<?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 Garima Anand on Medium]]></title>
        <description><![CDATA[Stories by Garima Anand on Medium]]></description>
        <link>https://medium.com/@garima-anand?source=rss-6f8e8d5ad9------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/2*Xme-lFo5jBmfQpqAkV1TBw.jpeg</url>
            <title>Stories by Garima Anand on Medium</title>
            <link>https://medium.com/@garima-anand?source=rss-6f8e8d5ad9------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 16 Nov 2026 22:22:49 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@garima-anand/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[GENDER DISPARITIES IN HIV INFECTIONS AMONG ADOLOSCENTS IN SUB-SAHARAN AFRICA]]></title>
            <link>https://garima-anand.medium.com/gender-disparities-in-hiv-infections-among-adoloscents-in-sub-saharan-africa-7893c39b1f17?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/7893c39b1f17</guid>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[charts]]></category>
            <category><![CDATA[gender]]></category>
            <category><![CDATA[storytelling]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Fri, 22 Jan 2021 01:41:32 GMT</pubDate>
            <atom:updated>2021-01-22T01:41:32.652Z</atom:updated>
            <content:encoded><![CDATA[<p>As we step into the new year, full of hope and optimism, believing in the fact that things will change for the better, let us tackle a new dataset that looks at HIV infections among adolescents in the 10–19year age group in Sub-Saharan Africa from 1990–2019.</p><p>A multitude of inequities drives the HIV epidemic, but gender inequality is a major contributor to the continued spread of HIV globally.</p><p>Despite significant global progress in the work to reduce HIV infections and HIV/AIDS related deaths, women and girls continue to be disproportionately vulnerable to, and affected by HIV.</p><p>Early and forced marriage, gender-based violence, unequal access to information, including sexual health knowledge, and a lack of negotiating power and economic autonomy are among the factors that place women and adolescent girls at increased risk of HIV infection.</p><p>Sub-Saharan Africa is home to 88 per cent of the world’s children under 15 years of age living with HIV, and mothers2mothers, an NGO is actively working in 10 countries. This dataset tells the story of the extreme need and profound gender inequality that affects adolescent women and girls in these countries.</p><p>In <strong>2019,</strong> around <strong>130,000</strong> adolescent girls between the ages of 10 and 19 were newly infected with HIV compared to 44,000 boys of the same age. Girls therefore accounted for 75 per cent of new HIV infections among adolescents, globally.</p><p>These new infections disproportionately affect girls in countries where the HIV epidemic is driven by transmission during heterosexual intercourse, or in places where transactional sex is common. This is the case in Eastern and Southern Africa, and in West and Central Africa (the geographies of focus in this dataset) where girls account for <strong>83 per cent and 78 per cent</strong>, respectively, of new HIV infections among adolescents in the <strong>10–19</strong> age group.</p><p>However, there has been a fall in HIV incidence in many countries — a symptom of adolescents adopting safer sex practices — but this is not the case in sub-Saharan Africa. There, only <strong>38% of</strong> <strong>girls</strong> and <strong>52% of boys</strong> aged <strong>15–19</strong>, who are sexually active with a non-regular partner, used a condom. Further to this, fewer than a third of adolescent girls and boys aged 15–19 have comprehensive knowledge of HIV. The negative impact of this high rate of adolescent HIV infection is long-term and even generational. With such high rates of transmission among adolescent girls, the prevention of imminent mother-to-child HIV transmission, becomes much harder.</p><p>This dataset is a subset of UNICEF’s ‘Key HIV epidemiology indicators for children and adolescents aged 10–19, 1990–2019.’ This UNICEF data is sourced from <strong>UNAIDS 2020</strong> estimates, which provide ‘modeled estimates using the best available epidemiological and programmatic data to track the HIV epidemic’. Modeled estimates are used because counting the true numbers would require regularly testing entire populations for HIV, and investigating all deaths, which is logistically impossible and ethically problematic.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/624/1*DqSWi4ukib6kDCnrN0PwDA.png" /></figure><p><strong>What worked for the visualization:</strong></p><ol><li>All <strong>key metrics are included</strong> namely: HIV related deaths per 100,000 people, new infections and incidence rates among adolescents.</li><li>Each metric has a <strong>chart explaining the trends</strong>.</li><li>The titles are <strong>precise</strong> and communicate the idea well.</li></ol><p><strong>What did not work for the visualization:</strong></p><ol><li><strong>Color</strong> has been used separately for each metric. They do not work well together and seem to confuse rather than clearly explain the insights gathered.</li><li>An <strong>explanation behind axis titles is important</strong>. Since the audience is the general public without much knowledge of statistics, title definitions help in putting the point across.</li><li>The story that is presented <strong>does not seem to flow well</strong>.</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/624/1*xUaXJQGs1OwYVS_YBQp9OA.png" /></figure><p><strong>My Interpretation</strong>:</p><ol><li>I decided to include 2 separate views: <strong>1990–2019 chart trend</strong> and <strong>the 2019 country breakdown.</strong></li><li><strong>Metrics, Views and Countries</strong> are represented as parameters giving the user the ability to interact with the dashboard and see insights for themselves.</li><li>I used <strong>a dot plot</strong> to show trends in metrics across time (1990–2019) between male and female adolescents highlighting disparities.</li><li>I used <strong>a scatter plot</strong> to show how different countries performed across the metrics in 2019.</li><li>What is interesting to note is that <strong>1995–97</strong> comes across as years with peak rates of <strong>annual HIV infections</strong> and <strong>new HIV infections per 1000 of the population</strong>.</li><li>The <strong>no of AIDS related deaths per 100k of the population</strong> and <strong>annual AIDS related deaths</strong> have <strong>declined</strong> over the years implying <strong>better intervention</strong> and <strong>precautions</strong> among the infected.</li><li><strong>Females universally account for higher infections</strong> as compared to <strong>males</strong> across all relevant metrics highlighting the urgency of care and medical attention needed.</li><li><strong>South Africa</strong> beats every other country in terms of <strong>no of people living with HIV, annual AIDS related deaths, annual HIV infections.</strong></li></ol><p>Although relevant work is being done in the affected regions, a lot more needs to be taken care of before we even start talking about gender equality.</p><p>Let me know what you think about it. Comments are most welcome.</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/GenderDisparityInHIVInfections/revisedversion"><em>Click here to view my visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=7893c39b1f17" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Project Analysis: Week 4-JW Technology]]></title>
