STAT 601 – Assignment #7 (Due Wednesday, Oct



STAT 601 – Assignment #7

Review the following:

Lecture Handouts :

13 – Analysis of Categorical Data

Narrated Powerpoint Lectures:

under heading 13– Analysis of Categorical Data, parts (a) & (b)

Non-narrated Powerpoint Lectures: under heading 15 – Analysis of Categorical Data and under heading 10 – part (b) only.

RESEARCH PAPER QUESTION

Using the paper “Future Intentions of RN’s” answer the following questions:

a) Examine the χ2 values reported in Table 1. Are any of the values reported statistically significant at the p < .05 level?

b) In Table 1, Education (%): BA/BS , is compared between hospital and non-hospital groups. What does the (3) represent in χ2 (3) ’ 4.97?

c) What is the χ2 value reported for Education (%): AD when comparing the hospital part-time and non-hospital part-time groups of RNs? Is this χ2 significant? Provide a rationale for your answer.

d) How large must a chi-square statistic value with 3 df be in order to be statistically significant at the α = .05 level? How about at the α ’ .01 level?

e) Brewer and Nauenberg (2003) concluded that “Only RNs employed in hospital settings were significantly less satisfied and less committed to their organization than were non-hospital based nurses; however, these attitudes, frequently shown to be related to turnover behavior, did not result in intentions to leave” (Brewer & Nauenberg, 2003, in abstract, pg. 144) Discuss the meaning of this finding, and provide a rationale for this finding.

f) In your own opinion, should the results of this study be generalized to other nursing populations in other states? Provide a rational for your answer.

ADDITIONAL PROBLEMS

1 – Age of Onset and Family Histories of Individuals with Bipolar

Disorder

In their paper “Early Age at Onset as a Risk Factor for Poor Outcome of Bipolar Disorder”, Journal of Psychiatric Research, (2003), Carter et al. one of the relationships examined was that between age of onset (early age < 18, later age > 18) and family history of mood disorders. This paper is linked to the D2L site under categorical data analysis in the outline. Some the results from their study are contained in the files: Bipolar Family.JMP for part (a) and Bipolar Episode.JMP for part(b).

| |Age of Onset | |

|Family History | | |

|of Mood Disorders | |Row Totals |

| |Early (age < 18) |Later (age > 18) | |

| |(E) |(L) | |

|Negative (A) |28 |35 |63 |

|Bipolar disorder (B) |19 |38 |57 |

|Unipolar (C) |41 |44 |85 |

|Unipolar/bipolar (D) |53 |60 |113 |

|Column Totals |141 |177 |n = 318 |

a) Use these data to determine if there is a relationship between age of onset and family history for the population of individuals with bipolar disorder. Summarize your findings. (4 pts.)

b) The researchers also looked at type of episode which was classified as being depression, mania, or hypomania. Is there a relationship between the type of episode and age of onset? Summarize your findings. Note: this outcome was not recorded or missing for some of the patients in the study. (4 pts.)

| |Age of Onset | |

|Type of | | |

|Episode | |Row Totals |

| |Early (age < 18) |Late (age > 18) | |

| |(E) |(L) | |

|Depression (D) |79 |67 |146 |

|Manic (M) |13 |39 |52 |

|Hypomania (H) |16 |8 |24 |

|Column Totals |108 |114 |n = 222 |

2 – Practice Type and Compliance with Baseline Test Guidelines

The effects of nonsteroidal anti-inflammatory drugs (NSAID) include problems involing peptic ulceration, renal function, and liver disease. In 1996, the American College of Rheumatology issued and disseminated guidelines recommending baseline tests (CBC, hepatic panel, and renal tests) when prescribing NSAID. A study was conducted by Rothenberg and Holcomb, the results of which are in their paper “Guidelines for Monitoring of NSAIDS: Who Listened?”, Journal of Clinical Rheumatology (2000), to determine if physicians taking part in a national database of computerized medical records performed the recommended baseline tests when prescribing NSAID. The researchers classified physicians in the study into four categories; those practicing in internal medicine, family practice, academic family practice, and multispeciality groups.

