You are required to complete Four Lab exercises for this course. Detailed instructions are provided for each:
Note: For all labs, you must
Lab #1 Hypothetical Relationships
Purpose: To demonstrate how variables may be related by direction (positively, negatively, or zero) and magnitude.
Instructions:
(1) Construct or use an existing theory that explains the relationships
between four LINEAR variables (i.e. interval or ratio scale level) that are
relevant to your theoretical framework and that you plan to use in your project.
At least one should be an outcome variable related to your hypothesis (Use A for
this one):
A, B, C, and D.
(2) Make sure the data for the four variables have a range of about 1 to 50 and are
normally distributed.
This means they should NOT exceed the parameters for kurtosis and skewness.
(3) Create data that will support three hypotheses showing relationships that have probability of significance that is
not more than p > .05 and not less than p < .001:
H1. a positive significant relationship between A and B
H2. a negative significant relationship between A and C
H3. a non-significant relationship (near zero) between A and D.
N=30 (four observations A,B,C,D for 30 subjects).
(3) Create and input data to an SPSS file for data analysis
(4) Perform statistical analyses:
(5) Be sure to include a narrative explanation of your results indicating how they fit, or follow from your theory.
-> SPSS procedures:
1. Analyze/Descriptive statistics/descriptives. For all
four variables
2. Pearson Correlations among all four variables (SPSS:
Analyze>Correlate>Bivariate)
3. Plot the variables for which hypotheses were made (SPSS: Graphs>scatterplot).
Import your tables and figure (graph) into Word document using Academic Style tables.
Note I recomend that you delete the title of the table in SPSS and place the table number and title outside the imported SPSS table.
Table 1 should be for descriptives and table 2 the correlational matrix, Figure 1 (graph / scatterplot)
Explain how the four variables are related with regard to the direction, strength. If the relationship is counterintuitive, be sure to explain why.
(1) Create another variable that will serve as a TRUE
independent
variable (not a participant, i.e. subject variable). Make sure it is one
that follows from your theoretical framework.
This variable must have at least two levels (e.g.
High and Low) that should be coded as 1=LOW; 2=HIGH, e.g., or in some other way
to denote the two levels (e.g. attractive v. unattractive stimulus person). The new variable should be called IV (for Independent
Variable) and given a Variable label, .e.g. "attractiveness level of
stimulus person."
(2) You must "assign" subjects to groups (IV) in such a way to insure that
the group means will differ significantly on a dependent variable such as one of
the variables you created as an outcome, or dependent variable (A, if that was
used for your primary DV in Lab1), or B or C, (but not D).
NOTE: You must create data that will support
the hypothesis for your primary DV showing that IV groups differ in the
predicted direction but probability for rejection must be between p
.05 and .001.
(3) Now add the new variable and "assign" subjects to groups by entering the new values (1, 2, For n=15 in each group condition).
(4) Provide a short narrative explanation of your results, including how they fit your theory. Be sure to provide labels for variables and values that explain the nature of the variables.
(5) Import your tables and figures in Academic Style (SPSS) into your document report, making sure they conform to APA style for reporting results.
(6) DO NOT include your entire project for me to read. Include only what's relevant for this Lab 2.
**To create the new Statistics for Lab #2**
(Edit your SPSS data.sav file to include the new variable you defined
(IV) and input the data for "assigning" 30 subjects to each of your experimental
conditions)
Now work with the new file. Run SPSS, edit the output to correct
any errors, insure the results are significant (within specified p
levels), and print the file.
Lab 2 DATA (Example)
VARIABLE: VARIABLE LABELS
A
Productivity
B
Job satisfaction
C
Annual days late
D
Extraversion
IV
Autonomy level needed (high v. low)
-> SPSS procedures:
1. Analysis/Frequencies VARS=IV
2. Analysis/Descriptives VARS=A B C D
3. Analysis/ Compare means/ ONEWAY Anova (DVs= A B C D) (IV = 1,2)
Options: Descriptives
You may also want to run a
t-test to see how results compare with the
F test.
Incorporate your tables and figures with labels into your word processing
document.
Be sure to explain how your theory predicts results.
*** Lab #3 Two-way analysis of variance ***
Purpose: To demonstrate how two independent variables (factors) interact to produce outcomes different from what would have occurred if either was tested alone. In this lab, as in Lab #2, one of the factors must be a true IV, but the other may be a truly categorical, non-manipulated Subject Variable, (e.g. gender, race, educational status).
Instructions: Using your proposal topic, and the four variables and the IV you created for the Lab #2 assignment,
(1) Create a second IV (or two more new independent variables) that will serve as a
second factor (FAC2) in a factorial design that
that will produce a significant two-way interaction. Each factor should
have at least two levels or conditions (e.g. low and high, yes or no).
The new variables should be called FAC2 (for Independent var 2) and if the original IV1 is used it should be relabeled as FAC1. Each should be given Variable labels and Value labers.
You must develop an explanation (or use an existing one) which would logically predict how the variables would operate together to produce the interaction. The example I have used suggests that FAC1 (Autonomy: Low and High need) will interact with FAC2 (Surveillance: Low and High need) to produce effective performance. It is hypothesized that workers with a low need for autonomy will perform better under High Surveillance while those who have a high need for autonomy will perform better when they are not supervised closely (Low Surveillance).
