The data analysts start their analysis by visual examination of the data. This is to see if there are any patterns present or if there is any (apparent) relationship between variables. The data such plotted produced graphs of various types – an Excel Histogram is just one of them.

In today’s tutorial, we will learn a little but of theory about histogram, how to read it, few statistical terms and finally, how to plot a histogram using MS Excel.

The “Concise Oxford Dictionary of Mathematics” defines Histogram as:

“A diagram representing the frequency distribution of data grouped by means of class intervals. It consists of a sequence of rectangles, each of which has as its base one of the class intervals and is of a height taken so that the area is proportional to the frequency. If the class intervals are of equal lengths, then the heights of the rectangles are proportional to the frequencies.”

In this definition (and for the discrete data sets) the “frequency distribution” is the frequency of how often a number is repeated in a data set. The term “class interval ” represents the grouping of data in n-groups where n can be an arbitrary value.

The Nomenclature of a Histogram:

There are some features that can be found in every histogram. The following picture shows various parts of it!

The above figure is overall a histogram. In this histogram:

1. The yellow bars represent the frequency of items. For the fixed interval class, the height is proportional to the frequency of the items.
2. The X-Axis has “Intervals” or it represents the class width for which the frequency is reported. In above example class 60-65 has frequency of 25.
3. The Y-Axis represents the frequency axis.

Taking a sample data and working out Histogram:

If you have a data set for creating histogram that is great. If not, you can make one using excel function RANDBETWEEN(). This function can give you randomly generated numbers between an lower and an upper bounds and you can analyze it with histogram.

Let’s take an example of data generated between zero and 25 as shown in the following picture:

Generate data and keep only values (NO formula):

In order to make a histogram, the first step is to get rid of this RANDBETWEEN() formula when we have our data. To make this data static, copy the entire column and Paste Special as Value only. This will remove the formula but will keep the values and make data stationary.

Define “Class Width” and create a table for “Bins”:

Let’s assume the class width be 5 – this means data will be grouped in groups of 05 each. The bin represents interval by itself.

Use Data Analysis Tool Pack to Create a Histogram:

Excel’s data analysis tool pack is the easiest way to generate Histogram. To access the feature your first need to load the add-in from File>Options>Add-Ins>Manage Add-ins>Analysis Tool Pack. This will cause Data Analysis tool pack to be displayed in the data menu.

When you will choose data analysis tool pack, it will show you variety of options, you have to select Histogram. In the Histogram dialogue box, you need to enter the range referring to the data and the data bins.

After doing with the input range and the output options, you can press OK and a histogram will be produced like on shown below:

The table on the right is bin-wise frequency of the data and the same is shown through a bar chart on the right.

Adding More Options:

Let’s try tick all the options available in the lower left side of the dialogue box and see what is the result:

The first two columns in the table are the same as were in the last case. The third column reporting the cumulative % is calculated by dividing the running sum with the total values in the data set. (In our case it is 50 so 2/50=4.00%, (2+7)/50=18% and so on).

In the second part of the table the bins are sorted according to the highest frequency. Thus the bin with the highest one comes first (25 with count of 13) followed by 15 (count of 11) and so on and then the last column reports the percentage with running sum as we have calculated previously.

The chart shown on the left is a “prioritized histogram” – a type of histogram that shows the factors taking into account the effect or weight. So in this histogram the bin 25 has the highest effect (with highest frequency) and so on. The red line in the chart shows the cumulative effect and we can see that in light of 80/20 rule, the most important section of the data belongs to the first and the second bar i.e. data from Bin 25 and 15.

Conclusion:

We can still explore this histogram by choosing lesser options to see if the “skewness” and “kurtosis” of the data visually. Please download the sample for this tutorial to see how the things actually work.

The post Understanding How to Create a Histogram with MS Excel appeared first on Excel Zoom.

How many days an employee has worked, and should get paid for, has always been a point of concern for an organization. The department responsible for implementing this validation is typically the Payroll department along with Human Resources and other Accounting personnel that prepare the monthly payroll file/report for the company.

This important task could be done manually, as has been the practice for decades, but now spreadsheets can provide a more accurate, less tedious, and faster solution to this problem. In today’s post we will learn how to setup and use the Networkdays and Networkdays.Intl formulas in Excel to automate this task with greater accuracy.

How to use the Networkdays and Networkdays.Intl Functions:

Before we start this tutorial, please download the companion workbook so that it is easier for you to follow the instructions.

Networkdays Sample

MS Excel (2010) has two functions that are mostly used for this task:

1. NETWORKDAYS()
2. NETWORKDAYS.INTL()

We will learn how to use this syntax and setup a sample sheet for our company.

