aiou course code 8614-1 assignment autumn 2022

aiou course code 8614-1 assignment autumn 2022

aiou course code 8614 -1 assignment autumn 2022

Course: Educational Statistics (8614)

Semester: Autumn, 2022

ASSIGNMENT No. 1

Q.1 Why is Statistics important for a teacher or researcher?  (20)

The first  reason  is  to  be  able to effectively  conduct  research.  Without the  use of  statistics  it  would be  very  difficult  to make  decisions  based  on the  data  collected  from  a research project.  For  example,  in the  study cited  in Chapter  One,  is  the  difference in  recorded  absenteeism between psychiatric  and obstetrics  nurses  large  enough to conclude that  there is meaningful  difference in  absenteeism  between the  two units? There are two possibilities:  The first  possibility  is  that  the difference  between the  two groups  is  a result  of  chance factors.  In reality,  the  two jobs  have approximately  the  same amount  of absenteeism.  The second  possibility  is  that  there is  a real difference between the  two units  with the  psychiatric  unit  being more nurses missing work.  Without  statistics  we have no way  of  making an educated decision  between the  two possibilities.  Statistics,  however,  provides  us with a  tool  to make  an educated decision.  We will  be  able to  decide which  of  the  two possibilities  is  more likely  to be true.  We  will  base this decision  on our  knowledge  of  probability  and inferential  statistics. A  second point  about  research  should  be made.  It  is  extremely important  for  a researcher  to know  what  statistics  they  want  to use before they  collect  their  data.  Otherwise  data might  be  collected  that  is uninterpretable.  Unfortunately,  when this  happens  it  results  in a  loss  of data,  time,  and money. Now  many a student  may  by  saying to themselves:  “But  I  never  plan  on doing any  research.”  While you  may  never  plan  to be involved in research,  it  may  find its  way  into  your  life.  Certainly,  it  you  decide to continue your  education and work  on  a masters  or  doctoral  degree, involvement  in research will  result  from  that  decision.  Secondly,  more and more work  places  are  conducting internal research or are becoming part  of  broader  research  studies.  Thus,  you  may  find yourself  assigned to one of  these studies.  Finally,  many  classes  on  the undergraduate level may  require you  to conduct  research (for  example,  a research methods  or  experimental psychology  course).  In each of  these instances,  a knowledge of  measurements  and statistics  will  be invaluable.

Q.2 Discuss different types of data. Also elaborate differences between primary and secondary data.                                                                         (20)

 

Types of  Data

In  research,  different  methods  are  used  to  collect  data,  all  of  which  fall  into  two categories,  i.e.  primary  data  and  secondary  data.  It  is  a  common  classification  based  upon who collected  the  data.

1 Primary data :

As  the  name  suggests,  is  one  which  is  collected  for  the  first  time  by  the  researcher himself.  Primary  data  is  originated  by  the  researcher  for  the  first  time  for  addressing  his research  problem.  It  is  also  known  as  first  hand  raw  data.  The  data  can  be  collected  using various  methods  like  survey,  observations,  physical  testing,  mailed  questionnaire, questionnaire  filled  and  sent  by  enumerators,  personal  interviews,  telephonic  interviews, focus  groups discussion,  case studies,  etc.

2 Secondary  data  :

Point  towards  the  second  hand  information  already  collected  and  recorded  by  any  other person  with  a  purpose  not  relating  to  current  research  problem.  It  is  readily  available form  of  data  and  saves  time  and  cast  of  the  researcher.  But  as  the  data  is  gathered  for  the purpose  other  than  the  problem  under  investigation,  so  the  usefulness  of  the  data  may  be limited  in  a  number  of  ways  like  relevance  and  accuracy.  Also,  the  objectives  and methods  adopted  to  collect  data  may  not  be  suitable  to  the  current  situation.  Therefore, the  researcher  should  be  careful  when  using  secondary  data.  Examples  of  secondary  data are  censuses  data,  publications,  internal  records  of  the  organizations,  reports,  books, journal  articles, websites  etc.

Q.3 Explain ‘pictogram’ as a technique to explore/explain data. (20)

 

Pictograms:    A  pictogram  is  a  graphical  symbol  that  conveys  its  meaning  through  its  pictorial resemblance  to  a  physical  object.  A  pictogram  may  include  a  symbol  plus  graphic elements  such  as  border,  back  pattern,  or  color  that  is  intended  to  covey  specific information  s.  we  can  also  say  that  a  pictogram  is  a  kind  of  graph  that  uses  pictures instead  of  bars  to  represent  data  under  analysis.  A  pictogram  is  also  called  “pictograph”, or simply  “picto”.

