This study surveyed transplant educators in 1,694 U.S. dialysis centers about their transplant knowledge, use of 12 specific education practices, and 8 identified barriers to providing education. Transplant wait-listing rates were calculated using data from the USRDS.
Cronbachâs alpha is a measure used to assess the reliability, or internal consistency, of a set of scale or test items. In other words, the reliability of any given measurement refers to the extent to which it is a consistent measure of a concept, and Cronbachâs alpha is one way of measuring the strength of that consistency [1].
Results: 0.41, 95% CI: 0.36, 0.45.
## Some items ( ldbpd ) were negatively correlated with the total scale and
## probably should be reversed.
## To do this, run the function again with the 'check.keys=TRUE' option##
## Reliability analysis
## Call: alpha(x = df.alpha)
##
## raw_alpha std.alpha G6(smc) average_r S/N ase mean sd median_r
## 0.41 0.4 0.43 0.054 0.68 0.021 0.44 0.17 0.043
##
## lower alpha upper 95% confidence boundaries
## 0.36 0.41 0.45
##
## Reliability if an item is dropped:
## raw_alpha std.alpha G6(smc) average_r S/N alpha se var.r
## otyped 0.41 0.41 0.43 0.058 0.68 0.021 0.0092
## ldbpd 0.45 0.45 0.46 0.068 0.81 0.020 0.0079
## lvlongerd 0.40 0.40 0.42 0.057 0.66 0.022 0.0093
## pcttxfund 0.34 0.34 0.37 0.045 0.52 0.024 0.0082
## waittimed 0.43 0.42 0.45 0.063 0.74 0.020 0.0089
## surgdied 0.37 0.37 0.40 0.051 0.59 0.022 0.0084
## ldtxlastd 0.37 0.36 0.36 0.048 0.56 0.023 0.0048
## ddtxlastd 0.38 0.37 0.37 0.052 0.60 0.022 0.0048
## govtpayd 0.34 0.34 0.37 0.046 0.53 0.024 0.0084
## ldexpd 0.34 0.34 0.37 0.045 0.52 0.024 0.0082
## normactd 0.39 0.39 0.41 0.054 0.63 0.022 0.0088
## dialfunctd 0.39 0.39 0.42 0.056 0.65 0.022 0.0093
## med.r
## otyped 0.047
## ldbpd 0.057
## lvlongerd 0.037
## pcttxfund 0.029
## waittimed 0.056
## surgdied 0.037
## ldtxlastd 0.043
## ddtxlastd 0.048
## govtpayd 0.034
## ldexpd 0.034
## normactd 0.042
## dialfunctd 0.037
##
## Item statistics
## n raw.r std.r r.cor r.drop mean sd
## otyped 1629 0.32 0.30 0.119 0.082 0.62 0.49
## ldbpd 1636 0.18 0.18 -0.072 -0.056 0.33 0.47
## lvlongerd 1662 0.30 0.32 0.156 0.104 0.81 0.39
## pcttxfund 1652 0.49 0.47 0.405 0.266 0.48 0.50
## waittimed 1673 0.27 0.25 0.031 0.020 0.56 0.50
## surgdied 1675 0.41 0.39 0.279 0.179 0.44 0.50
## ldtxlastd 1665 0.40 0.43 0.410 0.210 0.22 0.41
## ddtxlastd 1669 0.36 0.39 0.344 0.159 0.23 0.42
## govtpayd 1681 0.48 0.46 0.393 0.260 0.59 0.49
## ldexpd 1672 0.48 0.47 0.407 0.268 0.44 0.50
## normactd 1655 0.37 0.36 0.213 0.140 0.35 0.48
## dialfunctd 1665 0.33 0.34 0.177 0.118 0.26 0.44
##
## Non missing response frequency for each item
## 0 1 miss
## otyped 0.38 0.62 0.04
## ldbpd 0.67 0.33 0.03
## lvlongerd 0.19 0.81 0.02
## pcttxfund 0.52 0.48 0.02
## waittimed 0.44 0.56 0.01
## surgdied 0.56 0.44 0.01
## ldtxlastd 0.78 0.22 0.02
## ddtxlastd 0.77 0.23 0.01
## govtpayd 0.41 0.59 0.01
## ldexpd 0.56 0.44 0.01
## normactd 0.65 0.35 0.02
## dialfunctd 0.74 0.26 0.02Note: I used the newly updated MICE package, pool() function to be sepcific, which does not provide lo 95 and hi 95 by default (was confusing at first as original code ran into error, not providing CIs), the new pool() function use 2.5% and 97.5% instead, and it has the option to exp() the estimates for you.
