Implementation of Statistical Methods using SPSS Sourish Saha PhD student Department of Statistics University of Florida [e-mail]

1
Implementation of Statistical Methods using
SPSS Sourish SahaPhD studentDepartment of
StatisticsUniversity of Floridasourish_at_ufl.edu

2
TOPICS

• Manipulating Data
• Recoding, Subsetting
• Descriptive Statistics
• Comparing MeansOne-Sample T Test,
  Independent-Samples T Test, Paired-Samples T
  TestOne-Way ANOVA, Multiple Comparison,
  Correlations
• Simple Multiple Regression Analysis
• Comparison of Several GroupsTwo-way
  ANOVAChi-Square as a Test of HomogeneityKruskal-
  Wallis Test
• Logistic Regression

3
To Recode the Values of a Variable into a New
Variable

• Transform -gt Recode -gt Into Different
  Variables
• Select the variables you want to recode.
• Enter an output (new) variable name and click
  Change.
• Click Old and New Values and specify how to
  recode values.

4
To Select Subsets of Cases Based on a
Conditional Expression

• Data
• Select Cases.
• Select If condition is satisfied.
• Click If.
• Enter the conditional expression.

5
Exploring the data in SPSS

• Analyze  Descriptive Statistics    Descriptives
• Descriptives provides basic descriptive
  statistics
• n, mean, standard deviation, min and max.

6
Exploring the data in SPSS

• Analyze  Descriptive Statistics    Explore
• Explore provides more descriptive statistics,
  including the variance, skewness, kurtosis, the
  median, percentiles and other descriptive
  statistics and information.
• Plots
• Boxplots, stem-and-leaf plots, histograms,
  normality plots.
• Reasons for using the Explore procedure include
  data screening, outlier identification,
  description, assumption checking.

7
Exploring the data in SPSS

• Analyze  Descriptive Statistics    Frequencies
• Frequencies produces a frequency distribution
  table.
• Statistics and plots.
• Frequency counts, percentages, cumulative
  percentages, quartiles, user-specified
  percentiles, bar charts, pie charts, and
  histograms and more

8
Exploring the data in SPSS

• Analyze  Descriptive Statistics    Crosstabs
• Crosstabs with 2 variables creates a two-way
  table or crosstabulation. With statistics button
  one can choose among many statistics, including
  the chi-square value along with its p-value.
• The Crosstabs procedure offers tests of
  independence and measures of association. One can
  obtain estimates of the relative risk of an
  event.

9
Exploring the data in SPSS

• Analyze  Descriptive Statistics    Ratio
  Statistics
• The Ratio Statistics procedure provides a
  comprehensive list of summary statistics for
  describing the ratio between two scale variables.

10
Means

• Analyze  Compare Means    Means
• The Means procedure calculates subgroup means and
  related univariate statistics for dependent
  variables within categories of one or more
  independent variables.
• The Means procedure is useful for both
  description and analysis of scale variables. A
  variety of statistics is available to
  characterize the central tendency and dispersion
  of your test variables.

11
One-Sample T Test

• Analyze  Compare Means    One Sample t-test
• The One-Sample T Test procedure tests the
  difference between a sample mean and a known or
  hypothesized value.
• Allows you to specify the level of confidence for
  the difference
• Produces a table of descriptive statistics for
  each test variable

12
Independent-Samples T Test

• Analyze  Compare Means    Independent Samples
  T-test
• The Independent-Samples T Test procedure compares
  means for two groups of cases. Ideally, for this
  test, the subjects should be randomly assigned to
  two groups, so that any difference in response is
  due to the treatment (or lack of treatment) and
  not to other factors.
• Also displayed are
• Descriptive statistics for each test variable
• A test of variance equality

13
Paired-Samples T Test

• Analyze  Compare Means    Paired-Samples T-test
• The Paired-Samples T Test procedure compares the
  means of two variables for a single group. It
  computes the differences between values of the
  two variables for each case and tests whether the
  average differs from 0.

14
One-Way ANOVA

• Let
• be independent random samples from m normal
  populations with the ith population having
  parameters
• Assuming equal variances, we want to test
  the null hypothesis
• against the alternative that any two of the
  population means are unequal.
• ANOVA involves partitioning the total
  variation in the combined sample into two parts.
  One part explains the variation between the
  samples while the second part explains the
  variation within each sample (SSTSSG SSE).

