diff --git a/sizingDemandResponseTrialsNZ.Rmd b/sizingDemandResponseTrialsNZ.Rmd
index 79b7f8d900fbfd49c528c0cafdfeded06b7aeb9e..89ffdf8a68322313f195f7bcbdd66bbbaf4fa0cc 100644
--- a/sizingDemandResponseTrialsNZ.Rmd
+++ b/sizingDemandResponseTrialsNZ.Rmd
@@ -7,7 +7,12 @@ title: '`r paste0(params$title)`'
subtitle: '`r paste0(params$subtitle)`'
author: '`r paste0(params$author)` (Contact: b.anderson@soton.ac.uk, `@dataknut`)'
date: 'Last run at: `r Sys.time()`'
+always_allow_html: yes
output:
+ bookdown::word_document2:
+ fig_caption: yes
+ toc: yes
+ toc_depth: 2
bookdown::html_document2:
code_folding: hide
fig_caption: yes
@@ -17,10 +22,6 @@ output:
toc: yes
toc_depth: 2
toc_float: yes
- bookdown::word_document2:
- fig_caption: yes
- toc: yes
- toc_depth: 2
bookdown::pdf_document2:
fig_caption: yes
keep_tex: yes
@@ -121,7 +122,7 @@ Code history is generally tracked via the paper [repo](https://github.com/datakn
## Data:
-This paper uses circuit level extracts for 'Heat Pumps', 'Lighting' and 'Hot Water' for the NZ GREEN Grid Household Electricity Demand Data (`r myParams$GGDataDOI` [@anderson_new_2018]). These have been extracted using the code found in
+This paper uses circuit level extracts for 'Heat Pumps', 'Lighting' and 'Hot Water' for the NZ GREEN Grid Household Electricity Demand Data (`r myParams$GGDataDOI` [@anderson_new_2018]). These have been extracted using the code found in https://github.com/CfSOtago/GREENGridData/blob/master/examples/code/extractCleanGridSpy1minCircuit.R
## Acknowledgements
diff --git a/sizingDemandResponseTrialsNZ.html b/sizingDemandResponseTrialsNZ.html
index 7cd8193cd95be91cf6a4ff81481c2caed166e9d9..b260d2ad16dfff52d2c4159ed11fb03da45b067d 100644
--- a/sizingDemandResponseTrialsNZ.html
+++ b/sizingDemandResponseTrialsNZ.html
@@ -240,7 +240,7 @@ div.tocify {
<h1 class="title toc-ignore">Statistical Power, Statistical Significance, Study Design and Decision Making: A Worked Example</h1>
<h3 class="subtitle"><em>Sizing Demand Response Trials in New Zealand</em></h3>
<h4 class="author"><em>Ben Anderson and Tom Rushby (Contact: <a href="mailto:b.anderson@soton.ac.uk">b.anderson@soton.ac.uk</a>, <code>@dataknut</code>)</em></h4>
-<h4 class="date"><em>Last run at: 2018-09-27 15:26:47</em></h4>
+<h4 class="date"><em>Last run at: 2018-09-27 15:34:32</em></h4>
</div>
@@ -292,7 +292,7 @@ div.tocify {
</div>
<div id="data" class="section level2">
<h2><span class="header-section-number">1.5</span> Data:</h2>
-<p>This paper uses circuit level extracts for ‘Heat Pumps’, ‘Lighting’ and ‘Hot Water’ for the NZ GREEN Grid Household Electricity Demand Data (<a href="https://dx.doi.org/10.5255/UKDA-SN-853334" class="uri">https://dx.doi.org/10.5255/UKDA-SN-853334</a> <span class="citation">(Anderson et al. 2018)</span>). These have been extracted using the code found in</p>
+<p>This paper uses circuit level extracts for ‘Heat Pumps’, ‘Lighting’ and ‘Hot Water’ for the NZ GREEN Grid Household Electricity Demand Data (<a href="https://dx.doi.org/10.5255/UKDA-SN-853334" class="uri">https://dx.doi.org/10.5255/UKDA-SN-853334</a> <span class="citation">(Anderson et al. 2018)</span>). These have been extracted using the code found in <a href="https://github.com/CfSOtago/GREENGridData/blob/master/examples/code/extractCleanGridSpy1minCircuit.R" class="uri">https://github.com/CfSOtago/GREENGridData/blob/master/examples/code/extractCleanGridSpy1minCircuit.R</a></p>
</div>
<div id="acknowledgements" class="section level2">
<h2><span class="header-section-number">1.6</span> Acknowledgements</h2>
@@ -506,13 +506,13 @@ n households
Control
</td>
<td style="text-align:right;">
-175.34594
+160.06236
</td>
<td style="text-align:right;">
-334.21512
+320.32863
</td>
<td style="text-align:right;">
-1055
+1070
</td>
</tr>
<tr>
@@ -520,13 +520,13 @@ Control
Intervention 1
</td>
<td style="text-align:right;">
-38.13993
+38.38931
</td>
<td style="text-align:right;">
-84.02911
+84.81464
</td>
<td style="text-align:right;">
-940
+899
</td>
</tr>
<tr>
@@ -534,13 +534,13 @@ Intervention 1
Intervention 2
</td>
<td style="text-align:right;">
-58.67461
+62.96979
</td>
<td style="text-align:right;">