A  pictogram  or  pictograph  represents  the  frequency  of  data  as  pictures  of  symbols.  Each picture  or  symbols may  represent one or more units of  data.

Pictograms  form  a  part  of  our  daily  lives.  They  are  used  in  transport,  medication, education,  computers  etc.  they  indicate,  in  iconic  form,  places,  directions,  actions  or constraints  on  actions  in  either  the  real  world  (a  road,  a  town,  etc)  or  in  virtual  world (computer,  internet  etc.).

To  successfully  convey  the  meaning, a pictogram:

Q.4 Pie Chart is a common way to depict data. Discuss its usage and drawbacks.

 

Pie Chart

 

A pie chart displays data  in  an easy  pie-slice format with varying  sizes. The size of a slice tells  how  much  data  exists  in  one  element.  The  bigger  the  slice,  the  more  of  that particular  data  was  gathered  and  vice  versa.  Pie  charts  are  mainly  used  to  show  comparison  among  various  segments  of  data.  When  items  are  presented  on  a  pie  chart,  it is  easy  to  see  which  item  has  maximum  frequency  and  which  is  not  or  which  item  is  the most  popular  and  which  is  not.  The  main  purpose  of  using  a  pie  chart  is  to  show  partwhole  relationship.  These  charts  are  used  for  displaying  data  that  are  classified  into nominal  or  ordinal categories.

How to Read a  Pie Chart?

It  is  easy  to  read  and  interpret  a  pie-chart.  Usually,  a  pie-chart  has  several  bits  of  data, and  each is pictured  on  a pie-chart  as  a  pie  slice.  Some  data  have larger  slices than  others. So it  is  easy  to decide which data have maximum  frequency  and which have minimum.

When to Use the  Pie Chart?

There  are  some  simple  criteria  that  can  be  used  to  determine  whether  a  pie  chart  is  right choice or not  for a given data.

Q.5 What do you understand by ‘measure of dispersion’? Also briefly discuss some common measures of dispersion.                                              (20)

 

Measures of Dispersion :

Measures  of  central  tendency  focus  on  what  is  an  average  or  in  the  middle  of  the distribution  of  scores.  Often  the  information  provided  by  these  measures  does  not  give  us clear  picture  of  the  data  and  we  need  something  more.  It  means  that  knowing  the  mean, median,  and  mode  of  a  distribution  does  allow  us  to  differentiate  between  two  or  more than  two  distributions;  and  we  need  additional  information  about  the  distribution.  This additional  information  is provided by  a series of measures which are commonly  known as measures of dispersion.

There  is  dispersion  when  there  is  dissimilarity  among  the  data  values.  The  greater  the dissimilarity, the greater the degree of dispersion will  be.

Measures of  dispersion are  needed  for four basic  purposes.

  1. i) To determine the reliability of an
  2. ii) To serve as a basis for the control of the variability.

iii)     To  compare two or more series with regard to  their variability.

Iv)     To  facilitate the use if other  statistical measures.

Measure  of  dispersion  enables  us  to  compare  two  or  more  series  with  regards  to  their variability.  It  is  also  looked  as  a  means  of  determining  uniformity  or  consistency.  A  high degree  would  mean  little  consistency  or  uniformity  whereas  low  degree  of  variation would  mean  greater  uniformity  or  consistency  among  the  data  set.  Commonly  used measures  of  dispersion  are  range,  quartile  deviation,  mean  deviation,  variance,  and standard  deviation.

Range:

The range  is the  simplest  measure  of  spread  and is  the difference  between  the  highest  and lowest  scores  in  a  data  set.  In  other  words  we  can  say  that  range  is  the  distance  between largest score  and  the  smallest score in  the  distribution.  We can calculate  range as: Range = Highest value of  the data  –  Lowest value of the data

For example, if  lowest  and  highest marks scored  in a  test are 22  and 95 respectively, then Range = 95  –  22  = 73

The  range  is  the  easiest  measure  of  dispersion,  and  is  useful  when  you  wish  to  evaluate whole  of  a  dataset.  But  it  is  not  considered  a  good  measure  of  dispersion  as  it  does  not utilize  the  other  information  related  to  the  spread.  The  outliers,  either  extreme  low  or extreme high value, can  considerably  affect the range. 

Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button
error: Content is protected !!
Scan the code