Difference between revisions of "SMHS LinearModeling"

From SOCR
Jump to: navigation, search
(Created page with "== Scientific Methods for Health Sciences - Linear Modeling == ===Statistical Software- Pros/Cons Comparison=== Using the SOCR_Simulated_HELP_Data|SOCR Health Eval...")
 
(→‎Scientific Methods for Health Sciences - Linear Modeling)
 
(29 intermediate revisions by 2 users not shown)
Line 1: Line 1:
 
==[[SMHS| Scientific Methods for Health Sciences]] - Linear Modeling ==
 
==[[SMHS| Scientific Methods for Health Sciences]] - Linear Modeling ==
  
−
===Statistical Software- Pros/Cons Comparison===
+
The following sub-sections represent a blend of model-based and model-free scientific inference, forecasting and validity.
−
Using the [[SOCR_Simulated_HELP_Data|SOCR Health Evaluation and Linkage to Primary (HELP) Care Dataset]] we can [https://umich.instructure.com/files/354289/download?download_frd=1 extract some sample data (00_Tiny_SOCR_HELP_Data_Simmulation.csv)].
 
  
−
# data_1 <- read.csv('00_Tiny_SOCR_HELP_Data_Simmulation.csv',as.is=T, header=T)
+
===[[SMHS_LinearModeling_StatsSoftware|Statistical Software]]===
−
# data_1 = read.csv(file.choose( ))
+
This section briefly describes the pros and cons of different statistical software platforms.
−
# data_1 <- read.table('00_Tiny_SOCR_HELP_Data_Simmulation.csv', header=TRUE,  sep=",", row.names="ID")
 
  
−
attach(data_1) 
+
===[[SMHS_LinearModeling_QC|Quality Control]]===
−
# to ensure all variables are accessible within R, e.g., using age instead of data_1$\$$age
+
Discussion of data Quality Control (QC) and Quality Assurance (QA) which represent important components of data-driven modeling, analytics and visualization.
−
# i2 maximum number of drinks (standard units) consumed per day (in the past 30 days range 0–184) see also i1
 
−
# treat randomization group (0=usual care, 1=HELP clinic)
 
−
# pcs SF-36 Physical Component Score (range 14-75)
 
−
# mcs SF-36 Mental Component Score(range 7-62)
 
−
# cesd Center for Epidemiologic Studies Depression scale (range 0–60)
 
−
# indtot Inventory of Drug Use Con-sequences (InDUC) total score (range 4–45)
 
−
# pss_fr perceived social supports (friends, range 0–14) see also dayslink
 
−
# drugrisk Risk-Assessment Battery(RAB) drug risk score (range0–21)
 
−
# satreat any BSAS substance abuse treatment at baseline (0=no,1=yes)
 
  
−
===Fragment of the data===
+
===[[SMHS_LinearModeling_MLR |Multiple Linear Regression]]===
−
<center>
+
Review and demonstration of computing and visualizing the regression-model coefficients (effect-sizes), (fixed-effect) linear model assumptions, examination of residual plots, and independence.
−
{| class="wikitable" style="text-align:center; " border="1"
 
−
|-
 
−
! ID ||i2 ||age ||treat ||homeless ||pcs ||mcs ||cesd ||indtot ||pss_fr ||drugrisk ||sexrisk ||satreat ||female ||substance ||racegrp
 
−
|-
 
−
| 1 ||0 ||25 ||0 ||0 ||49 ||7 ||46 ||37 ||0 ||1 ||6 ||0 ||0 ||cocaine ||black
 
−
|-
 
−
| 2 ||18 ||31 ||0 ||0 ||48 ||34 ||17 ||48 ||0 ||0 ||11 ||0 ||0 ||alcohol ||white
 
−
|-
 
−
| 3 ||39 ||36 ||0 ||0 ||76 ||9 ||33 ||41 ||12 ||19 ||4 ||0 ||0 ||heroin ||black
 
−
|-
 
−
| … || || || || || || || || || || || || || || ||
 
−
|-
 
−
| 100 ||81 ||22 ||0 ||0 ||37 ||17 ||19 ||30 ||3 ||0 ||10 ||0 ||0 ||alcohol ||other
 
−
|}
 
−
</center>
 
−
 
 
−
===Testing section===
 
−
 
 
−
summary(data_1)
 
−
 
−
x.norm <- rnorm(n=200, m=10, sd=20)
 
−
hist(x.norm, main="N(10,20) Histogram")
 
−
hist(x.norm, main="N(10,20) Histogram")
 
−
mean(data_1$\$$age)
 
−
sd(data_1$\$$age)
 
−
 
 
−
 
 
−
Simulate new data to match the properties/characteristics of observed data
 
−
 
 
−
* i2 [0: 184]
 
−
* age m=34,sd=12
 
−
* treat {0,1}
 
−
* homeless {0,1}
 
−
* pcs 14-75
 
−
* mcs 7-62
 
−
* cesd 0–60
 
−
* indtot 4-45
 
−
* pss_fr 0-14
 
−
* drugrisk 0-21
 
−
* sexrisk
 
−
* satreat (0=no,1=yes)
 
−
* female (0=no,1=yes)
 
−
* racegrp (black, white, other)
 
−
 
−
# Demographics variables
 
−
Sex <- ifelse(runif(NumSubj)<.5,0,1)
 
−
Weight <- as.integer(rnorm(NumSubj, 80,10))
 
−
Age <- as.integer(rnorm(NumSubj, 62,10))
 
−
 
 
−
# Diagnosis:
 
−
Dx <- c(rep("PD", 100), rep("HC", 100), rep("SWEDD", 82))
 