            <link>https://garima-anand.medium.com/project-analysis-week-4-jw-technology-e4eb476ad138?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/e4eb476ad138</guid>
            <category><![CDATA[analytics]]></category>
            <category><![CDATA[charts]]></category>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[dashboard]]></category>
            <category><![CDATA[hr-talent-management]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Thu, 05 Nov 2020 03:10:47 GMT</pubDate>
            <atom:updated>2020-11-05T03:10:47.175Z</atom:updated>
            <content:encoded><![CDATA[<p>This week’s visualization focused on fine tuning the strategies behind dashboard design by focusing on HR data.</p><p>JW Technology is interested in understanding employee turnover to better plan the organization’s long term growth. By delving into the when’s, why’s and who’s, the organization intends to spot trends and do a root cause analysis. This will help the company understand which groups need to begin actively recruiting for additional talent.</p><p>To do this, I created 2 vizzes per category(when, why, who). Let’s focus on each.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Pt1uuRp3QTafKU4dwBE7ZQ.png" /></figure><p><strong>WHEN</strong></p><p>For <strong>discrete date part of ‘quarters’</strong> , I created a <strong>line chart</strong> to understand when employees are terming the most.</p><p>To understand the <strong>length of tenure with the company</strong>, I created a <strong>bar chart </strong>focusing on turnover buckets, using the ‘Case statement’ and ‘IF-Then’ analysis. I also used color minimistically to highlight the period when maximum employees were terming.</p><p><strong>WHO</strong></p><p>I used a <strong>bar chart </strong>to show<strong> % of turnovers per department.</strong></p><p>For understanding which positions, termed the most, I used a <strong>bar chart </strong>focusing on<strong> % of terminations per position</strong>.</p><p><strong>WHY</strong></p><p>For <strong>categorical data</strong>, more specifically having only 2 categories, I used a <strong>pie chart </strong>to focus on the reason behind the termination.</p><p>A pie chart expresses a part-to-whole relationship in your data.Each slice represents one component and all slices added together equal the whole.</p><p>Pie charts should primarily be used when:</p><ol><li>If you want your audience to have a <strong>general sense of the part-to-whole relationship in your data</strong> and comparing the precise sizes of the slices is less important.</li><li>To convey that one segment of the total is relatively <strong>small</strong> or <strong>large.</strong></li></ol><p>In this case, there is a clear distinction between the % contribution of 2 categories. If the % contribution of the categories would have hovered around 50–50, the pie chart would not have been the ideal chart to use.</p><p>To understand<strong> reasons behind turnovers</strong>, I created a <strong>pictogram</strong> where each dot represents an employee. The blue color focuses on those employees who got terminated voluntarily. The color legend, helps in understanding the usage of blue here.</p><p><strong>ANALYSIS</strong></p><ol><li>Majority (36) of the employees were with the company for a year. Most employees churned in Q2 and Q3 of the fiscal years in consideration. The churn % was 10 times higher for the production department than the<br>software engineering and admin departments.</li><li>The principal data architect and enterprise architect saw the most churns at 100%. This implies that those who get hired under these positions also leave. This position goes by the hire and fire policy. There are no<br>such employees who can be classified as being with the company for a long period of time. These 2 positions churn at 1.5 times the second most churned position ie of an administrative assistant.</li><li>85% of the employees leave the company voluntarily. Of those who leave the company voluntarily, 23% of the employees cite ‘another position’ as the reason .16% of the employees who leave the company voluntarily<br>cite being ’unhappy’ at the company. Of those who left the company, involuntarily 40% of the employees cite ’attendance’ as their reason for churn. Clearly, the company needs to look into its policies of ‘hire and fire’ and employee wellness if it wants to reduce attrition rate.</li></ol><p>What do you think of the analysis? Did you find it useful?</p><p>Please like or comment on the post if there is something that you found interesting or want to draw my attention towards.</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/EmployeeTurnoveratJWTechnology-HRAnalytics/Dashboard1"><em>Click here to view my visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=e4eb476ad138" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Project Analysis : Week 3, Millenials and Data(MAD)]]></title>
            <link>https://garima-anand.medium.com/project-analysis-week-3-millenials-and-data-mad-aaed9c3e71d1?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/aaed9c3e71d1</guid>
            <category><![CDATA[storytelling]]></category>
            <category><![CDATA[trainin]]></category>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[analyst]]></category>
            <category><![CDATA[dashboard]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Wed, 21 Oct 2020 23:55:32 GMT</pubDate>
            <atom:updated>2020-10-21T23:55:32.661Z</atom:updated>
            <content:encoded><![CDATA[<h3>Project Analysis : Week 3, Millenials and Data(MAD)</h3><p>As part of the 3rd week at MAD(Millenials and Data) bootcamp spearheaded by Chantilly Jaggernauth, the project focused on implementing nuances of dashboard design while enhancing my understanding of the numbers behind the viz.</p><p>Without further adieu let’s dive right in.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*_hoCf9PPXtbOlGVBo6g6DA.png" /></figure><p>Webalytics is marketing company who specializes in analyzing web traffic data for clients. Representing KPI’s for a marketing company in a way that facilitates understanding among clients was my main task.</p><p>So how did I go about doing it.</p><p>Since this is a marketing company, the key metrics for analyzing web data were important for analysis. Vists per day, visits per region, visits per city, visits per source and visits per contet type was what I focused on.</p><p>Then, I decided to group them. Visits per city and region could be grouped together under ‘location’. Visits per source and content type could be grouped under ‘types of web traffic’. Visits per day solely represented a KPI that focused on ‘time’.</p><p>An overall picture of web traffic data was reprsented using BANS. According to Data School, UK, BANS(Big Ass Numbers) are important figures that give a glimpse to the data reprsented in the dashboard.