Q1: Is there an association between smoking (Yes/No) and hypertension? (Note: you will need to create a new variable called `SMOKER’ which will contain two groups (`Yes’ or `No’) using information on the number of cigarettes smoked per day). In the new variable name include the number of the dataset you have been assigned e.g if you have been assigned the dataset `Framingham_42.sav’, name the variable `SMOKER_42’.
Analytical plan:
STUDY DESIGN
ObservationalFraminton heart study was a cross sectional study
VARIABLES
IV : Smoker –categorical dichotomous
DV : Hypertension – categorical dichotomous
HYPOTHESIS
H0: The proportion of people who smoke is similar for people with hypertension and those without Hypertension
H1: The proportion of people who smoke is different for people with hypertension and those without Hypertension
UNIVARIATE ANALYSIS
Smokernumerical summary =proportion (or %) of sample with people with smoking habit; graphical summary could be a bar graph {note: since the data is dichotomous it is usually better to summarize numerically}
Hypertensionnumerical summary=proportion (or %) of sample with hypertension; graphical summary could be a bar graph.
BIVARIATE ANALYSIS
In this bivariate analysis we do the cross tabulation by contingency which interpret the results between the relation between hypertension and smokers
Numerical summary=2 x 2 contingency table Graphical summary=side –by side bar chart
STATISTICAL TESTS AND ASSUMPTIONS
Chisquare test of independent .because the table is 2x2 should use Fisher’s exact test or Continuity Correction, rather than Pearson’s Chisquare .I will use Fisher’s exact test.{note:the choice of which test to use is up to you.You should state which test you are going to use and then llist the assumptions for the test}
Fisher’s exact test assumptions :1) observations are independent
SIGNIFICANCE LEVELS
P
Results:
Univariate analysis:
In this sample there are 300 individuals in smoker_29 we have valid individuals of 296 are valid but we have 4 missing. In this sample the 166(55.3%) do not smoke ,130(43.3%) people do smoking as we have 4(1.3%) could not be calculated due to the missing data. Among the same sample 78(26%) are not with incident hypertension,222(74%) are the individuals with hypertension.
The below tables shows the summary on the results provided in the frequency tables.
Statistics


Smoker_29

Incident Hypertension





N

valid

296

300






Missing

4

0





SUMMARY TABLE SHOWING UNIVARIABLE ANALYSIS SMOKER_29


Frequency

Percent

Valid Percent

Cumulative




percent















Valid

No

166

55.3

56.1

56.1










Yes

130

43.3

43.9

100.0










Total

296

98.7










Missing 999

4

1.3


















Total


300

100.0











SUMMARY TABLE SHOWING UNIVARIABLE ANALYSIS  INCIDENT
HYPERTENSION

Frequency

Percent

Valid Percent

Cumulative



Percent













Valid No

78

26.0

26.0

26.0








Yes

222

74.0

74.0

100.0








Total

300

100.0

100.0









Graphical Representation
In univariate analysis the representation is done by bar diagram as they are categorical variable on which incident hypertension on xaxis and count on y axis .
GRAPH SHOWING UNIVARIATE VARIABLE (INCIDENT HYPERTENSION)
In this bar diagram it shows about the smoker_29 on which count is on y axis and smoker_29 is on xaxis showing yes and no. The number of people who smoke are more when compared to non smokers .
Bivariate analysis
In this analysis the sample consist of valid individuals of 296(98.7%) and 4(1.3%) are missing
Case processing summary






Cases
















Valid


Missing


Total












N


Percent

N


Percent

N


Percent











Incident










Hypertension*

296


98.7%

4


1.3%

300


100.0%

SMOKER_29




















In this contingency table here gives the interpretation of results between the relation of hypertension and smoker_29. Here we have an clear description that there are 31(39.4%) individuals do not smoke have no hypertension,47(60.3%) do smoke but do not have the hypertension. In the same sample individuals 135(61.9%) do not smoke but they have hypertension,83(38.1%)they do smoke and have hypertension.
Incident Hypertension*SMOKER_29 crosstabulation



