multiple Linear Regression, could be an option to make the COD measurement more effective. <strong>Objectives:</strong></span><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA; mso-bidi-font-weight: bold;" lang="EN-US">This research aims to determine the parameter that can predict COD concentration using correlation analysis and develop a Multiple Linear Regression Model for predictive analysis on COD level in the West Tarum Canal surface water. <strong>Method and results:</strong> The correlation analysis is done in Microsoft Excel using the Pearson Product Moment Correlation Analysis. The water quality dataset is inputted to the R Studio and made the MLR model. The model is validated using t-Test. The result showed that all models in all intake points are not showing good prediction results, and the predictors showed no effect on the COD level. <strong>Conclusion:</strong> The Multiple Linear Regression is not a fit tool for predicting the COD in the West Tarum Canal surface water. </span><a style="mso-comment-reference: rh_1; mso-comment-date: 20201202T0302; mso-comment-done: yes;"><strong style="mso-bidi-font-weight: normal;"><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US">Abstract</span></strong></a><span class="MsoCommentReference"><span style="font-size: 8.0pt; font-family: 'New York',serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: 'New York'; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US"><!--[if !supportAnnotations]--><a id="_anchor_1" class="msocomanchor" name="_msoanchor_1" href="file:///J:/THESIS/THESIS%20DOCUMENTS/JOURNAL%20SEMINAR/SUBMIT%20JENV/Julio%20Putra%20David_Development%20of%20Multiple%20Linear%20Regression%20Model%20to%20Predict%20COD%20Concentration%20based%20on%20West%20Tarum%20Canal%20Surface%20Water%20Quality%20Data.docx#_msocom_1"></a>[rh1]<!--[endif]--><span style="mso-special-character: comment;"> </span></span></span><strong style="mso-bidi-font-weight: normal;"><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US">. </span></strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA; mso-bidi-font-weight: bold;" lang="EN-US">COD level indicates the organic matter pollution in water. A predictive analysis, such as Multiple Linear Regression, could be an option to make the COD measurement more effective. <span style="mso-spacerun: yes;"> </span><a style="mso-comment-reference: rh_2; mso-comment-date: 20201202T0249; mso-comment-done: yes;"><strong>Objectives</strong></a></span><span class="MsoCommentReference"><span style="font-size: 8.0pt; font-family: 'New York',serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: 'New York'; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US"><!--[if !supportAnnotations]--><a id="_anchor_2" class="msocomanchor" name="_msoanchor_2" href="file:///J:/THESIS/THESIS%20DOCUMENTS/JOURNAL%20SEMINAR/SUBMIT%20JENV/Julio%20Putra%20David_Development%20of%20Multiple%20Linear%20Regression%20Model%20to%20Predict%20COD%20Concentration%20based%20on%20West%20Tarum%20Canal%20Surface%20Water%20Quality%20Data.docx#_msocom_2"></a>[rh2]<!--[endif]--><span style="mso-special-character: comment;"> </span></span></span><strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US">:</span></strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA; mso-bidi-font-weight: bold;" lang="EN-US">This research aims to determine the parameter that can predict COD concentration using correlation analysis and develop a Multiple Linear Regression Model for predictive analysis on COD level in the West Tarum Canal surface water. <a style="mso-comment-reference: rh_3; mso-comment-date: 20201202T0301; mso-comment-done: yes;"><strong>Method and results</strong></a></span><span class="MsoCommentReference"><span style="font-size: 8.0pt; font-family: 'New York',serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: 'New York'; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US"><!--[if !supportAnnotations]--><a id="_anchor_3" class="msocomanchor" name="_msoanchor_3" href="file:///J:/THESIS/THESIS%20DOCUMENTS/JOURNAL%20SEMINAR/SUBMIT%20JENV/Julio%20Putra%20David_Development%20of%20Multiple%20Linear%20Regression%20Model%20to%20Predict%20COD%20Concentration%20based%20on%20West%20Tarum%20Canal%20Surface%20Water%20Quality%20Data.docx#_msocom_3"></a>[rh3]<!--[endif]--><span style="mso-special-character: comment;"> </span></span></span><strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US">:</span></strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA; mso-bidi-font-weight: bold;" lang="EN-US"> The correlation analysis is done in Microsoft Excel using the Pearson Product Moment Correlation Analysis. The water quality dataset is inputted to the R Studio and made the MLR model. The model is validated using t-Test. The result showed that all models in all intake points are not showing good prediction results, and the predictors showed no effect on the COD level. <a style="mso-comment-reference: rh_4; mso-comment-date: 20201202T0301; mso-comment-done: yes;"><strong>Conclusion</strong></a></span><span class="MsoCommentReference"><span style="font-size: 8.0pt; font-family: 'New York',serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: 'New York'; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US"><!--[if !supportAnnotations]--><a id="_anchor_4" class="msocomanchor" name="_msoanchor_4" href="file:///J:/THESIS/THESIS%20DOCUMENTS/JOURNAL%20SEMINAR/SUBMIT%20JENV/Julio%20Putra%20David_Development%20of%20Multiple%20Linear%20Regression%20Model%20to%20Predict%20COD%20Concentration%20based%20on%20West%20Tarum%20Canal%20Surface%20Water%20Quality%20Data.docx#_msocom_4"></a>[rh4]<!--[endif]--><span style="mso-special-character: comment;"> </span></span></span><strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA;" lang="EN-US">:</span></strong><span style="font-size: 10.0pt; font-family: 'Calibri Light',sans-serif; mso-fareast-font-family: 'Times New Roman'; mso-bidi-font-family: Arial; mso-ansi-language: EN-US; mso-fareast-language: AR-SA; mso-bidi-language: AR-SA; mso-bidi-font-weight: bold;" lang="EN-US"> The Multiple Linear Regression is not a fit tool for predicting the COD in the West Tarum Canal surface water. </span><div style="mso-element: comment-list;"><!--[if !supportAnnotations]--><hr class="msocomoff" align="left" size="1" width="33%" /><!--[endif]--><div style="mso-element: comment;"><!--[if !supportAnnotations]--><div id="_com_1" class="msocomtxt"><!--[endif]--><span style="mso-comment-author: rhakiki;"><!--[if !supportAnnotations]--></span><p class="MsoCommentText"> </p></div></div><div style="mso-element: comment;"><div id="_com_4" class="msocomtxt"><!--[if !supportAnnotations]--></div><!--[endif]--></div></div>