</p><p>No of pageviews, no of downloads and total no of visits are classified under BANS. The only way to maximise impact of these numbers is to make them seriously big and make the text accompnying them small.</p><p>To maximize visual impact, I decided to group the bar charts together and give more space to the map as this allowed viewers to zoom in and out of the map with ease without compromising on the data quality.</p><p>Now that we have our layout decided, lets get down to understanding chart types.</p><p>When it comes to analyzing categorical data, bar charts are the ideal way of reprsenting them.Visits per region, per source and content type are commonly defined by levels of categories. Each categorical value claims one bar, and the length of each bar corresponds to the bar’s value. Bars are plotted on a common baseline to allow for easy comparison of values.</p><p>An area chart is a good way to demonstrate trends over time to the viewer, for example showing visits per day over a month. This chart is based on the line chart. The filled area can give a greater sense of the trends in a particular dataset.</p><p><strong>Symbol maps</strong> show symbols sized and colored according to the data. They work great for data for specific locations (like cities). In this case , visits per city turned out to be ideal for symbol maps. I also incorporated the basic attributes of size and color to the symbols. The bigger the size of the circle, the larger the no of visits to the city and the color red signified cities that received maximum web traffic .</p><p>Now that we have our chart types sorted, let’s get down to analysis:</p><ol><li>Webalytics received more than 1 million visits between August and September 2020 . 43% of the visits were from Europe and 22 % of the visits were from Asia. Together these 2 continents accounted for 65% of the web traffic the portal received. London accounted for the<br>maximum no of visits (45,216) from any city across the world.</li><li>Of the visits that accounted for maximum web traffic, 39% come from direct sources. This means that the user arrived directly on to the site and not through any third-party sites.Webalytics must be doing something right either through marketing or anything else to be receiving such heavy traffic. 55% of the visits were related to user content implying that<br>webalytics must be generating user content deemed necessary or useful.</li><li>18 September 2020, turns out to be the day when there was heavy traffic to the site. More than 100,000 visitors landed on the site that day. Its lowest footfall was on 8 September, 2020 with only 13,695 visitors. This was almost 8 times less than its maximum footfall.</li></ol><p>How did you like that? This brings me to the end of the analysis for this week’s project. Please feel free to comment or like the page if you found this useful.</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/webalytics_MarketingAnalysis/Dashboard1"><em>Click here to view my visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=aaed9c3e71d1" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Gender Pay Gap Talk at State-Funded Schools in England]]></title>
            <link>https://garima-anand.medium.com/the-gender-pay-gap-talk-at-state-funded-schools-in-england-fe8218ab829d?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/fe8218ab829d</guid>
            <category><![CDATA[education]]></category>
            <category><![CDATA[data-analysis]]></category>
            <category><![CDATA[reporting]]></category>
            <category><![CDATA[visualization]]></category>
            <category><![CDATA[gender-pay-gap]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Fri, 18 Sep 2020 20:55:07 GMT</pubDate>
            <atom:updated>2020-09-19T00:18:58.484Z</atom:updated>
            <content:encoded><![CDATA[<p>This week, I am looking at teacher pay across state-funded schools in England. The data for this week’s viz is taken from schools and local authorities in November 2019 as part of the school workforce census. The census collects detailed information on teachers, teaching assistants and other classroom and non-classroom-based school support staff.</p><p>Independent schools, non-maintained special schools, sixth form colleges and further education establishments are not in scope.</p><p>Before we get into the analysis bit, let us understand the data a bit more.</p><p>The <strong>time</strong> for the data consists of years 2010–11 to 2019–20.</p><p>Both <strong>male and female</strong> teachers are taken into consideration.</p><p>The teachers have been classified under the following categories: <strong>classroom teachers, head teachers, other leadership teachers and total.</strong></p><p>We are looking at <strong>state funded schools in the UK in England</strong>.</p><p><strong>Average mean</strong> consists of the mean pay of teacher salaries.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*8MLwz3LA30l0tQtP.png" /></figure><p><strong>What worked for the visualization:</strong></p><ol><li>A simple bar chart showing the mean pay of teachers by type for the year 2019 when the census was undertaken, arranged in ascending order is one of the best ways to visualize data that consists of one measure and one dimension. <strong>This is great for comparison of metric values specifically, mean pay across sub-groups of the data.</strong></li><li>The <strong>title is clear</strong> and provides context to the visualization.</li></ol><p><strong>What did not work for the visualization:</strong></p><ol><li>The use of <strong>varied colors</strong> to show different bars that represent categories is redundant. When people look at a data display and see visual differences, they try to determine the meaning to those differences. Here the title of the bar chart mentions clearly that we are looking at mean pay of teacher salaries broken down by type for the year 2019. Again, when trying to use color, ask yourself these questions: what purpose will this color serve? And will it serve the purpose effectively?</li><li>The axis consists of<strong> unlabeled numbers</strong>.</li><li><strong>The use of gridlines</strong> in the chart is <strong>unnecessary</strong> and adds to visual clutter.</li><li><strong>The tool-tip </strong>highlights information that <strong>does not change dynamically</strong> as you hover over various bars. This could have been avoided by <strong>using text markers</strong> at the end of every bar to show mean salary of teachers.</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*nf_vhWW9rRM4tNpdHkiVbQ.png" /></figure><p><strong>My interpretation:</strong></p><ol><li>I wanted to understand how the mean pay of teachers broken down by type and gender compared over the periods 2010–11 to 2019–20.</li><li>For this purpose, I used the metric, <strong>difference in pay</strong>, in <strong>absolute and % terms</strong> to highlight the variation in mean pay of female and male teacher salaries over the years.