1. NETWORKDAYS() – Networkdays simply counts the number of days between two dates excluding the weekends – i.e. Saturday and Sundays and a list of holidays or absences from that range. The syntax of the function is:

=NETWORKDAYS(start_date,end_date,[holidays])

Where:
• Start Date = A value entered as a date (date entered as text will return an error)
• End Date = Enter the date that marks the end of the target period
• Holidays = Enter any holidays taken by the employee – larges braces “[]” mark that this is an optional argument.

In order to demonstrate the setup we have created the following example.  See the following picture where Employee’s name, Start Date and End date will be entered.

For example for Mr. Pearson in the following table, the network days can be calculated using the formula:

=NETWORKDAYS(B3,C3,E3:I3)

The formula takes into account the data provided in the following table and returns the corresponding workday count.

The formula will automatically discount the weekends and we can vacations to the right (again this is optional) – the reason behind adding workdays before vacations is to give more space for vacations.

It is also to be noted that we can add either single cell or a range of cells to the third argument of the formula.

Why Use NETWORKDAYS.INTL() when we have already NETWORKDAYS() at our disposal?

=NETWORKDAYS.INTL(start_date,end_date,[weekend],[holidays])

And the following table of options can be used to set the weekend:

For example in Middle East Region the normal weekly day off falls on a Friday.  The number of days a person works between two dates without any holidays will be:

The formula we used here is:

=NETWORKDAYS.INTL(B3,C3,E3,)

The third option for the holidays is omitted as it is optional. If we have some vacations as well, we can add it to the table like we did in the previous table and the formula becomes:

=NETWORKDAYS.INTL(B3,C3,E3,F3:J3)

Other uses of NETWORKDAYS() and NETWORK.INTL() functions:

It is not only Human resources and Accounting that can use this function but it’s also helpful for the Project Management and Customs departments as well. For project management related tasks, it is commonly used to find the number of days that work could be scheduled for and how many days the project team will not be working (weekends, holidays, etc)

Similarly, for the Customs department, it is used to find the time that goods will take to reach the destination considering local and international conditions – weekend settings, holidays and the days when customs and import operations staff will be available.  Download the sample file to try it out yourself and please comment if you have other questions about the application or use of this formula.

Networkdays Sample

The post How to Use Networkdays in Excel appeared first on Excel Zoom.

To help Excel 2007 newbies make the transition, I’ve designed a quick reference mapping of the Excel 2003 menus to the Excel 2007 ribbon on a convenient mouse pad.  For example, if you previously went to Format | Cells to access the format cells menu, you would go to Home Tab | Cells Group | Format in Excel 2007.

If you think it would help, check it out at CafePress.com by clicking on the image below.

The post Transition To Excel 2007 appeared first on Excel Zoom.

In addition to the new programs, Microsoft is also introducing Office Web Applications, which compliments Word, Excel, PowerPoint, and OneNote to allow you to access your files from anywhere with an internet connection.  It also allows you to share documents with others and even gives you the ability to work simultaneously on the same document.  Further adding to their product offerings is Office Mobile, which allows you to view Word, Excel, and PowerPoint files on a mobile version of the software.  Email will also be easier to manage with Outlook Mobile.

OK, so enough with the Office features, what’s new in Excel 2010?

Spreadsheets can now be run in your web browser, and be published to the web via the desktop version.  The browser version does not have as many features as the desktop version, however it is an improvement over Google Spreadsheets.  Additionally, a new analytic feature is called Sparklines, which produce a visual trend of a data set over time similar to a chart, except the Sparkline is contained within a single cell.  For example, if you’re tracking monthly sales of a product, you can set a Sparkline that will show the peaks and valleys that the data produces.

One thing users of Excel 2007 (and other Office 2007 programs) who are just getting used to the new Ribbon will not have to worry about is learning another new user interface.  The ribbon should remain essentially the same as in the 2007 version, except for a few new features.

This post will get updated as I discover new features, so please bookmark it and check back often.

The post Microsoft Office 2010 appeared first on Excel Zoom.

Excel will, by default, save information such as the author, file title, comments, etc. This information, could be potentially damaging if it was put in the wrong hands.

Luckily, Excel 2007 makes it easy to remove this information. Click the Office Button | Prepare | Inspect Document. Check all the options on the menu that appears, and click Inspect. Excel will then check each category to see if there is any document information that can be removed and will show a Remove All button next to each that has any information. Click the button, and the information is removed.

The post Remove Personal Information From Excel 2007 appeared first on Excel Zoom.

