Post on 06-Aug-2015
PART 2
SPSS (the Statistical Package for the Social Sciences)
Lesson objectives Recap SPSS
Data entry Data view Variable view
Descriptive analysis Determining reliability Inferential Statistics with SPSS
Inferential Statistics Based on the assumption that the
sample is random Types of tests
Chi Squared Correlation T test
Example research
Purpose : To determine if V-ROTAN method of teaching will lead to higher achievement and learning satisfaction among visual learners
Design
Population: EDU Research student (100) Sample ( chosen at random, 3 lessons taught by
the same person using the ‘method’) Class 1 (40) Class 2 (40)
Dependent VariableIndependent Variable
AchievementSatisfaction
Learning styles
INTERVENTIONTeaching method
Instruments Learning style inventory
Scores will determine learning styles Can categorize as visual, tactile or auditory
Questionnaire Satisfaction regarding the teaching method higher score – higher lesson satisfaction
Test Scores will determine achievement
Establishing causality To establish causality, one must use
an experimental or quasi-experimental design.
True experimental designs include: Pre-test/Post-test control group design Solomon Four-Group design Post-test only control group design
Threats in experimental research
-Definite weakness+ controlled? Source of concern
What to describe? Descriptive stats
Age Gender Program Learning styles
Cross tabulate? Gender and learning styles
Significance If significant, unlikely to have
occurred by chance (kebetulan) there is statistical evidence that
there is a difference, a correlation, an association between etc….
Probability of something happening? Probability that you will die someday
= _____?
Significance level Significance levels show you how likely a result is due to
chance. The most common level, used to mean something is good
enough to be believed, is 0.95 The finding has a 95% chance of being true. No statistical package will show you "95%" or ".95" to
indicate this level. Instead it will show you ".05," meaning that the finding has a five percent (.05) chance of not being true, which is the converse of a 95% chance of being true.
To find the significance level, subtract the number shown from one. For example, a value of ".01" means that there is a 99% (1-.01=.99) chance of it being true
Hypothesis testing The Null hypothesis states there is no true
difference/no relationship between parameters in the population We reject or fail to reject the null hypothesis
It is rejected only when it becomes evidently false, that is, when the researcher has a certain degree of confidence, usually 95% to 99%, that the data do not support the null hypothesis
Example There is no significant difference between the
mean test scores of visual and tactile learners
Hypothesis testing YOU ALWAYS TEST THE NULL
HYPOTHESIS!
Significance Test of significance
To decide whether to reject the null hypothesis
Select probability 5 out of 100 times the difference did not
occur by chance ( Significance level: 0.05) 1 out of 100 times the difference did not
occur by chance ( Significance level: 0.01) Confidence level?
95% or 99%
Example Null hypothesis
There is no relationship between variables.. Significance level : 0.05 Test statistic
Probability value 0.009 or Sig. 0.009 (smaller than 0.05)
What does that mean? very unlikely that there’s no relationship
between the variables Variables not independent of each other REJECT Null hypothesis
Example Null hypothesis
There is no relationship between variables.. Significance level : 0.01 Test statistic
Probability value 0.12 or Sig. 0.12(greater than 0.01)
What does this mean? Higher likelihood that there’s no relationship
between the variables Variables are independent of each other Fail to reject (accept?) Null hypothesis
Let’s get on with inferential statistics
Now.. What to infer? Independence/ Association Correlation Differences
Independence test –Chi squared Chi squared test is used in situations
where you have two categorical variables Gender and employment sector Gender and learning styles
Chi-square test of independence tests the null hypothesis that there is no association between the two variables
Example: Test for independence Gender
Female Male
Learning styles Visual Tactile Auditory
Null Hypothesis: No association between gender and learning styles
Using SPSS for chi squared Click
Analyze Descriptive
Crosstabs Statistics
Using SPSS for chi squared Low chi squared statistic Sig.961 Fail to reject the null
hypothesis There is no association… Variables independent of
each otherChi-Square Tests
.079a 2 .961
.080 2 .961
10
Pearson Chi-Square
Likelihood Ratio
N of Valid Cases
Value dfAsymp. Sig.
(2-sided)
6 cells (100.0%) have expected count less than 5. Theminimum expected count is .90.
a.
Correlation Measure of the linear relationship between two variables. A correlation coefficient has a value ranging from -1 to 1. Values that are closer to the absolute value of 1 indicate
that there is a strong relationship between the variables being correlated whereas values closer to 0 indicate that there is little or no linear relationship.