</li><li><strong>The variation in mean pay for male and female teachers exists</strong>. The highlight point here is that <strong>the variation is higher for female teachers than male teachers</strong>. This points to the fact that male teachers have had consistent pay over the years while female teachers have succumbed to highs and lows of salaries over the years. The only exception here is that of head teachers. Even though head teachers (both genders) have a higher mean pay than other categories of teachers, the variation is 1.16 times higher for male head-teachers than female head teachers over the period 2010–2020.</li><li>Also, what is universally noted is that <strong>male teachers across all categories have a higher mean pay than female teachers</strong>.</li><li><strong>Female classroom teachers</strong> have the <strong>lowest mean salary of 36,985.4 pounds</strong>. This was<strong> 0.92 </strong>times lower than their male counter parts. Also, this is to be considered the <strong>highest pay gap</strong> between male and female teachers at base level.</li></ol><p>The <strong>Equal Pay</strong> Act 1970 was an Act of the Parliament of the <strong>United Kingdom</strong> that prohibited any less favorable treatment between men and <strong>women</strong> in terms of <strong>pay</strong> and conditions of employment.</p><p>Yet in 2019 the gender pay gap persists <strong>— </strong><a href="https://www.ons.gov.uk/employmentandlabourmarket/peopleinwork/earningsandworkinghours/bulletins/annualsurveyofhoursandearnings/2017provisionaland2016revisedresults#gender-pay-differences"><strong>standing at 4.1%</strong></a> for UK full-time and part-time employees. Based on the data analyzed in this week’s viz, what is found is <strong>that women are paid on average 7% less than men</strong>. The Institute for Fiscal Studies reports that the gap for women educated to A-level and degree level is approximately the same as it was 20 years ago.</p><p>The data just validated this. What are your thoughts on this?</p><h4><a href="https://public.tableau.com/profile/garima1910#!/vizhome/VariationsinMeanSalariesofState-FundedSchoolTeachersintheUK/Dashboard1">Click here to view my visualization</a></h4><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=fe8218ab829d" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Why Batting Averages Don’t Make Sense in Cricket.]]></title>
            <link>https://garima-anand.medium.com/why-batting-averages-dont-make-sense-in-cricket-b5c77279bffe?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/b5c77279bffe</guid>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[descriptive-statistics]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data-analytics]]></category>
            <category><![CDATA[cricket]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Sat, 05 Sep 2020 03:06:13 GMT</pubDate>
            <atom:updated>2020-09-05T03:06:13.152Z</atom:updated>
            <content:encoded><![CDATA[<p>Dear Cricket,</p><p>You are all about a ball and bat. It is a hit and run case. There are 11 odd people from each team that chase a ball-very similar to chasing a child who is on a sugar rush. Pretty exhausting right! However, I never knew I would enjoy delving into the statistics of a game that sounded crazy to me.</p><p>This week’s viz focuses on <strong>batting averages against left arm pacers of key Indian batsman since world cup 2015</strong>. So, without any further ado let us understand what these terms really mean.</p><p><strong>Batting average</strong> — The<strong> traditional metric</strong> to determine a batsman’s performance over several matches is the batting average. It is simply defined as the <strong>number of runs scored for every time he is dismissed.</strong> It is calculated as the number of runs scored by a batsman in, a given time, or a series or over a career divided by the number of times he is dismissed over the same time.</p><p><strong>Left arm pacers</strong>- If there is a bowler who can make the batsman change tack before a ball is bowled, it must be a left-arm fast bowler bowling over the stumps. When a right-hand batsman is facing a left-armer bowling over the wicket, he needs to open his stance a bit, for otherwise the point the ball is delivered from creates a blind spot for the batsman.</p><p>What is with these statistics? Why are we interested in analyzing them?</p><p>For starters, we are analyzing these statistics to see how Indian cricketers fare against left arm bowlers. And — a bit more on the nuances.</p><p>Firstly, let us understand<strong> why batting averages are not that great in terms of conveying information.</strong> Any measure of central tendency (like mean, median, mode) effectively tries to summarize all the information using one number and irrespective of how this number turns out, some information is lost. It is no different with a batting average.</p><p>Instead of using the batting average, what about using the metric, <strong>median runs scored per innings?</strong> This is basically (batting average*number of dismissals)/ number of dismissals.</p><p>To understand this further and see the applications of this metric, let us first dive into the original visualization and see what stood out and what did not stand out in the viz.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*ru_Iz_T_l0_MFLnn" /></figure><p><strong>What worked for the visualization:</strong></p><p>1. The title of the viz is clear and precise conveying important information.</p><p><strong>What did not work for the visualization:</strong></p><ol><li>The images of the cricketers are not particularly useful and does not convey anything useful in the viz.</li><li>Some context on what batting average and left arm pacing means would be helpful.</li><li>Bars and color legends would make the chart easier to understand.</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*ApZDEWYzQ8xh2CfsGh0KQQ.png" /></figure><p><strong>My interpretation:</strong></p><ol><li>From our previous discussion, we realized that batting averages is not a useful measure to convey information. <strong>Kohli has the highest batting average amongst those listed but that could also be possible by making some big scores in some matches.</strong> He stands as an <strong>outlier</strong> in the chart.</li><li>A better measure of central tendency is median number of runs scored per innings that does not get affected by big scores. Based on this metric, we find that <strong>Dhawan has the highest score of 12</strong>. This implies, that half the times Dhawan goes to bat, he makes at least 12 runs. <strong>Kohli, on the other hand scores poorly on this measure</strong>. This implies that <strong>Dhawan is the more consistent player.</strong> A <strong>higher ratio</strong> in terms of median runs scored may not necessarily imply that Dhawan is a better batsman, but he is surely more <strong>consistent.</strong></li><li><strong>But all this still does not unequivocally state that things are better for Dhawan than Kohli despite a low batting average and high median score for Dhawan. </strong>The<strong> role of the team </strong>features in perspective as well. For an <strong>opening batsman like Kohli</strong>, <strong>time </strong>is usually <strong>not much of a constraint</strong> and the ability to play a<strong> long innings</strong> has a <strong>great impact</strong> on the <strong>team’s score</strong>. So even if Kohli makes 5 runs or less half the time, the fact that he can hit a big score will weigh significantly in his favor. For someone like <strong>Dhawan</strong>, who is lower down in the batting order and has <strong>little opportunity to play a long innings</strong>, a <strong>consistent 12 </strong>might be <strong>valued much higher</strong>. Or the speed might trump the number of runs he made.</li></ol><p>Hence, the batting average might be a great metric for an opening batsman but might result in loss of information for a batsman placed somewhere else in the batting line-up.</p><p>Now, that was quite some cricket information! Do you agree with the above?</p><p>Sincerely,</p><p>New Cricket Aficionado</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=b5c77279bffe" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[DO WOMEN IN LOWER-MIDDLE-INCOME-COUNTRIES(LMICs) HAVE THE RESOURCES TO PLAN FOR THEIR FUTURE?]]></title>