15
One-Way ANOVA

• Analyze  Compare Means    One-Way
  Anova
• Produces a one-way analysis of variance for a
  quantitative
• dependent variable by a single factor
  (independent) variable.
• Used to test the hypothesis that several means
  are equal.
• Extension of the two-sample t test.
• In order to know which means differ.
• Two types of tests for comparing means a priori
  contrasts and post hoc tests. Contrasts are tests
  set up before running the experiment, and post
  hoc tests are run after the experiment has been
  conducted.

16
One-Way ANOVA

• For each group number of cases, mean, standard
  deviation, standard error of the mean, minimum,
  maximum, and 95 confidence interval for the
  mean.
• Levenes test for homogeneity of variance,
  analysis-of-variance table and robust tests of
  the equality of means for each dependent
  variable, user-specified a priori contrasts, and
  post hoc range tests and multiple comparisons
  Bonferroni, Tukeys honestly significant
  difference, Scheffé, and least-significant
  difference.

17
Multiple Comparison tests

• Tests suitable for the simultaneous testing of
  several hypotheses concerning the equality of
  three or more population means.
• When samples have been taken from several
  populations, as a preliminary to the more general
  question of whether the populations differ, there
  is the simpler question of whether they have
  different means.
• If our null hypothesis is rejected then we wish
  to know where the differences lie, like for
  example using Tukeys test (HSD).

18
Multiple Comparison tests

• With m populations,
• If null is rejected then we wish to know where
  the differences lie. There are
• pairs of populations that could be
  compared.

19
Bivariate Correlations

• The Bivariate Correlations procedure computes
  Pearsons correlation coefficient (r), Spearmans
  rho, and Kendalls tau-b with their significance
  levels.
• Correlations measure how variables or rank orders
  are related.
• Before calculating a correlation coefficient, one
  should screen the data for outliers (which can
  cause misleading results) and evidence of a
  linear relationship.
• Pearsons correlation coefficient is a measure of
  linear association. Two variables can be
  perfectly related, but if the relationship is not
  linear, Pearsons correlation coefficient is not
  an appropriate statistic for measuring their
  association.

20
Rank Correlation Coefficient

• Rank correlation is a method of finding the
  degree of association between two variables.
• The calculation for the rank correlation
  coefficient the same as that for the Pearson
  correlation coefficient, but is calculated using
  the ranks of the observations and not their
  numerical values.
• This method is useful when the data are not
  available in numerical form but information is
  sufficient to rank the data.

21
(No Transcript)
22
Recode ComputeCreate new variable

• Transform -gt Compute
• Give the name of the Target variable
• In the Numeric Expression box choose the
  Function of your
• choice

23
(No Transcript)
24
(No Transcript)
25
(No Transcript)
26
(No Transcript)
27
Simple Linear Regression

• The simple linear regression is aimed at finding
  the "best-fit" values of two parameters in the
  following regression equation
•    
• "the y-intercept of the regression line
• "the slope of the regression line"
• A popular method for finding the "best-fit"
  values is the Least Squares Regression method.

28
Multiple Regression

• Multiple (linear) regression is a regression
  technique aimed at finding a linear relationship
  between the dependent variable and multiple
  independent variables.
• The multiple regression model is as follows
• Multiple regression finds the set of parameters
• that provides the best fit between the model
  and the given data .

29
(No Transcript)
30
Kruskal - Wallis Test

• The Kruskal-Wallis test is a nonparametric test
  for finding if three or more independent samples
  come from populations having the same
  distribution.
• It is a nonparametric version of ANOVA.

31
(No Transcript)
32
Logistic Regression

• Useful for situations in which we want to predict
  the presence or absence of a characteristic or
  outcome based on values of a set of predictor
  variables.
• Similar to a linear regression model BUT it is
  suited to models where the dependent variable is
  dichotomous.
• Logistic regression coefficients can be used to
  estimate odds ratios for each of the independent
  variables in the model.

33
Logistic Regression

• To perform logistic regression, go to
• Analyze
• Choose Regression
• Then click on Binary Logistic