-109.15877
+116.10543
</td>
<td style="text-align:right;">
-1013
+1056
</td>
</tr>
<tr>
@@ -548,13 +548,13 @@ Intervention 2
Intervention 3
</td>
<td style="text-align:right;">
-64.75981
+66.80930
</td>
<td style="text-align:right;">
-140.54042
+145.74274
</td>
<td style="text-align:right;">
-1192
+1175
</td>
</tr>
</tbody>
@@ -570,17 +570,17 @@ Figure 5.1: Mean W demand per group for large sample (Error bars = 95% confidenc
## Welch Two Sample t-test
##
## data: largeTestDT[group == "Intervention 2"]$meanW and largeTestDT[group == "Control"]$meanW
-## t = -10.757, df = 1284.7, p-value < 2.2e-16
+## t = -9.3142, df = 1348.3, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
-## -137.9495 -95.3932
+## -117.54191 -76.64322
## sample estimates:
## mean of x mean of y
-## 58.67461 175.34594</code></pre>
+## 62.96979 160.06236</code></pre>
<p>In this case:</p>
<ul>
-<li>effect size = 116.6713324W or 66.54% representing a still <em>reasonable bang for buck</em> for whatever caused the difference;</li>
-<li>95% confidence interval for the test = -137.95 to -95.39 representing <em>much less</em> uncertainty/variation;</li>
+<li>effect size = 97.0925661W or 60.66% representing a still <em>reasonable bang for buck</em> for whatever caused the difference;</li>
+<li>95% confidence interval for the test = -117.54 to -76.64 representing <em>much less</em> uncertainty/variation;</li>
<li>p value of 0 representing a <em>very low</em> risk of a false positive result as it passes all conventional thresholds.</li>
</ul>
<p>So now we are able to be much more confident in our decision to implement Intervention 2 since the average effect is reasonably large, the expected variation in the effect size is reasonably narrow and the risk of a Type I (false positive) error is extremely small.</p>
@@ -619,7 +619,7 @@ Figure 5.1: Mean W demand per group for large sample (Error bars = 95% confidenc
</div>
<div id="runtime" class="section level1">
<h1><span class="header-section-number">8</span> Runtime</h1>
-<p>Analysis completed in 78.36 seconds ( 1.31 minutes) using <a href="https://cran.r-project.org/package=knitr">knitr</a> in <a href="http://www.rstudio.com">RStudio</a> with R version 3.5.1 (2018-07-02) running on x86_64-apple-darwin15.6.0.</p>
+<p>Analysis completed in 71.73 seconds ( 1.2 minutes) using <a href="https://cran.r-project.org/package=knitr">knitr</a> in <a href="http://www.rstudio.com">RStudio</a> with R version 3.5.1 (2018-07-02) running on x86_64-apple-darwin15.6.0.</p>
</div>
<div id="r-environment" class="section level1">
<h1><span class="header-section-number">9</span> R environment</h1>
diff --git a/sizingDemandResponseTrialsNZ.md b/sizingDemandResponseTrialsNZ.md
index eec11aa06e0aee95e0d6088e2c95d56232e49c7a..a4e47b206d3dd7055950493f87acdf1428ae474a 100644
--- a/sizingDemandResponseTrialsNZ.md
+++ b/sizingDemandResponseTrialsNZ.md
@@ -6,7 +6,8 @@ params:
title: 'Statistical Power, Statistical Significance, Study Design and Decision Making: A Worked Example'
subtitle: 'Sizing Demand Response Trials in New Zealand'
author: 'Ben Anderson and Tom Rushby (Contact: b.anderson@soton.ac.uk, `@dataknut`)'
-date: 'Last run at: 2018-09-27 15:26:47'
+date: 'Last run at: 2018-09-27 15:34:32'
+always_allow_html: yes
output:
bookdown::html_document2:
code_folding: hide
@@ -81,7 +82,7 @@ Code history is generally tracked via the paper [repo](https://github.com/datakn
## Data:
-This paper uses circuit level extracts for 'Heat Pumps', 'Lighting' and 'Hot Water' for the NZ GREEN Grid Household Electricity Demand Data (https://dx.doi.org/10.5255/UKDA-SN-853334 [@anderson_new_2018]). These have been extracted using the code found in
+This paper uses circuit level extracts for 'Heat Pumps', 'Lighting' and 'Hot Water' for the NZ GREEN Grid Household Electricity Demand Data (https://dx.doi.org/10.5255/UKDA-SN-853334 [@anderson_new_2018]). These have been extracted using the code found in https://github.com/CfSOtago/GREENGridData/blob/master/examples/code/extractCleanGridSpy1minCircuit.R
## Acknowledgements
@@ -284,27 +285,27 @@ Suppose instead that we had designed and implemented our sample recruitment acco