            <link>https://garima-anand.medium.com/do-women-in-lower-middle-income-countries-lmics-have-the-resources-to-plan-for-their-future-3b0680170386?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/3b0680170386</guid>
            <category><![CDATA[social-good]]></category>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[reproductive-health]]></category>
            <category><![CDATA[visualization]]></category>
            <category><![CDATA[gender-identity]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Sat, 29 Aug 2020 01:05:16 GMT</pubDate>
            <atom:updated>2020-08-29T01:05:16.948Z</atom:updated>
            <content:encoded><![CDATA[<p>The expansion and adoption of <strong>sexual and reproductive health rights</strong> is a critical priority within the 2030 SDG Agenda. SDG 5 target 5.6 seeks to, “ensure universal access to sexual and reproductive health and reproductive rights.” Contained within target 5.6 are a number of indicators, including: “the proportion of women aged 15–49 years who make their own informed decisions regarding sexual relations, contraceptive use and reproductive health care,” and the “number of countries with laws and regulations that guarantee full and equal access to women and men aged 15 years and older to sexual and reproductive health care, information, and education.” In <strong>LMICs </strong>there are currently as many as <strong>923 million women</strong> of reproductive age who want to avoid pregnancy</p><p><strong>Adding It Up (AIU)</strong> is an ongoing Guttmacher Institute project in which researchers estimate the need for and the use, costs and impacts of various sexual and reproductive health services in developing countries.</p><p>The Adding It Up approach starts with estimating the need, current use (or coverage), and the unmet need for care for components of sexual and reproductive health care: Need — Coverage =<strong>Unmet Need</strong>.</p><p>Unmet need is highest among the <strong>most vulnerable</strong> in society: adolescents, the poor, those living in rural areas and urban slums. It is disproportionately high among adolescents, with <strong>43%</strong> of them being <strong>15–19-year-old</strong>. Once pregnant, these adolescent girls often find that their journeys through education systems come to end. This makes them less likely to be able to work, placing them in a position of economic and social dependence, and increasing the likelihood that they will be victims of gender-based violence and sexual abuse. Unmet contraceptive need has a lasting impact on the health and wellbeing of these women and girls for the remainder of their lives. Beyond that, there is also a long-lasting generational impact.</p><p>Unmet needs for services are greatest in the poorest countries. For example, only <strong>59%</strong> of women in low-income countries deliver their babies in a health facility, compared with <strong>97%</strong> in <strong>upper-middle–income countries.</strong></p><p>In this analysis, women aged <strong>15–49</strong> in <strong>each country</strong> were classified according to their risk for unintended pregnancy and contraceptive method use. These subgroups were summed to show <strong>women not wanting</strong> and <strong>wanting to avoid a pregnancy</strong>.</p><p>All currently <strong>married women</strong> are assumed to be <strong>sexually active</strong>. Because of the stigma attached to nonmarital sex, the level of sexual activity — and therefore risk for unintended pregnancy — is likely to be underestimated among unmarried women, especially in Asian and Arab countries, where stigma is especially strong. Almost all surveys in Sub-Saharan Africa and Latin America include unmarried women, although their sexual activity is likely to be somewhat underreported. However, unmarried women are largely excluded from surveys in Asia and Northern Africa, and, where they are included, underreporting of their sexual activity is likely to be extensive.</p><p>Let us look at what this means:</p><p><strong>UNMET NEED FOR MODERN CONTRACEPTION</strong></p><p><strong>Women with unmet need for modern contraception are those who want to avoid a pregnancy but are currently not using a method or are using a traditional method</strong>. Women using traditional methods face higher risks of unintended pregnancy than those using modern methods and hence have been included in this category.</p><p><strong>CONTRACEPTIVE NEED AND USE DISTRIBUTION</strong></p><p><strong>Not wanting to avoid a pregnancy and not in need of contraception</strong> — Unmarried women who are not sexually active (in the last three months), women who are infecund, those who want to have a child in the next two years, and those who are currently experiencing a pregnancy identify as having been intended or are experiencing postpartum amenorrhea from a pregnancy they identify as having been intended.</p><p><strong>Wanting to avoid a pregnancy and in need of modern contraception</strong> — Women using a contraceptive method and non-users wanting to avoid a pregnancy, including women not wanting a child in the next two years (spacing) and those wanting no (more) children (limiters).</p><p><strong>Using a modern contraceptive method (Met need)</strong> — Women relying on female or male sterilization (limiters only), IUD, implant, injectable, oral contraceptives, contraceptive patch or ring, emergency contraceptive pills, male or female condom, LAM, fertility-awareness-based method or other supply methods.</p><p><strong>Using a traditional contraceptive method (Unmet need) — </strong>Women relying on periodic abstinence, withdrawal, or other non-supply methods.</p><p><strong>Non-users in need (Unmet need) — </strong>Women using no contraceptive method wanting to avoid childbearing for at least two years, pregnant/in postpartum amenorrhea from an unintended pregnancy or using an ineffective method (herbs, charms, folk methods or vaginal douching).<strong>This is our target audience.</strong></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*DxjBF1hl7xYjVK67.png" /></figure><p><strong>What worked for the visualization</strong>:</p><p>1. The viz gives a <strong>big picture</strong> of the data represented.</p><p>2. The data is broken down by <strong>region</strong> and is <strong>color-coded</strong>. This results in <strong>grouping of data</strong> in categories.