−
 
 
−
# Genetics
 
−
chr12_rs34637584_GT <- c(ifelse(runif(100)<.3,0,1), ifelse(runif(100)<.6,0,1), ifelse(runif(82)<.4,0,1))                              # NumSubj Bernoulli trials
 
−
chr17_rs11868035_GT <- c(ifelse(runif(100)<.7,0,1), ifelse(runif(100)<.4,0,1), ifelse(runif(82)<.5,0,1))                              # NumSubj Bernoulli trials
 
−
 
 
−
# Clinical          # rpois(NumSubj, 15) + rpois(NumSubj, 6)
 
−
UPDRS_part_I <- c( ifelse(runif(100)<.7,0,1)+ifelse(runif(100)<.7,0,1),
 
−
ifelse(runif(100)<.6,0,1)+ ifelse(runif(100)<.6,0,1),
 
−
ifelse(runif(82)<.4,0,1)+ ifelse(runif(82)<.4,0,1) )
 
−
UPDRS_part_II <- c(sample.int(20, 100, replace=T), sample.int(14, 100, replace=T),
 
−
sample.int(18, 82, replace=T) )
 
−
UPDRS_part_III <- c(sample.int(30, 100, replace=T), sample.int(20, 100, replace=T),
 
−
    sample.int(25, 82, replace=T) )
 
−
 
 
−
# Time: VisitTime – done automatically below in aggregator
 
−
 
 
−
# Data (putting all components together)
 
−
sim_PD_Data <- cbind(
 
−
          rep(Cases, each= NumTime),                          # Cases
 
−
          rep(L_caudate_ComputeArea, each= NumTime), # Imaging
 
−
          rep(Sex, each= NumTime),                            # Demographics
 
−
          rep(Weight, each= NumTime),
 
−
          rep(Age, each= NumTime),
 
−
          rep(Dx, each= NumTime),                            # Dx
 
−
          rep(chr12_rs34637584_GT, each= NumTime),            # Genetics
 
−
          rep(chr17_rs11868035_GT, each= NumTime),
 
−
          rep(UPDRS_part_I, each= NumTime),                  # Clinical
 
−
          rep(UPDRS_part_II, each= NumTime),
 
−
          rep(UPDRS_part_III, each= NumTime),
 
−
          rep(c(0,6,12,18), NumSubj)                          # Time
 
−
)
 
−
 
 
−
# Assign the column names
 
−
colnames(sim_PD_Data) <- c(
 
−
"Cases",
 
−
"L_caudate_ComputeArea",
 
−
"Sex", "Weight", "Age",
 
−
"Dx", "chr12_rs34637584_GT", "chr17_rs11868035_GT",
 
−
"UPDRS_part_I", "UPDRS_part_II", "UPDRS_part_III",
 
−
"Time"
 
−
)
 
−
 
 
−
# some QC
 
−
summary(sim_PD_Data)
 
−
dim(sim_PD_Data)
 
−
head(sim_PD_Data)
 
−
 
 
−
 
 
−
.....
 
−
 
 
−
<center>[[Image:SMHS_DataSimulation_Fig1.png|500px]] </center>
 
−
 
 
−
 
 
−
....
 
  
 +
===[[SMHS_LinearModeling_LMM |Linear mixed effects analyses]]===
 +
Scientific inference based on fixed and random effect models, assumptions, and mixed effects logistic regression.
  
 +
===[[SMHS_LinearModeling_MachineLearning|Machine Learning Algorithms]]===
 +
Data modeling, training , testing, forecasting, prediction, and simulation.
  
 
<hr>
 
<hr>
 
* SOCR Home page: http://www.socr.umich.edu
 
* SOCR Home page: http://www.socr.umich.edu
−
 
 
{{translate|pageName=http://wiki.socr.umich.edu/index.php?title=SMHS_LinearModeling}}
 
{{translate|pageName=http://wiki.socr.umich.edu/index.php?title=SMHS_LinearModeling}}

Latest revision as of 07:47, 19 May 2016

Scientific Methods for Health Sciences - Linear Modeling

The following sub-sections represent a blend of model-based and model-free scientific inference, forecasting and validity.

Statistical Software

This section briefly describes the pros and cons of different statistical software platforms.

Quality Control

Discussion of data Quality Control (QC) and Quality Assurance (QA) which represent important components of data-driven modeling, analytics and visualization.

Multiple Linear Regression

Review and demonstration of computing and visualizing the regression-model coefficients (effect-sizes), (fixed-effect) linear model assumptions, examination of residual plots, and independence.

Linear mixed effects analyses

Scientific inference based on fixed and random effect models, assumptions, and mixed effects logistic regression.

Machine Learning Algorithms

Data modeling, training , testing, forecasting, prediction, and simulation.

Translate this page:

(default)
Uk flag.gif

Deutsch
De flag.gif

Español
Es flag.gif

Français
Fr flag.gif

Italiano
It flag.gif

Português
Pt flag.gif

日本語
Jp flag.gif

България
Bg flag.gif

الامارات العربية المتحدة
Ae flag.gif

Suomi
Fi flag.gif

इस भाषा में
In flag.gif

Norge
No flag.png

한국어
Kr flag.gif

中文
Cn flag.gif

繁体中文
Cn flag.gif

Русский
Ru flag.gif

Nederlands
Nl flag.gif

Ελληνικά
Gr flag.gif

Hrvatska
Hr flag.gif

Česká republika
Cz flag.gif

Danmark
Dk flag.gif

Polska
Pl flag.png

România
Ro flag.png

Sverige
Se flag.gif

Retrieved from "https://wiki.socr.umich.edu/index.php?title=SMHS_LinearModeling&oldid=16004"