First, select your list. Right click and choose Filter | Filter by Selected Cells Color. You can then select the filter drop down in your list’s first cell and choose which color to filter. Next, in a row that is outside your list, type in the following formula: =SUBTOTAL(103,A1:A100), where A1:A100 are the cells in your list. Whenever you filter the list, this formula will tell you how many cells are not hidden.

You can remove the filter at anytime, by choosing the Data tab, and clicking the Filter button, and the formula will give you the count of your whole list (i.e. 100 in the example of A1:A100).

The post Count Colored Cells in a List in Excel 2007 appeared first on Excel Zoom.

1. Office Button: This button contains most of the functions found in the File Menu from previous versions of Excel. Commands, such as New, Open, Save, Print and others can be found here.
2. Quick Access Toolbar: The Quick Access Toolbar is fully customizable, and allows you to display commonly used commands. In the image above, there is Save, Undo, Redo, Print Preview and New Workbook.
3. Ribbon: The Ribbon replaces the traditional menus found in previous versions of Excel. The standard ribbon tabs are Home, Insert, Page Layout, Formulas, Data, Review, and View. Excel will automatically add menus as necessary to allow you to work with the content of your worksheet. You’ll notice that there is also a Developer and an Add-Ins tab in the image above. This is because there are macros stored in the workbook, which are shown in the Developer tab, as well as several Add-Ins that are running.
4. Help: The Help button provides one click access to be able to browse Excel’s help topics.
5. Name Box: The Name Box isn’t different from previous versions of Excel, however it is one of the lesser known features found in Excel. This displays the cell reference when selecting a cell (the column and row cross section). You can also type a named range in here. To learn more about naming ranges, take a look at our article Tips – Naming Ranges.
6. Insert Function: By clicking the Insert Function button, Excel will open the Insert Function dialogue box. Here you can search for functions by typing keywords in the search box, or by selecting a category from the drop down menu. The Insert Functions interface is the same as in previous versions of Excel.
7. Formula Bar and Expand Formula Bar Button: The Formula Bar should look familiar to you if you have used Excel before. What’s different in Excel 2007 is the Expand Formula Bar Button on the right. When working with long formulas, this button increases the height of the formula bar, without covering over the data in the first few rows of your spreadsheet. It also enables you to scroll vertically through the formula with the scrolling buttons it displays after clicking the Expand Formula Bar Button.
8. Right Click MiniBar: When right clicking a cell in Excel 2007, you’ll see a new MiniBar in addition to the usual shortcut menu, which displays commonly used editing features. This is makes editing easier, so you don’t have to keep clicking back to the Home tab on the Ribbon in order to format your worksheet.
9. Right Click Shortcut Menu: The shortcut menu in Excel 2007 hasn’t changed much, but also displays with the MiniBar when right clicking.
10. Vertical/Horizontal Split Box: The split boxes in Excel 2007 are not a new feature, but are not very well known. By clicking and dragging either the vertical or horizontal bars, you can split your worksheet into several scrollable panes, allowing you to view different areas of your worksheet at once. To learn more about the split box, take a look at our article Tips – Split a Worksheet Into Multiple Panes.
11. Status Bar: The status bar shows information about Excel. In the image above it says “Ready”, however if you’re saving a file, it will display the status there. The AutoSave feature will also display a status in this location when it is saving your work. The status bar also displays the selected cell statistics, quick views bar and zoom level. The status bar is also customizable. Simply right click somewhere in the status bar to display the customization menu.
12. Worksheet Tabs and Insert New Worksheet Button: The worksheet tabs should be a familiar sight from previous versions of Excel, but the Insert New Worksheet button is a new addition. You can now insert new worksheets with one click of the Insert New Worksheet button.
13. Selected Cell Statistics: In previous versions of Excel, when highlighting several cells with numbers Excel would, by default, show the sum of those numbers here. In Excel 2007, it also displays the average and count of those cells in addition to the sum. For purposes of the illustration above, we’ve edited the image to display the selected cell statistics as if we were to highlight two cells, one with a 5 and the other with a 1. We did this so we could also illustrate the right click menu, that would have otherwise obscured the data in the selected cells.
14. Quick Views: The Quick Views bar allows you to quickly switch between Normal, Page Layout and Page Break Preview views. While these page views aren’t new to Excel 2007, the easy access quick views bar is.
15. Zoom Level: The Zoom Level bar replaces the zoom level drop down menu from previous versions of Excel. You can change the zoom by dragging the arrow left or right to a minimum zoom of 10% or a maximum zoom of 400%. Alternatively, you can click the + or – buttons to increase/decrease the zoom level by 10% with each click.

The post Excel 2007 appeared first on Excel Zoom.