</p><p>3. The <strong>data source</strong> is clearly <strong>state</strong>d.</p><p>4. <strong>The bar chart</strong> highlights what <strong>‘unmet needs’ consists</strong> of and this helps in focusing on the target question of where women’s needs are not met.</p><p><strong>What did not work for the visualization:</strong></p><p>1. The dataset includes only <strong>148 of 195 countries</strong>. The title of the viz suggests the use of <strong>contraceptives</strong> <strong>‘world-wide’</strong> which is <strong>misleading</strong>.</p><p>2. A <strong>table </strong>is a great way to <strong>store information</strong>. But is it one of the best ways <strong>to visualize data</strong> here?</p><p>3. Is there a <strong>story behind the numbers</strong>? If so, what is it? The original viz gives a lot of information but does not bring about a ‘<strong>a call to action’</strong>. What is the audience to gain out of this?</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*7ieueL6XdCO6JVM-kaG-gQ.png" /></figure><p><strong>My interpretation:</strong></p><p>1. I wanted to focus on the <strong>top 25 countries</strong> with the <strong>highest percentage</strong> of <strong>unmet needs</strong> <strong>among women wanting to avoid pregnancy</strong>.</p><p>2. I decided to use a <strong>horizontal dot plot</strong> to visualize <strong>categorical data (countries)</strong> using variables of <strong>position and color</strong>. The dot plot helps in <strong>identifying patterns</strong> much quicker than looking at the raw data of the table. It also has <strong>high scalability</strong> which means it can display plenty of data in a single chart. It is also <strong>space-efficient</strong> and a good way to show individual values across the entire distribution.</p><p>3. From the above visualization we see that <strong>Trinidad &amp;Tobago</strong> in the <strong>Caribbean</strong> has the <strong>highest % of women</strong> with <strong>unmet needs</strong>. On the other hand, <strong>Sao Tome and Principe</strong> in <strong>Central Africa</strong> is the only country in the list where <strong>32%</strong> of the women have <strong>met their</strong> <strong>needs</strong> in terms of access to modern contraceptives.</p><p>4. I also created a dot plot that analyzed the <strong>gap</strong> between <strong>women having met and unmet needs country-wise</strong>. The <strong>Democratic Republic of Congo</strong> has the <strong>biggest gap</strong> between those having met and unmet needs. <strong>Majority of the women </strong>do <strong>not</strong> use <strong>any method</strong> implying lack of education and age- old rituals pre -dominating their area of residence.</p><p>5. <strong>Trinidad &amp; Tobago</strong> in the Caribbean is the only country to have nearly <strong>32%</strong> of the women <strong>not using any contraceptive method</strong>.</p><p>6. Out of all the countries listed here, <strong>18</strong> of them are from <strong>Africa</strong>,<strong>1</strong> from <strong>Latin America</strong>,<strong>2</strong> from <strong>Asia</strong>,<strong>1</strong> from <strong>Oceania</strong> and <strong>1</strong> from the <strong>Middle East</strong>.</p><p>Most women in lower middle-income countries (LMICs) do not get the kind of support that is needed to help them plan their future. What do you think?</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/Contraceptiveneedsofwomenaroundtheworld/Dashboard1"><em>Click Here To View My Visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3b0680170386" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[The Rise of Tech Companies in Scotland]]></title>
            <link>https://garima-anand.medium.com/the-rise-of-tech-companies-in-scotland-28d2f88a3206?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/28d2f88a3206</guid>
            <category><![CDATA[data]]></category>
            <category><![CDATA[visualization]]></category>
            <category><![CDATA[analytics]]></category>
            <category><![CDATA[tableau]]></category>
            <category><![CDATA[consulting]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Fri, 21 Aug 2020 03:54:36 GMT</pubDate>
            <atom:updated>2020-08-21T03:54:36.288Z</atom:updated>
            <content:encoded><![CDATA[<p>Scotland’s digital technology sector is expected to grow twice as fast as the Scottish economy overall in the years to 2024, according to a new report by Skills Development Scotland and the Scottish government backed Digital Technologies Skills Group. The tech sector accounted for 5% of the Scottish economy’s business base. The sector now employs 2% of the national workforce.</p><p>It is estimated that Scotland has up to 12,800 tech job opportunities annually- a 16% increase over previous year demand. The report also found that more than 60,000 people were employed in tech businesses across Scotland.</p><p>With a simple dataset on the prevalence of tech companies in Scotland, this week’s makeover is easy as butter on toast.</p><p>The original viz is a map of Scotland showcasing where tech companies are located using size and color for visualizing purposes. The bigger the size of the circle, the greater the concentration of companies in that location. Color is used to differentiate between different locations.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/595/0*c2_8LDuOrDXFWrut.jpg" /></figure><p>What worked for the visualization?</p><p>1. The location and number of companies in each location are explicitly mentioned enhancing understanding of the viz.</p><p>2. The data source is clearly mentioned.</p><p>3. The title of the viz is self-explanatory.</p><p>What did not work for the visualization:</p><p>1. The use of so many colors to highlight each location is unnecessary. It distracts the user.</p><p>2. The use of circles, more specifically size of the circle to display concentration of companies is poorly used. For e.g.: Aberdeenshire and Glasgow seem to have the same number of companies at first sight. The numbers on the other hand say that Glasgow has 2.1 times the number of companies in Aberdeenshire.</p><p>3. The viz looks very cluttered.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*8T_sTAsNi3EJej_sh9L1zw.png" /></figure><p>My interpretation:</p><p>1. The use of the map of Scotland with the added feature of explaining where there is a greater concentration of companies using a diverging color palette made sense to me. It enhanced the visual appeal of the numbers and created more structure in the infographic through the presence of a legend that explained the connection between color and numbers.</p><p>2. A synchronous color-coded bar chart representing categorical data with the height of each column showing the number of companies located in each region added more depth to the analysis.</p><p>3. Of the 1843 companies, 1328 companies are located in Midlothian, Glasgow and Aberdeenshire. These three counties accounted for 71% of all tech companies in Scotland.</p><p>4. 32.4%, 26.7% and 12.2% of all tech companies in Scotland are found in Midlothian, Glasgow and Aberdeenshire, respectively.</p><p>5. Borders ranks the lowest with only 1.5% of digital companies located in its region.</p><p>What do you think of this digital surge in a land known for its Scottish whisky and bagpipes? How would you visualize it?</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/PrevalenceofDigitalCompaniesinScotland/Dashboard1"><em>Click here to view my visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=28d2f88a3206" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[REMOTE WORKING IS THE NEW NORMAL]]></title>