(2) You must "assign" subjects to groups in such a way to insure that a significant INTERACTION occurs. You don't have to produce a CROSSED interaction but it will be very impressive if you do!
NOTE: You must create data that will support the hypothesis for your crossed interaction on your primary DV with a probability for rejection between p >.05 and < .001.
(3) You must provide a rationale for the predicted interaction outcome (FAC1 or FAC2). Interaction must be significant for your primary DV (e.g. A) but not necessarily for others (B and C, etc). What significant differences, if any, would you expect to find for the other DVs? Why?
Hint: think about the relationships you established
among the four variables in Lab 1.
NOTE: If you are using a student
version of SPSS, you will not have Multivariate under Analyze/General Linear
Model. Therefore, you can run only one DV at a time using Analyze/General Linear
Model/Univariate.
Note: Using SPSS in the labs, you can run all DVs under
Multivariate procedures.
Hint: it will help to set up a 2 X 2 table for the four cells and plug in "dummy" or hypothetical means in each cell to determine how they will have to vary. It will also help to sort your primary dependent variable before you attempt to assign subjects to conditions.
You can do this by including the SPSS procedure: Data/Sort Cases..Sort BY....
(3) Now add the new variable(s) in the data list and "assign" subjects to groups by entering the new values (1, or 2, for each subject). If you have 30 subjects, you will have to assign 7 to two cells and 8 to the other two cells. Hint: you may find it easier to use the "view value labels" option under View while in Data View (bottom tab) (not in Variable View).
-> SPSS procedures:
(4) Describe and explain how all four means fit (or follow from) your theory or reasoning.
Lab 3 data definition
VARIABLE LABELS:
FAC1 Autonomy
FAC2
Surveilance
VALUE LABELS:
Fac1
1 Lo need auto 2 High need auto
Fac2
1 Lo need surveil 2 High need surveil
Data analysis for Lab 3 Two way anova (easy as 1,2,3)
Steps:
#1. Create data: After defining your data variables and labels, in data view, choose View [value labels]. This will make it easier to work with changing subject values to fit your hypotheses.
To calculate how your “assigned” Ss are distributed to conditions (cells):
Analyze/Descriptives/Crosstabs
a. Fac1 -> Row
b. Fac2 -> Column
#2. Test your hypotheses: To test your
hypothesis (no significant main effects, but a 2-way interaction), use
a Two-way ANOVA:
Analyze/General Linear Model/Multivariate (for SPSS student version, use /Univariate and run each DV separately)
a. DVs -> Dependent variable(s)
b. Fac 1 -> Fixed Factor
c. Fac 2-> Fixed Factor
Choose under: Options
d. Descriptive statistics
e. Estimates of effect size
(move each fac plus the interaction fac1*fac2 over to the
"display means for")
f.. Plots: fac1 -> Horizontal; fac 2 -> separate [add]
#3. Analyze data:
Inspect Cross tab results to ensure that Ss are (almost) equally distributed
into four cells, i.e. 7 or 8 in each.
Inspect Univariate ANOVAs to make sure:
1. There are no main effects for either fac1 or fac2
2. There is a significant interaction (probability of rejection
between p < 05 but not less than .001).
3. The means are in the predicted direction.
Explain results in the narrative.
Note: (Important!) If results are counterintuitive, you must be careful to explain how the theory predicts the findings.
Import your Academic tables and figures with numbers and labels into your word processing document.
Purpose: To show that regression analysis will produce the same outcome as ANOVA and how, using multiple regression, two or more variables may together explain more variance in a criterion variable than just one. Run the procedures and answer the questions in bold.
Use your Lab #2 data set for which you had one IV.
1. Correlations: First, compute the correlation matrix which includes your original four linear variables (as you did in Lab #1).
-> SPSS procedure: Analyze/Correlation/Bivarate
Import the correlation matrix and into your Word document and label it as Table 1.
2. Compare F and regression output for IV and one DV: Using your Lab #2 data, compare the ANOVA output with the regression output. Use your IV (with two levels) and compare the output from ANOVA and Regression (bivariate). Use only one IV and one DV
-> SPSS procedures for ANOVA: Analyze/General Linear Model/Univariate (Option: descriptives)
Import the Descriptives Statistics table into your Word document and label it Table 2.
Import the Tests of Between Subjects Effects table into your Word document and label it Table 3.
-> SPSS procedure for simple regression: Analyze/Regression/Linear. Use the same IV and DV that you used for the ANOVA.
Import the following three tables and label them: Table 4 Model Summary ; Table 5 ANOVA; Table 6 Coefficients
Inspect the output from ANOVA and Regression
Explain:
1. why do ANOVA and Regression produce the same results?
2. in Table 4, what does R and R2
tell you?
3. in Table 5, compare the F value with the F
in Table 2. What does this tell you?
4. in Table 6, explain what the t value means.
3. Using the same data, compute a multiple regression analysis to determine how much each of two predictor variables (i.e. IVs), e.g. B and C, account for the variance in one of your other linear variables. (you may choose to use any one of the first three variables, A,B,C as your dependent variable)
-> SPSS procedure for Multiple Regression: Analyze/regression/
(Options: add
R square Change to the two already checked: Statistics/
Estimates, Model fit)
Import SPSS tables into Word document:
table 7 Model Summary
table 8 ANOVA
table 9 Coefficients