*Estimates are IRRs.| estimate | 2.5 % | 97.5 % | p.value | |
|---|---|---|---|---|
| detdisc_all | 1.074 | 0.936 | 1.233 | 0.309 |
| detdisc_all1 | 1.092 | 0.957 | 1.245 | 0.190 |
| qck_int_all | 1.149 | 0.972 | 1.358 | 0.105 |
| qck_int_all1 | 1.166 | 0.995 | 1.367 | 0.057 |
| rfr_out_all | 1.218 | 1.068 | 1.388 | 0.003 |
| rfr_out_all1 | 1.183 | 1.044 | 1.341 | 0.008 |
| extnd_all | 1.300 | 0.926 | 1.824 | 0.130 |
| extnd_all1 | 1.247 | 0.907 | 1.715 | 0.174 |
| extnd_di | 1.238 | 1.069 | 1.433 | 0.004 |
| extnd_di1 | 1.168 | 1.016 | 1.343 | 0.029 |
Note: 1. educationer race/ethnicity were not significant when added back into the models. results shown below are univariate first and followed by adjusted. 2. The interaction between rural status and for profit status were found to be non-significant for all models. p values in the comments. 3. Job title was not a significant predictor.
| estimate | 2.5 % | 97.5 % | p.value | |
|---|---|---|---|---|
| detdisc_all | 1.096 | 0.973 | 1.233 | 0.130 |
| detdisc_all1 | 1.108 | 0.990 | 1.240 | 0.074 |
| qck_int_all | 1.132 | 0.979 | 1.308 | 0.093 |
| qck_int_all1 | 1.134 | 0.989 | 1.300 | 0.072 |
| rfr_out_all | 1.152 | 1.029 | 1.289 | 0.014 |
| rfr_out_all1 | 1.127 | 1.012 | 1.255 | 0.029 |
| extnd_all | 1.217 | 0.905 | 1.635 | 0.194 |
| extnd_all1 | 1.156 | 0.875 | 1.527 | 0.307 |
| extnd_di | 1.190 | 1.049 | 1.351 | 0.007 |
| extnd_di1 | 1.127 | 0.999 | 1.271 | 0.053 |
Note: The hypothesis test functions used by default are chisq.test() for categorical variables (with continuity correction). Fisher’s exact test used for variable txvideo but gives similar p value with Chisq.
| Medical Director/Physician | Nurse Manager/Facility Administrator | Nurse | Dietician | Social Worker | Dialysis Technician | p | test | |
|---|---|---|---|---|---|---|---|---|
| n | 133 | 257 | 116 | 941 | 171 | 73 | ||
| rfr_out_all = 1 (%) | 74 (55.6) | 122 (47.5) | 22 (19.0) | 546 (58.0) | 75 (43.9) | 39 (53.4) | <0.001 | |
| qck_int_all = 1 (%) | 26 (19.5) | 40 (15.6) | 2 ( 1.7) | 174 (18.5) | 26 (15.2) | 16 (21.9) | <0.001 | |
| detdisc_all = 1 (%) | 52 (39.1) | 81 (31.5) | 9 ( 7.8) | 309 (32.8) | 47 (27.5) | 29 (39.7) | <0.001 | |
| extnd_di = 1 (%) | 41 (30.8) | 54 (21.0) | 7 ( 6.0) | 202 (21.5) | 57 (33.3) | 24 (32.9) | <0.001 |
Or if you group jobtitle by 3 categories, 1 = Social worker, 2= Nurse, and 3 = all others. The table looks like this:
| Social Worker | Nurse | All others | p | test | |
|---|---|---|---|---|---|
| n | 941 | 257 | 493 | ||
| rfr_out_all = 1 (%) | 546 (58.0) | 122 (47.5) | 210 (42.6) | <0.001 | |
| qck_int_all = 1 (%) | 174 (18.5) | 40 (15.6) | 70 (14.2) | 0.101 | |
| detdisc_all = 1 (%) | 309 (32.8) | 81 (31.5) | 137 (27.8) | 0.145 | |
| extnd_di = 1 (%) | 202 (21.5) | 54 (21.0) | 129 (26.2) | 0.101 | |
| Note: | |||||
| rfr_out_all: Oral recommendation strategy |
More Info