# Analyzing Data - PowerPoint PPT Presentation

1 / 11
Title:

## Analyzing Data

Description:

### 1,MALE 1106 42.64 1106 42.64. 2,FEMALE 1488 57.36 2594 100.00 ... Cramer's V 0.1027. Measuring differences between two groups: ... – PowerPoint PPT presentation

Number of Views:42
Avg rating:3.0/5.0
Slides: 12
Provided by: chr7164
Category:
Tags:
Transcript and Presenter's Notes

Title: Analyzing Data

1
Analyzing Data
PHC 6716 July 7, 2009 Chris McCarty
2
Frequency table of nominal variable
Respondent's sex
Cumulative Cumulative
SEX Frequency Percent
Frequency Percent

1,MALE
1106 42.64 1106 42.64
2,FEMALE 1488 57.36
2594 100.00
3
Frequency table of ordinal variable
Current financial condition
Cumulative
Cumulative CURFIN
Frequency Percent Frequency Percent

-9,NA 9 0.35
9 0.35 -8,DK
12 0.46 21 0.81
1,BETTER NOW 1053 40.59
1074 41.40 2,SAME
819 31.57 1893
72.98 3,WORSE NOW 701
27.02 2594 100.0
4
Crosstabulation
EMPLOY(Are you employed now)
SEX(Respondent's sex)
Frequency
Percent
Row Pct
Col Pct 1,MALE 2,FEMALE Total

-9,NA 5
5 10
0.19 0.19 0.39
50.00 50.00
0.45 0.34

-8,DK 6 2 8
0.23
0.08 0.31
75.00 25.00
0.54 0.13

1,YES 640
712 1352
24.67 27.45 52.12
47.34 52.66
57.87 47.85

2,NO 455 769 1224
17.54
29.65 47.19
37.17 62.83
41.14 51.68

Total 1106
1488 2594
42.64 57.36 100.00
5
Significance test for a table
• Significance test tells you the probability that
the relationship you see in the table is due to
chance
• Significance test does NOT tell you whether the
relationship is meaningful
• Chi-square is a commonly used significance test
for a table
• It is very sensitive to the number of cells

6
Modified crosstabulation
EMPLOY(Are you employed now)
SEX(Respondent's sex)
Frequency
Percent
Row Pct
Col Pct 1,MALE 2,FEMALE Total

1,YES 640
712 1352
24.84 27.64 52.48
47.34 52.66
58.45 48.08

2,NO 455 769 1224
17.66
29.85 47.52
37.17 62.83
41.55 51.92

Total 1095
1481 2576
42.51 57.49 100.00
Frequency Missing 18

Statistic DF Value
Prob

Chi-Square 1
27.1563 lt.0001 Likelihood
Ratio Chi-Square 1 27.2376 lt.0001
26.7420 lt.0001
Mantel-Haenszel Chi-Square 1 27.1458
lt.0001 Phi Coefficient
0.1027
Contingency Coefficient 0.1021
Cramer's V
0.1027

7
Measuring differences between two groupsT-test
with insignificant difference
Lower CL Upper CL Lower CL
Upper CL Variable BLDRO N Mean
Mean Mean Std Dev Std Dev Std Dev Std
Err PCOUNT 1,OWN 1996 2.4964
2.5556 2.6148 1.3088 1.3494 1.3926
0.0302 PCOUNT 2,RENT 432 2.4348
2.588 2.7411 1.5184 1.6197 1.7355
0.0779 PCOUNT Diff (1-2) -0.178
-0.032 0.1135 1.3629 1.4013 1.4418
0.0744
T-Tests Variable Method
Variances DF t Value Pr gt t
PCOUNT Pooled Equal
2426 -0.44 0.6635
PCOUNT Satterthwaite Unequal 567
-0.39 0.6988
Equality of Variances
Variable Method Num DF Den DF F
Value Pr gt F PCOUNT
Folded F 431 1995 1.44 lt.0001
8
T-test with significant difference
Lower CL Upper CL Lower CL
Upper CL Variable SEX N Mean
Mean Mean Std Dev Std Dev Std Dev Std
Err indexus 1,MALE 1106 92.903
95.242 97.582 38.062 39.648 41.373
1.1922 indexus 2,FEMALE 1488 82.522
84.396 86.27 35.575 36.853 38.227
0.9554 indexus Diff (1-2) 7.8824
10.846 13.81 37.061 38.07 39.135
1.5114
T-Tests Variable Method
Variances DF t Value Pr gt t
indexus Pooled Equal
2592 7.18 lt.0001
indexus Satterthwaite Unequal 2281
7.10 lt.0001
Equality of Variances
Variable Method Num DF Den DF F
Value Pr gt F indexus
Folded F 1105 1487 1.16 0.0090
9
T-test with significant difference
Lower CL Upper CL Lower CL
Upper CL Variable BLDRO N Mean
Mean Mean Std Dev Std Dev Std Dev Std
Err indexus 1,OWN 2007 88.335
90.038 91.741 37.734 38.902 40.144
0.8684 indexus 2,RENT 439 81.377
84.912 88.447 35.348 37.687 40.359
1.7987 indexus Diff (1-2) 1.1291
5.1262 9.1233 37.632 38.687 39.803
2.0384
T-Tests Variable Method
Variances DF t Value Pr gt t
indexus Pooled Equal
2444 2.51 0.0120
indexus Satterthwaite Unequal 658
2.57 0.0105
Equality of Variances
Variable Method Num DF Den DF F
Value Pr gt F indexus
Folded F 2006 438 1.07 0.4071
10
Means of Persons per household by age group
Analysis Variable PCOUNT Person Count, FL
usual residence Broader age group of
N respondent Obs N
Mean Std Dev Minimum
Maximum

18-24 161 159 3.2955975
1.5733278 1.0000000 12.0000000
25-34 276 272 3.1985294
1.5620965 1.0000000 16.0000000
35-44 392 388 3.3479381
1.4924689 1.0000000 12.0000000
45-54 511 507 2.7159763
1.2877506 1.0000000 9.0000000
55-64 479 472 2.1440678
1.0033949 1.0000000 7.0000000 gt65
722 715 1.8293706
1.2040915 1.0000000 20.0000000

11
ANOVA Testing differences between more than two
groups
Dependent Variable PCOUNT Person Count, FL
usual residence
Sum of Source
DF Squares Mean Square F
Value Pr gt F Model
6 913.010024 152.168337 89.99
lt.0001 Error 2557
4323.607761 1.690891 Corrected
Total 2563 5236.617785
R-Square Coeff Var Root MSE
PCOUNT Mean 0.174351
51.16756 1.300343 2.541342
Source DF Anova SS
Mean Square F Value Pr gt F AGE1
6 913.0100235
152.1683373 89.99 lt.0001