<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Predicted Trend line (ytrend) vs. Regression line for time series data in SAS Programming</title>
    <link>https://communities.sas.com/t5/SAS-Programming/Predicted-Trend-line-ytrend-vs-Regression-line-for-time-series/m-p/647668#M193860</link>
    <description>&lt;P&gt;Are these two lines the same? This is based on a segmented regression that I'm doing. I'm trying to use two separate methods to create the plots:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;1. Do separate regression lines by using sgplot and the "group" option for under regression.&lt;/P&gt;&lt;P&gt;2. Generating values for ytrend using proc autoreg, then plotting the trend line.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;The lines from 1 and 2 above seem to fit the points differently. Option 1 gives me a better fit. If I'm interested in connecting the two regression lines generated in option (1) above, how would I do that? (I'm trying to show a level change in my interrupted time series analysis.&lt;/P&gt;</description>
    <pubDate>Thu, 14 May 2020 03:36:28 GMT</pubDate>
    <dc:creator>ajames2020</dc:creator>
    <dc:date>2020-05-14T03:36:28Z</dc:date>
    <item>
      <title>Predicted Trend line (ytrend) vs. Regression line for time series data</title>
      <link>https://communities.sas.com/t5/SAS-Programming/Predicted-Trend-line-ytrend-vs-Regression-line-for-time-series/m-p/647668#M193860</link>
      <description>&lt;P&gt;Are these two lines the same? This is based on a segmented regression that I'm doing. I'm trying to use two separate methods to create the plots:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;1. Do separate regression lines by using sgplot and the "group" option for under regression.&lt;/P&gt;&lt;P&gt;2. Generating values for ytrend using proc autoreg, then plotting the trend line.&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;The lines from 1 and 2 above seem to fit the points differently. Option 1 gives me a better fit. If I'm interested in connecting the two regression lines generated in option (1) above, how would I do that? (I'm trying to show a level change in my interrupted time series analysis.&lt;/P&gt;</description>
      <pubDate>Thu, 14 May 2020 03:36:28 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Programming/Predicted-Trend-line-ytrend-vs-Regression-line-for-time-series/m-p/647668#M193860</guid>
      <dc:creator>ajames2020</dc:creator>
      <dc:date>2020-05-14T03:36:28Z</dc:date>
    </item>
    <item>
      <title>Re: Predicted Trend line (ytrend) vs. Regression line for time series data</title>
      <link>https://communities.sas.com/t5/SAS-Programming/Predicted-Trend-line-ytrend-vs-Regression-line-for-time-series/m-p/656809#M196954</link>
      <description>&lt;P&gt;A regression line is different from a trend line,Though both can be correlated some times. This is more evident in time series plots. For a time series the following are how things are looked at&lt;/P&gt;
&lt;P&gt;Y=intercept+seasonality(seasonal patterns)+Other causals&lt;/P&gt;
&lt;P&gt;as an example if you are measuring sales due to an advertising campaign Other causals represent your marketing actvity and Y is the sales response, then your intercept+seasonality must be able to capture trend.&lt;/P&gt;</description>
      <pubDate>Thu, 11 Jun 2020 02:34:28 GMT</pubDate>
      <guid>https://communities.sas.com/t5/SAS-Programming/Predicted-Trend-line-ytrend-vs-Regression-line-for-time-series/m-p/656809#M196954</guid>
      <dc:creator>smantha</dc:creator>
      <dc:date>2020-06-11T02:34:28Z</dc:date>
    </item>
  </channel>
</rss>