The sign of a correlation coefficient describes the type of relationship between the variables being correlated. A positive correlation coefficient indicates that there is a
positive linear relationship between the variables: as one variable increases in value, so does the other.
A negative value indicates a negative linear relationship between variables: as one variable increases in value, the other variable decreases in value.
Example: Correlation Correlation between learning styles
and test scores Correlation between learning styles
and satisfaction
Correlation in SPSS Start at the Analyze menu. Select the Correlate option from this
menu. You will see three options for correlating variables: Bivariate Partial Distances.
The bivariate correlation is for situations where you are interested only in the relationship between two variables
Correlation in SPSS Then, consider is the type of correlation coefficient.
Pearson's is appropriate for continuous data Kendall's tau-b and Spearman's, are designed for ranked
data. The choice between a one and two-tailed significance test
in the Test of Significance box should be determined by the hypothesis you are testing if you are making a prediction that there is a negative or
positive relationship between the variables, then the one-tailed test is appropriate
if you are not making a directional prediction, you should use the two-tailed test (there is not a specific prediction about the direction of the relationship between the variables)
Output
Correlations
1.000 .498**
. .003
30 30
.498** 1.000
.003 .
30 30
Pearson Correlation
Sig. (1-tailed)
N
Pearson Correlation
Sig. (1-tailed)
N
LSVISUAL
TEST
LSVISUAL TEST
Correlation is significant at the 0.01 level (1-tailed).**.
Output
Correlation is not statistically significant
Correlations
1.000 .127
. .252
30 30
.127 1.000
.252 .
30 30
Pearson Correlation
Sig. (1-tailed)
N
Pearson Correlation
Sig. (1-tailed)
N
LSVISUAL
QNAIRE
LSVISUAL QNAIRE
Let’s check for significant difference
Differences between test scores of the groups of learners
Differences: Using t test The t test is a useful technique for
comparing mean values of two sets of numbers. Statistic for evaluating whether the difference
between two means is statistically significant. t tests can be used either
to compare two independent groups (independent-samples t test)
to compare observations from two measurement occasions for the same group (paired-samples t test).
Remember
t test - tests the null hypothesis / that there is no difference …
t test If you are using the t test to compare two
groups, the groups should be randomly drawn from normally distributed and independent populations.
Using SPSS Analyze
Compare Means One-Sample T test... Independent-Samples T test... Paired-Samples T test...
Types of t-test The one-sample t test is used compare a single sample
with a population value. Example, a test could be conducted to compare the average
test scores of U5C with a value that was known to represent the whole EDU 540 population.
The independent-sample t test is used to compare two groups' scores on the same variable. Example : Compare the test scores of U5C and PKPG to
evaluate whether there is a difference in their scores. The paired-sample t test is used to compare the means of
two variables within a single group. Example, it could be used to see if there is a statistically
significant difference between test 1 and test 2 among the members of U5C
Using SPSS : t test
Output
Notice the two parts of the output Equal variances assumed Equal variance not assumed
Which to use? Look at Levene’s test for equality of variance If small Sig. - groups have unequal variances
Independent Samples Test
.814 .378 -6.024 19 .000 -11.528 1.914 -15.533 -7.523
-5.483 10.805 .000 -11.528 2.103 -16.166 -6.890
Equal variancesassumed
Equal variancesnot assumed
TESTF Sig.
Levene's Test forEquality of Variances
t df Sig. (2-tailed)Mean
DifferenceStd. ErrorDifference Lower Upper
95% ConfidenceInterval of the
Difference
t-test for Equality of Means
Output
t-statistics is -6.024 Sig. level : .000 The significance level tells us that the probability that
(there is no difference between visual and tactile learners) – the “NULL” is very small
Hence, there is a significant difference in the test scores between visual and tactile learners
Independent Samples Test
.814 .378 -6.024 19 .000 -11.528 1.914 -15.533 -7.523
-5.483 10.805 .000 -11.528 2.103 -16.166 -6.890
Equal variancesassumed
Equal variancesnot assumed
TESTF Sig.
Levene's Test forEquality of Variances
t df Sig. (2-tailed)Mean
DifferenceStd. ErrorDifference Lower Upper
95% ConfidenceInterval of the
Difference
t-test for Equality of Means
Have fun with SPSS!
Proceed to Qualitative Analysis and Ethics in Research