<tbody>
<tr>
<td style="text-align:left;"> Control </td>
- <td style="text-align:right;"> 175.34594 </td>
- <td style="text-align:right;"> 334.21512 </td>
- <td style="text-align:right;"> 1055 </td>
+ <td style="text-align:right;"> 160.06236 </td>
+ <td style="text-align:right;"> 320.32863 </td>
+ <td style="text-align:right;"> 1070 </td>
</tr>
<tr>
<td style="text-align:left;"> Intervention 1 </td>
- <td style="text-align:right;"> 38.13993 </td>
- <td style="text-align:right;"> 84.02911 </td>
- <td style="text-align:right;"> 940 </td>
+ <td style="text-align:right;"> 38.38931 </td>
+ <td style="text-align:right;"> 84.81464 </td>
+ <td style="text-align:right;"> 899 </td>
</tr>
<tr>
<td style="text-align:left;"> Intervention 2 </td>
- <td style="text-align:right;"> 58.67461 </td>
- <td style="text-align:right;"> 109.15877 </td>
- <td style="text-align:right;"> 1013 </td>
+ <td style="text-align:right;"> 62.96979 </td>
+ <td style="text-align:right;"> 116.10543 </td>
+ <td style="text-align:right;"> 1056 </td>
</tr>
<tr>
<td style="text-align:left;"> Intervention 3 </td>
- <td style="text-align:right;"> 64.75981 </td>
- <td style="text-align:right;"> 140.54042 </td>
- <td style="text-align:right;"> 1192 </td>
+ <td style="text-align:right;"> 66.80930 </td>
+ <td style="text-align:right;"> 145.74274 </td>
+ <td style="text-align:right;"> 1175 </td>
</tr>
</tbody>
</table>
@@ -322,19 +323,19 @@ In comparison to \ref(fig:ggMeanDiffs) we can now see (\ref(fig:largeNmeanDiffs)
## Welch Two Sample t-test
##
## data: largeTestDT[group == "Intervention 2"]$meanW and largeTestDT[group == "Control"]$meanW
-## t = -10.757, df = 1284.7, p-value < 2.2e-16
+## t = -9.3142, df = 1348.3, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
-## -137.9495 -95.3932
+## -117.54191 -76.64322
## sample estimates:
## mean of x mean of y
-## 58.67461 175.34594
+## 62.96979 160.06236
```
In this case:
- * effect size = 116.6713324W or 66.54% representing a still _reasonable bang for buck_ for whatever caused the difference;
- * 95% confidence interval for the test = -137.95 to -95.39 representing _much less_ uncertainty/variation;
+ * effect size = 97.0925661W or 60.66% representing a still _reasonable bang for buck_ for whatever caused the difference;
+ * 95% confidence interval for the test = -117.54 to -76.64 representing _much less_ uncertainty/variation;
* p value of 0 representing a _very low_ risk of a false positive result as it passes all conventional thresholds.
So now we are able to be much more confident in our decision to implement Intervention 2 since the average effect is reasonably large, the expected variation in the effect size is reasonably narrow and the risk of a Type I (false positive) error is extremely small.
@@ -374,7 +375,7 @@ We would like to thank collaborators and partners on a number of applied researc
-Analysis completed in 78.36 seconds ( 1.31 minutes) using [knitr](https://cran.r-project.org/package=knitr) in [RStudio](http://www.rstudio.com) with R version 3.5.1 (2018-07-02) running on x86_64-apple-darwin15.6.0.
+Analysis completed in 71.73 seconds ( 1.2 minutes) using [knitr](https://cran.r-project.org/package=knitr) in [RStudio](http://www.rstudio.com) with R version 3.5.1 (2018-07-02) running on x86_64-apple-darwin15.6.0.
# R environment
diff --git a/sizingDemandResponseTrialsNZ_files/figure-docx/largeNmeanDiffs-1.png b/sizingDemandResponseTrialsNZ_files/figure-docx/largeNmeanDiffs-1.png
index b619e4eaa8476db1ace09425ab00dab10d51ce33..fe937d858fbb62ea06f042d3aaeb42981891ee5b 100644
Binary files a/sizingDemandResponseTrialsNZ_files/figure-docx/largeNmeanDiffs-1.png and b/sizingDemandResponseTrialsNZ_files/figure-docx/largeNmeanDiffs-1.png differ
diff --git a/sizingDemandResponseTrialsNZ_files/figure-html/largeNmeanDiffs-1.png b/sizingDemandResponseTrialsNZ_files/figure-html/largeNmeanDiffs-1.png
index 9d83e9a8231b17c34590995a11bc36686af41e2c..ca959c953f9ef84cb6664b8ccfa7e4f890fe8643 100644
Binary files a/sizingDemandResponseTrialsNZ_files/figure-html/largeNmeanDiffs-1.png and b/sizingDemandResponseTrialsNZ_files/figure-html/largeNmeanDiffs-1.png differ