Assignment 3: Tests of Statistical Significance

Name: ______

(Please do the following problems using SPSS. There are text instructions and video instructions in SPSS References link.)

(Please include only the SPSS outputs that are used in reporting your results such as test statistics and p-values.)

In SPSS Assignment 1, you had created an SPSS data file. The data was from a study for investigating body fat percentage. A copy of this data file can be downloaded from the following link: .Variables observed in the data file are the body fat percentage (% fat), age and sex, and whether the subject smoked cigarette or not, for 30 normal adults. Please perform a hypothesis test to see if the average body fat of smokers in the sampled population is statistically significantly greater than 25, at 5% level of significance. (You need to use the Select Cases option to select the group of smokers in the data first, and then perform the analysis.See SPSS References page for instructions. You need to also check the normality assumption and report the normality test p-value and t-test p-value with SPSS output tables attached.)

In a pediatric clinic study, researchers wish to see how effective aspirin is in reducing temperature. Seven 6-year-old children suffering from influenza had their temperatures taken immediately before and one hour after administration of aspirin. The results are given in the following table. At 5% level of significance, test to see if the aspirin is reducing the temperature.

Temperature

Child / Before / After
1 / 101.1 / 99.8
2 / 103.2 / 101.1
3 / 102.9 / 100.4
4 / 103.1 / 101.2
5 / 102.4 / 100.8
6 / 102.5 / 100.2
7 / 101.9 / 100.3

State the hypothesis in words, and perform a paired-samplet-test to test whether there is significance reductionin body temperature after administration of aspirin, at the  = 5%.

1) Perform the parametric t-test.

a) State the hypothesis.

Null Hypothesis:

Alternative Hypothesis:

b) Report Normality test result using p-value. (Show SPSS normality test table)

c) The value of the test statistic is =

d) Write the conclusion using p-value.

(Show SPSS t-test table, and also comment on whether there is statistically significant reduction of body temperature after administration of aspirin?)

2)Perform the nonparametric signed rank test.

a) Value of the test statistic is =

b) Conclusion with p-value.

(Show SPSS Signed rank test table, and also comment on whether there is statistically significant reduction of body temperature after administration of aspirin?)

A study was performed concerning risk factors for carotid artery stenosis for men born in 1940 and residing in city A. Two independent random samples were taken from this population, one with stenosis and one with no symptom of stenosis. The following data were reported for blood-glucose level:

Blood glucose (mmol/L)

Stenosis: 4.2 4.7 4.8 5.0 5.3 6.2 3.8 5.6

No Stenosis: 4.9 4.7 5.3 4.7 4.0 6.7 6.9 5.8

Perform independent samples t-test to test whether there is significant difference in average blood-glucose levels between men with carotid artery stenosis and those who had no carotid artery stenosis, at 5% level of significance. (Write few paragraphs to explain your tests and results, and tests for the necessary assumptions. The conclusion of these tests should be reported using p-values. Attach the SPSS test tables used in your conclusions.)

4. Studies conducted in Australia indicate that there may be a difference between the pain thresholds of blondes and brunettes. Men and women of various ages were divided into four categories according to hair color: light blond, dark blond, light brunette, and dark brunette. The purpose of the experiment was to determine whether hair color is related to the amount of pain evoked by common types of mishaps and assorted types of trauma. Each person in the experiment was given a pain threshold score based on his or her performance in a pain sensitivity test (the higher the score, the higher the person’s pain tolerance).

Light Blond / Dark Blonde / Light Brunette / Dark Brunette
62 / 63 / 42 / 32
60 / 57 / 50 / 39
71 / 52 / 41 / 51
55 / 41 / 37 / 30
48 / 43 / 35

a)Use the SPSS output to conduct a test to determine whether the mean pain thresholds differ among people possessing the four types of hair color. Report the p-value of the test and draw a conclusion using the level of significance  = 0.05.

b)Check the homogeneity of variances assumption using p-value of the test, and attach the SPSS output?

c)Use Scheffe’s multiple comparisons methods to perform the multiple comparisons to find homogeneous subsets and interpret your result. You must attach the homogeneous subsets output from SPSS.

5. Investigation of Food Poisoning: A local health department realized that there were many reports from residents in the city that had signs and symptoms of acute gastrointestinal illness include nausea, vomiting, diarrhea, fever, and abdominal pain. All these reports were occurred during a weekend from a graduation party held in the backyard of a family. Investigators from the local health department were sent out to interview all the residents that went to this party in order to find out what may be the reasons that caused the outbreak of the disease.The objective of this study is to analyze data from the ingestion of various types of food in the party to determine the most likely cause of the outbreak.

Data Link:

Data was collected by the epidemiological team who interviewed 75 persons known to have been present at the party. Not all attendees ate at the same time, but all ate within four and one half hours of one another. The data obtained from the interviews consisted of the following: age, sickness, types of food eaten, and time to onset of illness. The food at the party consisted of: baked ham, spinach, mashed potatoes, cabbage, jello, rolls, brown bread, milk, coffee, water, cake, vanilla ice cream, chocolate ice cream, and fruit salad. All ill persons had attended the party, and family members who had not attended the picnic did not become ill. There were no laboratory data on any food sources or patient specimens.

Please do the best you can to identify the one food that is most like the problem, and perform a chi-square test of independence, at 5% level of significance, to see if it has significant correlation with the disease. (Please attach the chi-square test table that shows p-value of the test.)