SMOKER_29









Total





No

Yes









Incident

No

Count

31

47

78


Hypertension















%within Incident

39.7%

60.3%

100.0%




Hypertension













Yes

Count

135

83

218




%within Incident







61.9%

38.1%

100.0%




Hypertension












Total


Count

166

130

296











%within Incident

56.1%

43.9%

100.0%




Hypertension















Incident Hypertension*SMOKER_29 crosstabulation



SMOKER_29









Total





No

Yes









Incident

No

Count

31

47

78


Hypertension















%within Incident

39.7%

60.3%

100.0%




Hypertension













Yes

Count

135

83

218




%within Incident







61.9%

38.1%

100.0%




Hypertension












Total


Count

166

130

296











%within Incident

56.1%

43.9%

100.0%




Hypertension















Graphical representation
In bivariate analysis the relation of incident hypertension and smoker29 is shown by the side –byside diagram.
Chisquare analysis:
In this sample we do Chisquare tests because it is the 2x2 contingency table.In this we get the degree of freedom, the continuity correction and Fisher’s exact test are calculated.
For Fisher’s exact test we use two tailed hypothesis. Hence the pvalue for this sample is 0.001.this means it is lesser than 0.05.this means we reject the null hypothesis as we do not have any significant analysis and conclude that the proportion of people who smoke is different for people with hypertension and those without Hypertension as we know that the Fisher’s Exact Test observations are independent as it is due to the study design.
The proportion of people who smoke is different for people with hypertension and those without Hypertension the Fisher’s Exact test,p=0.001)
This summary, gives a clear descriptive summary and provides the explanation of the data and the relationship between the smokers_29 and hypertension.
Chi – Square Tests



Asympotic

Exact sig.

Exact Sig.


Value

Df

Significance

(2sided)

(1sided)




( 2 sided)









Pearson Chisquare

11.477a

1

.001









Continuity correction

10.594

1

.001









Likelihood Ratio

11.440

1

.001









Fisher Exact Test




.001

.001







Linearbylinear

11.438

1

.001









Association

296











N of Valid Cases

11.477a

1

.001









SUMMARY:
This is the data which shows consists of two variables with independent variable as smoker_29 and dependent variable as hypertension these are dichotonomous categorical variables which are done with graphical representation by bar diagrams and bivariate by side by side chart. The statistical analysis is done by chi square test in which fisher exact value i.e p value is 0.001 which is lesser than 0.05 in which we reject the null hypothesis and shows the that the proportion of people who smoke is different for people with hypertension and those without Hypertension
APPENDIX:
Statistics



Incident



SMOKER_29

Hypertension





N

Valid

296

300


Missing

4

0





FREQUENCY TABLE
SMOKER_29





Cumulative



Frequency

Percent

Valid Percent

Percent







Valid

No

166

55.3

56.1

56.1


Yes

130

43.3

43.9

100.0


Total

296

98.7

100.0


Missing

999

4

1.3



Total


300

100.0









Incident Hypertension




Cumulative


Frequency

Percent

Valid Percent

Percent






Valid No

78

26.0

26.0

26.0

Yes

222

74.0

74.0

100.0

Total

300

100.0

100.0







CROSS TABS
Case Processing Summary

Cases
















Valid


Missing


Total












N

Percent

N

Percent

N

Percent










Incident Hypertension *

296

98.7%

4

1.3%

300

100.0%


SMOKER_29

















Incident Hypertension * SMOKER_29 Crosstabulation
Count


SMOKER_29









No

Yes

Total






Incident

No

31

47

78

Hypertension

Yes

135

83

218

Total


166

130

296






Incident Hypertension*SMOKER_29 crosstabulation



SMOKER_29













No

Yes

Total









Incident

No

Count

31

47

78


Hypertension


% within Incident

39.7%

60.3%

100.0%




Hypertension
















Yes

Count

135

83

218




% within Incident

61.9%

38.1%

100.0%




Hypertension















Total


Count

166

130

296









% within Incident
56.1% 43.9% 100.0%
Hypertension
ChiSquare Tests

















Asymptotic







Significance

Exact Sig. (2

Exact Sig. (1



Value

df

(2sided)

sided)

sided)









Pearson ChiSquare

11.477a

1

.001




Continuity Correctionb

10.594

1

.001




Likelihood Ratio

11.440

1

.001




Fisher`s Exact Test




.001

.001


LinearbyLinear

11.438

1

.001




Association










N of Valid Cases

296

