            <link>https://garima-anand.medium.com/remote-working-is-the-new-normal-774ea212e1f9?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/774ea212e1f9</guid>
            <category><![CDATA[remote-work]]></category>
            <category><![CDATA[pandemic]]></category>
            <category><![CDATA[dataviz]]></category>
            <category><![CDATA[analysis]]></category>
            <category><![CDATA[tableau-consulting]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Fri, 14 Aug 2020 17:27:32 GMT</pubDate>
            <atom:updated>2020-08-14T17:27:32.923Z</atom:updated>
            <content:encoded><![CDATA[<p><strong>REMOTE WORKING IS THE NEW NORMAL</strong></p><p>From co working spaces to the all-pervading mini coffee shops with free Wi-Fi, a growing number of people are working remotely, and this is slowly changing the way we live our lives.</p><p>According to the U.S. Census Bureau, one-third of the workforce and nearly half of all ‘information workers’ are able to work from home. Though the number of people working remotely partially or fully has been on the rise for years now, especially in the U.S., the COVID 19 pandemic may have pressed the fast-forward button.</p><p>With millions of people now participating in this work from home experiment, it is worth asking how companies and people feel about working from home?</p><p>The visualization in focus looks at the benefits of working from home. Also, the data was collected prior to the COVID 19 pandemic.</p><p><strong>A survey of 3500+ workers by the State of Remote Work</strong> revealed some of the things that people value highly using a <strong>stacked bar chart</strong>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/820/0*uYP0F9XVSPm9-eBo.png" /></figure><p><strong>What worked for the visualization:</strong></p><ol><li>The title and labels are marked and clearly defined.</li><li>The chart looks simple and efficient. The message is getting communicated.</li><li>The source is included.</li></ol><p><strong>What did not work for the visualization:</strong></p><ol><li>The picture is very prominent and tends to distract. The data should be the focus.</li><li>The use of colors for each benefit is not necessary. Focusing on a story or a subset of the data using the same color for the data points that stand out would be more effective.</li><li>‘Benefits’ in the title is underlined in yellow as ‘working from home’. Not sure if this is deliberate</li></ol><figure><img alt="" src="https://cdn-images-1.medium.com/max/1000/1*bH9IG7l5HPTG2dQYcuFRaw.png" /></figure><p><strong>My interpretation:</strong></p><p>1. I used a <strong>spider chart </strong>to showcase the categories that stand out and to convey the information more effectively. A radar or spider chart is a two-dimensional chart type designed to plot one or more series of values over multiple quantitative variables. Each variable has its own axis and all variables are joined at the center of the figure. These charts are useful for showing which variables score high or low in the dataset, hence making them ideal for showcasing performance.</p><p>2. 32%, 26% and 21% of the respondents prefer having the ability to run a flexible schedule, to have the option to work from anywhere and to not commute to their place of work, respectively.</p><p><strong>Spider or Radar charts are also often criticized by data designers mainly for the following reasons:</strong></p><p>1. <strong>Can be hard to read</strong>: Quantitative values are easier to read when they are laid out on a single vertical or horizontal axis. This is a general reproach made to circular layouts.</p><p>2. <strong>Category order has a huge impact</strong>: Radar charts focus on the shape observed. This shape depends on the ordering of the categories observed.</p><p>3. <strong>Small changes tend to be more exaggerated</strong>: The area of a radar chart changes quadratically rather than linearly which may deceive viewers into thinking that small changes are more significant than they are.</p><p>In this case, a <strong>bar chart or a lollipop chart</strong>, ranking the variables are the ideal alternatives to display information with a single series where all quantitative variables have the same scale (% in this study).</p><p>Let me know what you think about the viz. Are there any suggestions that you want to make? What do you think of Remote Work in 2020?</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/RemoteWork_15970958361760/Radar"><em>Click here to view my visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=774ea212e1f9" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[THE PENGUIN PARADOX]]></title>
            <link>https://garima-anand.medium.com/the-penguin-paradox-72c9122e15f?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/72c9122e15f</guid>
            <category><![CDATA[scientific]]></category>
            <category><![CDATA[analytics]]></category>
            <category><![CDATA[visualization]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[tableau]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Tue, 14 Jul 2020 23:48:03 GMT</pubDate>
            <atom:updated>2020-07-14T23:48:03.784Z</atom:updated>
            <content:encoded><![CDATA[<p>This week’s dataset involved deep diving into penguin habits to understand their behavior.</p><p>The Palmer Penguins is a dataset constructed by Dr. Kirsten Gorman and relates to the structural size measurements of 3 species of penguins: adult, male and female Adelie, Chinstrap and Gentoo penguins. The data was collected at Palmer station Antarctica LTER between the period 2007–09. For each species, 4 structural size measurements were collected: bill length, bill depth, flipper length, and body mass. In total 344 samples were collected (however 2 samples have missing structural size measurements).</p><p>The data on the 3 different species of Penguins was collected from 3 islands in the Palmer archipelago in Antarctica. These islands are the Dream island, Torgerson island and Biscoe island.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/624/1*Tc5JL4yxlfPD7xbwWmsscQ.png" /></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/624/1*2tuZiGCzqg5tDOqxUO_hSg.png" /></figure><p>What worked for the visualization?</p><p>1. A scatter plot depicting the relationship between 2 structural size measurements is ideal.</p><p>2. The labels are accurate and easy to read.</p><p>3. The differentiation in color across marks based on species helps in understanding how each species correlated between the 2 measurements.</p><p>What did not work for the visualization:</p><p>1. The segregation of species based on color would have been enough. Creating different shapes for different species is unnecessary and adds to visual clutter.</p><p>2. The prevalence of gridlines across the scatter plot is not needed. It does not enhance the analysis.