<div dir="ltr"><font class="Apple-style-span" size="4">Dear Corpora Listers,</font><div><font class="Apple-style-span" size="4"><br></font></div><div><font class="Apple-style-span" size="4">I have run a number of POS tagging experiments in a 5 fold cross validation setting. Imagine the results of the 5 folds (in terms of accuracy) are these fictitious numbers:</font><div>
<font class="Apple-style-span" size="4"><br></font></div><div><font class="Apple-style-span" size="4">93.4% 93.7% 92.9% 93% 93.1%</font></div><div><font class="Apple-style-span" size="4"><br></font></div><div>
<font class="Apple-style-span" size="4">I then added feature x to the feature set, which gave the following results:</font></div><div><font class="Apple-style-span" size="4"><br></font></div><div><font class="Apple-style-span" size="4">93.7% 94% 92.7% 93.2% 93.4%</font></div>
<div><font class="Apple-style-span" size="4"><br></font></div><div><font class="Apple-style-span" size="4">My question is: Do I need to use any significance test to show that adding feature x really helps? if no, why not? and if yes, what are the appropriate tests in such a case?</font></div>
<div><br></div><div>Thank you in anticipation </div><div><br clear="all"><br>-- <br><div dir="ltr"><font size="1"><span style="color:rgb(255, 0, 0);background-color:rgb(255, 204, 51);font-family:comic sans ms,sans-serif">Emad Soliman Ali Mohamed </span><br style="color:rgb(255, 0, 0);background-color:rgb(255, 204, 51);font-family:comic sans ms,sans-serif">
<span style="color:rgb(255, 0, 0);background-color:rgb(255, 204, 51);font-family:comic sans ms,sans-serif">aka Emad Nawfal </span><span style="color:rgb(255, 0, 0);font-family:'comic sans ms', sans-serif">(<b>عماد نوفل</b>)</span><br style="color:rgb(255, 0, 0);background-color:rgb(255, 204, 51);font-family:comic sans ms,sans-serif">
</font></div><div dir="ltr"><font size="1"><span style="color:rgb(255, 0, 0);font-family:'comic sans ms', sans-serif">Suez Canal University, Egypt</span></font></div>
</div></div></div>