TAT: Thematic Apperception Test (Story From Picture)

 TAT : Thematic Apperception test (Story from
picture)
Business Research Methods
Module-5
 Hypothesis: The quality of the hypothesis
determines the value of the results obtained from
the research.
 Meaning: “Hypothesis are questions asked about
the object of research and at the same time about
the facts gathered by observation and proposals for
answers to these questions”
 Hypothesis is a predictive statement that relates
independent variable to a dependent variable and
this is open to testing.
Types
 Descriptive Hypothesis
 Describes some characters of an object. E.g., why
youngster prefer “X” soft drinks.
 Relational Hypothesis
 It describes the relationship between the 2
variables. Example: Demand and quality are
related., Price and demand (hypothesis indicates
association), difference between the English
graduates and others (Hyp., which indicates the
difference)
Sources
 Theory
 Observation
 Past Experience
 Case studies
 Similarity
Characteristics:
 A hypothesis must be valid.
 Clear and precisely stated.
 Doubtful.
 Capable of being tested.
 Transitory phase
 Consistent
 Accessible to all.
 Time
 Empirical reference (clearly explained)
Two tailed and one-tailed test:
 Two tailed : =/
 One tailed:
 Right tailed: >
 Left tailed: <
 Null and Alternative Hypothesis
 Null: No difference between pop., and sample
 Alternative: Difference is there.
 Ho = u
 Ho not equal to u
 Ho less than u
 Ho greater than u
Errors in Hypothesis testing:
 Type I error:
 Rejecting a null hypothesis when it is correct.
 Type II error:
 Accepting a null hypothesis that is false.
Formulation of Hypothesis/ Hypothesis
testing procedure
 Formulate the null and alternate hypothesis
 Select on appropriate test assuming Ho to be true.
 Calculate the value
 Select the level of significance
 Find the critical region (one tail & two tail)
 Select test criteria: ( If sample is large 30 or more then Z-test is
used. If sample is small <30 then T-test is used)
 Compute
 If calculated value lies within the critical region the reject Ho
 State the conclusion in writing.
Types of Tests:
 Parametric test
 Powerful, (Ratio and Interval Measurement)
 It is assumed that the data follows normal distribution. (z-
test, T-test, F-test)
 Selection of one item should not affect the chances of
selecting others be included in the sample.
 Non-Parametric Test
 Nominal and Ordinal data
 Distribution free test
 Easy to compute
 E.g., Binomial test is used when sample size is small, Chi-
square test, Mann-Whitney U test, Sign test.
Types of Parametric Test:
 Z-test
 T-test
Types of Non-Parametric Test
 Chi-Square test
 Sample observation should be independent.
 Sample should contain at least 50 observation (or)
 Total frequency should be greater than 50.
 There should be minimum of 5 observations in any
cell
 Cox and Stuart test
 It is used to examine the presence of trends. E.g.,
sales volume figures month wise for a year is
analysed.
Types of Non-Parametric Test (Cont...)
 Mann Whitney “U” test (Rank Sum test)

 Two set of samples from 2 population
 E.g ., Performance of programmers/employees
working in 2 different branches located in 2
different cities.
 Kruskal-Wallis test / H- test (Rank Sum test)
 It is an extension of Mann Whitney’s test were
more than 2 population are involved
 E.g., 3 different workers(Population) wages are
same or different.
Types of Non-Parametric Test
(Cont...)
Rank Correlation test
This is used to find out the correlation between 2 sets of ranks.

 Kolmogorov-smirnov test
 It is used to examine the efficacy of fit between observed samples
and expected frequency distribution of data when the variables is

in the ordinal scale. E.g., cosmetic shades (very light to dark
shades)
 Run test for Randomness
 E.g., telephone department Males and female run count
 Sign test
 This test is used to identify the pairs and decide whether the pair
has more or less similar characteristics.

 E.g., effect of brand name on quality perception.
 10 persons response on 2 identical sample’s taste perceptions.
Chocolate/beverages

TAT: Thematic Apperception Test (Story From Picture)

Uploaded by

Copyright:

Available Formats

TAT: Thematic Apperception Test (Story From Picture)

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

TAT: Thematic Apperception Test (Story From Picture)

Uploaded by

Copyright:

Available Formats

 TAT : Thematic Apperception test (Story from

 Mann Whitney “U” test (Rank Sum test)

and expected frequency distribution of data when the variables is

has more or less similar characteristics.

 10 persons response on 2 identical sample’s taste perceptions.

You might also like