</p><p>3. Showing variation across the 3 structural measurements by species would have made the analysis more insightful and thought provoking.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/533/1*NNBJjNagoPVy3iVRKvoSpg.png" /></figure><p>My interpretation:</p><p>1. I wanted to understand the correlation between the 3 structural size measurements of Adelie, Gentoo and Chinstrap penguins using scatter plot analysis.</p><p>2. A basic understanding of the data gave me insight into the characteristics of the penguin species. Gentoos are the largest of the Palmer penguins. Male Gentoos have an average body mass of 5485 gms with an average flipper length of 221.54 mm. The female Gentoos are 17% less heavy than their male counterparts but their flipper lengths are nearly as long as that of the males with an average length of 213 mm.</p><p>3. Chinstrap and Gentoo penguins have the longest bills (culmen length). Male culmen lengths average 51mm and 49 mm respectively while female culmen lengths average 46mm and 45 mm respectively.</p><p>4. Adelie and Chinstrap penguins have the deepest bills (culmen depth). Male culmen depths for both species average 19mm. Culmen depths for females of both species average 18 mm.</p><p>5. There is a positive correlation between body mass and flipper lengths across all species of penguins.</p><p>6. There is a positive correlation between body mass and bill lengths across Gentoo and Adelie penguins. The same cannot be said about Chinstrap penguins.</p><p>7. There is no such relation between body mass and bill depths across all species of penguins. The correlation reverses in this case implying that the species exhibit what is called ‘The Simpson Paradox’.</p><p>Simpson’s paradox, or the Yule–Simpson effect, is a phenomenon in probability and statistics, in which a trend appears in several different groups of data but disappears or reverses when these groups are combined. It is sometimes given the descriptive title ‘reversal paradox’.</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/ThePenguinParadox/Dashboard1?publish=yes"><em>click here to view my visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=72c9122e15f" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Amazon’s Tiny Profits Explained.]]></title>
            <link>https://garima-anand.medium.com/amazons-tiny-profits-explained-610096456cfe?source=rss-6f8e8d5ad9------2</link>
            <guid isPermaLink="false">https://medium.com/p/610096456cfe</guid>
            <category><![CDATA[financial-analysis]]></category>
            <category><![CDATA[data-visualization]]></category>
            <category><![CDATA[data]]></category>
            <category><![CDATA[amazon]]></category>
            <category><![CDATA[analytics]]></category>
            <dc:creator><![CDATA[Garima Anand]]></dc:creator>
            <pubDate>Sat, 27 Jun 2020 06:28:51 GMT</pubDate>
            <atom:updated>2020-06-27T06:28:51.630Z</atom:updated>
            <content:encoded><![CDATA[<p>In it is early years Amazon began as an online marketplace that sold books, but over the past 2 decades it has expanded into becoming a household name. From books to household items to art, Amazon sells it all. The company is known for having “Earth’s biggest collection” of products. So, how does it do that?</p><p>For a long time, Amazon skeptics have repeated the narrative that the e-commerce giant worth $880 billion today has exceptionally low profit margins and that it is business model will eventually fail.</p><p>According to a report form July 2015, Amazon only made $92 million for the previous quarter’s profit. When comparing this margin to other tech giants like Google, which netted $3.93 billion that quarter Amazon does not measure up. How can the company be expanding so rapidly with low net income?</p><p>Amazon intentionally posts low profits because it takes most of its profits and invests them into the company so that it benefits even more in the future.</p><p>Look at the Chart below:</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/624/1*ruLM-QVd69I-bxtELDc64Q.png" /></figure><p>Think of <strong>revenue</strong> as Amazon’s cut from third party sales or the total of your amazon shopping cart. This includes sale of goods and services, including when Amazon ships goods for third parties.</p><p><strong>Net income</strong> is how much of those total sales Amazon gets to keep after it accounts for the cost of selling those items i.e. the items themselves ,the shipping cost , packaging, theft protection, marketing and keeping the lights on.</p><p><strong>What worked for the visualization?</strong></p><p>· The title in one line tells me the story behind revenue and profit across first quarters of various years.</p><p>· The lines are clearly labeled, and the colors make them easy to identify.</p><p>· The usage of a line chart to show trends across time is apt.</p><p><strong>What did not work for the visualization?</strong></p><p>· The chart seems to use the word revenue and sales interchangeably. That confuses the reader.</p><p>· An explanation behind the seasonal peaks and troughs on the revenue line or more details in terms of how the profit is distributed across years could have added more depth to the story.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/624/1*t8ACRrRfTEixpuECnlBSzw.png" /></figure><p><strong>My interpretation:</strong></p><p>· I decided to create a dual axis chart showing revenue and net income trends over the years.</p><p>· I wanted to understand how the net income is distributed quarter wise. A bar chart is great for comparison purposes. Net income was negative for only 5 quarters over a span of 15 years from 2005–20.</p><p>· After Q1 in 2015, Amazon has been consistently making positive profits as can be seen from the line chart on the right-hand side implying that the company only recently became profitable.</p><p>· Amazon lost $437 million dollars of net income in the 3rd quarter of 2014. This was its biggest loss since the company started.</p><p>· Amazon recorded $3,513 million dollars of net income in the first quarter of 2019. This was almost 8 times higher than its lowest recorded income in 2014.</p><p>· The company saw its biggest jump between the last quarter of 2017 and the first quarter of 2018 when net income increased by 536%.</p><p>· In the first quarter of 2020, Amazon’s revenue was almost 30 times its net income or profit.</p><p>What is interesting to note here is that Amazon invests its profits back into the business with capital expenses such as data centers, upgrading distribution networks and new technology like AWS (Amazon Web Services). Since it does not have to borrow money to do so, it does not incur any interest costs, and this allows them to have incredibly free cash flow.</p><p>The revenue figures are staggering, and the profit margins are incredibly low. But Bezos manages to re imagine the way we conduct business by strategizing investment.</p><p><a href="https://public.tableau.com/profile/garima1910#!/vizhome/Amazonstinyprofits_15928784176440/Dashboard1"><em>Click here to view my visualization</em></a></p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=610096456cfe" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>