-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
1/15
Metodologi Penelitian
ANALISIS DATA
DANUJI HIPOTESIS
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
2/15
Proposal Penelitian (23 Mei 2011)
Abstrak
I. Pendahuluan: Latar Belakang; Rumusan Masalah;
Batasan Penelitian; Tujuan Penelitian
II. Landasan Teori: Teori Model Penelitian Hi otesis
III. Metodologi: Objek; Populasi dan Sampel Penelitian;
Uji Hipotesis (Formula dan Cara Uji Hipotesis); Flow
Chart Penelitian
Referensi
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
3/15
(1) Identify a broad area of study. What is the general area of research?
(2) Select the research topic. What is the central research question?
(3) Decide the approach. What is the general philosophical position of
the research?
7 Steps of Research
(4) Formulate the plan. What is the project plan, or research design?
(5) Collect the data or information. What quantitative and/or
qualitative data should be collected?
(6) Analyze and interpret the data. What methods of analysis are being
applied to quantitative and qualitative data analysis?
(7) Present the findings. Are the findings supportable? In other words,
are they valid?
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
4/15
Data Types
Order Interval Origin
Nominal none none none
r na yes unequa none
Interval yes equal or none
unequal
Ratio yes equal zero
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
5/15
Validity
Face Validity
Content Validity : content validity (also known aslogical validity) refers to the extent to which a measure
.
Criterion-Related Validity: measure of how wellone variable or set of variables predicts an outcome
based on information from other variables
Construct Validity: refers to whether a scalemeasures or correlates with the theorized scientific
construct that it purports to measure.
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
6/15
Reliability
Stability
Test-retest
Equivalence
Parallel forms
Internal Consistency
Split-half
Cronbachs alpha
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
7/15
Approaches to Hypothesis Testing
Classical Statistics
sampling-theory approach
objective view of probability
decision makin rests on anal sis of available sam lin
data
Bayesian Statistics
extension of classical statistics
consider all other available information
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
8/15
Types of Hypotheses
Null
that no statistically significant difference exists between
the parameter and the statistic being compared
Alternative logical opposite of the null hypothesis
that a statistically significant difference does exist
between the parameter and the statistic being
compared.
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
9/15
Logic of Hypothesis Testing
Two tailed test
nondirectional test
considers two possibilities
directional test
places entire probability of an unlikely outcome to the
tail specified by the alternative hypothesis
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
10/15
Testing for Statistical Significance
State the null hypothesis
Choose the statistical test
Select the desired level of significance
Compute the calculated difference value
Obtain the critical value
Interpret the test
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
11/15
Classes of Significance Tests
Parametric tests
Z or ttest is used to determine the statistical
significance between a sample distribution mean and a
population parameter
Assumptions:
independent observations
normal distributions
populations have equal variances
at least interval data measurement scale
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
12/15
Classes of Significance Tests
Nonparametric tests
Chi-square test is used for situations in which a test for
differences between samples is required
Assum tions independent observations for some tests
normal distribution not necessary
homogeneity of variance not necessary
appropriate for nominal and ordinal data, may beused for interval or ratio data
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
13/15
Parametric Test
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
14/15
Non-parametric Test
-
8/6/2019 Metopen 2 - Analisa Data Dan Hipotesis 16 Mei 2011 [Compatibility Mode]
15/15
Multivariate
Analysis