<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Adil Rahman on Medium]]></title>
        <description><![CDATA[Stories by Adil Rahman on Medium]]></description>
        <link>https://medium.com/@adilrahman_1337?source=rss-581de0337d22------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*dkDQPuN5cSqLWzzgWeN-Ng.jpeg</url>
            <title>Stories by Adil Rahman on Medium</title>
            <link>https://medium.com/@adilrahman_1337?source=rss-581de0337d22------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Sat, 21 Nov 2026 09:39:06 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@adilrahman_1337/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Statistics Concepts You Should Know As a Data Scientist]]></title>
            <link>https://medium.com/@adilrahman_1337/statistics-concepts-you-should-know-as-a-data-scientist-99bbe83b35a6?source=rss-581de0337d22------2</link>
            <guid isPermaLink="false">https://medium.com/p/99bbe83b35a6</guid>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[machine-learning]]></category>
            <category><![CDATA[artificial-intelligence]]></category>
            <category><![CDATA[statistics]]></category>
            <category><![CDATA[deep-learning]]></category>
            <dc:creator><![CDATA[Adil Rahman]]></dc:creator>
            <pubDate>Tue, 09 Aug 2022 15:20:34 GMT</pubDate>
            <atom:updated>2022-08-09T15:28:39.121Z</atom:updated>
            <content:encoded><![CDATA[<figure><img alt="statistics concepts for data science" src="https://cdn-images-1.medium.com/max/1000/0*xswv3jy46rDQ8C-o.png" /></figure><h3>Distribution</h3><p>A distribution is simply a collection of data and it describes how values are distributed for a field</p><p>In other words, the statistical distribution shows which values are common and uncommon in the collection</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/922/1*eGb77zuhispLkFd-q1iBOw.png" /><figcaption>Distribution of Age of nobal prize winners</figcaption></figure><p>In the given distribution we can see that most of the Nobel prize winners age are between 40–80 and it also means that getting a Nobel prize in less than 40 or greater than the 80s is very rare cases</p><h3>Population and sample</h3><h4>Population</h4><p>The population is the entire set of items. It can be a group of individuals, a set of items, the height of people on planet earth or All employee’s salaries in an office …etc.</p><h4>Sample</h4><p>A sample is a smaller and more manageable representation of a larger group in other words we can say that it’s a subset of a larger population that contains characteristics of that population.</p><blockquote>A sample is used in statistical testing or studies when the population size is too large.</blockquote><p>eg:- if we want to conduct a study on people’s heights on planet earth. In this case, collecting everyone’s height is too impractical so so we can take a sample from the entire population [assume the sample can represent the entire population] and then can study the sample data to know about the population</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*OXOK8x8F62naEuyR.png" /><figcaption>population and sample</figcaption></figure><h3><strong>Population parameter and Sample statistics</strong></h3><h4>Population Parameter</h4><p>A parameter is a number describing a whole population.</p><blockquote>eg:- population mean, population variance, population standard deviation</blockquote><h4>Sample statistics</h4><p>A statistic is a number describing a sample</p><p>A sample is also a part or a subset, of a population, So by using sample statistics we can provide an accurate estimate of a population parameter.</p><blockquote>e.g:- sample mean, sample variance, sample standard deviation</blockquote><figure><img alt="" src="https://cdn-images-1.medium.com/max/897/1*LqMIjzMDHhkmC0Ia1D_pVQ.png" /><figcaption>Notations</figcaption></figure><h3>Sampling error</h3><p>Sampling error is the absolute difference between a population parameter and a sample statistic.</p><blockquote>eg:- the difference between a population mean and a sample mean is sampling error.</blockquote><h3>Null hypothesis and Alternate hypothesis</h3><p>A <strong>null Hypothesis</strong> is a statement or <strong>assumption</strong> that states that there is <strong>no significant difference</strong> exist <strong>between the set of variables.</strong><br>It is often represented by H0</p><p>An <strong>alternative Hypothesis</strong> is a statement or <strong>assumption</strong> which is states that <strong>there is a significant difference </strong>between the <strong>set of variables. </strong>It is simply the <strong>opposite of the null hypothesis</strong>, often denoted by H1. So, It is what we actually seek to <strong>prove</strong> in an <strong>indirect way</strong></p><blockquote>Variables :- sample mean</blockquote><p>So, <strong>technically</strong> we can say that <strong>h0 </strong>and<strong> h1</strong> are <strong>mutually exclusive hypothesis</strong></p><blockquote>eg:- when we want to test the population mean is 100 [ Assume we <strong>don’t know anything about the population parameters</strong>, So we are testing the population mean by using the sample mean ]</blockquote><blockquote>Null hypothesis (h0):- population mean is 100 [i.e there is no difference both are the same]</blockquote><blockquote>Alternative hypothesis (h1):- population mean is not 100</blockquote><blockquote>The<strong> acceptance</strong> of the <strong>alternative hypothesis</strong> <strong>depends on</strong> the <strong>rejection of the null hypothesis</strong>. i.e. until and unless the null hypothesis is rejected, an alternative hypothesis cannot be accepted.</blockquote><h3>P-value</h3><p>In Simple Terms, We can say that <strong>P-Value</strong> is the <strong>probability</strong> of the <strong>Null hypothesis </strong>being <strong>TRUE</strong></p><p>P-value value can take any value between 0 and 1</p><p><strong>P value close to 1</strong> suggests that the <strong>null hypothesis</strong> we hold is more likely to be <strong>TRUE</strong> [ i.e. no difference between the groups ]. Whereas <strong>P value close to 0</strong> indicates that the <strong>null hypothesis</strong> is more likely to be <strong>FALSE</strong>, and indirectly it implies that the <strong>Alternative hypothesis</strong> is more likely to be <strong>TRUE</strong> [ i.e. the observed difference is unlikely to be due to chance ]</p><h3>Critical or rejection region</h3><p>The rejection region is represented by using a probability value that is represented using alpha, the value of alpha will vary for different tests<br>but mostly we consider 0.05 (5%) as the alpha value.</p><p>So if the p-value falls in the rejection region, it means that we have a statistically significant result to reject the null hypothesis. If the p-value falls outside the rejection region, it means your results aren’t enough to reject the null hypothesis</p><blockquote>eg:- Assume that you want to test if the covid pandemic is affected the country’s economy or not. In this test, there can be countries that are not affected by covid but most of the countries are affected. so we assume that there are 5% of the total countries that are not affected by covid pandemic so in order to accept our hypothesis its p-value must be greater than that 5% [ because the 5% error is expected ]</blockquote><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=99bbe83b35a6" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>