AIM, OBJECTIVES AND HYPOTHESIS

• Is suicidal thought associated with depression? Research Question

• Two-thirds of people with depression commit suicide. Research Problem.
• To find out if suicidal thought is related with depression. Research aim
• Objectives – break the aim into several actionable tasks
• To assess the suicidal thought in patients with depression
• To ascertain the relationship between suicidal thought and depression
• Constructing a hypothesis
• IV
• DV
• Operating Verb
• There will be no significant relationship between suicidal thought and depression
in the sample.
Decisions concerning rejecting the
null hypothesis…

The true status of the null hypothesis…

True False
The researcher’s decision about the

Type II Error
Accept Correct

Type I Error
null hypothesis…

Reject Correct
 Alpha vs. Beta
• a is the probability of Type I error
• b is the probability of Type II error
• The experimenters have the freedom to set the
-level for a particular hypothesis test. That
level is called the level of significance for the
test. Changing a can (and often does) affect the
results of the test—whether you reject or fail to
reject H0.
• As  increases,  decreases and vice versa.
(Inverse Relationship)
The Normal Distribution
• Three Main
Characteristics:
• Symmetrical: perfectly
symmetrical about the
mean; the two halves are
identical
• Mean = Median = Mode
• Asymptotic Tail: the tails
come closer and closer to
the horizontal axis, but
they never touch
PARAMETRIC TESTS
DEPENDENT VARIABLE
DISCRETE CONTINUOUS

t test
Chi-Square ANOVA
DISCRETE Logistic Regression
Regression Point bi-serial
INDEPENDENT correlation
VARIABLE
Logistic
Regression Regression
CONTINUOUS
Point bi-serial Pearson r
correlation
 NON PARAMETRIC TESTS
MORE THAN TWO MEASURE OF
TWO SAMPLES
SAMPLES CORRELATION

Contingency
McNemar Test (Related) χ2Test
Co-efficient or
NOMINAL χ2Test (Independent) (Independent)
(χ2Test, test of
association)

Sign Test (Related)

Mann-Whitney U Test Friedman (Related) Spearman rank
ORDINAL (Independent) Kruskal-Wallis correlation
Wilcoxon’s Signed Ranks test (Independent) coefficient
(Related)
 CORRELATION COEFFICIENT
• The correlation coefficient computed from the sample data measures the strength and
direction of a linear relationship between two variables.
• The symbol for the sample correlation coefficient is r. The symbol for the population
correlation coefficient is r (Greek letter rho).
• There are several types of correlation coefficients. i.e., Pearson’s Product Moment
Correlation and Spearman’s RHO
• The range of the correlation coefficient is from 1 to 1.
• If there is a strong positive linear relationship between the variables, the value of r
will be close to 1.
• If there is a strong negative linear relationship between the variables, the value of r
will be close to 1.
• When there is no linear relationship between the variables or only a weak
relationship, the value of r will be close to 0.
 COMPARING TWO MEANS
• Large or Small
Sample t tests z tests
• Dependent or • When the population • The samples must be independent
Independent standard deviations are not of each other. That is, there can be
known no relationship between the
• Variance • One or both sample sizes are subjects in each sample.
Known or less than 30. • The populations from which the
Unknown samples were obtained must be
normally distributed
• The standard deviations of the
variable must be known
• The sample sizes must be greater
than or equal to 30.
 Analysis of Variance (F test)
• It is used to test claims involving three or more means.
• It can only show whether a difference exists among the
three means.
• It cannot reveal where the difference lies—that is,
between 1 and 2, or 1 and 3, or 2 and 3.
• Followed by establishing the significance difference,
statistical tests are used to find where the difference
exists using Scheffé test and the Tukey test.
• If only one variable is compared in the groups-One way
Anova, if there are two variables-Two way Anova and
Manova if there are more than two variables
ASSUMPTIONS FOR THE f TEST
COMPARING THREE OR MORE MEANS
• The Population from which the
samples were obtained must be
normally or approximately
normally distributed
• The samples must be independent
of each other
• The variances of the populations
must be equal
WHICH POST HOC TEST?
• The Scheffé test is the most general, and it can be
used when the samples are of different sizes.
• However, the Tukey test is more powerful than the
Scheffé test when making pairwise comparisons for
the means.
• A rule of thumb for pairwise comparisons is to use
the Tukey test when the samples are equal in size and
the Scheffé test when the samples differ in size.
 Chi-squared tests are only valid when
Chi-Square Test you have reasonable sample size. For
2x2 tables (ie only two categories in
Testing hypotheses about the each variable)
relationship between two • If the total sample size is greater than 40,
variables in a population, or Chi-Square can be used
Testing hypotheses about • If the total sample size is between 20 and
differences between 40, and the smallest expected frequency
proportions for two or more is at least 5, Chi-Square can be used (see
note 'a.' at the bottom of SPSS output to
populations. see if this is a problem)
• Otherwise Fisher's exact test must be
used (SPSS will automatically give this)

13
 REGRESSION
• If the value of the correlation coefficient is significant, the next step is to
determine the equation of the regression line, which is the data’s line of best
fit.
• The regression line can be used to make predictions for the dependent variable
• In simple linear regression, the regression equation contains one independent
variable x and one dependent variable y’
• For any specific value of the independent variable x, the value of the dependent
variable y must be normally distributed about the regression line.
• The standard deviation of each of the dependent variables must be the same
for each value of the independent variable.
 STRUCTURE
• Preliminary • Text • Appendix
• Cover page • Introduction • Questionnaire
• Title page • Literature Review • Videos/Audio
• Declaration • Method • Voice/interview
• Supervisor • Results and transcripts
certificate Discussion • Raw data
• Acknowledgement • Summary and • Tables
• Table of contents Conclusion • Published Articles
• List of Tables • Bibliography
• List of Figures
• List of SCIENCE SUBJECTS SOCIAL SCIENCES
Abbreviations
• Synopsis Ph.D. Dark Maroon/ Dark Gray Light Maroon/ Light Gray

M.Phil Dark green/ Black Light Green/ Black

 WRITING MECHANICS
• Chapters • A4 • Font
• Five to Seven • Single side • TimesnewRoman 12 or Arial 10
Chapters • Flush left, right ragged • 18 highest (titles) – 9 least
• Length • Double spacing (Text) (table and foot note)
• 200-250 pages • Single spacing (Long • Styles
• About 80000 words tables, quotations,
Footnotes) • APA (Social Sciences)
• Title (20 words)
• Margins • Harvard (UK Universities)
• Abstract (250 words) • Chicago (Business/History/Fine
• 4 cms Top and left
• Keywords- 3 to 5 Arts)
• 25 cms Right and
• Sections bottom • MLA (Humanities)
• Preliminary (small • AMA (Medical Sciences)
roman)
• Captions, Titles and
• Text (Arabic) Headings • References
• Appendix (A,B,C..) • Boldcase, Italics
• At least 200
• Three to five levels
MAKING A TABLE
REPORTING STATISTICS
• Mean and SD in one decimal
• Test statistics in two decimals
• P value and effect size in three decimals