The results are in the data file: Practice Compliance.JMP and are presented below.

| |Performed Baseline Tests | |

|Practice Type | |Row Totals |

| |Yes |No | |

|Internal medicine (IM) |294 |921 |1215 |

|Family practice (FP) |98 |2862 |2960 |

|Academic family practice (AFP) |50 |3064 |3114 |

|Multispeciality groups (MG) |203 |2652 |2855 |

|Column Totals |645 |9499 |n = 10144 |

a) Do these data provide evidence for us to conclude that type of practice and

performance of the recommended baseline tests are related? Summarize your findings.

(4 pts.)

b) Find 95% CI’s for the compliance percent for each of the four practice areas.

Interpret (4 pts.)

[pic] [pic]

3 – Alcohol Use During Pregnancy and Spontaneous Abortion

In their paper “Cigarette, Alcohol, and Coffee Consumption and Spontaneous Abortion”, American Journal of Public Health (1992), Armstrong et al. reported the following results regarding alcohol use (drinks/week) and spontaneous abortion. These results are contained in the file Alcohol and Spontaneous Abortions.JMP.

|Alcohol Use |Number of |Spontaneous |Spontaneous |

|(Drinks per Week) |Pregnancies |Abortions |Abortion (%) |

|a None |33164 |6793 | |

|b 1 – 2 |9099 |2068 | |

|c 3 – 6 |3069 |776 | |

|d 7 – 20 |1527 |456 | |

|e 21+ |287 |98 | |

a) For each level of alcohol use estimate the probability that a woman who becomes pregnant will undergo a spontaneous abortion. Stated another way, estimate the percentage of women in each alcohol use category that will have a spontaneous abortion. Place the results in the provided column. Discuss. (3 pts.)

b) Conduct a test to determine if there is a relationship between alcohol use during pregnancy and spontaneous abortions. Summarize your findings. (4 pts.)

c) For each category of alcohol use find the odds ratio associated with each use level relative to women who do not drink during pregnancy. Hint: You might find it useful to construct a 2 X 2 table for each drinking level relative to nondrinkers. Discuss. (6 pts.)

You can do this in JMP by excluding and hiding all drink levels except for the nondrinkers and the level of alcohol use of interest.

[pic]

|Drink per week |OR |CI for OR |

|1 – 2 | | |

|3 – 6 | | |

|7 – 20 | | |

|21 + | | |

4 – Use of Oral Contraceptives and Thromboembolism

In their paper “Thromboembolism and Oral Contraceptives: an Epidemiologic Case-Control Study” Sartwell et al. (1969) conducted a case-control study to examine the potential relationship between thromboembolism and oral contraceptive use. The cases were 175 women of reproductive age (15 – 44), discharged alive from 43 hospitals in five cities after initial attacks of idiopathic (i.e. of unknown cause) thrombophlebitis, pulmonary embolism, or cerebral thrombosis or embolism. The controls were matched with their cases for hospital, residence, time of hospitalization, race, age, marital status, parity, and pay status. More specifically, the controls were female patients from the same hospital during the same 6-month interval. The controls were within 5 years of age and matched on parity (0, 1, 2, 3, or more prior pregnancies). The hospital pay status (ward, semi-private, or private) was the same. The data for oral contraceptive use are presented in the table below:

| |Control OC Use? | |

|Case OC Use? | |Total |

| |Yes |No | |

|Yes |10 |57 |67 |

|No |13 |95 |108 |

|Total |23 |152 |175 |

a) Do these data provide evidence that the population proportion of oral contraceptive use amongst cases is greater than the population proportion of oral contraceptive use amongst similar controls? (4 pts.)

b) OR for Dependent Samples or Matched-Pair Data

(This is NOT in Powerpoint, you are seeing it here for the first time)

The estimated odds ratio (OR) from matched-pair data is given by

[pic]

and one form of the 95% CI for the OR is as follows:

[pic]

Find a 95% CI for the OR in this study and interpret. (4 pts.)

-----------------------

Select Analyze > Distribution and place

Baseline Tests? In the Y box and Practice Type in the By box.

For each practice type select 95% CI

Highlight the rows to temporarily remove. Select both Exclude/Unexclude and High/Unhide from the Rows pull-down menu. Fit Y by X now will allow us to compare 1-2 drinks/week to nondrinkers in terms of risk of spontaneous abortion. To restore all cases select Clear Row States from the same menu, then move on to the next group

Note: b and c are as defined in the Powerpoint on Comparing Two Population Proportions Using Dependent Samples

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download