Scribd
Upload
17 views12 pages

PSY1004 Session 09

PSYC1004 Introduction to quantitative methods in psychology Week 9Lecture notes

Uploaded by

winnieleee6
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
17 views12 pages

PSY1004 Session 09

PSYC1004 Introduction to quantitative methods in psychology Week 9Lecture notes

Uploaded by

winnieleee6
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

PSYC1004

Introduction to quantitative methods in


psychology

Session 9

1
Hypothesis testing (the previous session’s example)
Productivity of flextime workers
Hypothesized mean: 193.8
Sample mean: 202.94 -1.96 1.96

Population SD: 31.55


N: 50
Significance criterion: 5%

If the null hypothesis is true, 2.05

Since the sample’s z score (2.05) is


outside of the range of ±1.96, the
Standard error occurrence probability of such a z
(SE) = 31.55/ SQRT (50) score is below 5% - the preset
= 4.46
significance criterion for rejecting the
null hypothesis
The null hypothesis can be rejected.
z score of the sample mean
Mean = (202.94 – 193.8)/SE
(population) = 9.14 / 4.46 = 2.05
2
Statistical significance
• When a study’s results are statistically significant, it means that if the null
hypothesis is true, it is unlikely that the sample results would have turned
out
• The criterion for statistical significance or the alpha level (e.g., 5%) should be
preset
• Critical value of the test statistic (e.g., z or t): the value that separates the
region of rejection and the region of non-significance in the sampling
distribution
Sampling distribution of the test
statistic if the null hypothesis is true
(Area = 1 - alpha)

Probability
density

(source:
Hatcher)

Critical value 3
One-sample t test
• Testing whether the mean of a population represented
by a sample (mean = M; size = N) differs from a
hypothesized value (), when the population’s SD is
unknown and needs to be estimated as the sample’s
SD (s)
• The test statistic (t score) is (M
– ) / [ s/SQRT(N)]
• This test statistic should be
evaluated using the t-
distribution for the
appropriate df (= N - 1).

4
One-sample t test
(an example from Howell)

Data from a sample of 36 children of parents diagnosed with


cancer:
• The children’s sample mean score on a social desirability scale =
4.389;
• Sample SD = 2.611
The mean score of the general children population = 3.87, but their
population SD is not available
• Research hypothesis: the population mean social desirability
score of the children of cancer-patient parents is different from
3.87
• Null hypothesis: the population mean social desirability score of
the children of cancer-patient parents is 3.87
5
One-sample t test (example)
• Let the population mean of the cancer-patient parents’ children
be ,
Null hypothesis (Ho):  = 3.87; Research hypothesis (H1):  ≠ 3.87
• If Ho is true, t score = (M – ) / [ s/SQRT(N)] Sample mean = 4.389
Sample SD = 2.611
= (4.389 – 3.87) / [2.611/SQRT(36)] = 1.193
• The df of the sampling distribution of the t score = 36 – 1 = 35
• The critical t value for a significance criterion of 5% ~ 2.03
• Since the t score observed is smaller than the critical t value by
absolute value, the null hypothesis is not rejected: no sufficient
evidence to conclude that the children of cancer-patient parents
score differently on the social desirability scale relative to the
general children population.
6
p value

JAMOVI
output

This p value corresponds to the probability of observing the test statistic value (1.193)
or a more extreme value if the null hypothesis is true.

NOTE: in this course,


students are not required
to obtain the p value of a
test statistic by hand-
calculation or from a
statistical table

1.193 7
Statistical significance
• If the p value of the sample’s test statistic is no more than alpha (), i.e., the test
statistic is in the region of rejection:
 the null hypothesis is rejected
 the results are statistically significant; the research hypothesis is supported
• If the p value of the sample’s test statistic is more than alpha (), i.e., the test
statistic is in the region of non-significance:
 the null hypothesis is not rejected (but not “accepted” either)
 the research hypothesis is not supported by the results.

8
Matched samples t test (example)
This test compares the means of two matched samples (i.e., of
the same/equivalent individuals)

Example
A study examining whether participants with anorexia gain weight after
going through a treatment program:
• Null hypothesis (Ho): Pre-program mean = post-program mean
• Research hypothesis (H1): Pre-program mean  post-program mean

Weight (in lb)


Source:
Howell

9
Matched samples t test (example)
• The pre-program and post-program scores can be transformed
to one set of scores by taking the difference score (or gain
score) for each individual
• The null hypothesis (Ho) will become: If Ho is true, how likely a
mean of the difference scores = 0 sample mean difference
score as large as 7.26
would have turned out?
Weight gain (in lb)

10
Matched samples t test (example)
• If Ho is true, the t score of the sample mean
difference score = (M – ) / [ s/SQRT(N)]
The mean and SD
of weight gain are
7.265 and 7.157
= 7.265 / [ 7.157 / SQRT (17) ] = 4.185 respectively

• Taking the alpha level as 5%, the critical t value


(df = 17 – 1 = 16) = 2.120

• Since the t score is greater than the critical t value


by absolute value, the null hypothesis is rejected

• Participants of the program weighed significantly


more after the program than before it, mean
weight gain = 7.265 lbs, t(16) = 4.185, p < .05.
11
Matched samples t test (JAMOVI output)

Participants of the program weighed significantly more


after the program than before it, mean weight gain =
7.265lbs, t(16) = 4.185, p < .001.

12

You might also like