Abstract line waves
School of Six Sigma

Descriptive Statistics

Know­ing how to improve your process­es and work­flow depends on how well you can inter­pret the data you col­lect dur­ing your test­ing phas­es. Even if data is col­lect­ed appro­pri­ate­ly, if it is report­ed and inter­pret­ed incor­rect­ly, it will not improve your organization’s performance.

To make sure that every­one on your team can cor­rect­ly read and inter­pret your data, learn more about descrip­tive sta­tis­tics and how to prop­er­ly use them in your quest to improve your organization.

Unlock­ing action­able insights from data can be a par­tic­u­lar chal­lenge for orga­ni­za­tions across indus­tries. How­ev­er, it’s increas­ing­ly becom­ing a crit­i­cal skill set for busi­ness pro­fes­sion­als to devel­op. The world’s most valu­able resource is data. 

School of Six Sig­ma cours­es can make under­stand­ing how to report, ana­lyze, and incor­po­rate this data eas­i­er. The data-dri­ven method­ol­o­gy of Six Sig­ma was designed to improve busi­ness process­es, prod­ucts, and ser­vices and, by exten­sion, pro­vide more val­ue to the end consumer.

The Six Sig­ma method­ol­o­gy com­pris­es five phas­es: Define, Measure, Analyze, Improve, Control. The Ana­lyze phase exam­ines the data col­lect­ed dur­ing the Mea­sure stage to iden­ti­fy any inef­fi­cien­cies, defects, and dis­crep­an­cies. Insights gleaned here will pave the way for process improve­ments for your team to implement.

What You’ll Learn in this Online Course

From mea­sures of cen­tral ten­den­cy to mea­sures of dis­per­sion, this course will break down all of the things you need to know in about Descrip­tive Statistics.

This course will go over the mean­ing of descrip­tive sta­tis­tics and how to use the appro­pri­ate tech­niques to sum­ma­rize and describe data accu­rate­ly. You will also be offered descrip­tive sta­tis­tics exam­ples in every­day life to help you bet­ter grasp the con­cept through the use of real-world examples.

What Is Descriptive Statistics?

Descrip­tive sta­tis­tics is the process of orga­niz­ing, ana­lyz­ing, and report­ing data. It includes the aver­age, mean, mode, mea­sure about the prob­lem fre­quen­cy, and the vari­abil­i­ty of the data.

Analy­sis of this data will help your team deter­mine the scope of the prob­lem and how often it occurs, as well as pro­vid­ing val­i­da­tion that a prob­lem tru­ly exists.

Any vari­a­tion along your pro­duc­tion process will impact your out­come, which makes the descrip­tive sta­tis­tics, mean­ing the accu­rate report­ing of your data, very useful.

You can mea­sure the vari­a­tions by focus­ing on these two char­ac­ter­is­tics: mea­sures of cen­tral ten­den­cy and mea­sures of dispersion.

Measures of Central Tendency

The mea­sures of cen­tral ten­den­cy con­sist of two char­ac­ter­is­tics: the mean and the median.

The first char­ac­ter­is­tic is the mean, which is the arith­metic bal­ance or aver­age of a dis­tri­b­u­tion. To cal­cu­late the mean, you need to add all the fig­ures with­in a data set and then divide by the num­ber of fig­ures with­in the set. You can tell if your data is nor­mal­ly dis­trib­uted by look­ing at it in the form of a histogram.

The sec­ond mea­sure of cen­tral ten­den­cy is the medi­an, which is the mid­point of a data set. To cap­ture this, you need to arrange the num­bers in ascend­ing order, and then locate the num­ber that lands in the mid­dle of that data set. In the event that you have a data set made up of even num­bers, you would sim­ply aver­age the two mid­dle fig­ures to cal­cu­late the median.

When refer­ring to the mode of a data set, we’re describ­ing the num­ber in the set that occurs most often. The mode is most use­ful when deal­ing with attrib­ut­es data and is usu­al­ly the sta­tis­tic used to cre­ate Pare­to charts.

Measures of Dispersion

In descrip­tive sta­tis­tics, dis­per­sion is a way of describ­ing how spread out a set of data is. It defines how the data dis­pers­es, stretch­es, or spreads in dif­fer­ent cat­e­gories. The three pri­ma­ry mea­sures of dis­per­sion are range, vari­ance, and stan­dard deviation.

Range is the dif­fer­ence between the largest and small­est obser­va­tion in a data set and is gen­er­al­ly used when the data is not nor­mal­ly dis­trib­uted. In oth­er words, when decid­ing to use the medi­an as your cen­tral ten­den­cy because your data is skewed or you have out­liers that appear to be dri­ving the aver­age up, you can use your range as the mea­sure of dispersion.

Sam­ple vari­ance is the aver­age squared dis­tance between obser­va­tion and the mean. It is used to check the devi­a­tion of data points with respect to the data’s aver­age.
The final mea­sure of dis­per­sion is stan­dard devi­a­tion, which is the square root of the sam­ple variance.

Benefits of This Online Course

The main advan­tages of tak­ing this course are being able to present data in a mean­ing­ful way by accom­plish­ing the fol­low­ing tasks:

  • Iden­ti­fy­ing numer­i­cal mea­sures such as range, vari­ance, and stan­dard deviation.
  • Learn­ing how to use tables and charts to com­pare com­bi­na­tions of variables.
  • Explor­ing the rela­tion­ships between variables.
  • Ana­lyz­ing any issues you may encounter in inter­pret­ing your results.